Station Importance Evaluation in Dynamic Bike-Sharing Rebalancing Optimization Using an Entropy-Based TOPSIS Approach

Abstract

As an eco-friendly travel mode, bike-sharing has prevailed around the world. However, the systems are imbalanced due to the asymmetric spatial and temporal distribution of user demand. Station prioritization strategies are needed to rebalance more shared bikes for more important stations. This paper proposes an evaluation method of station importance in dynamic bike-sharing rebalancing. Firstly, a shortterm demand prediction model is applied to capture the temporal and spatial characteristics of bike-sharing trip data and predict bike-sharing demand at the station level. Based on the prediction results, the method of determining rebalancing quantity is proposed with consideration of bike-sharing usage throughout the rebalancing period. Then, three criteria are employed to evaluate the importance of bike-sharing stations, including rebalancing quantity, closeness to inventory threshold, and distance from the key station. An entropy-based Technique for Order of Preference by Similarity to the Ideal Solution (TOPSIS) approach is proposed to weigh different criteria and evaluate station importance. Furthermore, the experiments on bikesharing data from Nanjing City demonstrate the effectiveness of the proposed methods. This research is helpful for operators and managers to dynamically rebalance shared bikes with high efficiency and improve the service quality of bike-sharing systems.

Mobility prediction for uneven distribution of bikes in bike sharing systems

“…Gimon et al 25 formulated the effects of station choice for a bike rent of morning bike commuters for re-balancing of bikes, using utility theory. He et al 26 proposed an entropy-based model to determine re-balancing quantity by predicting the short-term demand of bike rent and return using Graph Convolution Long Short-Term Network (GC-LSTM). Ji et al 27 proposed a model to address the re-balance problem by using users as the re-balancing factor using monetary incentives for the dockless bike-sharing environment.…”

The optimization method for park load active aggregation according to flexibility and relevancetion

“…When the park receives the dispatching instruction from the power grid, the park could respond in real time and make optimization strategies to coordinate and plan the dispatching mode between park loads [3]. It avoids confusion in the production process, equipment damage and massive waste of energy.In the day ahead, the park can make a plan in advance according to the historical records of participating in the demand response scheduling and typical application scenarios [4][5]. The loads in the park are divided into a certain number of groups in advance, participate in the response in turn according to the priority, and obtain the actual conversion rate after the aggregated number [6].…”