Neural Network-Enhanced Frequency-Constrained Optimal Power Flow With Worst RoCoF and Frequency Deviation
Listen
Radio episode about this paper
Transcript
Introduction to the show: ident: Robotics Radio. Generated commentary on the latest robotics and control papers.
Rosa: We're looking at the paper: "Neural Network-Enhanced Frequency-Constrained Optimal Power Flow With Worst RoCoF and Frequency Deviation".
Dev: Here's the gist of the paper. Deep neural networks (DNNs) are utilized to capture the nonlinear mapping between system operating conditions and key frequency performance metrics in real-time frequency-constrained optimal power flow (FCOPF).
Rosa: This approach is significant because it addresses the challenge of accurately modeling system frequency dynamics through analytical formulations, which are inherently nonlinear and complex.
Dev: Model Development The primary contribution involves developing a DNN-based frequency predictor (DNN-FP) that simultaneously estimates both the worst rate of change of frequency (RoCoF) and the frequency nadir (FN) for FCOPF.
Rosa: This DNN-FP is trained using high-fidelity electromagnetic transient (EMT) simulation data generated in PSCAD/EMTDC to capture multigovernor dynamics without the computational burden of differential-algebraic equations (DAEs).
Title and authors: Rosa: So we're looking at this paper titled "Neural Network-Enhanced Frequency-Constrained Optimal Power Flow With Worst RoCoF and Frequency Deviation." It sounds like they’re tackling a really tough problem in power systems where you need to keep frequency stable while running the power grid optimally.
Dev: Yeah, it’s about those explicit constraints on the rate of change of frequency, RoCoF, and the frequency nadir, FN. The paper suggests that modeling those things directly with traditional math is messy because it’s nonlinear and complicated to solve in real-time.
Taro: So what they’re doing is using deep neural networks to figure out that complicated relationship between how the system is running and those key frequency metrics. It sounds like an attempt to bypass the hard analytical modeling.
Rosa: Exactly, they developed this deep neural network frequency predictor, or DNN-FP, which estimates both the worst rate of change of frequency and the nadir for this optimal power flow problem. They trained it using high-fidelity simulation data from PSCAD/EMTDC to get past those nonlinear dynamics without dealing with differential algebraic equations.
Dev: And then they take that trained deep neural network and transform it into a mixed-integer linear programming form, which is then put right into the optimal power flow problem as new constraints. This creates what they call the DNN-FCOPF formulation.
Taro: So, instead of solving a complex nonlinear system during operation, you embed these predictions as simple linear constraints in a mixed-integer linear program to make sure stability happens. That sounds like it could help with real-time performance and solution accuracy simultaneously.
Rosa: Right, the paper says that they used high-fidelity time-domain simulation data generated in PSCAD/EMTDC for training the DNN, which is important because the quality of that dataset really dictates how good the prediction model turns out to be.
Dev: They collected a lot of data by running independent simulations with different load levels, initial generator outputs, and even looking at where a tripped generator was located. For each simulation, they calculated RoCoF and FN using a ten cycle window for a sixty hertz system <ref:2602.11063#pg3>.
Taro: And they used the center of inertia, or COI, to get the system frequency because frequency can vary across different buses; that’s how they calculate the worst rate of change and nadir consistently.
Title and authors: Rosa: The paper compares this new DNN-FCOPF approach against a traditional optimal power flow without any frequency constraints, and also against a linearized version of the FCOPF that uses simplified linear RoCoF and FN constraints.
Dev: The traditional optimal power flow, or T-OPF, just focuses on minimizing the total operating cost subject to all the standard power balance and line thermal limits. It doesn't have those frequency limits built in at all.
Taro: And then you have the linearized FCOPF, which tries to add some frequency constraints using simpler linear expressions for RoCoF and FN, but that’s where they think they run into trouble.
Rosa: The DNN-FCOPF is different because it uses the trained DNN-FP embedded in the problem as those frequency related constraints, so it should be better than the linearized approach at capturing more of the true system behavior.
Dev: The paper shows that while the linearized FCOPF struggles to keep RoCoF within acceptable limits, the proposed DNN-FCOPF successfully meets both stability requirements. The results show that RoCoF constraints are binding, but the FN constraints stay nonbinding in their case studies on standard test systems like IEEE nine-bus and thirty-nine-bus.
Taro: That’s interesting because it means this model is robust; it handles the worst frequency events well without overconstraining things unnecessarily, which is a good sign for real-world application where the world might misbehave.
Rosa: The accuracy of that DNN-FP is quite high for both RoCoF and FN; they report that the RoCoF errors in the linearized approach can be as high as sixty percent, whereas their DNN-FCOPF consistently shows errors below five percent.
Dev: So, to summarize this paper, it’s about using a deep neural network to predict frequency performance metrics like worst RoCoF and nadir so that you can embed those predictions into an optimal power flow problem as linear constraints for the DNN-FCOPF formulation. This is meant to improve both computational speed and solution accuracy compared to older methods <ref:2602.11063#pg1>.
Taro: It’s about making the optimization framework smarter by replacing complex nonlinear equations with these learned predictions, which should lead to a more reliable dispatch solution during real-time operation.
Title and authors: Rosa: The paper suggests that this DNN-FCOPF framework delivers superior stability performance compared to both the traditional T-OPF and the linearized L-FCOPF approaches when tested on standard IEEE systems. This means it really captures those governor dynamics that simpler models miss.
Dev: It’s a step up from just adding simplified linear constraints; they are capturing more complexity in how frequency responds across different buses, which is what the center of inertia helps them do with the calculation <ref:2602.11063#pg3>.
Taro: So, for someone who only listens to this show, it means that if you have a system where frequency security is paramount and you can't afford slow solvers, this DNN approach offers a path to much better stability guarantees than just using basic linear approximations.
Rosa: And they do flag a limitation: the paper mentions that the applicability of these deep learning approaches to unit commitment problems, or UC problems, is limited because system inertia can be adjusted through generator commitment decisions in UC which isn't feasible in real-time operation <ref:2602.11063#pg2>.
Dev: That’s a fair point; the paper notes that while they introduce this DNN-FP for FCOPF, applying it directly to unit commitment problems might not work because you can’t adjust inertia decisions in real-time like that <ref:2602.11063#pg2>.
Taro: So, the focus here is clearly on the real-time optimal power flow aspect of FCOPF, and they’re showing a viable strategy for injecting stability constraints into those specific problems using this neural network prediction.
Rosa: To wrap up, the paper "Neural Network-Enhanced Frequency-Constrained Optimal Power Flow With Worst RoCoF and Frequency Deviation" shows that incorporating a DNN predictor allows you to enforce frequency security through mixed-integer linear programming constraints within the FCOPF framework. This leads to superior stability results compared to traditional or linearized methods on standard test systems, with accuracy errors below five percent in their case studies <ref:2602.11063#pg1>.
Dev: It means that for power system operators, they have a tool to enhance system frequency stability by explicitly modeling the nonlinear relationship between operating conditions and critical frequency metrics through data-driven prediction.
Taro: The next thing I’m interested in is how this framework handles scenarios where the world misbehaves or when we integrate more complex resources like inverter-based energy sources, because that seems to be the next natural step for this kind of AI application.
The paper's summary: Rosa: So we're looking at this paper, "Neural Network-Enhanced Frequency-Constrained Optimal Power Flow With Worst RoCoF and Frequency Deviation." This work basically shows how you can use a deep neural network to predict exactly what the worst rate of change of frequency and the lowest frequency nadir will be under different operating conditions.
Dev: Yeah, it takes those predictions—RoCoF and nadir—and embeds them into a mixed-integer linear programming problem that runs alongside the power flow optimization. It’s not just an estimate; it’s a hard constraint you have to meet for the system to stay stable while it's trying to run at its most efficient cost.
Taro: So, what this means for someone driving or just watching their house—it means we can build a dispatch model that doesn't just look at the immediate power flow, but anticipates the actual frequency response of the grid. It’s about making sure the system has enough headroom so that when things go wrong, like a sudden load change, it doesn't crash instantly.
Rosa: Exactly. Think about what this says for real-time operations. Instead of using these messy differential equations that are hard to solve fast, the AI does the heavy lifting and spits out a prediction that fits neatly into an optimization box we can solve quickly on a computer.
Dev: The real win here is the accuracy of that constraint. The paper shows that when you use this method, the RoCoF constraints—the speed at which frequency can drop—are exactly where they need to be binding, while the nadir constraints are just there as a safety net, not actually active during normal operation.
Taro: That distinction is important. It means the system is stable because it's fast enough to handle sudden shocks, but it’s not constantly worried about dropping frequency to its absolute lowest point unless things are truly extreme. It gives the control system a much clearer picture of its operational safety envelope.
Rosa: And on top of that, they compared this DNN approach against two other methods: a traditional optimal power flow without any frequency limits and a linearized version that uses simpler linear constraints for RoCoF and nadir. The DNN model clearly wins on accuracy when it comes to those critical frequency numbers, with errors under five percent in their tests.
Dev: That low error rate is what makes it viable for real-time use. If you're running a loop at a certain speed, you need to know if your constraint calculation is reliable enough to keep the power flow stable without causing unnecessary shutdowns or instability.
Taro: It’s about robustness against those tricky, nonlinear dynamics that traditional math often simplifies away. It suggests we can get much closer to the true behavior of how frequency responds in a complex system when we use data-driven prediction instead of just relying on simplified approximations.
Rosa: So, to put it plainly, this research gives operators a way to make their optimal power flow solutions smarter by letting an AI model predict exactly how fast and how low the frequency will go under stress, which lets them enforce those rules accurately in real time.
Dev: It’s a tool for stability. But they do mention a catch: this whole deep learning setup works best when you're focused on the optimal power flow itself, not necessarily on long-term decisions about which generators to commit or how to change inertia—that’s where things get trickier.
Taro: Yeah, that’s the caveat. The paper shows it’s fantastic for optimizing what's happening right now in terms of power flow, but if you want to talk about big decisions like adding new resources or changing generator commitment strategy over a longer time horizon, this specific AI predictor might not be the right tool for that job.
The paper's improvements: Rosa: So we're looking at what they suggest to do next with this AI model, "Neural Network-Enhanced Frequency-Constrained Optimal Power Flow With Worst RoCoF and Frequency Deviation." They're not just stopping at the prediction part.
Dev: Right, they are looking at how to make this framework even more useful by using it for things that aren't just optimal power flow. They’re thinking about applying these learned frequency predictions to unit commitment problems, which is a bigger challenge because you can't change inertia decisions in real time like you can during power flow optimization.
Taro: That makes sense. If the system has to make huge decisions about generator commitment—which is slow and strategic—we need a way to use this frequency knowledge to guide those long-term plans, even if the AI isn't running every millisecond.
Rosa: Exactly. They’re talking about extending this concept beyond just real-time dispatch, into that unit commitment space, where the trade-off between operational efficiency and system stability is much more complicated.
Dev: The implication there is that this approach could help in designing better long-term scheduling for power systems, giving those commitment decisions a built-in awareness of how they affect frequency stability. It’s about adding intelligence to those slower, strategic planning loops.
Taro: I think it's also pointing toward integrating these AI predictions with other things we see happening in the field, like handling inverter-based resources better, since that was a big area they flagged for future work.
Rosa: Yeah, they’re suggesting this is a good starting point for figuring out how to manage those new types of power sources that are changing the grid structure. It shows that this AI technique has potential to be more than just solving one specific math problem; it could be a tool for managing the whole evolving energy system.
Dev: So, they’re moving from just solving a fast operational loop to building a more comprehensive framework that accounts for how frequency constraints interact with strategic decisions across different time scales. That’s where the real control engineering challenge lies.
Taro: It's about making sure the AI isn't just accurate in one scenario, but that it has a robust strategy for when the grid starts behaving unexpectedly or when those new resources are plugged in and things get messy.
Conclusion: Rosa: So we're wrapping up this look at "Neural Network-Enhanced Frequency-Constrained Optimal Power Flow With Worst RoCoF and Frequency Deviation." The main point is that using a deep neural network to predict frequency metrics lets us build an optimal power flow model that actually respects those stability limits in a way that simpler linear models can't.
Dev: Yeah, it really proves the value of these learned constraints. It’s not just about getting a fancy prediction; it’s about embedding that prediction into the optimization so the system actually behaves safely under stress. The results show errors dropping to below five percent on standard test systems for those RoCoF and nadir metrics.
Taro: I just want to say that this framework shows how we can use AI to capture those nonlinear governor dynamics that are usually hidden in complex models, which is crucial when you’re testing systems under real-world failures. It gives the optimization a much better sense of system safety.
Rosa: It means for the world, we have a way to make power system dispatch smarter and more resilient by using data-driven prediction instead of just relying on older analytical approximations. We've seen it works on those standard IEEE test systems, which is a good sign that it can be applied elsewhere too.
Dev: The caveat is that this specific AI predictor works best for the power flow part, and they noted it’s not the best fit for unit commitment problems where you make long-term decisions about generator commitment. So we have to be careful about applying it everywhere in the system design.
Taro: That’s fair. The focus here is clearly on real-time optimization during operation, and they leave the door open for future work on how this AI can help manage more complex things, like integrating those inverter-based resources we talked about earlier.
Rosa: So, to summarize, by using the DNN-FCOPF framework with its DNN frequency predictor and embedding it into a mixed-integer linear programming structure, they've delivered superior stability performance compared to both the traditional optimal power flow and the linearized version on standard test systems.
Dev: It’s a solid tool for enhancing system frequency stability by explicitly modeling those nonlinear relationships through data-driven prediction, ensuring critical metrics stay within safety thresholds.
Taro: It’s a step toward making control more adaptive, allowing the system to recover gracefully when things go wrong because it understands the dynamics better.
Rosa: That's right. We've seen how this framework can provide a powerful way for operators to enhance system frequency stability by capturing those complex governor dynamics overlooked by simpler models.
Dev: The next thing we need to watch is how this approach scales up when we try to integrate more distributed energy resources, because that’s where the next big challenge in power systems is heading.
University of Houston · Georgia Institute of Technology
eess.SY, cs.SY
Submitted: 2026-02-11
Updated: 2026-11-09
License: http://creativecommons.org/licenses/by-nc-sa/4.0/
Importance score: 89/100
The gist: Deep neural networks (DNNs) are utilized to capture the nonlinear mapping between system operating conditions and key frequency performance metrics in real-time frequency-constrained optimal power…
Key concepts
- Deep Neural Network-based Frequency Predictor (DNN-FP)
- A specialized AI model trained on high-fidelity simulation data to predict the worst frequency metrics, specifically RoCoF and FN. It learns the nonlinear relationship between system conditions and frequency performance without needing complex differential equations.
- Mixed-Integer Linear Programming (MILP) Formulation
- The DNN's complex output is transformed into a set of linear constraints using piecewise linearization. This allows the optimization problem to use standard, efficient MILP solvers while still enforcing the critical frequency limits derived from the AI prediction.
- Worst Rate of Change of Frequency (RoCoF)
- This metric measures how quickly system frequency can drop under stress, representing a critical stability limit. The DNN-FCOPF model ensures this constraint is binding, meaning the optimization prioritizes keeping RoCoF within safe operational bounds.
- Frequency Nadir (FN)
- The lowest point the system frequency reaches during a transient event. This constraint ensures that even during severe disturbances, the frequency does not drop below a predefined safety threshold, providing a measure of overall frequency security.
Terminology
Summary
Deep neural networks (DNNs) are utilized to capture the nonlinear mapping between system operating conditions and key frequency performance metrics in real-time frequency-constrained optimal power flow (FCOPF). p. 0 To address this issue, deep neural networks (DNNs) are
utilized to capture the nonlinear mapping between system operating conditions and key frequency performance metrics. In this
paper, a DNN-based frequency prediction model is developed
and trained using the high-fidelity time-domain simulation data
generated in PSCAD/EMTDC. However, accurately
modeling system frequency dynamics through analytical formulations is challenging due to their inherent nonlinearity and complexity. To address this issue, deep neural networks (DNNs) are
utilized to capture the nonlinear mapping between system operating conditions and key frequency performance metrics.Where the paper says it
Where the paper says it
Model Development
The primary contribution involves developing a DNN-based frequency predictor (DNN-FP) that simultaneously estimates both the worst rate of change of frequency (RoCoF) and the frequency nadir (FN) for FCOPF. This DNN-FP is trained using high-fidelity electromagnetic transient (EMT) simulation data generated in PSCAD/EMTDC to capture multigovernor dynamics without the computational burden of differential-algebraic equations (DAEs). p. 1 The
main contributions of this paper are summarized as follows:
A DNN-FP for predicting RoCoF and FN is developed
and trained using high-fidelity electromagnetic transient
(EMT) simulation data. By explicitly capturing multigovernor dynamics, the model can achieve higher accuracy without the computational burden of DAEs. By explicitly capturing multigovernor dynamics, the model can achieve higher accuracy without the computational burden of DAEs. The trained DNN-FP is first piecewise-linearized and
formulated as a set of mixed-integer linear constraints,
and then embedded into FCOPF, resulting in the proposed DNN-based FCOPF (DNN-FCOPF) model that
can guarantee frequency security with dispatch solutions.Where the paper says it
Where the paper says it
Training Data Acquisition
Acquiring a high-quality dataset is critical for training the DNN-FP and improving its accuracy, as the quality of the dataset has a direct impact on the model’s performance. The training data are generated through a large number of independent simulation runs, considering variations in load levels, initial generator outputs, and the locations of the tripped generator. p. 1 Accordingly, a PSCAD/EMTDC model is employed
in this paper to generate the high-fidelity training dataset, ensuring that EMT dynamics are properly captured. The training data are generated through a large number of
independent simulation runs, considering variations in load
levels, initial generator outputs, and the locations of the
tripped generator. For each simulation, the RoCoF and FN are
calculated. The RoCoF measurement window is typically selected between 5 and 10 cycles [24]; in this work, a 10-cycle
window (0. 3
measured value within this window is used as the RoCoF label. It is worth noting that frequency response may vary at different buses; hence, the center of inertia (COI) [25] is applied to
obtain system frequency and calculate RoCoF and FN. 3
measured value within this window is used as the RoCoF label. It is worth noting that frequency response may vary at different buses; hence, the center of inertia (COI) [25] is applied to
obtain system frequency and calculate RoCoF and FN.Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Optimization Frameworks
The paper compares three optimization formulations: a traditional Optimal Power Flow (T-OPF) without frequency constraints, a linearized FCOPF (L-FCOPF) incorporating simplified linear RoCoF and FN constraints, and the proposed DNN-FCOPF. The T-OPF minimizes the total operating cost subject to nodal power balance, power flow relations, generator output limits, and thermal limits of transmission lines. p. 2 𝑚𝑖𝑛 ∑ (𝑐ଶ,𝑃
ଶ
∈𝒢 + 𝑐ଵ,𝑃 + 𝑐,) (6)
where c2,i, c1,i, c0,i are generator cost coefficients, and Pi is the
active power output of i-th generator. The constraints of the T-OPF consist of nodal power balance, power flow relations, generator output limits, and thermal limits of transmission lines, which are given in (7)-(10),
respectively. ∆𝑓 = −
ோା ൬1 + 𝑒
ିకఠ௧ೌೝට
்(ோିி)
ଶுೞೞ ൰ (25)
(25) is linear with respect to ΔPe, and can therefore be incorporated into FCOPF formulation through constraint (26). 𝑓 −
ோା ൬1 + 𝑒
ିకఠ௧ೌೝට
்(ோିி)
ଶுೞೞ ൰ ≥ 𝑓௧ (26)
In summary, the L-FCOPF is an enhanced T-OPF with extra frequency constraints given in (13) and (26). 𝑎 ≤ 𝑧 − ℎ(1 − 𝐵) (27)
𝑎 ≥ 𝑧 (28)
𝑎 ≤ ℎ௨𝐵 (29)
𝑎 ≥ 0 (30)
where hu and hl are the lower boundary and upper boundary of
the value of all possible zm, and Bm is a binary variable. By applying this BigM linearization approach, the DNN-FP
can be embedded into the FCOPF formulation without loss of
accuracy, thereby transforming the resulting DNN-FCOPF into
a mixed-integer linear programming (MILP) problem.Where the paper says it
Where the paper says it
Where the paper says it
Performance Evaluation
The effectiveness of the proposed DNN-FCOPF is verified through comparisons with high-fidelity EMT simulation results and the two benchmark OPF models on the IEEE 9-bus and 39-bus standard test systems. Case studies show that while L-FCOPF fails to maintain RoCoF within permissible limits, the DNN-FCOPF successfully fulfills both stability requirements, with RoCoF constraints being binding and FN constraints remaining nonbinding. p. 6 Specifically, while the L-FCOPF
model satisfies the FN requirement, it fails to maintain the
RoCoF within permissible limits. In contrast, the proposed
DNN-FCOPF successfully fulfills both stability requirements,
ensuring a more robust frequency response. 7, the prediction accuracy for RoCoF
in the proposed DNN-FCOPF significantly surpasses that of
the L-FCOPF model. Specifically, RoCoF errors in the LFCOPF approach reach approximately 60%, whereas the
DNN-FCOPF consistently exhibits errors below 5%.Where the paper says it
Where the paper says it
Conclusion
The proposed DNN-FCOPF framework delivers superior SFR performance compared to both T-OPF and L-FCOPF by capturing complex governor dynamics overlooked by linearized models. The DNN-FP enables the optimization framework to significantly enhance system frequency stability, ensuring that critical frequency metrics are maintained within safety thresholds. p. 7 In summary, case studies conducted on the IEEE 9-bus system demonstrate that the proposed DNN-FCOPF framework
delivers superior SFR performance compared to both T-OPF
and L-FCOPF. By maintaining critical frequency metrics
within safety thresholds, the proposed approach significantly
enhances overall system frequency stability. 9
edly improving grid stability over the T-OPF and L-FCOPF
benchmarks. Building upon these findings, future research will
extend the DNN-FCOPF model to inverter-based resources,
incorporating grid-following and grid-forming control strategies to address the challenges of low-inertia renewable energy
integration.Where the paper says it
Where the paper says it
ACKNOWLEDGMENT
This research was (in part) supported by the National Science Foundation (NSF) under Grant No. 2337598; and it was partly supported by the NSF AI Institute for Advances in Optimization (Award 2112533) and the Georgia Tech Strategic Energy Institute. p. 8 ACKNOWLEDGMENT
This research was (in part) supported by the National
Science Foundation (NSF) under Grant No. 2337598; and it
was partly supported by the NSF AI Institute for Advances in
Optimization (Award 2112533) and the Georgia Tech Strategic
Energy Institute. 2337598; and it
was partly supported by the NSF AI Institute for Advances in
Optimization (Award 2112533) and the Georgia Tech Strategic
Energy Institute. This work was also in part supported by
University of Houston Chevron Energy Graduate Fellows
Awards.Where the paper says it
Where the paper says it
REFERENCES
[1] F. Jiang, X. Li and P. Van Hentenryck, A Deep Neural Network-based Frequency Predictor for Frequency-Constrained Optimal Power Flow,
2025 IEEE IAS Annual Meeting, Taipei, pp. 1-5.
[2] F. Milano, F. Dörfler, G. p. 8 Van Hentenryck, "A Deep Neural Network-based
Frequency Predictor for Frequency-Constrained Optimal Power Flow,"
2025 IEEE IAS Annual Meeting, Taipei, pp. Dörfler, G. Dörfler, G. Hill, and G. Hill, and G. Verbič, “Foundations
and challenges of low-inertia systems (Invited paper),” 2018 Power Systems Computation Conference (PSCC), Jun.Where the paper says it
Where the paper says it
Where the paper says it
[3] F. Jiang and X. p. 0 1
Deep Neural Network-Enhanced
Frequency-Constrained Optimal Power Flow
with Multi-Governor Dynamics
Fan Jiang, Student Member, IEEE, Xingpeng Li, Senior Member, IEEE, and
Pascal Van Hentenryck, Senior Member, IEEE
Abstract—To ensure frequency security in power systems, both
the rate of change of frequency (RoCoF) and the frequency nadir
(FN) must be explicitly accounted for in real-time frequencyconstrained optimal power flow (FCOPF). However, accurately
modeling system frequency dynamics through analytical formulations is challenging due to their inherent nonlinearity and complexity. 1
Deep Neural Network-Enhanced
Frequency-Constrained Optimal Power Flow
with Multi-Governor Dynamics
Fan Jiang, Student Member, IEEE, Xingpeng Li, Senior Member, IEEE, and
Pascal Van Hentenryck, Senior Member, IEEE
Abstract—To ensure frequency security in power systems, both
the rate of change of frequency (RoCoF) and the frequency nadir
(FN) must be explicitly accounted for in real-time frequencyconstrained optimal power flow (FCOPF). However, accurately
modeling system frequency dynamics through analytical formulations is challenging due to their inherent nonlinearity and complexity. Jiang and X. Li, “Frequency-Dynamics-Aware Economic Dispatch
with Optimal Grid-Forming Inverter Allocation and Reserved Power
Headroom”, Dec. Li, “Frequency-Dynamics-Aware Economic Dispatch
with Optimal Grid-Forming Inverter Allocation and Reserved Power
Headroom”, Dec. 2025, arXiv:2512. 2025, arXiv:2512. 01814 2025.Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
[4] G. Zhang and J. p. 8 01814
[4] G. Zhang and J. Zhang and J. McCalley, “Optimal power flow with primary and secondary frequency constraint,” 2014 North American Power Symposium
(NAPS), Sep.Where the paper says it
Where the paper says it
[5] Q. Shi, F. Li, and H. Cui, “Analytical Method to Aggregate MultiMachine SFR Model With Applications in Power System Dynamic Studies,” IEEE Transactions on Power Systems, vol. p. 8 McCalley, “Optimal power flow with primary and secondary frequency constraint,” 2014 North American Power Symposium
(NAPS), Sep. Cui, “Analytical Method to Aggregate MultiMachine SFR Model With Applications in Power System Dynamic
Studies,” IEEE Transactions on Power Systems, vol. Cui, “Analytical Method to Aggregate MultiMachine SFR Model With Applications in Power System Dynamic
Studies,” IEEE Transactions on Power Systems, vol. 6355–6367, Nov. Cui, “Analytical Method to Aggregate MultiMachine SFR Model With Applications in Power System Dynamic
Studies,” IEEE Transactions on Power Systems, vol. 6355–6367, Nov.Where the paper says it
Where the paper says it
Where the paper says it
[6] H. Ahmadi and H. p. 8 6355–6367, Nov. Ahmadi and H. Ahmadi and H. Ghasemi, “Security-Constrained Unit Commitment
With Linearized System Frequency Limit Constraints,” IEEE Transactions on Power Systems, vol. Ghasemi, “Security-Constrained Unit Commitment
With Linearized System Frequency Limit Constraints,” IEEE Transactions on Power Systems, vol. 1536–1545, Jul.Where the paper says it
Where the paper says it
Where the paper says it
[7] K. Li et al., “Frequency security constrained robust unit commitment for sufficient deployment of diversified frequency support resources,” IEEE Transactions on Industry Applications, vol. p. 8 1536–1545, Jul. , “Frequency security constrained robust unit commitment for
sufficient deployment of diversified frequency support resources,” IEEE
Transactions on Industry Applications, vol. , “Frequency security constrained robust unit commitment for
sufficient deployment of diversified frequency support resources,” IEEE
Transactions on Industry Applications, vol. 1725–1737,
Jan.Where the paper says it
Where the paper says it
[8] M. Tuo and X. Li, “Security-constrained unit commitment considering locational frequency stability in low-inertia power grids,” IEEE Transactions on Power Systems, vol. p. 8 1725–1737,
Jan. Li, “Security-constrained unit commitment considering
locational frequency stability in low-inertia power grids,” IEEE Transactions on Power Systems, vol. Li, “Security-constrained unit commitment considering
locational frequency stability in low-inertia power grids,” IEEE Transactions on Power Systems, vol. 4134–4147, Sep.Where the paper says it
Where the paper says it
[9] G. Cui, Z. Chu, and F. p. 8 4134–4147, Sep. Chu, and F. Chu, and F. Teng, “Control-mode as a grid service in software-defined power grids: GFL vs GFM,” IEEE Transactions on Power
Systems, vol. Teng, “Control-mode as a grid service in software-defined power grids: GFL vs GFM,” IEEE Transactions on Power
Systems, vol. 314–326, Jan.Where the paper says it
Where the paper says it
Where the paper says it
[10] H. Chávez, R. p. 8 314–326, Jan. Chávez, R. Chávez, R. Baldick, and S. Baldick, and S. Sharma, “Governor Rate-Constrained
OPF for Primary Frequency Control Adequacy,” IEEE Transactions on
Power Systems, vol. Sharma, “Governor Rate-Constrained
OPF for Primary Frequency Control Adequacy,” IEEE Transactions on
Power Systems, vol. 1473–1480, May 2014.Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
[11] P. M. Anderson and M. p. 2 To facilitate simplified estimation of frequency behavior, P. Anderson et al. Anderson and M. Mirheydar, “A low-order system frequency
response model,” IEEE Transactions on Power Systems, vol. Mirheydar, “A low-order system frequency
response model,” IEEE Transactions on Power Systems, vol. 720-729, Aug.Where the paper says it
Where the paper says it
Where the paper says it
[12] N. Nguyen, S. Almasabi, A. p. 8 720-729, Aug. Almasabi, A. Almasabi, A. Bera, and J. Bera, and J. Mitra, “Optimal Power Flow
Incorporating Frequency Security Constraint,” IEEE Transactions on
Industry Applications, vol. Mitra, “Optimal Power Flow
Incorporating Frequency Security Constraint,” IEEE Transactions on
Industry Applications, vol. 6508–6516, Nov.Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
[13] Z. Zhang, M. Zhou, Z. Wu, S. Liu, Z. Guo, and G. p. 8 2019
[13] Z. Guo, and G. 2019
[13] Z. Guo, and G. Guo, and G. Li, “A frequency
security constrained scheduling approach considering wind farm providing frequency support and reserve,” IEEE Transactions on Sustainable
Energy, vol. Guo, and G. Li, “A frequency
security constrained scheduling approach considering wind farm providing frequency support and reserve,” IEEE Transactions on Sustainable
Energy, vol. Li, “A frequency
security constrained scheduling approach considering wind farm providing frequency support and reserve,” IEEE Transactions on Sustainable
Energy, vol. 1086–1100, Apr. Li, “A frequency
security constrained scheduling approach considering wind farm providing frequency support and reserve,” IEEE Transactions on Sustainable
Energy, vol. 1086–1100, Apr.Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
[14] L. Sang, Y. Xu, Z. Yi, L. Yang, H. Long, and H. p. 8 1086–1100, Apr. Long, and H. Long, and H. Sun, “Conservative
Sparse Neural Network Embedded Frequency-Constrained Unit Commitment With Distributed Energy Resources,” IEEE Transactions on
Sustainable Energy, vol. Sun, “Conservative
Sparse Neural Network Embedded Frequency-Constrained Unit Commitment With Distributed Energy Resources,” IEEE Transactions on
Sustainable Energy, vol. 2351–2363, Oct.Where the paper says it
Where the paper says it
Where the paper says it
[15] X. Zhao, H. Wei, J. Qi, P. Li, and X. Bai, “Frequency Stability Constrained Optimal Power Flow Incorporating Differential Algebraic Equations of Governor Dynamics,” IEEE Transactions on Power Systems, vol. p. 8 2351–2363, Oct. Bai, “Frequency Stability Constrained Optimal Power Flow Incorporating Differential Algebraic Equations of Governor Dynamics,” IEEE Transactions on Power Systems,
vol. Bai, “Frequency Stability Constrained Optimal Power Flow Incorporating Differential Algebraic Equations of Governor Dynamics,” IEEE Transactions on Power Systems,
vol. 1666–1676, May 2021.Where the paper says it
Where the paper says it
[16] B. Zhou, R. Jiang, and S. p. 0 1
Deep Neural Network-Enhanced
Frequency-Constrained Optimal Power Flow
with Multi-Governor Dynamics
Fan Jiang, Student Member, IEEE, Xingpeng Li, Senior Member, IEEE, and
Pascal Van Hentenryck, Senior Member, IEEE
Abstract—To ensure frequency security in power systems, both
the rate of change of frequency (RoCoF) and the frequency nadir
(FN) must be explicitly accounted for in real-time frequencyconstrained optimal power flow (FCOPF). However, accurately
modeling system frequency dynamics through analytical formulations is challenging due to their inherent nonlinearity and complexity. Jiang, and S. Shen, “Frequency Stability-Constrained Unit
Commitment: Tight Approximation Using Bernstein Polynomials,”
IEEE Transactions on Power Systems, vol. Shen, “Frequency Stability-Constrained Unit
Commitment: Tight Approximation Using Bernstein Polynomials,”
IEEE Transactions on Power Systems, vol. 5907–5919,
Jul.Where the paper says it
Where the paper says it
Where the paper says it
[17] L. Fang, F. Jiang, A. Toms, and X. p. 8 5907–5919,
Jul. Toms, and X. Toms, and X. Li, “Analysis of Learning-based
Offshore Wind Power Prediction Models with Various Feature Combinations”, IEEE PES General Meeting, Austin, TX, USA, Jul.Where the paper says it
Where the paper says it
[18] C. Li et al., “Optimal Power Flow in a highly renewable power system based on attention neural networks,” Applied Energy, vol. p. 8 Li, “Analysis of Learning-based
Offshore Wind Power Prediction Models with Various Feature Combinations”, IEEE PES General Meeting, Austin, TX, USA, Jul. , “Optimal Power Flow in a highly renewable power system
based on attention neural networks,” Applied Energy, vol. , “Optimal Power Flow in a highly renewable power system
based on attention neural networks,” Applied Energy, vol. 122779, Apr.Where the paper says it
Where the paper says it
[19] J. Rahman, C. Feng, and J. p. 8 122779, Apr. Feng, and J. Feng, and J. Zhang, “Machine Learning-Aided Security
Constrained Optimal Power Flow,” 2020 IEEE Power & Energy Society
General Meeting (PESGM), Aug.Where the paper says it
Where the paper says it
[20] T. Pham and X. p. 8 Zhang, “Machine Learning-Aided Security
Constrained Optimal Power Flow,” 2020 IEEE Power & Energy Society
General Meeting (PESGM), Aug. Pham and X. Pham and X. Li, “Reduced Optimal Power Flow Using Graph Neural
Network,” 2022 North American Power Symposium (NAPS), Oct.Where the paper says it
Where the paper says it
[21] M. Tuo and X. Li, “Deep Learning based Security-Constrained Unit Commitment Considering Locational Frequency Stability in Low-Inertia Power Systems”, 54th North American Power Symposium, Salt Lake City, UT, USA, Oct. p. 8 Li, “Reduced Optimal Power Flow Using Graph Neural
Network,” 2022 North American Power Symposium (NAPS), Oct. Li, “Deep Learning based Security-Constrained Unit
Commitment Considering Locational Frequency Stability in Low-Inertia
Power Systems”, 54th North American Power Symposium, Salt Lake
City, UT, USA, Oct.Where the paper says it
[22] Y. Zhang et al. p. 8 01814
[4] G. Zhang and J. Zhang et al. , “Encoding Frequency Constraints in Preventive Unit
Commitment Using Deep Learning With Region-of-Interest Active
Sampling,” IEEE Transactions on Power Systems, vol. , “Encoding Frequency Constraints in Preventive Unit
Commitment Using Deep Learning With Region-of-Interest Active
Sampling,” IEEE Transactions on Power Systems, vol. 1942–1955, May 2022.Where the paper says it
Where the paper says it
Where the paper says it
[23] B. She, F. Li, H. Cui, J. Wang, Q. Zhang, and R. p. 8 01814
[4] G. Zhang and J. Zhang, and R. Bo, “Virtual Inertia
Scheduling (VIS) for Real-Time Economic Dispatch of IBR-Penetrated
Power Systems,” IEEE Transactions on Sustainable Energy, vol. Bo, “Virtual Inertia
Scheduling (VIS) for Real-Time Economic Dispatch of IBR-Penetrated
Power Systems,” IEEE Transactions on Sustainable Energy, vol. 938–951, Apr.Where the paper says it
Where the paper says it
Where the paper says it
[24] T. Amraee, M. G. Darebaghi, A. p. 8 938–951, Apr. Darebaghi, A. Darebaghi, A. Soroudi, and A. Soroudi, and A. Keane, “Probabilistic
under frequency load shedding considering RoCoF relays of distributed
generators,” IEEE Trans. Keane, “Probabilistic
under frequency load shedding considering RoCoF relays of distributed
generators,” IEEE Trans. Power Syst. Power Syst. 3587–3598,
Jul.Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
[25] F. Milano, “Rotor speed-free estimation of the frequency of the center of inertia,” IEEE Transactions on Power Systems, vol. p. 8 3587–3598,
Jul. Milano, “Rotor speed-free estimation of the frequency of the center of
inertia,” IEEE Transactions on Power Systems, vol. Milano, “Rotor speed-free estimation of the frequency of the center of
inertia,” IEEE Transactions on Power Systems, vol. 1153-
1155, Jan.Where the paper says it
Where the paper says it
[26] Q. Shi, F. Li, and H. Cui, “Analytical Method to Aggregate MultiMachine SFR Model with Applications in Power System Dynamic Studies,” IEEE Transactions on Power Systems, vol. p. 8 McCalley, “Optimal power flow with primary and secondary frequency constraint,” 2014 North American Power Symposium
(NAPS), Sep. Cui, “Analytical Method to Aggregate MultiMachine SFR Model With Applications in Power System Dynamic
Studies,” IEEE Transactions on Power Systems, vol.Where the paper says it
[27] Z. Zhang, M. Zhou, Z. Wu, S. Liu, Z. Guo, and G. Li, “A frequency security constrained scheduling approach considering wind farm providing frequency support and reserve,” IEEE Transactions on Sustainable Energy, vol. 13, no. 2, pp. 1086–1100, Apr. 2022.
[28] C. Zhao, F. Jiang and X. Li, “Linearization of ReLU Activation Function for Neural Network-Embedded Optimization: Optimal Day-Ahead Energy Scheduling”, arXiv:2310. p. 8 Jiang and X. Li, “Linearization of ReLU Activation Function for Neural Network-Embedded Optimization: Optimal Day-Ahead
Energy Scheduling”, arXiv:2310. Li, “Linearization of ReLU Activation Function for Neural Network-Embedded Optimization: Optimal Day-Ahead
Energy Scheduling”, arXiv:2310. 01758, Oct.Where the paper says it
Where the paper says it
[29] Manitoba Hydro International Ltd. p. 8 01758, Oct. 2023
[29] Manitoba Hydro International Ltd.Where the paper says it
May
[Online]. Available: https://www. p. 8 , “IEEE 09 Bus System”, May 22,
2018. Available: https://www. Available: https://www. com/knowledgebase/article/25
[30] PowerWorld Corporation, “Powerworld simulator 18 block diagrams,”
2014.Where the paper says it
Where the paper says it
[30] PowerWorld Corporation, “Powerworld simulator 18 block diagrams,” 2014. p. 8 Available: https://www. com/knowledgebase/article/25
[30] PowerWorld Corporation, “Powerworld simulator 18 block diagrams,”
2014.Where the paper says it
[31] pdf
[31] "IEEE Recommended Practice for Excitation System Models for Power
System Stability Studies," in IEEE Std 421. 5-2016 (Revision of IEEE
Std 421. 5-2016 (Revision of IEEE
Std 421. 5-2005), vol. 5-2005), vol. 1-207, 26 Aug.IEEE Recommended Practice for Excitation System Models for Power System Stability Studies,
in IEEE Std 421.5-2016 (Revision of IEEE Std 421. p. 8Where the paper says it
Where the paper says it
Where the paper says it
[32] J. Lu and X. Li, “Transmission Expansion Planning for RenewableEnergy-Dominated Power Grids Considering Climate Impact”, Journal of Modern Power Systems and Clean Energy, vol. p. 8 1-207, 26 Aug. Li, “Transmission Expansion Planning for RenewableEnergy-Dominated Power Grids Considering Climate Impact”, Journal
of Modern Power Systems and Clean Energy, vol. Li, “Transmission Expansion Planning for RenewableEnergy-Dominated Power Grids Considering Climate Impact”, Journal
of Modern Power Systems and Clean Energy, vol. 1737-
1748, Nov.Where the paper says it
Where the paper says it
[33] Anantha Pai. p. 8 1737-
1748, Nov. [33] Anantha Pai. [33] Anantha Pai. Energy Function Analysis for Power System Stability. Energy Function Analysis for Power System Stability. Springer, 1989.Where the paper says it
Where the paper says it
Where the paper says it
TABLE I
OBJECTIVES AND CONSTRAINTS OF T-OPF, L-FCOPF AND DNN-FCOPF
Model Objective Shared Constraints Unique Constraints
T-OPF (6) (7)-(10) None None None
L-FCOPF (13), (26) Frequency nadir and RoCoF constraints.
DNN-FCOPF (1)-(2), (4), (27)-(32) DNN-FP, frequency nadir and RoCoF constraints. p. 5 2 4 6 8 10 12 14 16 18 20 22 24
59. 5
2 4 6 8 10 12 14 16 18 20 22 24
Hour
Hour FN/Hz RoCoF/Hz∙s-1
DNN-FCOPF L-FCOPF T-OPF DNN-FCOPF L-FCOPF T-OPF
(a) Frequency nadir
(b) Rate of change of frequency
Fig.Where the paper says it
TABLE II
PARAMETERS IN THE FULL-ORDER FREQUENCY RESPONSE MODEL
Gen T1 T2 T3 T4 T5 F K R
G1m 0.15 0.05 0.3 0.26 8 0.27 1, G2ji 0.1, G2ji: This table lists the parameters in the full-order frequency response model. p. 4 PARAMETERS IN THE FULL-ORDER FREQUENCY RESPONSE MODEL
Gen T1 T2 T3 T4 T5 F K R
G1m 0. 05
Based on the modified IEEE 9-bus system, T-OPF, LFCOPF and DNN-FCOPF are implemented according to the
objective and constraints in Table I.Where the paper says it
Green — the paper says it, and the page is printed. Red — no passage carries it, so treat that sentence as unverified. The same check runs on your own text: check a summary against its source, $5.
Improvements for AI systems
-
DNN-based frequency predictor (DNN-FP) development allows AI systems to capture
the nonlinear mapping between system operating conditions and key frequency performance metrics,
which enables real-time prediction of worst rate of change of frequency (RoCoF) and frequency nadir (FN). -
The transformation of the trained DNN into a mixed-integer linear programming (MILP) form embeds these predictions as
additional constraints to explicitly enforce frequency security,
allowing the optimization problem to guarantee system stability through dispatch solutions. -
The proposed DNN-FCOPF model can perform real-time generation redispatch while simultaneously improving both
computational speed and solution accuracy
compared to conventional methods by replacing complex Differential Algebraic Equation (DAE)-based nonlinear constraints. -
The system can achieve superior frequency response by ensuring that the
RoCoF constraints are binding, whereas the FN constraints are nonbinding,
leading to a more robust frequency response where stability is primarily governed by RoCoF limitations. -
Case studies on IEEE 9-bus and 39-bus systems demonstrate that the DNN-FCOPF framework
delivers superior SFR performance compared to both T-OPF and L-FCOPF
by maintaining critical frequency metrics within safety thresholds.
Abstract
Frequency-constrained optimal power flow (FCOPF) should keep the rate of change of frequency (RoCoF) and the frequency deviation (FD) within their limits after a specified generator out-age. The linearized frequency constraints commonly used in FCOPF are derived from aggregated system frequency response (SFR) models, which describe the center of inertia (COI) fre-quency with simplified governor dynamics and can underesti-mate the frequency excursions experienced by individual genera-tors. To address this issue, this paper develops a neural network-based frequency predictor (NN-FP) trained on electromagnetic transient (EMT) simulations in PSCAD/EMTDC. The NN-FP predicts the worst RoCoF and the worst FD over the monitored generators, namely the generators at all buses other than the contingency bus. The trained NN-FP is reformulated and embed-ded into FCOPF with tightened frequency limits obtained from the test set prediction errors of NN-FP, leading to the proposed NN-FCOPF. The proposed model is compared with a traditional optimal power flow and a linearized FCOPF. EMT validation of 24-hour dispatches on the IEEE 9-bus and 39-bus systems shows that NN-FCOPF satisfies both limits in all hourly cases for the specified contingency, whereas the linearized FCOPF violates the limits in some hours because it underestimates the worst genera-tor RoCoF and FD.
Sources
- Frequency-Dynamics-Aware Economic Dispatch with Optimal Grid-Forming Inverter Allocation and Reserved Power Headroom
- Linearization of ReLU Activation Function for Neural Network-Embedded Optimization: Optimal Day-Ahead Energy Scheduling
Related papers
- Industrial Load Modeling and Optimization for Market-Based Interaction with Power Systems
- Exact and Approximate Convex Reformulation of Linear Stochastic Optimal Control with Chance Constraints
- Certified Set Convergence for Piecewise Affine Systems
- Symbolic Control for Stochastic Systems via Finite Parity Games
- Multiobjective optimization-based design and dispatch of islanded, hybrid microgrids for remote, off-grid communities in sub-Saharan Africa
- Physiology-informed layered sensing for intelligent human-exoskeleton interaction