Top Read Articles

Published in last 1 year |  In last 2 years |  In last 3 years |  All

Please wait a minute...


For Selected: Download Citations EndNote Ris BibTeX Toggle Thumbnails

Select

Application and prospect of federated learning in new power systems LYU Yongsheng, ZHANG Xiaoyu, WANG Xirong, GUO Peiqian Integrated Intelligent Energy    2024, 46 (11): 54-64.   DOI: 10.3969/j.issn.2097-0706.2024.11.007 Abstract （1343）   HTML （14）    PDF （1033KB）（1528）       Knowledge map    New power systems aiming to make clean， low-carbon， safe， flexible and efficient power supply is a key measure to achive the "dual carbon" target. However， with the widespread access of renewable energy， the fusion of artificial intelligence technologies and the rapid development of smart microgrids and distributed energy sources， such as electric vehicles， traditional centralized data processing methods fall short in protecting data privacy and enabling intelligent management. Federated learning （FL）， an innovative distributed machine learning technology， offers an effective efficiency optimization solution for new power systems due to its data privacy protection capability and intelligence. In reviews on the applications of FL in new power systems， basic principles and main algorithms of FL are expounded， practical cases of FL applied in load forecasting， anomaly detection， distributed power control and energy management under data privacy protection are analysed. Then the current technical challenges encounter by FL are also discussed. Finally， the prospects of FL in new power systems are made. Table and Figures | Reference | Related Articles | Metrics

Select

Calculation and prediction of carbon emission factors for the national power grid from 2005 to 2035 WEI Xikai, TAN Xiaoshi, LIN Ming, CHENG Junjie, XIANG Keqi, DING Shuxin Integrated Intelligent Energy    2024, 46 (3): 72-78.   DOI: 10.3969/j.issn.2097-0706.2024.03.009 Abstract （1012）   HTML （27）    PDF （539KB）（514）       Knowledge map    In the view of delayed data updates and inaccurate calculations on the carbon emission factor of the national power grid， a calculation method based on IPCC's carbon emission accounting method is proposed for the factor. IPCC's carbon emission accounting method can be employed on 25 kinds of fuels for power generation. First， carbon emission factors of the national power grid from 2005 to 2022 are obtained by the proposed methods. Then， the calculation results are compared with the official published data with an average deviation of 1.45%， which prove the accuracy of the algorithm. Finally， the emission factors from 2023 to 2035 are predicted under three scenarios， basic scenario， low-carbon scenario， and intensive carbon reduction scenario. In 2035， the emission factor decreased to 0.506 4， 0.480 7，and 0.443 8 kg/（kW·h） under the three scenarios，keeping the carbon emissions from power industry constantly low. As the proposed method has a high accuracy， it can dynamically reflect the current situation and development trend of China's power structure， and provide support for accurate evaluating on carbon emissions from electricity consumers. Table and Figures | Reference | Related Articles | Metrics

Select

Performance simulation and analysis of an isobaric compressed air energy storage system based on Aspen Plus HU Xueru, XING Lingli, LI Yuanyuan, SU Wen, LIU Pengfei, DING Ruochen, LIN Xinxing Integrated Intelligent Energy    2024, 46 (12): 72-80.   DOI: 10.3969/j.issn.2097-0706.2024.12.009 Abstract （937）   HTML （12）    PDF （1104KB）（236）       Knowledge map    Compressed air energy storage （CAES） is an effective solution for integrating renewable energy generation into the grid and improving grid stability. To reduce the volume of the air storage reservoir and maintain stable system operation， a thermodynamic simulation model for a 100 MW×4 h isobaric compressed air energy storage （I-CAES） system was developed using the industrial process simulation software Aspen Plus. The system's performance was calculated under design conditions， and the effects of compressor outlet temperature and the number of compression-expansion stages on system operation were analyzed. The results showed that when the compressor outlet temperature was 160 ℃， the I-CAES system with 4 compression and 4 expansion stages achieved an energy storage efficiency of 62.61% and an energy storage density of 5.99 kW·h/m³. For every 10 ℃ increase in compressor outlet temperature， both the energy storage density and efficiency increased by 2.66 kW·h/m³ and 1.49 percentage points， respectively. Additionally， for each additional compression-expansion stage， the energy storage density and efficiency increased by 6.34 kW·h/m³ and 0.81 percentage points， respectively. Table and Figures | Reference | Related Articles | Metrics

Select

Research on transformer fault diagnosis method based on improved TCN model XU Bo, WEI Yijun, DENG Fangming Integrated Intelligent Energy    2024, 46 (11): 38-45.   DOI: 10.3969/j.issn.2097-0706.2024.11.005 Abstract （751）   HTML （1）    PDF （1419KB）（1115）       Knowledge map    Transformer diagnosis methods based on traditional machine learning have been limited by low accuracy， single-source data， and a scarcity of fault samples. This paper proposes a transformer fault diagnosis model utilizing multi-source heterogeneous data fusion and the Mud Ring Algorithm （MRA） to optimize the Temporal Convolutional Network （TCN）. Oil chromatography data， infrared high-voltage bushing detection images， ultrasonic discharge detection images， and ultra-high frequency partial discharge detection images were selected as input information for the transformer fault diagnosis model. The Informer network and ResNet （Residual Network） were applied to extract and learn features from different data types， followed by feature fusion of multi-type data. The MRA algorithm was used to optimize the parameters of the TCN network， and the integrated results were used for fault classification. Experimental results showed that the proposed method achieved a Nash efficiency coefficient of 0.82 and an accuracy of 94.83%， with faster convergence， demonstrating its effectiveness in enhancing transformer fault diagnosis performance. Table and Figures | Reference | Related Articles | Metrics

Select

Control strategy of virtual synchronous generators based on adaptive control parameter setting DING Leyan, KE Song, YANG Jun, SHI Xingye Integrated Intelligent Energy    2024, 46 (3): 35-44.   DOI: 10.3969/j.issn.2097-0706.2024.03.005 Abstract （744）   HTML （0）    PDF （1093KB）（656）       Knowledge map    The new power system with new energy as the main body presents the characteristics of "low inertia and low damping". Since the virtual synchronous generator （VSG） control strategy can simulate the mechanical motion equation and electromagnetic characteristics of the synchronous generator， the strategy can enhance the stability of the power system by making the distributed inverters possess the inertia and damping characteristics of the synchronous generator. However， the strategy will compromise their dynamic regulation performances. Thus， a VSG control strategy based on adaptive control parameter setting is proposed. Firstly，the effects of inertia moment and damping coefficient on system frequency and output in transient process are analyzed by establishing a small signal model of VSGs. Then，the correlation between the adaptive moment of inertia， angular velocity variation ratio and angular velocity offset，and the correlation between the adaptive damping coefficient and the angular velocity offset are analyzed by the power angle-frequency oscillation curve of a synchronous generator. The selection principle for the inertia moment and damping coefficient in different intervals is obtained，and their calculation formula and the trigger thresholds are designed. Furthermore，by adding adaptive droop coefficient considering the upper and lower limits of frequency modulation power，a control strategy of VSGs based on adaptive control parameter setting is proposed. Finally， the simulation analysis on the off-grid VSG model is built by Matlab/Simulink，and the simulation results verify that the proposed control strategy can reduce the frequency offset， and improve the frequency stability and dynamic regulation ability of the system. Table and Figures | Reference | Related Articles | Metrics

Select

Analysis and research on carbon emission reduction from co-firing green ammonia in coal-fired power plants SHEN Mingzhong, Hu Xiaofu, SHEN Jianyong, HOU Pengfei Integrated Intelligent Energy    2024, 46 (10): 67-72.   DOI: 10.3969/j.issn.2097-0706.2024.10.009 Abstract （708）   HTML （4）    PDF （2296KB）（66）       Knowledge map    Co-firing green ammonia with coal-based fuels is a feasible carbon reduction pathway for coal-fired power plants.Analyzing carbon reduction across the entire chain not only facilitates the development of the green hydrogen and green ammonia industries and effectively promotes their efficient utilization，but also supports the advancement of ammonia-coal co-firing technology.In a scenario where green ammonia was produced using renewable energy-powered green electricity and co-fired of ammonia with coal in coal-fired power plants， the total CO2 reduction throughout the chain was calculated.The results showed that using 445 GW·h of green electricity to produce green ammonia and co-firing it in coal-fired units achieved a total CO2 reduction of 100.7 thousand tons/year.The CO2 reduction per unit of green electricity was approximately 226.29 g/（kW·h），and annual carbon reduction cost savings were estimated at 9.5 665×106 yuan. Table and Figures | Reference | Related Articles | Metrics

Select

Research on security and privacy protection of electric power data sharing XING Huidi, GONG Gangjun, ZHAI Mingyue, LIU Xuesong, WANG Haomiao, YANG Shuang Integrated Intelligent Energy    2024, 46 (5): 30-40.   DOI: 10.3969/j.issn.2097-0706.2024.05.004 Abstract （701）   HTML （13）    PDF （1839KB）（1976）       Knowledge map    Electric power data can reflect the development status of society and is promising in the opening and integrated applications. In order to create and release the value of power data， power companies need to build a data sharing service system for all industries. However， there are security issues such as privacy leakage， data tampering and shortage of data security aggregation method in the process of power data sharing. At present， there are three main technologies that can deal with the security problems above， blockchain， privacy computing and desensitization. Based on reviews on relevant literatures， a demand model for and privacy data protection in power data sharing is proposed. The three security and privacy protection technologies for electric power data sharing are summarized，and their integration and applications in different scenarios are comparatively analyzed. Different security and privacy protection schemes provide references for promoting electric power data opening and sharing. Table and Figures | Reference | Related Articles | Metrics

Select

Optimal capacity configuration of off-grid wind-solar hybrid hydrogen production and green ammonia synthesis system WANG Haiming, ZHANG Runzhi, ZHOU Jiahui, XU Gang, GENG Jiaxi Integrated Intelligent Energy    2024, 46 (11): 73-82.   DOI: 10.3969/j.issn.2097-0706.2024.11.009 Abstract （690）   HTML （9）    PDF （1748KB）（108）       Knowledge map    To address the significant fluctuations and storage and transportation challenges associated with renewable energy， an off-grid wind-solar hybrid hydrogen production and green ammonia synthesis system was proposed. The levelized cost of ammonia（LCOA） between the wind-solar hybrid system and standalone wind and solar energy systems was compared， and sensitivity analysis on the green ammonia cost of the system was performed. Based on actual wind-solar output data， the system tightly coupled capacity design with operation scheduling. Hourly scheduling optimization was performed under constraints of equipment operation status and capacity configuration， aiming to maximize the system's economic returns through a mixed-integer linear programming （MILP） algorithm. The hybrid strategy effectively reduced renewable energy volatility. Energy storage devices smoothed out hydrogen and electricity fluctuations， ensuring continuity and stability of energy supply. The research results provide a feasible basis for implementing wind-solar hydrogen-ammonia integrated projects in remote and weak-grid areas or regions where grid connection is challenging， and serve as a reference for the construction of future demonstration projects. Table and Figures | Reference | Related Articles | Metrics

Select

Key technologies for load forecasting in new power systems and their applications in diverse scenario ZHANG Dongdong, LI Fangning, LIU Tianhao Integrated Intelligent Energy    2025, 47 (3): 47-61.   DOI: 10.3969/j.issn.2097-0706.2025.03.005 Abstract （660）   HTML （15）    PDF （1269KB）（187）       Knowledge map    To achieve the goal of "dual carbon"， the new power system is transitioning towards greening， intelligence， and diversity. Load forecasting is crucial for ensuring the safe， economic， and reliable operation of the new power system. While traditional statistical methods perform well in forecasting load data with clear patterns， the high proportion of renewable energy and the stochastic user load in new power systems pose significant challenges to these methods. Artificial intelligence technologies， particularly machine learning and deep learning， have become research hotspots due to their advantages in dealing with complex data and extracting patterns， effectively improving the accuracy and robustness of load forecasting. In this context， load forecasting methods based on mathematical and statistical principles are reviewed and their limitations are discussed in this study. The latest advancements in applications of AI techniques in load forecasting are summarized， and the characteristics of traditional machine learning， deep learning， and hybrid forecasting models are analysed. Technical challenges of load forecasting and key applications under these five scenarios are summarized and discussed：regional system-level load forecasting， net load forecasting under high proportion of renewable energy scenarios，integrated energy system load forecasting in multi-type heterogeneous energy complementary scenarios， building load forecasting， and electric vehicle load forecasting. The future directions of load forecasting technologies are forecasted. Table and Figures | Reference | Related Articles | Metrics

Select

Research on the loss of magnetic components based on a data-driven method HUANG Wenxuan, ZENG Haozheng, LIN Yijin, YIN Linfei Integrated Intelligent Energy    2025, 47 (4): 73-84.   DOI: 10.3969/j.issn.2097-0706.2025.04.006 Abstract （638）   HTML （3）    PDF （5633KB）（354）       Knowledge map    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. Table and Figures | Reference | Related Articles | Metrics

Select

Study on optimized operation model and strategy for virtual power plants considering multi-energy coupling JIANG Yan, SONG Chenhui, ZHANG Ning, HE Bo, LU Yuting Integrated Intelligent Energy    2025, 47 (1): 34-41.   DOI: 10.3969/j.issn.2097-0706.2025.01.005 Abstract （600）   HTML （5）    PDF （2342KB）（103）       Knowledge map    An optimized operation model for virtual power plants（VPPs），which considers the multi-energy coupling characteristics of energy parks，is proposed to address issues like energy supply-demand imbalance and operational inefficiency caused by large-scale integration of renewable energy into the power grid. First，the basic concept of a VPP tailored for a multi-energy coupling park was introduced. Then，a power balance model for various energy systems within the VPP was developed，taking into account both multi-energy economic operations and renewable energy consumption needs within the park. Building upon this power balance model，an optimal operation model for a multi-energy coupled VPP was formulated，utilizing mixed integer linear programming for solving the model. Finally，simulations were conducted on the VPP incorporating multi-energy coupling equipment，demonstrating that this optimized model significantly enhanced the comprehensive utilization efficiency of heterogeneous energy sources，reduced operational costs，and improved the rate of renewable energy consumption. Table and Figures | Reference | Related Articles | Metrics

Select

Application and prospect of multimodal knowledge graph in electric power operation inspection LIN Jiajun, YAN Weidan, HU Junhua, ZHENG Yiming, SHAO Xianjun, GUO Bingyan Integrated Intelligent Energy    2024, 46 (1): 65-74.   DOI: 10.3969/j.issn.2097-0706.2024.01.008 Abstract （550）   HTML （19）    PDF （3326KB）（1151）       Knowledge map    In the context of building a new power system with new energy as the main body，knowledge graph（KG），a large-scale visual semantic network，is expanding its applications rapidly in power operation and inspection. The applications of KG in power operation and inspection mainly focus on semantic information processing. However，a large amount of heterogeneous data will be generated in power grid operation，being able to uphold the construction of multimodal knowledge graph（MMKG） which provides data support for various downstream tasks. In view of functional requirements on electric power inspection， MMKG is introduced to support the intelligent query answering system and fault handling. Expounding the construction technology of MMKG for power inspection data，the scenarios of power operation and inspection that MMKG can give full play in are summarized，and the development direction is forecasted. Finally，the challenges that will be faced by MMKG is analyzed comprehensively，which provides a reference for the development of intelligent power operation and inspection. Table and Figures | Reference | Related Articles | Metrics

Select

Optimal scheduling strategy of distributed PV‒energy storage systems based on PV output characteristics DONG Qiang, XU Jun, FANG Dongping, FANG Lijuan, CHEN Yanqiong Integrated Intelligent Energy    2024, 46 (4): 17-23.   DOI: 10.3969/j.issn.2097-0706.2024.04.003 Abstract （504）   HTML （17）    PDF （1052KB）（462）       Knowledge map    With the transformation and upgrading of China's energy mix， solar power generation technology has received increasing attention. However， large-scale grid-connection of distributed PV power stations will cause power fluctuations in the power grid. Since energy storage systems can facilitate load and frequency regulations， a joint optimal scheduling method for PV‒energy storage systems is proposed. Firstly， the optimal scheduling model of a PV‒energy storage system is constructed considering its economy and technical indicators， and the charging and discharging power of the energy storage modules are optimized with the aim of minimizing the variance of active power fluctuations. Secondly， a real-time scheduling strategy based on predicted PV outputs is proposed to improve the orderly grid-connection of distributed PV‒energy storage systems， which can smooth the load fluctuation of the grid and reduce load‒valley difference. Finally， a simulation study is designed and carried out to verify the feasibility of the method. Table and Figures | Reference | Related Articles | Metrics

Select

Photovoltaic power forecasting model based on probabilistic TCN-Transformer SHENG Ruixiang, ZHANG Xiaoyu Integrated Intelligent Energy    2024, 46 (11): 10-18.   DOI: 10.3969/j.issn.2097-0706.2024.11.002 Abstract （476）   HTML （17）    PDF （1450KB）（1306）       Knowledge map    A short-term PV power prediction method based on a temporal convolutional network （TCN） and a Transformer structure is proposed. Firstly， the main factors affecting PV power generation，such as wind speed， rainfall， light intensity and cloudiness， are analysed. Then， TCN is used to extract the global spatial features of the sequence， and Transformer is used to extract the temporal features of long-term dependencies in the sequence， so that a TCN-Transformer composite model with a high prediction precision is applied to PV power deterministic and probabilistic prediction. Simulation analyses are performed on the dataset from DKASC（Australia）， and the results show that the improved TCN-Transformer model exhibits excellent prediction performance under different weather conditions， improving the short-term prediction accuracy on PV power. Table and Figures | Reference | Related Articles | Metrics

Select

Research on multi-scale load prediction in parks based on CNN-LSTM-Self attention YANG Lanqian, GUO Jinmin, TIAN Huili, HUANG Chang, LIU Min, CAI Yang Integrated Intelligent Energy    2025, 47 (2): 79-87.   DOI: 10.3969/j.issn.2097-0706.2025.02.008 Abstract （460）   HTML （14）    PDF （1224KB）（160）       Knowledge map    Accurate load prediction is critical for improving the energy efficiency and profitability of zero-carbon smart parks. However， the application of conventional load prediction techniques faces two main challenges which are the difficulty in obtaining hourly numerical weather forecast data and the need for predictions across different time scales. In the absence of weather forecast data， a method using Convolutional Neural Networks（CNN） was proposed to extract the coupled spatial features between multiple loads. The reconstructed features were input into a Long Short-Term Memory（LSTM） network to extract temporal features of the load， followed by the application of a self-attention mechanism to enhance the model's ability to extract feature information. A fully connected network was then employed for load prediction， resulting in a multi-variable-load， multi-time-scale prediction model based on CNN-LSTM-Self attention. A case study of a park was used to predict its cooling， heating， and electrical loads for the next 1 hour， 1 day， and 1 week. Experimental results showed that the CNN-LSTM-Self attention model outperformed the CNN， LSTM， and CNN-LSTM models in terms of prediction accuracy across multiple time scales. Specifically， the CNN-LSTM-Self attention model showed a more significant advantage in predicting the 1-hour load， with the mean absolute percentage error（MAPE） of cooling， heating， and electrical load predictions improved by 16.25%， 19.16%， and 10.24%， respectively， compared to the CNN-LSTM model. Table and Figures | Reference | Related Articles | Metrics

Select

Review on the application of artificial intelligence in data mining and wind and photovoltaic power forecasting ZHANG Dongdong, SHAN Linke, LIU Tianhao Integrated Intelligent Energy    2025, 47 (3): 32-46.   DOI: 10.3969/j.issn.2097-0706.2025.03.004 Abstract （449）   HTML （8）    PDF （1386KB）（2398）       Knowledge map    As global demand for renewable energy continues to surge， efficiently and intelligently managing and forecasting renewable energy generation has become a pivotal research objective in energy sector. Applications of artificial intelligence （AI） technologies in the multi-dimensional data processing and intelligent forecasting of renewable energy generation are explored， focusing on its role in handling complex and highly variable data. First，the role of multi-dimensional feature mining techniques in processing wind and solar energy generation data from the perspective of meteorological conditions and spatiotemporal features is studied. Subsequently， a systematic analysis on intelligent forecasting techniques applied across different spatiotemporal scales and scenarios is offered， with particular emphasis on its usage in machine learning and deep learning models. These models have gained significant attention for their outstanding performance in dealing with nonlinear and high-dimensional data. Thorough reviews on the latest research findings demonstrate the substantial benefits of these AI technologies in enhancing the accuracy and efficiency of wind and solar energy generation forecasts. Additionally， it delves into the strengths and limitations of existing technologies and their development directions， particularly emphasizing the importance of improving the robustness， real-time processing capabilities， and adaptability of intelligent forecasting models in various scenarios. This study provides theoretical insights and practical guidance for advancing the development of renewable energy. Table and Figures | Reference | Related Articles | Metrics

Select

Design and economic analysis of the molten salt heat storage system for a 300 MW coal-fired heating unit ZHAO Dazhou, XIE Yurong, ZHANG Zhongping, DENG Ruifeng, LIU Lili Integrated Intelligent Energy    2024, 46 (9): 45-52.   DOI: 10.3969/j.issn.2097-0706.2024.09.006 Abstract （442）   HTML （7）    PDF （1883KB）（156）       Knowledge map    Deep peak shaving for thermal power units is an important measure to ensure the stable operation of the power grid. A thermodynamic model of a 300 MW coal-fired heating unit in China is established by software EBSILON. The accuracy of the model is verified by comparing the simulation parameters with the design values. To further enhance the deep peak shaving capability of the unit， two molten salt heating schemes powered by extracted main steam and reheat steam are proposed. To meet heating demands， the molten salt heat storage system is coupled to the original thermodynamic model， considering the storaged/released heating power of the system and molten salt heat storage capacity. Based on the model， the peak shaving depth and the power generation during non-peak shaving period are obtained. The main steam extraction scheme and the reheat steam extraction scheme can increase the peak shaving depth by 34.26 MW and 19.30 MW， respectively， and raise the peak power generation by 14.77 MW and 12.33 MW. At the same time， the economic performance analyses of the system in the electricity auxiliary service market and the electricity spot market are carried out. The results show that under certain peak shaving subsidies or peak-valley electricity price differences， the capital internal return rate of the project can reach 10%. Table and Figures | Reference | Related Articles | Metrics

Select

Digital empowerment of transport-energy integration：Technological pathways， application scenarios and future prospects LIU Bin, SUN Zhou, JIANG Zhiwei, GUO Mingyang, CAO Can Integrated Intelligent Energy    2025, 47 (2): 1-12.   DOI: 10.3969/j.issn.2097-0706.2025.02.001 Abstract （439）   HTML （11）    PDF （1018KB）（268）       Knowledge map    With the advancement of China's "dual-carbon" strategic goals and the accelerated development of the construction of a strong transportation network， the deep integration of transportation and energy has become a vital measure to enhance new productivity in the transportation systems. Driven by the wave of digitalization， technologies such as the internet of things （IoT），big data， and artificial intelligence （AI） offer new opportunities for the integration of transportation and energy. In this study， how digital technologies empower transport-energy integration is analysed from three aspects： technological pathways， application scenarios， and future prospects. The current state of transport-energy integration is reviewed and the advantages and challenges of digital technology applications in this field are explored. Leveraging typical cases such as wind-solar-storage-charge integrated intelligent highways， the technological pathways and demonstration applications of digital empowerment of transport-energy are expounded. The future prospects of digital technologies in transport-energy integration are envisioned and strategic recommendations in areas such as government policies， standard systems， and business models are offered. This study aims to provide reference for promoting the digitalization process of transportation and energy integration in China. Table and Figures | Reference | Related Articles | Metrics

Select

Optimal scheduling of virtual power plants integrating electric vehicles based on reinforcement learning LI Mingyang, DOU Mengyuan Integrated Intelligent Energy    2024, 46 (6): 27-34.   DOI: 10.3969/j.issn.2097-0706.2024.06.004 Abstract （436）   HTML （6）    PDF （1102KB）（783）       Knowledge map    Disorderly charging behaviors of massive electric vehicles （EVs） may cause violent fluctuations in power loads， affecting the security and stability of the power grid. With the application of vehicle to grid（V2G） technology， the scheduling method can be optimized by aggregating EV charging stations and surrounded distributed renewable energy generators into a virtual power plant（VPP）. The aggregation can improve the economy of charging behaviors and satisfaction of EV users， raise the utilization rate of distributed renewable energy， and mitigate load fluctuations in the grid. However， the overall charging or discharging load is the aggregation result of random charging or discharging behaviors of massive individual EVs， which is difficult to be accurately described by mathematical models. Thus，an interactive optimal scheduling framework based on deep reinforcement learning is presented for a VPP including EVs， with the objective of maximizing the benefit of all EV users in the VPP. The VPP control center，serving as an intelligent agent， can decide the charging and discharging of individual EVs without their detailed models. The agent continuously learns and updates its strategies through interactions with regional grids， overcoming the limitations of centralized optimal scheduling. The framework is solved by Deep Deterministic Policy Gradient（DDPG） algorithm. Simulation results show that， compared with the centralized scheduling， the proposed method improves the benefits of individual EV users， and the coordinative scheduling of EV charging/discharging loads and renewable energy outputs shaves the peak loads in the grid， and boosts the overall performance of the VPP. Table and Figures | Reference | Related Articles | Metrics

Select

Optimized scheduling of the power grid with participation of distributed microgrids considering their uncertainties TAN Jiuding, LI Shuaibing, LI Mingche, MA Xiping, KANG Yongqiang, DONG Haiying Integrated Intelligent Energy    2024, 46 (1): 38-48.   DOI: 10.3969/j.issn.2097-0706.2024.01.005 Abstract （431）   HTML （9）    PDF （1943KB）（478）       Knowledge map    Connecting distributed microgrids characterized by high-proportion renewable energy to the grid system can effectively reduce the carbon emissions from the whole system， but seriously impact the stable operation for the system as well. A wind-solar-power-battery integrated system is constructed in pursuit of the optimal economy，highest quality of power，lowest carbon emissions and highest level of customer satisfaction. The negative effects of grid-connection of distributed sources， such as wind power and solar power， on the operation of power grid are summarized. Then， the uncertain parametric model for the microgrid is constructed using probabilistic model， fuzzy affiliation model， robust uncertainty set and interval-censored data set as reference. Different solutions for the optimization scheduling plans for the microgrid considering the uncertainties of renewable energy are proposed and compared. Finally， the development outlook of the power sources with uncertainties is proposed to guide the optimization scheduling of the distributed microgrids. Table and Figures | Reference | Related Articles | Metrics