一种求解机组组合优化问题的降维半解析动态规划方法(英文)

Dimension-Reduced Semi-Analytical Dynamic Programming Approach for Solving Unit Commitment Problem

提出一种启发式的动态规划改进方法,可以与其他经济调度算法相结合,用以解决多种约束条件下的机组组合优化问题。通过比较各时段负荷及机组参数,剔除各时段下不满足要求的组合状态,从而减少动态规划中的状态点数;根据机组的最小连续运行、停运时间限制,计及机组功率上升、下降速度的约束,剔除了状态点间的无效路径,从而减少了动态规划的路径个数,达到降维的目的;在确定机组启停状态后,再采用解析法进行机组的功率分配,可以大大提高动态规划方法的效率。经算例检验,该算法简单、有效、实用。

A dimension-reduced semi-analytical dynamic programming approach is presented in this paper, which is a modified heuristic dynamic programming approach that could be committed with other economical dispatch arithmetic used to solve the problem of unit commitments with restrictions. This approach eliminates the commitments that can not meet the requirements by comparing loads and units parameters during every period, to reduce the number of statuses in dynamic programming. It also eliminates the invalid paths between statuses considering the restriction of minimum continuous time of on and off, and tamps rates, thereby reducing the number of paths in dynamic programming and attaining the aim of reducing dimensions. After confirming the running or suspended status of units, the approach is used to distribute powers among units, thereby increasing the efficiency of dynamic programming greatly. This arithmetic is proved to be simple, effective and applicable through tests in numeral examples.