The permutation flowshop scheduling problem (PFSP) has been extensively studied in the scheduling literature. In this paper, we present an improved memetic algorithm (MA) to solve the PFSP to minimise the total flowtime. In the proposed MA, we develop a stochastic local search based on a dynamic neighbourhood derived from the NEH method. During the evolution process, the size of the neighbourhood is dynamically adjusted to change the search focus from exploration to exploitation. In addition, we introduce a new population generation mechanism to guarantee both the quality and diversity of the new populations. We also design a diversity index for the population to monitor the diversity of the current population. If the diversity index is less than a given threshold value, the current population will be replaced by a new one with good diversity so that the proposed MA has good ability to overcome local optima. We conduct computational experiments to test the effectiveness of the proposed algorithm. The computational results on randomly generated problem instances and benchmark problem instances show that the proposed MA is effective and superior or comparable to other algorithms in the literature.

Recently, both the learning effect scheduling and re-entrant scheduling have received more attention separately in research community. However, the learning effect concept has not been introduced into re-entrant scheduling in the environment setting. To fill this research gap, we investigate re-entrant permutation flowshop scheduling with a position-based learning effect to minimize the total completion time. Because the same problem without learning or re-entrant has been proved NP-hard, we thus develop some heuristics and a genetic algorithm (GA) to search for approximate solutions. To solve this problem, we first adopt four existed heuristics for the problem; we then apply the same four methods combined with three local searches to solve the proposed problem; in the last stage we develop a heuristic-based genetic algorithm seeded with four good different initials obtained from the second stage for finding a good quality of solutions. Finally, we conduct experimental tests to evaluate the behaviours of all the proposed algorithms when the number of re-entrant times or machine number or learning effect or job size changes.

Accurate forecasting of taxi demand has facilitated the rational allocation of urban public transport resources, reduced congestion in urban transport networks, and shortened passenger waiting time. However, virtual station discovery and modelling of the demand when forecasting through graph convolutional neural networks remains challenging. In this study, the virtual station discovery problem was addressed by using a two-stage clustering approach, which considers the geographical and load characteristics of taxi demand. Furthermore, a fusion model combining non-negative matrix decomposition and a graph convolutional neural network was proposed in order to extract the features of the nodes for dimension reduction and adaptive adjacency matrix computation. By the construction of a local processing structure, further extraction of the local characteristics of the demand was achieved. The experimental results show that the method in this study outperforms state-of-the-art methods in terms of the root mean square error and average absolute value error. Therefore, the model proposed in this study is able to achieve accurate forecasting of taxi demand.

Shared bicycles provide a green, environmentally friendly, and healthy mode of transportation that effectively addresses the “final mile” problem in urban travel. However, the uneven distribution of bicycles and the imbalance of user demand can significantly impact user experience and bicycle usage efficiency, which makes it necessary to predict bicycle demand. In this paper, we propose a novel shared-bicycle demand prediction method based on station clustering. First, to address the challenge of capturing patterns in station-level bicycle demand, which exhibits significant fluctuations, we employ a clustering method that combines graph information from the bicycle transfer graph and potential energy. This method aggregates closely related stations into corresponding prediction regions. Second, we use the GCN-CRU-AM (Graph Convolutional Network-Gated Recurrent Unit-Attention Mechanism) model to predict bicycle demand in each region. This model extracts the spatial information and correlation between regions, integrates time feature data and local weather data, and assigns weights to the input features. Finally, experimental results based on the data from Citi Bike System in New York City demonstrate that the proposed model achieves a more accurate demand prediction.

This paper studies a single-machine multitasking scheduling problem together with two-agent consideration. The objective is to look for an optimal schedule to minimize the total tardiness of one agent subject to the total completion time of another agent has an upper bound. For this problem, a branch-and-bound method equipped with several dominant properties and a lower bound is exploited to search optimal solutions for small size jobs. Three metaheuristics, cloud simulated annealing algorithm, genetic algorithm, and simulated annealing algorithm, each with three improvement ways, are proposed to find the near-optimal solutions for large size jobs. The computational studies, experiments, are provided to evaluate the capabilities for the proposed algorithms. Finally, statistical analysis methods are applied to compare the performances of these algorithms.

Studies on the customer order scheduling problem have been attracting increasing attention. Most current approaches consider that either component processing times for customer orders on each machine are constant or all customer orders are available at the outset of production planning. However, these assumptions do not hold in real-world applications. Uncertainty may be caused by multiple issues including a machine breakdown, the working environment changing, and workers’ instability. On the basis of these factors, we introduced a parallel-machine customer order scheduling problem with two scenario-dependent component processing times, due dates, and ready times. The objective was to identify an appropriate and robust schedule for minimizing the maximum of the sum of weighted numbers of tardy orders among the considered scenarios. To solve this difficult problem, we derived a few dominant properties and a lower bound for determining an optimal solution. Subsequently, we considered three variants of Moore’s algorithm, a genetic algorithm, and a genetic-algorithm-based hyper-heuristic that incorporated the proposed seven low-level heuristics to solve this problem. Finally, the performances of all proposed algorithms were evaluated.