pith. sign in

arxiv: 2606.27602 · v1 · pith:LI2HJM26new · submitted 2026-06-25 · 🧮 math.OC

Uncertainty-aware Power System Planning via Gradient Descent

Mehrnoush Ghazanfariharandi , Robert Mieth This is my paper

Pith reviewed 2026-06-29 00:34 UTC · model grok-4.3

classification 🧮 math.OC
keywords power system planninguncertaintystochastic gradient descentday-ahead real-time operationsrenewable integrationinvestment decisionstwo-stage optimizationramping constraints
0
0 comments X

The pith

A projected stochastic gradient descent method lets power system planners account for day-ahead and real-time uncertainty and still obtain lower total costs while meeting renewable targets.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

Traditional power system planning models collapse operations into a single stage and therefore ignore uncertainty in each stage, which leads to underinvestment in transmission and flexible resources when renewables are stochastic. This paper introduces an optimization approach that keeps explicit two-stage day-ahead and real-time decisions, preserves ramping and storage time-coupling constraints, and solves the resulting problem with projected stochastic gradient descent plus a primal-dual framework and exponential moving average smoothing. When the resulting investment plans are tested in a two-stage simulation, they produce lower system-wide costs than a classic perfect-knowledge model while still satisfying the same renewable integration targets.

Core claim

By solving the two-stage planning problem with projected stochastic gradient descent, a primal-dual framework, and exponential moving average smoothing, the method produces investment decisions that, when evaluated in a two-stage day-ahead and real-time simulation, yield lower total system costs than a perfect-knowledge baseline while still achieving the prescribed renewable integration targets.

What carries the argument

projected stochastic gradient descent algorithm combined with a primal-dual optimization framework and exponential moving average smoothing strategy to solve the two-stage uncertain expansion planning problem

If this is right

  • Investment portfolios selected by the method meet renewable integration targets at lower total system cost than portfolios chosen under perfect-knowledge assumptions.
  • Time-coupling constraints for generator ramping and energy storage remain enforceable while uncertainty is modeled across both operational stages.
  • The same computational approach can be used to compare technology mixes under different renewable penetration targets without collapsing operations into a single stage.
  • Planning models that retain explicit two-stage decisions avoid the underinvestment in transmission and flexibility previously shown to result from ignoring operational uncertainty.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

  • Planners facing higher renewable shares may need to replace single-stage models with two-stage gradient-based solvers to prevent systematic under-procurement of flexible assets.
  • The method's convergence behavior under real data sets could be tested by replacing the exponential moving average smoother with alternative stabilization techniques.
  • Extending the framework to include transmission or distribution network constraints would show whether the cost advantage persists when network physics are modeled at higher fidelity.

Load-bearing premise

The two-stage day-ahead and real-time simulation used to score the investment plans accurately reflects the operational uncertainties, ramping limits, and market interactions that determine real costs and renewable performance.

What would settle it

Running the uncertainty-aware investment plans through an operational simulation that includes additional uncertainties or constraints omitted from the two-stage model and finding that total costs exceed those of the perfect-knowledge baseline would falsify the claimed advantage.

Figures

Figures reproduced from arXiv: 2606.27602 by Mehrnoush Ghazanfariharandi, Robert Mieth.

Figure 1
Figure 1. Figure 1: Schematic representation of our proposed investment–operation modeling framework and [PITH_FULL_IMAGE:figures/full_fig_p014_1.png] view at source ↗
Figure 2
Figure 2. Figure 2: (a): Augmented objective values for projected SGD with a Primal-Dual method ( [PITH_FULL_IMAGE:figures/full_fig_p023_2.png] view at source ↗
Figure 3
Figure 3. Figure 3: Comparison of optimal expansion decisions from the uncertainty-aware method (blue) [PITH_FULL_IMAGE:figures/full_fig_p024_3.png] view at source ↗
read the original abstract

Power system planning models provide important guidance on long-term investment strategies with significant socio-economic impact. To remain computationally manageable, however, such planning models compromise on the level of complexity with which power system operations and physics are captured. A common approach in most planning models is to collapse multi-stage power system operational processes into a single stage and, as a result, give up on the ability to account for uncertainty in each operational stage. In light of newly emerging load patterns and the continuing adoption of weather-dependent stochastic renewable generation, this uncertainty, however, becomes increasingly impactful on operations, and ignoring it has been shown to cause underinvestment in transmission capacity and flexible resources. In this work, we present a computational approach for power system expansion planning that explicitly considers two-stage day-ahead (DA) and real-time (RT) operational decisions under uncertainty while retaining time-coupling constraints to allow modeling generator ramping and energy storage. To solve the resulting optimization problem efficiently, we employ a projected stochastic gradient descent algorithm combined with a primal-dual optimization framework and an exponential moving average smoothing strategy to improve convergence stability. We evaluate the resulting investment decisions within a two-stage DA and RT simulation framework and compare them with a classic expansion planning model that assumes perfect knowledge of renewable generation. Our experiments show that the proposed framework achieves lower total system costs while ensuring that the implemented technology portfolio achieves set renewable integration targets.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Referee Report

2 major / 0 minor

Summary. The manuscript proposes a projected stochastic gradient descent algorithm augmented with a primal-dual framework and exponential moving average smoothing to solve a two-stage day-ahead/real-time power system expansion planning problem that retains ramping and storage constraints while explicitly modeling uncertainty. Investment decisions obtained from this solver are evaluated in a matching two-stage DA/RT simulation and reported to yield lower realized system costs than a perfect-foresight baseline while still satisfying renewable integration targets.

Significance. If the reported cost reductions prove robust, the work would demonstrate a scalable gradient-based route to uncertainty-aware planning that avoids the usual single-stage aggregation of operations, addressing documented underinvestment in flexibility. The combination of stochastic gradient methods with primal-dual updates for a multi-stage planning model with time-coupling constraints would be a technical contribution worth documenting, provided convergence behavior and implementation details are supplied.

major comments (2)
  1. [Abstract] Abstract: the headline empirical claim (lower total system costs while meeting renewable targets) is stated without any description of the test system, number of scenarios, uncertainty sampling procedure, or statistical significance of the cost differences; these omissions make it impossible to assess whether the advantage is attributable to the proposed method rather than to modeling choices.
  2. [Abstract] Evaluation framework (implicit in the comparison to the perfect-knowledge baseline): the two-stage DA/RT simulator used to score the investment decisions appears to employ the same operational constraints, uncertainty realizations, and market rules as the planning model itself; no out-of-sample validation against a higher-fidelity operational model or real market data is described, leaving open the possibility that reported savings arise from internal consistency rather than improved planning under realistic uncertainty.

Simulated Author's Rebuttal

2 responses · 0 unresolved

We thank the referee for their constructive comments, which highlight opportunities to strengthen the presentation of our results. We address each major comment below.

read point-by-point responses

  1. Referee: [Abstract] Abstract: the headline empirical claim (lower total system costs while meeting renewable targets) is stated without any description of the test system, number of scenarios, uncertainty sampling procedure, or statistical significance of the cost differences; these omissions make it impossible to assess whether the advantage is attributable to the proposed method rather than to modeling choices.

    Authors: We agree that the abstract would benefit from additional context on the experimental setup. The body of the manuscript reports results on a modified IEEE 118-bus system using 100 scenarios drawn from an empirical distribution of renewable generation; cost differences were evaluated across repeated simulation runs. We will revise the abstract to include a concise statement of the test system, scenario count, sampling approach, and consistency of the observed cost reductions. revision: yes

  2. Referee: [Abstract] Evaluation framework (implicit in the comparison to the perfect-knowledge baseline): the two-stage DA/RT simulator used to score the investment decisions appears to employ the same operational constraints, uncertainty realizations, and market rules as the planning model itself; no out-of-sample validation against a higher-fidelity operational model or real market data is described, leaving open the possibility that reported savings arise from internal consistency rather than improved planning under realistic uncertainty.

    Authors: The evaluation deliberately employs the identical two-stage operational model and uncertainty realizations for both the proposed method and the perfect-foresight baseline. This controlled design isolates the effect of uncertainty-aware planning on investment decisions. We acknowledge that the absence of out-of-sample testing against higher-fidelity models or real market data is a limitation. We will revise the manuscript to clarify the rationale for the current evaluation framework and to add an explicit discussion of this limitation together with suggestions for future validation. revision: yes

Circularity Check

0 steps flagged

No circularity; algorithmic solver evaluated against external baseline.

full rationale

The paper formulates a two-stage planning optimization and solves it via projected stochastic gradient descent with primal-dual updates and EMA smoothing. Investment decisions are then evaluated in a separate two-stage DA/RT simulation and compared to a perfect-foresight planning baseline. No load-bearing step reduces by the paper's own equations to a fitted parameter, self-citation, or input quantity by construction. The derivation chain consists of standard optimization techniques applied to an explicitly stated model; the empirical claim rests on out-of-sample simulation comparison rather than internal redefinition.

Axiom & Free-Parameter Ledger

0 free parameters · 1 axioms · 0 invented entities

Abstract-only view yields no explicit free parameters, invented entities, or non-standard axioms beyond routine assumptions of linear power system models and stochastic sampling.

axioms (1)
  • domain assumption Power system operations can be approximated by linear constraints and two-stage decisions under sampled uncertainty.
    Standard in planning models; invoked implicitly when collapsing multi-stage processes.

pith-pipeline@v0.9.1-grok · 5773 in / 1124 out tokens · 29150 ms · 2026-06-29T00:34:26.111060+00:00 · methodology

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Reference graph

Works this paper leans on

78 extracted references · 6 canonical work pages · 2 internal anchors

  1. [1]

    Available at SSRN 5169721 , year=

    Degleris, Anthony and El Gamal, Abbas and Rajagopal, Ram , title =. Available at SSRN 5169721 , year=

  2. [2]

    JuMP 1.0: Recent improvements to a modeling language for mathematical optimization , journal =

    Lubin, Miles and Dowson, Oscar and Garcia, Joaquim Dias and Huchette, Joey and Legat, Beno. JuMP 1.0: Recent improvements to a modeling language for mathematical optimization , journal =. 2023 , publisher =

    2023

  3. [3]

    Two-Stage ML-Guided Decision Rules for Sequential Decision Making under Uncertainty , journal =

    Rosemberg, Andrew and Street, Alexandre and Vallad. Two-Stage ML-Guided Decision Rules for Sequential Decision Making under Uncertainty , journal =

  4. [4]

    Flexible Differentiable Optimization via Model Transformations , journal =

    Besan. Flexible Differentiable Optimization via Model Transformations , journal =. 2023 , doi =

    2023

  5. [5]

    European Journal of Operational Research , volume =

    Pineda, Salvador and Morales, Juan M and Boomsma, Trine K , title =. European Journal of Operational Research , volume =. 2016 , publisher =

    2016

  6. [6]

    International Conference on Machine Learning , pages =

    Amos, Brandon and Kolter, J Zico , title =. International Conference on Machine Learning , pages =. 2017 , organization =

    2017

  7. [7]

    2013 , publisher =

    Morales, Juan M and Conejo, Antonio J and Madsen, Henrik and Pinson, Pierre and Zugno, Marco , title =. 2013 , publisher =

    2013

  8. [8]

    Annals of Operations Research , volume =

    Pozo, David and Sauma, Enzo and Contreras, Javier , title =. Annals of Operations Research , volume =. 2017 , publisher =

    2017

  9. [9]

    Rutgers Weather Research and Forecasting Model , year =

  10. [10]

    Annual Technology Baseline 2024 , year =

    2024

  11. [11]

    and Siddik, M

    Shehabi, Arman and Newkirk, Aaron and Smith, Sam and Hubbard, Alex and Lei, N. and Siddik, M. and others , title =. 2024 , doi =

    2024

  12. [12]

    Union, Europ. Directive 2009/28/EC of the European Parliament and of the Council of 23 April 2009 on the promotion of the use of energy from renewable sources and amending and subsequently repealing Directives 2001/77/EC and 2003/30/EC , journal =

    2009

  13. [13]

    Statistical analysis of wind power forecast error , journal =

    Bludszuweit, Hans and Dom. Statistical analysis of wind power forecast error , journal =. 2008 , publisher =

    2008

  14. [14]

    2014 , publisher =

    Ela, Erik and Milligan, Michael and Bloom, Aaron and Botterud, Audun and Townsend, Aaron and Levin, Todd , title =. 2014 , publisher =

    2014

  15. [15]

    Farghal, S. A. and Aziz, M. R. Abdel , title =. IEEE Transactions on Power Systems , volume =. 1988 , publisher =

    1988

  16. [16]

    IEEE Power Engineering Review , number =

    Caramanis, Michael C and Tabors, Richard D and Nochur, Kumar S and Schweppe, Fred C , title =. IEEE Power Engineering Review , number =. 2010 , publisher =

    2010

  17. [17]

    Applied Energy , volume =

    De Jonghe, Cedric and Delarue, Erik and Belmans, Ronnie and D'haeseleer, William , title =. Applied Energy , volume =. 2011 , publisher =

    2011

  18. [18]

    2011 IEEE Power and Energy Society General Meeting , pages =

    Palmintier, Bryan and Webster, Mort , title =. 2011 IEEE Power and Energy Society General Meeting , pages =. 2011 , organization =

    2011

  19. [19]

    IEEE Transactions on Power Systems , volume =

    Jin, Shan and Botterud, Audun and Ryan, Sarah M , title =. IEEE Transactions on Power Systems , volume =. 2014 , publisher =

    2014

  20. [20]

    IEEE Transactions on Power Systems , volume =

    Arabali, Amirsaman and Ghofrani, Mahmoud and Etezadi-Amoli, Mehdi and Fadali, Mohammed Sami and Moeini-Aghtaie, Moein , title =. IEEE Transactions on Power Systems , volume =. 2014 , publisher =

    2014

  21. [21]

    IEEE Transactions on Power Systems , volume =

    Orfanos, George A and Georgilakis, Pavlos S and Hatziargyriou, Nikos D , title =. IEEE Transactions on Power Systems , volume =. 2012 , publisher =

    2012

  22. [22]

    Journal of Regulatory Economics , volume =

    Munoz, Francisco D and Sauma, Enzo E and Hobbs, Benjamin F , title =. Journal of Regulatory Economics , volume =. 2013 , publisher =

    2013

  23. [23]

    IEEE Transactions on Power Systems , volume =

    Nanduri, Vishnu and Das, Tapas K and Rocha, Patricio , title =. IEEE Transactions on Power Systems , volume =. 2009 , publisher =

    2009

  24. [24]

    Generation capacity expansion in liberalized electricity markets: A stochastic MPEC approach , journal =

    Wogrin, Sonja and Centeno, Efraim and Barqu. Generation capacity expansion in liberalized electricity markets: A stochastic MPEC approach , journal =. 2011 , publisher =

    2011

  25. [25]

    IEEE Transactions on Power Systems , volume =

    Morales, Juan M and Pinson, Pierre and Madsen, Henrik , title =. IEEE Transactions on Power Systems , volume =. 2012 , publisher =

    2012

  26. [26]

    A representation and economic interpretation of a two-level programming problem , journal =

    Fortuny-Amat, Jos. A representation and economic interpretation of a two-level programming problem , journal =. 1981 , publisher =

    1981

  27. [27]

    Mathematical Programming , volume =

    McCormick, Garth P , title =. Mathematical Programming , volume =. 1976 , publisher =

    1976

  28. [28]

    Annals of Operations Research , volume =

    Zare, M Hosein and Borrero, Juan S and Zeng, Bo and Prokopyev, Oleg A , title =. Annals of Operations Research , volume =. 2019 , publisher =

    2019

  29. [29]

    Computers & Chemical Engineering , volume =

    Castro, Pedro M , title =. Computers & Chemical Engineering , volume =. 2015 , publisher =

    2015

  30. [30]

    Top , volume =

    Constante-Flores, Gonzalo and Conejo, Antonio J and Constante-Flores, S , title =. Top , volume =. 2022 , publisher =

    2022

  31. [31]

    International Conference on Artificial Intelligence and Statistics , pages =

    Lorraine, Jonathan and Vicol, Paul and Duvenaud, David , title =. International Conference on Artificial Intelligence and Statistics , pages =. 2020 , organization =

    2020

  32. [32]

    Efficient and modular implicit differentiation , journal =

    Blondel, Mathieu and Berthet, Quentin and Cuturi, Marco and Frostig, Roy and Hoyer, Stephan and Llinares-L. Efficient and modular implicit differentiation , journal =

  33. [33]

    International Conference on ``European Finance, Business and Regulation'' (EUFIRE 2020), Tofan, M., Bilan, I., Cigu, E

    Iarmenco, Mihaela and Donos, Evlampie and Plotnic, Olesea , title =. International Conference on ``European Finance, Business and Regulation'' (EUFIRE 2020), Tofan, M., Bilan, I., Cigu, E. (eds), Iasi, Romania , pages =

    2020

  34. [34]

    Computers & Operations Research , volume=

    Capacity expansion of stochastic power generation under two-stage electricity markets , author=. Computers & Operations Research , volume=. 2016 , publisher=

    2016

  35. [35]

    IEEE Transactions on Power Systems , volume=

    Security-constrained unit commitment with volatile wind power generation , author=. IEEE Transactions on Power Systems , volume=. 2008 , publisher=

    2008

  36. [36]

    Advances in Energy Systems: The Large-scale Renewable Energy Integration Challenge , pages=

    Handling renewable energy variability and uncertainty in power system operation , author=. Advances in Energy Systems: The Large-scale Renewable Energy Integration Challenge , pages=. 2019 , publisher=

    2019

  37. [37]

    Nature Energy , volume=

    Energy storage solutions to decarbonize electricity through enhanced capacity expansion modelling , author=. Nature Energy , volume=. 2023 , publisher=

    2023

  38. [38]

    Energy Economics , volume=

    On representation of energy storage in electricity planning models , author=. Energy Economics , volume=. 2024 , publisher=

    2024

  39. [39]

    Energy Reports , volume=

    Joint expansion planning of distribution network with uncertainty of demand load and renewable energy , author=. Energy Reports , volume=. 2022 , publisher=

    2022

  40. [40]

    IET Renewable Power Generation , volume=

    Stochastic multi-stage joint expansion planning of transmission system and energy hubs in the presence of correlated uncertainties , author=. IET Renewable Power Generation , volume=. 2023 , publisher=

    2023

  41. [41]

    Electric Power Systems Research , volume=

    Battery energy storage systems in transmission network expansion planning , author=. Electric Power Systems Research , volume=. 2017 , publisher=

    2017

  42. [42]

    IEEE Access , year=

    A review of evolving challenges in transmission expansion planning problems , author=. IEEE Access , year=

  43. [43]

    IEEE Transactions on Power Systems , volume=

    Incorporating non-convex operating characteristics into bi-level optimization electricity market models , author=. IEEE Transactions on Power Systems , volume=. 2019 , publisher=

    2019

  44. [44]

    Neural Computation , volume=

    Beyond backpropagation: bilevel optimization through implicit differentiation and equilibrium propagation , author=. Neural Computation , volume=. 2022 , publisher=

    2022

  45. [45]

    Computational Management Science , volume=

    Why there is no need to use a big-M in linear bilevel optimization: A computational study of two ready-to-use approaches , author=. Computational Management Science , volume=. 2023 , publisher=

    2023

  46. [46]

    SIAM Journal on Optimization , volume=

    KKT reformulation and necessary conditions for optimality in nonsmooth bilevel optimization , author=. SIAM Journal on Optimization , volume=. 2014 , publisher=

    2014

  47. [47]

    International conference on machine learning , pages=

    Bilevel programming for hyperparameter optimization and meta-learning , author=. International conference on machine learning , pages=. 2018 , organization=

    2018

  48. [48]

    International conference on machine learning , pages=

    Bilevel optimization: Convergence analysis and enhanced design , author=. International conference on machine learning , pages=. 2021 , organization=

    2021

  49. [49]

    Energy , volume =

    Wind data introduce error in time-series reduction for capacity expansion modelling , author =. Energy , volume =. 2022 , doi =

    2022

  50. [50]

    IEEE Transactions on Sustainable Energy , volume=

    Energy storage sizing taking into account forecast uncertainties and receding horizon operation , author=. IEEE Transactions on Sustainable Energy , volume=. 2016 , publisher=

    2016

  51. [51]

    2017 , publisher=

    First-order methods in optimization , author=. 2017 , publisher=

    2017

  52. [52]

    arXiv e-prints , pages=

    A Method for Learning to Solve Parametric Bilevel Optimization with Coupling Constraints , author=. arXiv e-prints , pages=

  53. [53]

    2013 , publisher=

    Integrating renewables in electricity markets: operational problems , author=. 2013 , publisher=

    2013

  54. [54]

    Operations research , volume=

    A single-settlement, energy-only electric power market for unpredictable and intermittent participants , author=. Operations research , volume=. 2010 , publisher=

    2010

  55. [55]

    Annals of Operations Research , volume=

    The impact of short-term variability and uncertainty on long-term power planning , author=. Annals of Operations Research , volume=. 2020 , publisher=

    2020

  56. [56]

    arXiv preprint arXiv:2603.00394 , year=

    Uncertainty-Aware Grid Planning in the Real World: A Method Enabling Large-Scale, Two-Stage Adaptive Robust Optimization for Capacity Expansion Planning , author=. arXiv preprint arXiv:2603.00394 , year=

    work page arXiv

  57. [57]

    Journal of Scientific Computing , volume=

    A two-phase stochastic momentum-based algorithm for nonconvex expectation-constrained optimization , author=. Journal of Scientific Computing , volume=. 2025 , publisher=

    2025

  58. [58]

    Advances in neural information processing systems , volume=

    Momentum-based variance reduction in non-convex sgd , author=. Advances in neural information processing systems , volume=

  59. [59]

    Stochastic Processes and their Applications , volume=

    Convergence and robustness of the Robbins-Monro algorithm truncated at randomly varying bounds , author=. Stochastic Processes and their Applications , volume=. 1987 , publisher=

    1987

  60. [60]

    International Conference on Machine Learning , pages=

    On gradient descent ascent for nonconvex-concave minimax problems , author=. International Conference on Machine Learning , pages=. 2020 , organization=

    2020

  61. [61]

    Mathematical Programming , volume=

    Stochastic first-order methods for convex and nonconvex functional constrained optimization , author=. Mathematical Programming , volume=. 2022 , publisher=

    2022

  62. [62]

    arXiv preprint arXiv:2305.19225 , year=

    Learning decision-focused uncertainty sets in robust optimization , author=. arXiv preprint arXiv:2305.19225 , year=

    work page arXiv

  63. [63]

    arXiv preprint arXiv:2510.25986 , year=

    A General and Streamlined Differentiable Optimization Framework , author=. arXiv preprint arXiv:2510.25986 , year=

    work page arXiv

  64. [64]

    Applied Energy , volume=

    The wind integration national dataset (wind) toolkit , author=. Applied Energy , volume=. 2015 , publisher=

    2015

  65. [65]

    Neurocomputing , volume=

    On hyperparameter optimization of machine learning algorithms: Theory and practice , author=. Neurocomputing , volume=. 2020 , publisher=

    2020

  66. [66]

    2026 , month = apr, url =

    2026

  67. [67]

    North American Electric Reliability Corporation (NERC), White Paper , year=

    Characteristics and risks of emerging large loads , author=. North American Electric Reliability Corporation (NERC), White Paper , year=

  68. [68]

    Integrated Investment and Policy Planning for Power Systems via Differentiable Scenario Generation

    Integrated Investment and Policy Planning for Power Systems via Differentiable Scenario Generation , author=. arXiv preprint arXiv:2604.14410 , year=

    work page internal anchor Pith review Pith/arXiv arXiv

  69. [69]

    IEEE Control Systems Letters , year=

    Value-oriented forecast combinations for unit commitment , author=. IEEE Control Systems Letters , year=

  70. [70]

    IEEE Transactions on Power Systems , volume=

    Fast security-constrained optimal power flow through low-impact and redundancy screening , author=. IEEE Transactions on Power Systems , volume=. 2020 , publisher=

    2020

  71. [71]

    SIAM Journal on Optimization , volume=

    Combining Progressive Hedging with a Frank--Wolfe Method to Compute Lagrangian Dual Bounds in Stochastic Mixed-Integer Programming , author=. SIAM Journal on Optimization , volume=. 2018 , publisher=

    2018

  72. [72]

    2021 , month =

    Ho, Jonathan and Becker, Jonathon and Brown, Maxwell and Brown, Patrick and Chernyakhovskiy, Ilya and Cohen, Stuart and Cole, Wesley and Corcoran, Sean and Eurek, Kelly and Frazier, Will and others , title =. 2021 , month =. doi:10.2172/1788425 , url =

    work page doi:10.2172/1788425 2021

  73. [73]

    2009 , publisher=

    Implicit functions and solution mappings , author=. 2009 , publisher=

    2009

  74. [74]

    Advances in neural information processing systems , volume=

    Task-based end-to-end model learning in stochastic optimization , author=. Advances in neural information processing systems , volume=

  75. [75]

    , author=

    An Updated Version of the IEEE RTS 24-Bus System for Electricity Market and Power System Operation Studies. , author=. 2016 , publisher=

    2016

  76. [76]

    IEEE Transactions on power apparatus and systems , number=

    IEEE reliability test system , author=. IEEE Transactions on power apparatus and systems , number=. 1979 , publisher=

    1979

  77. [77]

    On the Resolution of Stochastic MPECs over Networks: Distributed Implicit Zeroth-Order Gradient Tracking Methods

    On the Resolution of Stochastic MPECs over Networks: Distributed Implicit Zeroth-Order Gradient Tracking Methods , author=. arXiv preprint arXiv:2505.22916 , year=

    work page internal anchor Pith review Pith/arXiv arXiv

  78. [78]

    (2026) Data-Driven Uncertainty-aware Power System Planning via Gradient Descent Code Supplement

    https://github.com/MehrnoushGhazanfariharandi/Uncertainty-aware-PSP-via-SGD. (2026) Data-Driven Uncertainty-aware Power System Planning via Gradient Descent Code Supplement

    2026