User travel energy consumption prediction and path recommendation method considering user travel behaviors

Abstract

The invention provides a user travel energy consumption prediction and path recommendation method considering user travel behaviors. The method comprises the following steps: fusing road section vehicle speed into a static road network model to establish a dynamic traffic model, calculating a future travel feasible path of a user and a vehicle speed change condition by utilizing a depth-first search algorithm according to the dynamic traffic model and user data, and establishing a road network space-time travel chain based on a space-time trajectory space; according to the road network space-time travel chain, carrying out driving condition analysis to obtain characteristic parameters reflecting the driving condition and the energy consumption influence factors; calculating the energy consumption of the future travel feasible path of the user by using a neural network; and scoring the feasible paths according to the preference of the user, and recommending the path with the lowest score to the user as the optimal path. According to the method, a static road network model is converted into a dynamic traffic model, the road network space-time trip chain is applied to future travel energy consumption calculation and path recommendation, and a path evaluation index is established based on preferences of different users to serve as the basis of optimal path recommendation.

Description

technical field [0001] The invention relates to the technical field of energy consumption prediction, in particular to a user travel energy consumption prediction and path recommendation method considering user travel behavior. Background technique [0002] Due to the limited amount of non-renewable energy reserves and environmental problems that have caused serious negative impacts on the development of human society and human health, the low-carbon emission reduction characteristics of new energy vehicles have come into people's attention. Taking the models used by most residents for travel and work as an example, the average daily mileage of miniature and small passenger vehicles is about 49.3km, the average daily mileage of medium-sized passenger vehicles is about 85.8km, and the average daily mileage of large passenger vehicles is about 158.9km, and the average daily mileage of buses is about 164.4km. The average daily mileage of vehicles used by most residents for tra...

AI Technical Summary

Problems solved by technology

[0005] The disadvantages of the energy consumption prediction method of electric vehicles in the above prior art are: the user's future travel model is the link between the dynamic traffic model and the calculation of the user's future travel energy consumption. Only when the user's future travel model is established for the user's future travel can the user The time-space trajectory in the road network is described in detail, but this method only predicts energy consumption based on the historical driving data of electric vehicles, and does not consider the influence of user travel behavior characteristics and dynamic traffic on energy consumption calculation

[0006] This method only uses the starting point, starting time, destination, ending time and mileage to simulate the user's travel behavior, which will produce large errors in the case of dynamic changes in the road network; and does not consider different users when making route recommendations. The selection preferences of users and the preferences of users in different states are different, and the universality of the recommended path is poor.

Images