Estimation of Vehicle Miles Traveled Based on Improved Ant Colony Algorithm

Vehicle miles traveled (VMT) statistics is a key parameter which has many applications, such as the assessment of vehicle quality, evaluation of driving behavior and oil consumption, and other applications in vehicle monitoring system. In the earlier studies, the calculation of VMT usually focused on improving the accuracy and frequency of vehicle GPS data, but the VMT estimation error due to them were getting smaller with the development of positioning technology. Nowadays in the practical application of internet of vehicles, errors due to the out-of-order location data which caused by communication mechanism have become increasingly obvious. In this paper, we propose a VMT estimate method based on improved ant colony algorithm and local search method which is suitable for dealing with timestamp chaotic location data sequence. To evaluate our method, we use real-world vehicle data gathered by China mobile’s vehicle fleet management products, the analysis result shows the MRE of proposed ant colony algorithm is usually less than 8%, at least 3 percentage points lower than that of uniform motion distance accumulation statistics, at least 7 percentage points lower than that of Euclid distance accumulation statistics.