Investigating long-term vehicle speed prediction based on BP-LSTM algorithms

• Published in: IET intelligent transport systems Vol. 13; no. 8; pp. 1281 - 1290
• Main Authors: Yufang, Li, Mingnuo, Chen, Wanzhong, Zhao
• Format: Journal Article
• Language: English
• Published: The Institution of Engineering and Technology 01.08.2019
• Subjects: accurate on‐road vehicle speed prediction; back propagation‐long short‐term memory; BP‐LSTM algorithms; driver–vehicle–road–traffic historical characteristic parameters; driver–vehicle–road–traffic system; energy consumption prediction; historical driver–vehicle–road–traffic data; learning (artificial intelligence); long‐term individual vehicle speed prediction; long‐term prediction; long‐term vehicle speed prediction; neural nets; novel data‐driven vehicle speed prediction method; predicted vehicle speed; prediction accuracy; prediction performance; Research Article; road traffic; road vehicles; short‐term prediction; traffic engineering computing; transportation; travel time prediction; vehicle type; road traffic; accurate on-road vehicle speed prediction; vehicle type; driver–vehicle–road–traffic system; driver–vehicle–road–traffic historical characteristic parameters; novel data-driven vehicle speed prediction method; predicted vehicle speed; travel time prediction; traffic engineering computing; prediction performance; short-term prediction; transportation; BP-LSTM algorithms; energy consumption prediction; back propagation-long short-term memory; road vehicles; long-term vehicle speed prediction; long-term individual vehicle speed prediction; long-term prediction; historical driver–vehicle–road–traffic data; learning (artificial intelligence); prediction accuracy; neural nets
• ISSN: 1751-956X; 1751-9578
• DOI: 10.1049/iet-its.2018.5593

Vehicle speed prediction is quite essential for many intelligent vehicular and transportation applications. Accurate on-road vehicle speed prediction is challenging because individual vehicle speed is affected by many factors related to driver–vehicle–road–traffic system, e.g. the traffic conditions, vehicle type, and driver's behavior, in either a deterministic or stochastic way. Also machine learning makes vehicle speed predictions more accessible by exploring the potential relationship between the vehicle speed and its main factors based on the historical driving data in the context of vehicular networks. This study proposes a novel data-driven vehicle speed prediction method based on back propagation-long short-term memory (BP-LSTM) algorithms for long-term individual vehicle speed prediction along the planned route. Also Pearson correlation coefficient is adopted to analyse the correlation of driver–vehicle–road–traffic historical characteristic parameters for the enhancement of the model's computing efficiency. Finally, a real natural driving data in Nanjing is used to evaluate the prediction performance with a result that the proposed vehicle speed prediction method outperforms other ones in terms of prediction accuracy. Moreover, based on the predicted vehicle speed, this work studies and analyses its effectiveness in two scenarios of energy consumption prediction and travel time prediction.