Learning dispatching rules via novel genetic programming with feature selection in energy-aware dynamic job-shop scheduling

Abstract

The incorporation of energy conservation measures into production efficiency is widely recognized as a crucial aspect of contemporary industry. This study aims to develop interpretable and high-quality dispatching rules for energy-aware dynamic job shop scheduling (EDJSS). In comparison to the traditional modeling methods, this paper proposes a novel genetic programming with online feature selection mechanism to learn dispatching rules automatically. The idea of the novel GP method is to achieve a progressive transition from exploration to exploitation by relating the level of population diversity to the stopping criteria and elapsed duration. We hypothesize that diverse and promising individuals obtained from the novel GP method can guide the feature selection to design competitive rules. The proposed approach is compared with three GP-based algorithms and 20 benchmark rules in the different job shop conditions and scheduling objectives considered energy consumption. Experiments show that the proposed approach greatly outperforms the compared methods in generating more interpretable and effective rules. Overall, the average improvement over the best-evolved rules by the other three GP-based algorithms is 12.67%, 15.38%, and 11.59% in the meakspan with energy consumption (EMS), mean weighted tardiness with energy consumption (EMWT), and mean flow time with energy consumption (EMFT) scenarios, respectively.

Automatic Design of Energy-Efficient Dispatching Rules for Multi-Objective Dynamic Flexible Job Shop Scheduling Based on Dual Feature Weight Sets

“…These features are commonly utilized in existing research [33] and encompass various aspects such as information related to jobs, machines, and the job shop itself. The function set includes {+, −, ×, /, max, min} [27,33], where the division returns one if divided by zero. Additionally, max/min are functions that take two inputs and return their maximum/minimum values, respectively.…”

“…Table 3 shows the parameter setting of the GPHH in this section [27,33]. The feature weights are measured at the 51st generation, and this process is executed only once in the whole algorithm.…”

“…Therefore, reducing the number of features is a viable approach to narrow the search space of GPHH and enhance its searching efficiency [26,27]. The feature set of GPHH can encompass numerous features describing various aspects and forms of information pertaining to the job shop scheduling process, including system-related, machine-related, and job-related features.…”

“…From the perspective of sequencing rules, PT, SL, and WKR are three important features. Previous studies [26,27] have demonstrated their significant role in optimizing MT. Xu et al's research [33] also highlights the importance of these features in optimizing energy consumption related objectives.…”