Carbon peaking and carbon neutrality, which are the significant national strategy for sustainable development, have attracted considerable attention from production enterprises. In this study, the energy consumption is considered in the distributed blocking flow shop scheduling problem (DBFSP). A hyperheuristic with QQ -learning (HHQL) is presented to address the energy-efficient DBFSP (EEDBFSP). QQ -learning is employed to select an appropriate low-level heuristic (LLH) from a predesigned LLH set according to historical information fed back by LLH. An initialization method, which considers both total tardiness (TTD) and total energy consumption (TEC), is proposed to construct the initial population. The ε\varepsilon -greedy strategy is introduced to utilize the learned knowledge while retaining a certain degree of exploration in the process of selecting LLH. The acceleration operation of the job on the critical path is designed to optimize TTD. The deceleration operation of the job on the noncritical path is designed to optimize TEC. The statistical and computational experimentation in an extensive benchmark testified that the HHQL outperforms the other comparison algorithm regarding efficiency and significance in solving EEDBFSP.

中文翻译：

---

基于 Q-Learning 的超启发式多目标节能分布式阻塞流水车间调度问题


碳达峰和碳中和作为可持续发展的重大国家战略，引起了生产企业的高度关注。本研究在分布式阻塞流水车间调度问题（DBFSP）中考虑了能耗。提出了一种带有QQ学习（HHQL）的超启发式方法来解决节能DBFSP（EEDBFSP）问题。 QQ学习用于根据LLH反馈的历史信息从预先设计的LLH集合中选择合适的低级启发式(LLH)。提出了一种同时考虑总迟到（TTD）和总能耗（TEC）的初始化方法来构造初始群体。引入ε\varepsilon-贪婪策略来利用学到的知识，同时在选择LLH的过程中保留一定程度的探索。关键路径上作业的加速运行旨在优化TTD。非关键路径上作业的减速操作旨在优化 TEC。广泛基准测试中的统计和计算实验证明，在求解 EEDBFSP 的效率和显着性方面，HHQL 优于其他比较算法。