摘要
由于可再生能源发电的随机性和储能系统的时间序列耦合特性,在构建微电网经济调度模型时需要适当模拟不确定变量并相应地开发可高效处理多目标问题的优化算法。在此背景下提出了一种能够计及不确定性因素且高效的基于深度强化学习与启发式算法的微电网多时间尺度调度方法,以实现经济环保运行。所提方法从日前、日内两个时间尺度对微电网进行优化。日前优化阶段利用短期预测数据进行初步决策,以最小化运营成本。日内调度阶段以日前优化方案为参考,必要时对日前运行方案进行修正,以应对可再生能源的实时波动。将日内优化过程解耦为全局和局部两阶段,全局阶段被建模为一个非凸的非线性优化问题并采用启发式算法进行求解,局部阶段被建模为一个马尔可夫决策过程采用深度强化学习方法求解,将深度强化学习与启发式算法相结合提高了强化学习的训练速度和收敛性能,避免在复杂环境下的奖励函数设计困难问题。最后,算例分析验证了所提出的方案实现了调度成本和计算速度的优化,并且适用于微电网的实时调度。
Due to the randomness of renewable energy generation and the time series coupling characteristics of energy storage systems,it is necessary to properly model uncertain variables and develop optimization algorithms that can efficiently handle multiobjective problems when constructing economic scheduling models for microgrids.In this context,an efficient multi-time scale dispatching method for microgrids based on deep reinforcement learning and heuristic algorithms is proposed,which can take into ac⁃count uncertain factors and achieve economic and environmental protection operation.The proposed method optimizes the microgrid from two time scales:day-ahead and intra-day.The day-ahead optimization phase utilizes short-term forecast data for initial decision making to minimize the operating cost.For the intra-day dispatching phase,it utilizes the day-ahead optimization scheme as a refer⁃ence and revises the day-ahead operation scheme if necessary to cope with the real-time fluctuations of renewable energy.The process of intra-day optimization is decoupled into global and local two phases,the global stage is modeled as a non-convex nonlinear optimization problem and solved using heuristic algorithms,while the local stage is modeled as a Markov decision process and solved using deep reinforcement learning methods.Combining deep reinforcement learning with heuristic algorithms improves the training speed and convergence performance of reinforcement learning,avoiding the difficulty of designing reward functions in complex environments.Finally,the case analysis verifies that the proposed scheme achieves optimization of scheduling cost and computing speed,and is suitable for real-time scheduling of microgrids.
作者
徐钰涵
季天瑶
李梦诗
XU Yuhan;JI Tianyao;LI Mengshi(School of Electric Power Engineering,South China University of Technology,Guangzhou 510641,China)
出处
《南方电网技术》
CSCD
北大核心
2024年第9期106-116,共11页
Southern Power System Technology
基金
国家自然科学基金资助项目(52104149)。
关键词
微电网
多时间尺度
经济调度
深度强化学习
群搜索算法
microgrid
multi-time scale
economic scheduling
deep reinforcement learning
group search algorithm
