In humanitarian aid scenarios, the model of cumulative capacitated vehicle routing problem can be used in vehicle scheduling, aiming at delivering materials to recipients as quickly as possible, thus minimizing their wait time. Traditional approaches focus on this metric, but practical implementations must also consider factors such as driver labor intensity and the capacity for on-site decision-making. To evaluate driver workload, the operation times of relief vehicles are typically used, and multi-objective modeling is employed to facilitate on-site decision-making. This paper introduces a multi-objective cumulative capacitated vehicle routing problem considering operation time (MO-CCVRP-OT). Our model is bi-objective, aiming to minimize both the cumulative wait time of disaster-affected areas and the extra expenditures incurred by the excess operation time of rescue vehicles. Based on the traditional grey wolf optimizer algorithm, this paper proposes a dynamic grey wolf optimizer algorithm with floating 2-opt (DGWO-F2OPT), which combines real number encoding with an equal-division random key and ROV rules for decoding; in addition, a dynamic non-dominated solution set update strategy is introduced. To solve MO-CCVRP-OT efficiently and increase the algorithm’s convergence speed, a multi-objective improved floating 2-opt (F2OPT) local search strategy is proposed. The utopia optimum solution of DGWO-F2OPT has an average value of two fitness values that is 6.22% lower than that of DGWO-2OPT. DGWO-F2OPT’s average fitness value in the algorithm comparison trials is 16.49% less than that of NS-2OPT. In the model comparison studies, MO-CCVRP-OT is 18.72% closer to the utopian point in Euclidean distance than CVRP-OT.

Short-term load forecasting (STLF) plays an important role in facilitating efficient and reliable operations of power systems and optimizing energy planning in the electricity market. To improve the accuracy of power load prediction, an adaptive clustering long short-term memory network is proposed to effectively combine the clustering process and prediction process. More specifically, the clustering process adopts the maximum deviation similarity criterion clustering algorithm (MDSC) as the clustering framework. A bee-foraging learning particle swarm optimization is further applied to realize the adaptive optimization of its hyperparameters. The prediction process consists of three parts: (i) a 9-dimensional load feature vector is proposed as the classification feature of SVM to obtain the load similarity cluster of the predicted days; (ii) the same kind of data are used as the training data of long short-term memory network; (iii) the trained network is used to predict the power load curve of the predicted day. Finally, experimental results are presented to show that the proposed scheme achieves an advantage in the prediction accuracy, where the mean absolute percentage error between predicted value and real value is only 8.05% for the first day.

As the capacity of individual offshore wind turbines increases, prolonged downtime (due to maintenance or faults) will result in significant economic losses. This necessitates enhancing the efficiency of vessel operation and maintenance (O&M) to reduce O&M costs. Existing research mostly focuses on planning O&M schemes for individual vessels. However, there exists a research gap in the scientific scheduling for state-of-the-art O&M vessels. To bridge this gap, this paper considers the use of an advanced O&M vessel in the O&M process, taking into account the downtime costs associated with wind turbine maintenance and repair incidents. A mathematical model is constructed with the objective of minimizing overall O&M expenditure. Building upon this formulation, this paper introduces a novel restructuring particle swarm optimization which is tailed with a bespoke encoding and decoding strategy, designed to yield an optimized solution that aligns with the intricate demands of the problem at hand. The simulation results indicate that the proposed method can achieve significant savings of 28.85% in O&M costs. The outcomes demonstrate the algorithm’s proficiency in tackling the model efficiently and effectively.