现代电力2024，Vol.41Issue(4)：642-651,10.DOI:10.19725/j.cnki.1007-2322.2022.0309
基于改进生成对抗网络生成风光场景的微电网多时间尺度优化调度策略研究
Research on Multi-time Scale Optimization Scheduling Strategy of Microgrid Based on Improved Generative Adversarial Network for Wind and PV Power Scenario Generation
摘要
Abstract
Aiming to address the impact of renewable energy output uncertainty on optimal scheduling of microgrid,a multi-time scale optimal scheduling strategy for wind and PV power scenario generation in microgrid based on C-WGAN(condi-tional Wasserstein generative adversarial networks)is pro-posed.Firstly,the specified wind and PV power scenarios are generated through C-WGAN.Then,during the day-ahead op-timization scheduling stage,a comprehensive consideration is given to the cost of the connecting line and the battery degrada-tion,while introducing an optimized coefficient to optimize the interactive power of the connecting line.The primary objective during the intraday optimization scheduling phase is to track the results of day-ahead optimization scheduling,so as to effect-ively mitigate the impact of inaccuracies in day-ahead renew-able energy and load prediction data.The results indicate that the proposed method not only exhibits strong robustness,butalso effectively guarantees the economic operation of mi-crogrid.关键词
可再生能源/场景生成/多时间尺度/微电网优化调度/蓄电池退化成本/优化系数Key words
renewable energy/scenario generation/multi-time scale/optimal scheduling of microgrid/battery degrada-tion cost/optimized coefficient分类
信息技术与安全科学引用本文复制引用
程卓,许仪勋,李泽霜..基于改进生成对抗网络生成风光场景的微电网多时间尺度优化调度策略研究[J].现代电力,2024,41(4):642-651,10.基金项目
国家自然科学基金资助项目(61672337).Project Supported by the National Natural Science Foundation of China(61672337). （61672337）
