基于改进生成对抗网络场景生成的长-短期储能优化配置
Optimal Configuration of Long-term and Short-term Energy Storage Based on Improved Generative Adversarial Network Scenarios
王成磊 1匡熠 2濮永现 3唐岚 1黄力文 1束洪春1
作者信息
- 1. 昆明理工大学电力工程学院,昆明 650051
- 2. 云南电网有限责任公司电力调度控制中心,昆明 650000
- 3. 中国电建集团昆明勘测设计研究院有限公司,昆明 650000
- 折叠
摘要
占比不断提高的新能源对新型电力系统的灵活性调节能力提出了新需求.为此,提出了一种长-短期储能优化配置方法,通过短时功率与长期电量的双重调节来保障系统的多时间尺度灵活性调节能力.首先,提出了一种基于改进生成对抗网络的风光联合出力场景生成方法,通过加入月份标签信息对风光出力的边界进行准确刻画;其次,综合考虑不同类型储能的技术特点,提出一种长-短期储能的运行配合策略;最后,建立了兼顾经济性和灵活性双重目标的长-短期储能配置双层优化模型,通过对上下层模型的不断优化迭代得到最优储能配置方案.以改进的IEEE-RTS 24节点系统为例进行验证,研究结果表明所提方法可有效提升高渗透率电力系统的灵活性与经济性.
Abstract
The increasing proportion of renewable energy sources poses new demands on the flexibility regulation capa-bility of the new power system.To address this issue,this paper proposes a long-short term energy storage optimization method that guarantees multi-timescale flexibility regulation capability of the system through dual regulation of short-term power and long-term energy.First,a wind-solar joint output scenario generation method based on an improved generative adversarial network is proposed,which accurately characterizes the boundary of wind-solar output by adding month label information.Second,considering the technical characteristics of different types of energy storage,a long-short term energy storage operation coordination strategy is proposed.Finally,a dual optimization model of long-short term energy storage configuration that considers both economic and flexibility objectives is established.The optimal energy storage configuration plan is obtained through continuous optimization and iteration of the upper and low-er level models.The proposed method is validated on the improved IEEE-RTS 24-node system,and the results demonstrate that the proposed method can effectively improve the flexibility and economic performance of high-penetration power systems.
关键词
可再生能源/不确定性/生成对抗网络/储能配置/运行策略/场景生成Key words
renewable energy/uncertainty/generative adversarial networks/energy storage configuration/operation strategy/scene generation引用本文复制引用
基金项目
国家自然科学基金(52037003)
云南省科技重大专项(202002AF080001)
出版年
2024
国家科技期刊平台
NSTL
万方数据