pith. sign in

arxiv: 2605.21396 · v1 · pith:ZRYVYIHRnew · submitted 2026-05-20 · 📡 eess.SY · cs.SY

Grid-Aware Peer-to-Peer Energy Trading: A Learning-Augmented Framework

Devangi , Ankit Singhal , Yashasvi Bansal This is my paper

Pith reviewed 2026-05-21 03:20 UTC · model grok-4.3

classification 📡 eess.SY cs.SY
keywords peer-to-peer energy tradingmicrogridstransformer regressionDSO response predictiongrid constraintslearning-augmented frameworkdistribution networksprivacy preservation
0
0 comments X

The pith

A transformer regression model lets microgrids locally predict DSO responses to proposed P2P trades without sharing data.

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

The paper seeks to establish that a supervised transformer-based regression model, trained on trade proposals and operator responses, can accurately forecast how the distribution system operator will react to peer-to-peer energy exchanges among microgrids. This local prediction capability would let participants evaluate and adjust their trades independently, cutting communication volume while respecting network limits and keeping proposed deals private. The approach is tested on a modified IEEE 33-bus system with interconnected microgrids to check gains in market efficiency, higher trade acceptance, and lower computational load on the operator. If the predictions hold, active distribution networks could support more scalable P2P trading without constant central oversight.

Core claim

The central claim is that training a supervised transformer regression model enables microgrids to predict the DSO response to proposed P2P trades locally, so that prosumers can self-assess feasibility, refine decisions, and submit only viable trades without transmitting their proposals or waiting for repeated operator feedback.

What carries the argument

The supervised transformer-based regression model that maps proposed trade vectors to predicted DSO acceptance and network-feasibility signals.

If this is right

  • Prosumers can evaluate and adjust P2P trades locally before submission.
  • Direct sharing of trade proposals with the DSO is no longer required for feasibility checks.
  • DSO computational load drops because fewer invalid proposals reach it for review.
  • Transaction overhead and communication rounds decrease while preserving participant privacy.
  • Market efficiency and trade acceptance rates improve under the tested network constraints.

Where Pith is reading between the lines

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

  • The same prediction approach could extend to other distribution operators or larger radial networks if retrained on representative data.
  • Embedding the model inside local controllers might allow fully decentralized P2P clearing loops with minimal central involvement.
  • Accuracy on unseen load or generation patterns remains an open question that would require fresh test cases beyond the 33-bus validation set.

Load-bearing premise

The model trained on modified IEEE 33-bus data produces predictions accurate enough that prosumers can reliably refine trades without direct DSO communication.

What would settle it

Running the trained model on new trade proposals in the IEEE 33-bus test case and finding that more than a small fraction of accepted trades violate voltage or line limits, or that many feasible trades are rejected, would show the predictions are not reliable enough.

Figures

Figures reproduced from arXiv: 2605.21396 by Ankit Singhal, Devangi, Yashasvi Bansal.

Figure 1
Figure 1. Figure 1: Workflow of the proposed learning-augmented network-aware P2P trading framework [PITH_FULL_IMAGE:figures/full_fig_p002_1.png] view at source ↗
Figure 2
Figure 2. Figure 2: Utility function plot 2) Cost of generation: Generator costs follow a quadratic model (5) and its dispatch is constrained by the operating bounds (6). C(Gi,t) = ai · G2 i,t + bi · Gi,t (5) 0 ≤ Gi,t ≤ Gmax i,t (6) where, ai and bi denotes the quadratic and linear cost coeffi￾cients respectively. 3) Battery Energy Storage System (BESS): BESSs are now integral to modern microgrids, mitigating renewable interm… view at source ↗
Figure 3
Figure 3. Figure 3: Representation of radial distribution network under consider [PITH_FULL_IMAGE:figures/full_fig_p004_3.png] view at source ↗
Figure 4
Figure 4. Figure 4: Training process of learning - augmented model [PITH_FULL_IMAGE:figures/full_fig_p005_4.png] view at source ↗
Figure 5
Figure 5. Figure 5: Transformer encoder layer layer processes the input representation h (k) n through layer normalization, multi-head attention (MHA), and feed-forward neural network (FFNN) operations with residual connections. Specifically, layer normalization is first applied [28], and is given by: h˜(k) n = LN h (k) n  (24) A. Multi-Head Self Attention For self-attention, the query (Qn = h˜ (k) n WQ), key (Km = h˜ (k) m… view at source ↗
Figure 6
Figure 6. Figure 6: Network topology of IEEE-33 bus system ogy with a substation at Bus 1 and and an additional generator placed at Bus 18, details of which is shown in Table I. The line parameters and bus parameters are set as the standard IEEE 33- bus system [31]. The four microgrids are randomly positioned at Buses 17, 22, 25, and 32 in the network. Each microgrid in the system contains the load, generators, renewable and … view at source ↗
Figure 2
Figure 2. Figure 2: Generator cost coefficients vary across units (cheap [PITH_FULL_IMAGE:figures/full_fig_p006_2.png] view at source ↗
Figure 7
Figure 7. Figure 7: Dataset generation TABLE II: System parameters of microgrids Photovoltaic (PV) System Nominal PV capacity 10 kW Battery Energy Storage System (BESS) Rated power 10 kW Minimum/Maximum state of charge 4 kWh/20 kWh Charging / discharging efficiency 0.95 Diesel Generator (DG) Maximum generation (MG1, MG3) 52 kW Maximum generation (MG2, MG4) 44 kW to expensive), with linear coefficients in the range 0.079- 0.5 … view at source ↗
Figure 8
Figure 8. Figure 8: (a) c ls (Rs/KW2 ) (b) λcorr (Rs/KW2 ) (c) Load scale (d) Power factor (e) Solar uncertainty (%) TABLE III: Pearson correlation matrix for input parameters to the transformer model Pload n pf Pnet n c ls λcorr Pload n 1 -0.037247 0.000375 0.001291 -0.003418 pf -0.037247 1 -0.09222 0.047382 -0.04312 Pnet n 0.000375 -0.09222 1 -0.006556 -0.008725 c ls 0.001290 0.047382 -0.006556 1 -0.004120 λcorr -0.003418 -… view at source ↗
Figure 11
Figure 11. Figure 11: Illustration of the three case studies, where each case is a P2P [PITH_FULL_IMAGE:figures/full_fig_p008_11.png] view at source ↗
Figure 12
Figure 12. Figure 12: The box plot indicates a noticeable reduction in the [PITH_FULL_IMAGE:figures/full_fig_p008_12.png] view at source ↗
Figure 10
Figure 10. Figure 10: further demonstrates stable learning behavior, as the gradient norm decreases and stabilizes over epochs, indicating the absence of exploding or vanishing gradients. Similarly, the validation loss exhibits a rapid initial decline followed by smooth convergence, suggesting good generalization. The inset box plot highlights the balanced gradient flow across the embedding, encoder, and output layers, confirm… view at source ↗
Figure 14
Figure 14. Figure 14: Voltage profile of IEEE-33 bus system framework (Case 3), voltage profiles remain largely within permissible limits, with a maximum deviation of only +0.29%, which is negligible and demonstrates that the learned DSO re￾sponse effectively preserves network feasibility. Furthermore, the generator active and reactive power outputs, approximately (2.4, 1.5) MW and (1.75, 0.54) MVAr, operate within their respe… view at source ↗
Figure 13
Figure 13. Figure 13: Acceptance ratio The improvement in economic performance is directly associated with the higher trade acceptance ratio achieved under the proposed learning-augmented framework (Case 3) compared to Case 2, as shown in [PITH_FULL_IMAGE:figures/full_fig_p009_13.png] view at source ↗
read the original abstract

Distribution networks are transitioning from passive to active systems due to the growing integration of distributed energy resources (DERs). Peer to Peer (P2P) energy trading has emerged as a viable framework that enables local energy exchange among participants, represented here as aggregated microgrids (MGs). Incorporating network constraints is essential to ensure that P2P transactions remain physically feasible and consistent with grid's operating limits. However, existing P2P frameworks still lack advanced predictive mechanisms that allow prosumers to anticipate network feasibility or the distribution system operator (DSO) response during trade formulation. This paper proposes a learning augmented P2P and DSO interface that predicts the DSOs response to the proposed P2P trades, allowing prosumers to self-assess and refine their trading decisions. A supervised transformer based regression model is trained to enable MGs to locally predict the DSOs response without sharing their proposed trades, thereby reducing transaction overhead, alleviating DSO burden, and preserving information privacy. The proposed framework is validated on the modified IEEE 33 bus distribution power system with interconnected microgrids. Case studies are presented to validate the effectiveness of the proposed model in terms of market efficiency, trade acceptance and computational burden.

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 / 2 minor

Summary. The paper proposes a learning-augmented P2P energy trading framework in which a supervised transformer regression model, trained on simulation data from a modified IEEE 33-bus system, enables microgrids to locally predict the DSO response to proposed trades. This is intended to allow prosumers to self-assess and refine trades without direct communication, thereby reducing transaction overhead, alleviating DSO computational burden, and preserving privacy while respecting network constraints. The approach is validated through case studies on market efficiency, trade acceptance, and computational burden.

Significance. If the transformer predictions prove sufficiently accurate and generalizable, the framework could meaningfully lower communication and computational costs in grid-constrained P2P markets while maintaining privacy, addressing a practical bottleneck in active distribution networks with high DER penetration.

major comments (2)
  1. [§5] §5 (Case Studies): the abstract and case-study description assert that the framework is validated on market efficiency, trade acceptance, and computational burden, yet report no quantitative metrics (e.g., prediction RMSE/MAE for DSO response, trade-acceptance percentages, runtime comparisons against a direct DSO-query baseline, or training/validation split details). This absence makes it impossible to evaluate whether the claimed reductions in overhead and DSO burden are realized.
  2. [§4 and §5] §4 (Learning Model) and §5: the central claim that the transformer enables reliable local self-assessment rests on generalization beyond the training distribution of load, generation, and trade vectors. No out-of-distribution tests (different MG sizes, time-varying DER profiles, or adversarial trade proposals) are described; without them the prediction error could increase sharply for realistic unseen proposals, undermining the claimed privacy and efficiency gains.
minor comments (2)
  1. [§4] Notation for the transformer input features (proposed trade vectors, local measurements) is introduced without an explicit table or diagram showing the exact feature vector dimension and normalization.
  2. [§3] The modified IEEE 33-bus test system description omits the number of interconnected MGs, their internal DER capacities, and the exact network constraint formulation used to label the training data.

Simulated Author's Rebuttal

2 responses · 0 unresolved

We thank the referee for the constructive and detailed feedback. The points raised about quantitative validation and generalization are important for strengthening the manuscript. We address each major comment below, indicating the changes we will make.

read point-by-point responses

  1. Referee: [§5] §5 (Case Studies): the abstract and case-study description assert that the framework is validated on market efficiency, trade acceptance, and computational burden, yet report no quantitative metrics (e.g., prediction RMSE/MAE for DSO response, trade-acceptance percentages, runtime comparisons against a direct DSO-query baseline, or training/validation split details). This absence makes it impossible to evaluate whether the claimed reductions in overhead and DSO burden are realized.

    Authors: We agree that the case-study section would benefit from more explicit quantitative reporting. The current manuscript presents results on market efficiency, trade acceptance, and computational burden primarily through comparative figures and qualitative discussion of improvements. To address this, the revised version will include a new table in §5 with specific metrics: RMSE and MAE for the transformer predictions of DSO responses, trade-acceptance percentages across scenarios, runtime comparisons against a direct DSO-query baseline, and details on the training/validation split (e.g., 80/20 ratio). These additions will directly quantify the overhead reductions and DSO burden alleviation. revision: yes

  2. Referee: [§4 and §5] §4 (Learning Model) and §5: the central claim that the transformer enables reliable local self-assessment rests on generalization beyond the training distribution of load, generation, and trade vectors. No out-of-distribution tests (different MG sizes, time-varying DER profiles, or adversarial trade proposals) are described; without them the prediction error could increase sharply for realistic unseen proposals, undermining the claimed privacy and efficiency gains.

    Authors: The supervised transformer was trained on simulation data spanning diverse load, generation, and trade vectors from the modified IEEE 33-bus system to represent typical operating conditions. We acknowledge that explicit out-of-distribution evaluation would further substantiate the generalization claims. In the revision, we will add OOD tests in §5, including performance on varied MG sizes, time-varying DER profiles, and a set of adversarial trade proposals. Results will be reported alongside in-distribution metrics to confirm that prediction errors remain acceptable and support the privacy and efficiency benefits. revision: yes

Circularity Check

0 steps flagged

No significant circularity in the learning-augmented P2P framework

full rationale

The paper's central mechanism is a supervised transformer regression model trained on simulation data from the modified IEEE 33-bus system to predict DSO responses to proposed trades. This follows a standard supervised learning pipeline with no equations or derivations that reduce the claimed predictions to fitted quantities by construction. No self-citations, uniqueness theorems, or ansatzes are invoked to force the result; the model is presented as learning an independent mapping validated through case studies on market efficiency and trade acceptance. The derivation chain remains self-contained against external benchmarks.

Axiom & Free-Parameter Ledger

1 free parameters · 1 axioms · 0 invented entities

The central claim rests on the assumption that historical or simulated DSO responses form a representative training set for the transformer and that local predictions remain accurate enough to guide feasible trades. No new physical entities are introduced; the only free parameters are those internal to the supervised model.

free parameters (1)
  • Transformer model parameters
    Weights and biases of the regression model are fitted to data derived from the IEEE 33-bus simulations.
axioms (1)
  • domain assumption Training data captures representative DSO responses to P2P trades under network constraints
    Invoked when the abstract states that the model enables local prediction without sharing trades.

pith-pipeline@v0.9.0 · 5751 in / 1378 out tokens · 39725 ms · 2026-05-21T03:20:19.361890+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

33 extracted references · 33 canonical work pages · 2 internal anchors

  1. [1]

    Distributed energy resources based microgrid: Review of architecture, control, and relia- bility,

    A. Muhtadi, D. Pandit, N. Nguyen, and J. Mitra, “Distributed energy resources based microgrid: Review of architecture, control, and relia- bility,”IEEE Transactions on Industry Applications, vol. 57, no. 3, pp. 2223–2235, 2021

    work page 2021

  2. [2]

    Peer-to- Peer trading in electricity networks: An overview,

    W. Tushar, T. K. Saha, C. Yuen, D. Smith, and H. V . Poor, “Peer-to- Peer trading in electricity networks: An overview,”IEEE Transactions on Smart Grid, vol. 11, no. 4, pp. 3185–3200, 2020

    work page 2020

  3. [3]

    Stochastic cooperative bidding strategy for multiple microgrids with Peer-to-Peer energy trading,

    L. Wang, Y . Zhang, W. Song, and Q. Li, “Stochastic cooperative bidding strategy for multiple microgrids with Peer-to-Peer energy trading,”IEEE Transactions on Industrial Informatics, vol. 18, no. 3, pp. 1447–1457, 2021

    work page 2021

  4. [4]

    Distributed energy trading in microgrids: A game-theoretic model and its equilibrium analysis,

    J. Lee, J. Guo, J. K. Choi, and M. Zukerman, “Distributed energy trading in microgrids: A game-theoretic model and its equilibrium analysis,” IEEE Transactions on Industrial Electronics, vol. 62, no. 6, pp. 3524– 3533, 2015

    work page 2015

  5. [5]

    A converging non-cooperative & cooperative game theory approach for stabilizing Peer-to-Peer electricity trading,

    W. Amin, Q. Huang, M. Afzal, A. A. Khan, K. Umer, and S. A. Ahmed, “A converging non-cooperative & cooperative game theory approach for stabilizing Peer-to-Peer electricity trading,”Electric Power Systems Research, vol. 183, p. 106278, 2020

    work page 2020

  6. [6]

    Peer-to-Peer energy trading in smart grid considering power losses and network fees,

    A. Paudel, L. P. M. I. Sampath, J. Yang, and H. B. Gooi, “Peer-to-Peer energy trading in smart grid considering power losses and network fees,” IEEE Transactions on Smart Grid, vol. 11, no. 6, pp. 4727–4737, 2020

    work page 2020

  7. [7]

    A decentralized bilateral energy trading system for Peer-to-Peer electricity markets,

    M. Khorasany, Y . Mishra, and G. Ledwich, “A decentralized bilateral energy trading system for Peer-to-Peer electricity markets,”IEEE Trans- actions on Industrial Electronics, vol. 67, no. 6, pp. 4646–4657, 2020

    work page 2020

  8. [8]

    Interactive model for energy management of clustered microgrids,

    T. Lu, Z. Wang, Q. Ai, and W. J. Lee, “Interactive model for energy management of clustered microgrids,”IEEE Transactions on Industry Applications, vol. 53, no. 3, pp. 1739–1750, 2017

    work page 2017

  9. [9]

    Peer-to-Peer energy trading under network constraints based on generalized fast dual ascent,

    C. Feng, B. Liang, Z. Li, W. Liu, and F. Wen, “Peer-to-Peer energy trading under network constraints based on generalized fast dual ascent,” IEEE Transactions on Smart Grid, vol. 14, no. 2, pp. 1441–1453, 2022

    work page 2022

  10. [10]

    Incorporating P2P trading into DSO’s decision-making: A DSO-prosumers cooperated scheduling framework for transactive distribution system,

    H. Sheng, C. Wang, X. Dong, K. Meng, and Z. Dong, “Incorporating P2P trading into DSO’s decision-making: A DSO-prosumers cooperated scheduling framework for transactive distribution system,”IEEE Trans- actions on Power Systems, vol. 38, no. 3, pp. 2362–2375, 2022

    work page 2022

  11. [11]

    Cooperative P2P energy trading in active distribution networks: An MILP-based Nash bargaining solution,

    W. Zhong, S. Xie, K. Xie, Q. Yang, and L. Xie, “Cooperative P2P energy trading in active distribution networks: An MILP-based Nash bargaining solution,”IEEE Transactions on Smart Grid, vol. 12, no. 2, pp. 1264–1276, 2020

    work page 2020

  12. [12]

    Strategic decision-making of dis- tribution network operator with multi-microgrids considering demand response program,

    M. Jalali, K. Zare, and H. Seyedi, “Strategic decision-making of dis- tribution network operator with multi-microgrids considering demand response program,”Energy, vol. 141, pp. 1059–1071, 2017

    work page 2017

  13. [13]

    Direct energy trading of microgrids in distribution energy market,

    H. Kim, J. Lee, S. Bahrami, and V . W. Wong, “Direct energy trading of microgrids in distribution energy market,”IEEE Transactions on Power Systems, vol. 35, no. 1, pp. 639–651, 2019

    work page 2019

  14. [14]

    Distributed optimiza- tion for network-constrained Peer-to-Peer energy trading among multiple microgrids under uncertainty,

    L. Wang, Z. Wang, Z. Li, M. Yang, and X. Cheng, “Distributed optimiza- tion for network-constrained Peer-to-Peer energy trading among multiple microgrids under uncertainty,”International Journal of Electrical Power & Energy Systems, vol. 149, p. 109065, 2023

    work page 2023

  15. [15]

    Peer-to- Peer energy trading and energy conversion in interconnected multi- energy microgrids using multi-agent deep reinforcement learning,

    T. Chen, S. Bu, X. Liu, J. Kang, F. R. Yu, and Z. Han, “Peer-to- Peer energy trading and energy conversion in interconnected multi- energy microgrids using multi-agent deep reinforcement learning,”IEEE Transactions on Smart Grid, vol. 13, no. 1, pp. 715–727, 2022

    work page 2022

  16. [16]

    Data-driven stochastic game with social attributes for Peer-to-Peer energy sharing,

    L. Chen, N. Liu, L. Liu, X. Yu, and Y . Xue, “Data-driven stochastic game with social attributes for Peer-to-Peer energy sharing,”IEEE Transactions on Smart Grid, vol. 12, no. 6, pp. 5158–5171, 2021

    work page 2021

  17. [17]

    Optimal real-time pricing algorithm based on utility maximization for smart grid,

    P. Samadi, A. H. Mohsenian Rad, R. Schober, V . W. Wong, and J. Jatskevich, “Optimal real-time pricing algorithm based on utility maximization for smart grid,” inFirst IEEE International Conference on Smart Grid Communications, 2010, pp. 415–420

    work page 2010

  18. [18]

    Optimal operation approach with combined BESS sizing and PV generation in microgrid,

    Y . R. Lee, H. J. Kang, and M. K. Kim, “Optimal operation approach with combined BESS sizing and PV generation in microgrid,”IEEE Access, vol. 10, pp. 27 453–27 466, 2022

    work page 2022

  19. [19]

    Frequency stability constrained BESS sizing model for microgrids,

    M. Javadi, Y . Gong, and C. Chung, “Frequency stability constrained BESS sizing model for microgrids,”IEEE Transactions on Power Systems, vol. 39, no. 2, pp. 2866–2878, 2023

    work page 2023

  20. [20]

    Grid influenced Peer-to-Peer energy trading,

    W. Tushar, T. K. Saha, C. Yuen, T. Morstyn, H. V . Poor, R. Beanet al., “Grid influenced Peer-to-Peer energy trading,”IEEE Transactions on Smart Grid, vol. 11, no. 2, pp. 1407–1418, 2019

    work page 2019

  21. [21]

    Peer-to-Peer energy trading in transactive markets considering physical network constraints,

    M. H. Ullah and J. D. Park, “Peer-to-Peer energy trading in transactive markets considering physical network constraints,”IEEE Transactions on Smart Grid, vol. 12, no. 4, pp. 3390–3403, 2021

    work page 2021

  22. [22]

    Distributed transactive energy trading framework in distribution networks,

    J. Li, C. Zhang, Z. Xu, J. Wang, J. Zhao, and Y . J. A. Zhang, “Distributed transactive energy trading framework in distribution networks,”IEEE Transactions on Power Systems, vol. 33, no. 6, pp. 7215–7227, 2018

    work page 2018

  23. [23]

    A game-theoretic approach to energy trading in the smart grid,

    Y . Wang, W. Saad, Z. Han, H. V . Poor, and T. Bas ¸ar, “A game-theoretic approach to energy trading in the smart grid,”IEEE Transactions on Smart Grid, vol. 5, no. 3, pp. 1439–1450, 2014

    work page 2014

  24. [24]

    Convex relaxation of optimal power flow—Part I: For- mulations and equivalence,

    S. H. Low, “Convex relaxation of optimal power flow—Part I: For- mulations and equivalence,”IEEE Transactions on Control of Network Systems, vol. 1, no. 1, pp. 15–27, 2014

    work page 2014

  25. [25]

    Branch flow model: Relaxations and convexification—Part I,

    M. Farivar and S. H. Low, “Branch flow model: Relaxations and convexification—Part I,”IEEE Transactions on Power Systems, vol. 28, no. 3, pp. 2554–2564, 2013

    work page 2013

  26. [26]

    Attention is all you need,

    A. Vaswani, N. Shazeer, N. Parmar, J. Uszkoreit, L. Jones, A. N. Gomez, Ł. Kaiser, and I. Polosukhin, “Attention is all you need,”Advances in Neural Information Processing Systems, vol. 30, 2017

    work page 2017

  27. [27]

    Bert: Pre- training of deep bidirectional transformers for language understanding,

    J. Devlin, M. W. Chang, K. Lee, and K. Toutanova, “Bert: Pre- training of deep bidirectional transformers for language understanding,” inProceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, V olume 1 (long and short papers), 2019, pp. 4171–4186

    work page 2019

  28. [28]

    Layer Normalization

    J. L. Ba, J. R. Kiros, and G. E. Hinton, “Layer normalization,”arXiv preprint arXiv:1607.06450, 2016

    work page internal anchor Pith review Pith/arXiv arXiv 2016

  29. [29]

    An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale

    A. Dosovitskiy, “An image is worth 16x16 words: Transformers for image recognition at scale,”arXiv preprint arXiv:2010.11929, 2020

    work page internal anchor Pith review Pith/arXiv arXiv 2010

  30. [30]

    Effective LSTM neural network with adam optimizer for improving frost prediction in agriculture data stream,

    M. Arya and G. Hanumat Sastry, “Effective LSTM neural network with adam optimizer for improving frost prediction in agriculture data stream,” inInternational Conference on Modelling and Development of Intelligent Systems. Springer, 2022, pp. 3–17

    work page 2022

  31. [31]

    Network reconfiguration in distribution systems for loss reduction and load balancing,

    M. E. Baran and F. F. Wu, “Network reconfiguration in distribution systems for loss reduction and load balancing,”IEEE Transactions on Power Delivery, vol. 4, no. 2, pp. 1401–1407, 2002

    work page 2002

  32. [32]

    A. J. Wood, B. F. Wollenberg, and G. B. Shebl ´e,Power generation, operation, and control. John wiley & sons, 2013

    work page 2013

  33. [33]

    Distribution network-constrained optimization of Peer-to-Peer transactive energy trading among multi-microgrids,

    M. Yan, M. Shahidehpour, A. Paaso, L. Zhang, A. Alabdulwahab, and A. Abusorrah, “Distribution network-constrained optimization of Peer-to-Peer transactive energy trading among multi-microgrids,”IEEE Transactions on Smart Grid, vol. 12, no. 2, pp. 1033–1047, 2020

    work page 2020