A Hybrid Dispatch Strategy Based on the Demand Prediction of Shared Bicycles

Abstract

With the advent of pile-less shared bicycles, the techniques initially used for public bicycle dispatching were unable to fulfill the routine dispatch tasks, resulting in constant bicycle crowding. In this paper, to alleviate the mess of shared bicycles, we propose a hybrid dispatching algorithm based on bicycle demand data. We take the bicycle stations’ imbalance as an optimization index and use greedy ideas to ensure that after each dispatch all stations get the smallest imbalance. In addition, it is suggested that two assessment metrics evaluate the efficiency of the dispatching technique from the users and operators’ perspectives. It is shown that the proposed dispatching algorithm performs better in terms of user satisfaction and operator revenue, and is less affected by bicycle distribution compared with the traditional manual scheduling algorithm.

A Cluster-Then-Route Framework for Bike Rebalancing in Free-Floating Bike-Sharing Systems

“…In the following study, we test the effects on rebalancing effect of varying the length of the rebalancing period (30 min, 1 h, 3 h and 6 h), the period strategy (fixed or rolling), and the service vehicle capacity (30, 40 or 50 bikes); the other parameters are set to their default values. The experiment is conducted on three different clusters of 2, 5 and 10 nodes, respectively: S 1 = (2, 3), S 2 = (10, 16,19,21,46) and S 3 = (2, 3,24,25,26,37,38,44,55,59). We use three indicators to measure the rebalancing effect: (1) the proportion by which the number of shortages of shared bikes in the cluster was reduced upon completion of the rebalancing operations (RU S i : Equation ( 18)), (2) the proportion by which the total duration of shortages was reduced (RT S i : Equation ( 20)), and (3) the length of the vehicle route (D S i : Equation ( 21)).…”

“…Another major challenge to the DBRP in an FFBSS is fluctuation in user demand for bikes. The mainstream demand forecasting method [33][34][35][36][37][38][39][40] is the machine learning method. Here, we use the backpropagation (BP) neural network algorithm [41] as the prediction method for user demand.…”

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

“…When applying statistical parametric techniques, bikesharing demand prediction is usually defined as a time series prediction problem. The auto-regressive moving average model (ARMA) [16] and the auto-regressive integrated moving average (ARIMA) model [17] are well-known statistical parametric methods, as well as its diverse variants. For instance, using Dublin's bike-sharing data, Yoon et al [18] put forward an improved ARIMA model, considering signals from neighboring stations and seasonal trends to estimate available bicycles at each station.…”

“…Moreover, the weights for each feature have not been explored. Shen et al [48] illustrated that farther rebalancing distance brings higher rebalancing costs. As the basis for route optimization, the weighted path between two stations was calculated by dividing the station's imbalance by rebalancing distance.…”

“…The first step in the TOPSIS approach is to compute the normalized decision matrix using equation (15). Then, the weighted decision matrix is calculated by equation (16)(17)(18). It is noteworthy that the weighted decision matrix was obtained by multiplying a normalized decision matrix by the weight of the three criteria.…”