Navigation systems can help in allocating public charging stations to electric vehicles (EVs) with the aim of minimizing EVs’ charging time by integrating sufficient data. However, the existing systems only consider their travel time and transform the allocation as a routing problem. In this paper, we involve the queuing time in stations as one part of EVs’ charging time, and another part is the travel time on roads. Roads and stations are easily congested resources, and we constructed a joint-resource congestion game to describe the interaction between vehicles and resources. With a finite number of vehicles and resources, there exists a Nash equilibrium. To realize a self-adaptive allocation work, we applied the Q-learning algorithm on systems, defining sets of states and actions in our constructed environment. After being allocated one by one, vehicles concurrently requesting to be charged will be processed properly. We collected urban road network data from Chongqing city and conducted experiments. The results illustrate the proposed method can be used to solve the problem, and its convergence performance was better than the genetic algorithm. The road capacity and the number of EVs affected the initial of Q-value, and not the convergence trends.

No abstract

No abstract

The identification and analysis of the spatiotemporal dynamic traffic patterns in citywide road networks constitute a crucial process for complex traffic management and control. However, city-scale and synchronal traffic data pose challenges for such kind of quantification, especially during peak hours. Traditional studies rely on data from road-based detectors or multiple communication systems, which are limited in not only access but also coverage. To avoid these limitations, we introduce real-time, traffic condition digital maps as our input. The digital maps keep spatiotemporal urban traffic information in nature and are open to access. Their pixel colors represent traffic conditions on corresponding road segments. We propose a stacked convolutional autoencoder-based method to extract a low-dimension feature vector for each input. We compute and analyze the distances between vectors. The statistical results show different traffic patterns during given periods. With the actual data of Chongqing city, we compare the feature extraction performance between our proposed method and histogram. The result shows our proposed method can extract spatiotemporal features better. For the same data set, there is little difference in the number distribution of red pixels found in the statistics result of the histogram, while differences do exist in the results of our proposed method. We find the most fluctuated morning is on Friday; the most fluctuated evening is on Tuesday; and the most stable evening is on Wednesday. The distance captured by our method can represent the evolution of different traffic conditions during the morning and evening peak hours. Our proposed method provides managers with assistance to sense the dynamics of citywide traffic conditions in quantity.