Table of Content

25 April 2025, Volume 47 Issue 4

Previous Issue    Next Issue

Game Theory and Electricity Market Decision-Making Intelligent Power Systems and Control Optimization of Renewable Energy and Energy Storage Systems

Game Theory and Electricity Market Decision-Making

Review of demand response in smart grids from the perspective of game theory

CHENG Lefeng, LIU Yihang, ZOU Tao

2025, 47(4):  1-22.  doi:10.3969/j.issn.2097-0706.2025.04.001

Asbtract ( 107 )   HTML ( 8)   PDF (2026KB) ( 67 )  

Figures and Tables | References | Related Articles | Metrics

With the rapid development of smart grids and the deepening of power system reforms， demand-side users， as both buyers and sellers of electricity， face challenges in effectively participating in an open electricity market while achieving a win-win situation for all parties. This has emerged as a research hotspot and challenge. From the perspective of game theory， the main theoretical methods and practical applications of demand response（DR） in smart grids are reviewed and analyzed systematically. The typical game models on the electricity demand side are summarized， including static， dynamic， evolutionary， and cooperative games， and the application of game theory in DR optimization， profit distribution， and user behavior modeling in the context of distributed energy resource management， virtual power plants， and microgrids is explored. Additionally， the applicability and limitations of these models in addressing issues such as multi-agent decision-making， complex network structures， and information asymmetry are analyzed. The review indicates that game theory exhibits excellent flexibility and adaptability in the scenarios of multi-agent decision-making， particularly showing distinct advantages in addressing user load shifting， renewable energy fluctuations， and price incentive design. However， as the scale of the electricity market and smart grids continues to expand， three critical challenges remain： computational cost of dynamic game models， design of coordination mechanisms in multi-agent systems， and strategic uncertainties caused by information asymmetry. Integrating big data and artificial intelligence technologies can further enhance the feasibility and efficiency of game models in high-dimensional， incomplete information， and real-time response environments. Overall， game theory provides important theoretical support and technical solutions for optimizing multi-agent interactions in smart grid demand response. Future research can further explore hybrid game models and integrate emerging technologies like blockchain to improve user data sharing and settlement mechanisms. This can promote multi-energy coupling and interdisciplinary coordinated scheduling， thereby providing more comprehensive and efficient solutions for achieving safe， cost-effective， and low-carbon power grid operation.

Noise reduction optimization of wind farms considering fatigue damage using a multi-layer feedforward neural network-sequential quadratic programming approach

HUANG Linjie, XIE Zhishan, LIAO Yongxing, YIN Linfei

2025, 47(4):  23-32.  doi:10.3969/j.issn.2097-0706.2025.04.002

Asbtract ( 45 )   HTML ( 2)   PDF (1915KB) ( 21 )  

Figures and Tables | References | Related Articles | Metrics

An optimization scheme was developed to address the issue of excessive stress accumulation and fatigue damage in wind turbine components caused by mismatched dispatch instructions and wind speed during actual operation. To mitigate the unavoidable interference of noise and delay inherent in long-distance sensor data transmission， a seven-level real-time noise reduction feedforward neural network was developed by combining multiple feedforward neural networks. The collected signals were first denoised before being fed into the controller for further analysis. To verify the robustness of the seven-level real-time noise reduction feedforward neural network under complex scenarios， additional noisy and delayed data were used for testing. The results confirmed that the designed noise reduction neural network met the design requirements. To achieve real-time quantification of the cumulative fatigue damage in wind turbine components， the three-point rainflow counting method was improved. The dispatch instructions for wind turbines were optimized using the Sequential Quadratic Programming （SQP） algorithm. The optimized dispatch instructions were more reasonable， leading to a more uniform distribution of cumulative fatigue damage across turbines compared to pre-optimization. This avoids the excessive accumulation of fatigue damage in individual turbines.

Research on cost analysis and prediction methods for power transmission and transformation projects based on propagation models and neural networks

LU Handong, FANG Ming, LIU Ganggang, ZHOU Yan

2025, 47(4):  33-40.  doi:10.3969/j.issn.2097-0706.2025.04.003

Asbtract ( 40 )   HTML ( 2)   PDF (1938KB) ( 40 )  

Figures and Tables | References | Related Articles | Metrics

Accurate prediction on the costs of transmission and substation projects is crucial for the planning and implementation of modern power systems. Traditional prediction methods often suffer from low accuracy and poor adaptability while handling quantitative prediction problems such as time series and structural analyses. To improve prediction accuracy， a cost prediction method for transmission and substation projects was proposed based on the Susceptible-Infected-Removed （SIR） epidemic model and neural networks. This method utilized the SIR model for dynamic modeling of variable costs， and fitted the model parameters with nonlinear least squares. Historical data and model parameters were then input into a Feedforward Neural Network（FNN）， and predictions were obtained through training and computation. Finally， Bayesian optimization algorithm （BOA） was employed to optimize the hyperparameters of the FNN， completing the BOA-FNN model training. The study results indicated that this prediction method achieved a mean absolute percentage error （MAPE） as low as 0.430 7%， significantly enhancing prediction accuracy with stability and reliability.

Intelligent Power Systems and Control

Research and prospects of self-healing control methods and their applications in metro power supply systems

FENG Jianbing, YU Tao, CHENG Lefeng

2025, 47(4):  41-62.  doi:10.3969/j.issn.2097-0706.2025.04.004

Asbtract ( 91 )   HTML ( 4)   PDF (2027KB) ( 24 )  

Figures and Tables | References | Related Articles | Metrics

Metro is a crucial part of urban public transportation， and the stability and reliability of its power supply systems are of paramount importance. Unlike traditional high-voltage transmission networks， metro power supply systems operate within a closed AC-DC hybrid network， facing unique challenges such as highly dynamic load variations and short but densely distributed power supply links. Self-healing control ensures safe and continuous operation in the event of faults through real-time monitoring， intelligent diagnosis， and automatic recovery. Research progress on self-healing control methods for power supply systems is reviewed， with a focus on control architectures， intelligent optimization， and fault diagnosis methods. Based on the characteristics of metro power supply systems， the applications of multi-agent systems （MAS） and the IEC 61850 communication standard in self-healing control are explored. Given the trend of integrating distributed energy sources into metro power supply systems， a series of self-healing control strategies are proposed to effectively reduce dependence on centralized power supply. Additionally， emerging research directions based on big data， intelligent algorithms， and distributed control are discussed， providing key technical support for self-healing control in metro power supply systems.

Photovoltaic output prediction based on multi-convolutional combined large model

YIN Linfei, ZHANG Yiling

2025, 47(4):  63-72.  doi:10.3969/j.issn.2097-0706.2025.04.005

Asbtract ( 53 )   HTML ( 1)   PDF (2057KB) ( 17 )  

Figures and Tables | References | Related Articles | Metrics

To address the issue of low accuracy in photovoltaic output prediction， a multi-convolutional combined large model is proposed， integrating triple convolutional neural networks（TCNNs）， a weighted fully-connected regression network（WFRN），and improved bidirectional encoder representations from transformers（IBERT）. The TCNNs employed convolutional kernels of multiple sizes to efficiently extract feature information from photovoltaic data， progressing from shallow to deep layers. The weighted fully-connected regression network（WFRN） optimized the weight coefficients of the prediction outputs from two deep neural networks using particle swarm optimization algorithm， thereby enhancing prediction accuracy. The prediction results from TCNNs and WFRN were integrated and input into the IBERT for training. The attention mechanism of IBERT was then employed to perform interpretable feature analysis， determining the final photovoltaic output prediction value. The TCNNs-WFRN-IBERT model was applied to predict the hourly photovoltaic output power for the next day in Natal， Brazil. Simulation tests were conducted using actual photovoltaic output and meteorological data， and the results were compared with those of 38 algorithms. The results showed that the mean absolute error（MAE）， mean squared error（MSE）， and root mean squared error（RMSE） of the TCNNs-WFRN-IBERT model were 22.61 W， 1 818.20 W² and 42.64 W， respectively. Compared with other models， the evaluation metrics of TCNNs-WFRN-IBERT were lower than those of the other models， with its MAE value being at least 2.71% smaller than those of the other 38 comparative models， validating the effectiveness of the proposed model.

Research on the loss of magnetic components based on a data-driven method

HUANG Wenxuan, ZENG Haozheng, LIN Yijin, YIN Linfei

2025, 47(4):  73-84.  doi:10.3969/j.issn.2097-0706.2025.04.006

Asbtract ( 51 )   HTML ( 1)   PDF (5633KB) ( 14 )  

Figures and Tables | References | Related Articles | Metrics

To improve the efficiency of power converters， it is necessary to conduct a correlation analysis of the factors affecting the magnetic core loss of magnetic components in power converters. The core loss under the influence of specific factors can be predicted using regression methods. To improve the accuracy of core loss prediction， a data-driven method was adopted， employing a decision gradient boosting model and out-of-bag error variation to independently analyse the influencing factors. The K-means clustering method combined with the silhouette coefficient method was used to cluster the influencing factors and analyse the synergistic effects of factor combinations on core loss. Based on the importance analysis of these factors， the GhostNet neural network was used for prediction. A multi-objective genetic algorithm was used to explore the conditions under which magnetic components achieved maximum transmitted magnetic energy while minimizing core loss. Simulation results demonstrated that the proposed GhostNet-based core loss prediction method achieved excellent accuracy and strong generalization， with an coefficient of determination of 0.986 5， mean absolute error of 2.154 9×10⁴， and mean bias error of 3.418 2×10⁶ on the test set. Furthermore， the proposed multi-objective genetic algorithm exhibited excellent global search capabilities， effectively avoiding local optima and identifying a smaller Pareto front.

Optimization of Renewable Energy and Energy Storage Systems

Research on operation optimization and benefit distribution of integrated energy systems for industrial enterprises with inclusion of energy storage operators

HAO Ning, ZHANG Tianbo, JIANG Li

2025, 47(4):  85-97.  doi:10.3969/j.issn.2097-0706.2025.04.007

Asbtract ( 64 )   HTML ( 5)   PDF (1979KB) ( 35 )  

Figures and Tables | References | Related Articles | Metrics

The successful promotion and practical implementation of integrated energy systems in industrial enterprises require collaborative efforts among all stakeholders.Focused on industrial enterprises，an integrated energy system was developed incorporating investment and operation participation from energy storage operators.Based on the principles of cost-sharing，benefit-sharing，risk-sharing and win-win cooperation，the optimal operation strategies of the energy system，the quantification of collaborative benefits，and fair benefit distribution were explored.Considering demand response of power loads，a mathematical optimization model was established for the operation of an integrated energy system coupled with energy storage.A three-level evaluation index system was then developed，covering both direct economic benefits and indirect social benefits.On this basis，the monetization value equivalence method was applied to quantify collaborative benefits， and the cost-benefit method was used to ensure fair benefit distribution among multiple stakeholders.Case study results showed that the proposed mathematical optimization model and benefit distribution mechanism were reasonable and effective，with the B/C values exceeding 1 for both the overall system and individual stakeholders.

Research on multi-objective optimal economic dispatch of power systems based on NSMFO-BERT algorithm

ZENG Haozheng, YIN Linfei

2025, 47(4):  98-106.  doi:10.3969/j.issn.2097-0706.2025.04.008

Asbtract ( 61 )   HTML ( 4)   PDF (2251KB) ( 18 )  

Figures and Tables | References | Related Articles | Metrics

With the increasing integration of renewable energy， traditional power system models can no longer meet the complex demands of modern power systems. To adapt to the trend of multi-energy collaborative power generation， a new-type power system model was developed， primarily based on thermal power generation with renewable energy as supplementary sources. Due to the multi-objective trade-offs between power generation costs and carbon emission targets in the new-type power system， an intelligent optimization method was required to dynamically adjust the output of each generating unit and fully leverage the advantages of various energy sources. Therefore， a non-dominated sorting moth-flame optimization algorithm based on bidirectional encoder representations from transformers （NSMFO-BERT） was proposed. As a large model， BERT excelled in handling complex data relationships. By learning from NSMFO， it established the relationship between the active power of generating units and load forecasting， rapidly developing scheduling strategies for a large number of generating units. Simulation results showed that compared to NSMFO， the multi-objective grey wolf algorithm， and the multi-objective ant lion algorithm， NSMFO-BERT could find a Pareto curve with lower target values for power generation costs and carbon emissions. Furthermore， the computation speed of the proposed algorithm was 69.3%， 61.4%， and 90.9% faster than the aforementioned algorithms， respectively. It demonstrated strong generalization ability， suitable for addressing large-scale power system scheduling problems.