Solving The Software Project Scheduling Problem With Hyper-Heuristics
ARTIFICIAL INTELLIGENCEAND SOFT COMPUTING, PT I(2019)
摘要
Search-based Software Engineering applies meta-heuristics to solve problems in the Software Engineering domain. However, to configure a meta-heuristic can be tricky and may lead to suboptimal results. We propose a hyper-heuristic (HH), GE-SPSP, to configure the Speed-Constrained Particle Swarm Optimization (SMPSO) meta-heuristic based on Grammatical Evolution (GE) to solve the Software Project Scheduling Problem. A grammar describes several parameters types and values to configure the SMPSO and the HH use it to return the best configuration set found during the search. The results are compared to conventional meta-heuristics and suggest that GE-SPSP can achieve statistically equal or better results than to the compared meta-heuristics.
更多查看译文
关键词
Search-based software engineering, Scheduling, Hyper-heuristic
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络