Compromising productivity in exchange for energy saving does not appeal to highly capitalized manufacturing industries. However, we might be able to maintain the same productivity while significantly reducing energy consumption. This paper addresses a flexible job shop scheduling problem with a shutdown (on/off) strategy aiming to minimize makespan and total energy consumption. First, an alternative mixed integer linear programming model is proposed. Second, a novel constraint programming is proposed. Third, practical operational scenarios are compared. Finally, we provide benchmarking instances, CPLEX codes, and genetic algorithm codes, in order to promote related research, thus expediting the adoption of energy-efficient scheduling in manufacturing facilities. The computational study demonstrates that (1) the proposed models significantly outperform other benchmark models and (2) we can maintain maximum productivity while significantly reducing energy consumption by 14.85% (w/o shutdown) and 15.23% (w/shutdown) on average.

This paper addresses the problem of predicting the express local train choices of metro passengers. The model was built and tested on the preferences observed from smart card data. The revealed preference data, because of intensiveness, can also accurately capture the marginal effects of the core attributes, in-vehicle time and wait time, on the express train choices by metro passengers. To be specific, the marginal disutility of a path decreases in in-vehicle time and increases in wait time. Accordingly, this paper employs a Box–Cox transform to adjust the constant marginality of a linear model to the nonconstant marginal disutility. The resulting nonlinear logit model improved the predictability of a conventional linear model. Tested on the Incheon–Yongsan interval of the Gyeong-In Line of the Seoul metropolitan area in South Korea, the model predicted a correct choice by a passenger in 99.9% and 99.5% of the cases during peak and nonpeak hour periods, respectively, compared with 96.9% and 95.8%, respectively, from a linear model. The model, applied to Line 9 without a parameter tuning, achieved a predictability greater than 95%.

The disturbance of local areas with complex railway networks and high traffic density not only impedes the efficient use of rail networks in those areas, but also propagates delays to the entire railway network. This has motivated research on train rescheduling problems in high-density local areas to minimize train delays by modifying their planned arrival and departure times. In this paper, we present a train rescheduling method based on Q-learning in reinforcement learning. More specifically, we used deep neural networks to approximate the action-value function, and the underlying Markov decision process (MDP) is based on the alternative graph formulation for the train rescheduling problem. In the proposed MDP formulation, the status of the alternative graph corresponding to the current schedule is defined as the state, and the alternative arc corresponds to the action the agent can take. The MDP is approximately solved via deep Q-learning in which deep neural networks are used to approximate the action-value function in Q-learning. Although the size of the alternative graph depends on the number of trains, our MDP formulation is independent of the number of trains, which makes the proposed method more scalable. The evaluation of the method was performed on a simple railway network and a real-world example in Seoul, South Korea, with randomly generated initial train schedules and train delays. The experimental result showed that the proposed method is comparable to the mixed-integer-linear-programming (MILP)-based exact approach with respect to the quality of the solution.