In this paper, we study an electric vehicle routing problem while considering the constraints on battery life and battery swapping stations. We first introduce a comprehensive model consisting of speed, load and distance to measure the energy consumption and carbon emissions of electric vehicles. Second, we propose a mixed integer programming model to minimize the total costs related to electric vehicle energy consumption and travel time. To solve this model efficiently, we develop an adaptive genetic algorithm based on hill climbing optimization and neighborhood search. The crossover and mutation probabilities are designed to adaptively adjust with the change of population fitness. The hill climbing search is used to enhance the local search ability of the algorithm. In order to satisfy the constraints of battery life and battery swapping stations, the neighborhood search strategy is applied to obtain the final optimal feasible solution. Finally, we conduct numerical experiments to test the performance of the algorithm. Computational results illustrate that a routing arrangement that accounts for power consumption and travel time can reduce carbon emissions and total logistics delivery costs. Moreover, we demonstrate the effect of adaptive crossover and mutation probabilities on the optimal solution.

This paper compares three different evolutionary algorithms for solving the node covering problem: EA-I relies on the definition of the problem only without using any domain knowledge, while EA-II and EA-III employ extra heuristic knowledge. In theory, it is proven that all three algorithms can find an optimal solution in finite generations and find a feasible solution efficiently; but none of them can find the optimal solution efficiently for all instances of the problem. Through experiments, it is observed that all three algorithms can find a feasible solution efficiently, and the algorithms with extra heuristic knowledge can find better approximation solutions; but none of them can find the optimal solution to the first instance efficiently. This paper shows that heuristic knowledge is helpful for evolutionary algorithms to find good approximation solutions, but it contributes little to search the optimal solution for some instances.

For e-commerce platforms such as Taobao and Amazon, advertisers play an important role in the entire digital ecosystem: their behaviors explicitly influence users' browsing and shopping experience; more importantly, advertiser's expenditure on advertising constitutes a primary source of platform revenue. Therefore, providing better services for advertisers is essential for the long-term prosperity for e-commerce platforms. To achieve this goal, the ad platform needs to have an in-depth understanding of advertisers in terms of both their marketing intents and satisfaction over the advertising performance, based on which further optimization could be carried out to service the advertisers in the correct direction. In this paper, we propose a novel Deep Satisfaction Prediction Network (DSPN), which models advertiser intent and satisfaction simultaneously. It employs a two-stage network structure where advertiser intent vector and satisfaction are jointly learned by considering the features of advertiser's action information and advertising performance indicators. Experiments on an Alibaba advertisement dataset and online evaluations show that our proposed DSPN outperforms state-of-the-art baselines and has stable performance in terms of AUC in the online environment. Further analyses show that DSPN not only predicts advertisers' satisfaction accurately but also learns an explainable advertiser intent, revealing the opportunities to optimize the advertising performance further.

No abstract