Research on Dynamic Scheduling of Unbalanced Supply and Demand of the SROC Based on the Customers Priority Principle

The problem of imbalance between supply and demand in car-sharing scheduling has greatly restricted the development of car-sharing. This paper first analyzes the three supply and demand modes of car-sharing scheduling systems. Secondly, for the station-based with reservation one-way car-sharing problem (SROC), this article establishes a dynamic scheduling model under the principle of customer priority. The model introduces balance coefficients to predict the balance mode, and systematically rebalance the fleet networks in each period. In the case of meeting customer needs, the model objective function is to maximize the total profit and minimize the scheduling and loss costs. Then, in view of the diversity and uncertainty of scheduling schemes, a scheme information matrix is constructed. In the iterative process of genetic algorithm, individuals are selected and constructed according to the pheromone matrix, and evolution probability is proposed to control the balance between global search and local search of genetic algorithm. Finally, the data of Haikou City is used for simulation experiment.

Modelling on Car-Sharing Serial Prediction Based on Machine Learning and Deep Learning

The car-sharing system is a popular rental model for cars in shared use. It has become particularly attractive due to its flexibility; that is, the car can be rented and returned anywhere within one of the authorized parking slots. The main objective of this research work is to predict the car usage in parking stations and to investigate the factors that help to improve the prediction. Thus, new strategies can be designed to make more cars on the road and fewer in the parking stations. To achieve that, various machine learning models, namely vector autoregression (VAR), support vector regression (SVR), eXtreme gradient boosting (XGBoost), k-nearest neighbors (kNN), and deep learning models specifically long short-time memory (LSTM), gated recurrent unit (GRU), convolutional neural network (CNN), CNN-LSTM, and multilayer perceptron (MLP), were performed on different kinds of features. These features include the past usage levels, Chongqing’s environmental conditions, and temporal information. After comparing the obtained results using different metrics, we found that CNN-LSTM outperformed other methods to predict the future car usage. Meanwhile, the model using all the different feature categories results in the most precise prediction than any of the models using one feature category at a time