Scheduling is an important optimisation problem that reflects the practical and challenging issues in real-world scheduling applications such as order picking in warehouses, the manufacturing industry and grid/cloud computing. Genetic programming, as a hyper-heuristic approach, has been successfully and widely used to learn scheduling heuristics for the scheduling problems. Learning scheduling heuristics with genetic programming has attracted the attention of researchers over the years due to its flexible representation. Other machine learning approaches such as reinforcement learning has also been widely used for scheduling problems. A number of machine learning techniques such as surrogate, feature selection, and multitask learning can be used to improve the quality of learned solutions/heuristics for scheduling. With the growth of new technologies, researchers in this field have to continuously face new challenges, which requires innovative approaches for scheduling.This special session focuses on both practical and theoretical aspects of genetic programming and machine learning approaches for scheduling. Fundamental theoretical based approaches about genetic operators such as crossover, mutation are welcome. Novel approaches that use machine learning techniques for solving difficult scheduling problems are highly encouraged. Examples of machine learning techniques include surrogate, feature selection, and multitask learning. This special session is related to the IEEE Symposium on Evolutionary Scheduling and Combinatorial Optimisation (IEEE ESCO), which involves a wide range of evolutionary algorithms for different combinatorial optimisation problems. However, this special session focuses on using genetic programming and machine learning techniques to learn scheduling heuristics/solutions for the scheduling problems.We welcome the submissions of quality papers that effectively use genetic programming to solve the scheduling problems. Papers with rigorous analyses of genetic programming, machine learning techniques and innovative solutions to handle challenging issues in scheduling problems are also highly encouraged.
Topics of interest include, but not limited to:
- Production scheduling including job shop scheduling, open shop scheduling, flow shop scheduling
- Project scheduling
- Other scheduling problems
- Genetic programming
- Reinforcement learning
- Hyper-heuristics, including heuristic generation and heuristic selection
- Genetic operators of genetic programming and machine learningapproaches
- Adaptive genetic programming and machine learning approaches
- Surrogate genetic programming and machine learning approaches
- Feature selection in scheduling
- Transfer learning in scheduling
- Multitask scheduling
- Genetic programming with local search in scheduling
- Hybridisation of genetic programming with other machine learning andoptimisation techniques for scheduling
Organizers: Fangfang Zhang, Yi Mei, Su Nguyen, Mengjie Zhang