面向主动配电网的调峰需求系统调度学习优化

System scheduling learning optimization for peak load regulation in active distribution network

为实现主动配电网调峰需求,以包含PV、各类柔性负荷、VRB储能装置为基础建立工业园区主动配电系统模型,同时建立最小代价的目标函数。为求解该目标函数,考虑到模型参数多的问题,提出一种模拟退火改进Q学习优化算法对目标函数进行求解。结果表明,改进算法无论是在算法的收敛速度,还是在负荷调整方面,都具有非常明显优势。

in order to realize the peak load regulation demand of active distribution network,the active distribution system model of industrial park is established based on PV,various flexible loads and VRB energy storage devices,and the objective function with minimum cost is established.In order to solve the objective function,a simulated annealing improved Q-learning optimization algorithm is proposed to solve the problem of multiple model parameters.The results show that the improved algorithm has obvious advantages in both convergence speed and load adjustment.