Distributed forecasting and ant colony optimization for the bike-sharing rebalancing problem with unserved demands

Abstract

Bike-sharing systems (BSS) have widely spread over many cities in the world as an environmentally friendly means to reduce air pollution and traffic congestion. This paper focuses on the bike-sharing rebalancing problem (BRP), which consists of two aspects: determining desired demands at each station and designing routes to redistribute bikes among stations. For the first task, we firstly apply the random forest, a very efficient machine learning algorithm, to forecast desired demands for each station, which can be easily implemented with distributed computing. For the second task, it belongs to the broad class of the vehicle routing problem with pickup and delivery (VRPPD). In most existing settings, all of the demands being strictly satisfied can lead to longer routes and add operational costs. In this paper, we propose a new model with unserved demands by relaxing demands satisfying constraints. Then, we design a distributed ant colony optimization (ACO) based algorithm with some specific modifications to increase its efficiency for the proposed model. We propose to use the percentage of average cost saving per bike as a metric to evaluate the performance of our method on cost-reducing and compare with existing methods and best-known values. Computational results on benchmarks show the advantage of our approach. Finally, we provide a real case study of BSS in Hangzhou, China, with insightful elaborations.

A Framework for Investigating the Adoption of Key Technologies: Presentation of the Methodology and Explorative Analysis of Emerging Practices

“…External performance encloses attracting investors since key technologies enhance financial attractiveness [72] and can improve financial performance [73], long-term shareholder value [74], or stock price performance [75]. Moreover, higher external performances can be achieved in terms of brand reputation [76], competitive advantage [77], customer satisfaction [78], and product/service quality/value/differentiation [79]. Finally, the label revenues enclose all emerging practices that support selling activities or sales growth [80].…”

Research on Urban National Sports Fitness Demand Prediction Method Based on Ant Colony Algorithm

“…In the research and analysis, Alireza et al used the ant colony algorithm to analyze the highway network of Kerman province, the largest province in Iran, which can identify the existing bottlenecks and predict the potential bottlenecks in the future [ 6 ]. Fan y et al proposed a new model with unservice requirements by relaxing the requirements of meeting constraints, designed an algorithm based on distributed ant colony optimization (ACO), and made some specific modifications to it, using the average cost-saving percentage of each bicycle as a measure to evaluate the performance of our method in reducing costs [ 7 ]. Prasad et al designed a method combining multistage multivariable empirical mode decomposition with ant colony optimization and random forest (i.e., MEMD-ACO-RF) to predict monthly solar radiation (RN).…”

A survey of the state-of-the-art swarm intelligence techniques and their application to an inverse design problem

“…The criteria for selecting the direction based on the path by the ants are depending on the higher trail intensity. This path intensity is regarded as the system's global memory [12]. Daemon's actions are used to collect global information.…”