Research on Multi-Timescale Coordinated Source-Load Forecasting and Control for Multiple Distributed Resources
Main Article Content
Keywords
distributed generation, adjustable load, multi-timescale forecasting, power shortfall, optimal control
Abstract
Socioeconomic development continues to increase urban electricity demand. At the same time, the global greenhouse effect has made extreme heat events more frequent and prolonged in recent years, substantially affecting urban power loads. Cities are major load centers but are often far from large power-generation bases, resulting in an inverse geographical distribution of sources and loads. During extreme-heat peak-load periods, remote power supplies may be insufficient because of various constraints. It is therefore necessary to coordinate distributed generation, energy storage, adjustable loads, and other resources in or near cities with remote power supplies across regions to support urban demand and ensure a reliable electricity supply. This paper develops a three-stage, multi-timescale coordinated forecasting and control method for multiple distributed resources. The day-ahead analysis and forecasting, intraday rolling optimization, and real-time coordinated optimization stages are solved sequentially to coordinate multi-resource output. Case-study simulations in a typical grid scenario with an inverse source-load distribution verify the method's feasibility.
References
- [1]Li Lei. Power Fluctuation Analysis and Frequency Control Strategy for Distributed Generation Systems in Power Engineering[J]. Electric Engineering, 2025, 12: 405-407.
- [2]Zou Zhengwei. Grid-Connection Strategies for Wind and Photovoltaic Power Generation Based on Energy-Storage Requirements[J]. Proceedings of the Forum on New Quality Productive Forces Driving Secondary-Industry Development and Innovation in Tendering and Procurement, 2025: 85-86.
- [3]Li Zhengxi, Chen Laijun, Zhou Wanpeng, et al. A Low-Carbon Scheduling Strategy for an Integrated Electricity-Heat-Hydrogen Energy System Considering Equivalent Energy Storage[J]. Distributed Energy, 2025, 10(6): 62-74.
- [4]Liang Suidong. Optimization of Energy Storage Operation and Coordinated Scheduling of Adjustable Resources for Virtual Power Plants[J]. Power System and Clean Energy, 2025, 41(9): 27-36.
- [5]Wang Xiaohan, Wen Yanhua. Optimal Configuration and Economic Analysis of Distributed Generation and Energy Storage in Integrated Energy Systems[J]. Automation Application, 2025, 66(12): 60-65.
- [6]Zhang Bin. Multi-Level Short-Term Power Forecasting for Distributed Photovoltaic Systems Based on Deep Learning[D]. Master's thesis, 2024.
- [7]Liu Shujun. A Deep-Learning-Based Method for Ultra-Short-Term Power Forecasting of Wind Turbines[D]. Doctoral dissertation, 2025.
- [8]Qi Xin, Yang Huibiao, Meng Fei, et al. A Horizontal-Federated-Learning-Based Method for Ultra-Short-Term Power Forecasting of Distributed Photovoltaic Systems[J]. Acta Energiae Solaris Sinica, 2025, 46(1): 686-695.
- [9]Lai Wenzhe. Short-Term Power Forecasting for Regional Distributed Photovoltaic Systems Based on Subregion Partitioning and Spatiotemporal Correlations[D]. Master's thesis, 2024.
- [10]Fu Zhiwei, Shen Xiaoyang, Fang Chaoying, et al. A Multi-Layer Coordinated Control Strategy for Power Generation Based on the Multiple-Experience-Replay-Pool MATD3 Algorithm[J]. Power System Optimization and Intelligent Dispatch, 2025, 53(11): 56-64.
- [11]Li Zikai, Yang Bo, Zhou Zhongtang, et al. A Microgrid Optimization Strategy Based on a Reinforcement Learning Algorithm[J]. Shandong Electric Power, 2024, 51(6): 27-35.
- [12]Lv Shuai, Gong Xiaoyu, Zhang Zhenghao, et al. A Review of Deep Reinforcement Learning Methods Combined with Evolutionary Algorithms[J]. Chinese Journal of Computers, 2022, 45(7): 1478-1499.
- [13]Fan Peixiao, Yang Jun, Wen Yuxin, et al. An Intelligent Generation Control Strategy for Multiple Microgrids with Electric Vehicles Based on Evolutionary Model Predictive Control[J]. Transactions of China Electrotechnical Society, 2024, 39(3): 699-713.
Article Sidebar
This work is licensed under a Creative Commons Attribution 4.0 International License.