Abstract
This paper builds a demand prediction model for electric vehicle sharing based on the location history archive collected from a taxi telematics system in Jeju area, which is currently hosting and testing diverse business models in smart transportation. For a set of set of sharing stations virtually placed by our analysis tool, our experiment traces the number of available electric vehicles on each station according to the pick-up and drop-off event detections. For better prediction, the traced results are modeled using artificial neural networks by taking each demand for the previous 5 hours as inputs and the next one as an output value. The movement data set is converted to learning patterns and the neural network library functions are invoked for pattern learning, network creation, and prediction generation. After all, the model for the international airport area shows the accuracy of 96 %, making it possible to develop an accurate vehicle relocation and management algorithm.
This research was supported by the MKE, Republic of Korea, under IT/SW Creative research program supervised by the NIPA (NIPA-2012-(H0502-12-1002).
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Lee, J., Park, G.: Design and Implementation of a Movement History Analysis Framework for the Taxi Telematics System. In: APCC, pp. 89–94 (2008)
Ma, Z., Callaway, D., Hiskens, I.: Decentralized Charging Control for Large Population of Plug-in Electric Vehicles: Application of the Nash Certainty Equivalence Principle. In: IEEE ICCA, pp. 191–195 (2010)
Kek, A., Cheu, R., Meng, Q., Fung, C.: A Decision Support System for Vehicle Relocation Operations in Carsharing Systems. Transportation Research Part E, 149–158 (2009)
Lee, J., Park, G., Kwak, H., Lee, M.: Analysis Framework for Electric Vehicle Sharing Systems Using Vehicle Movement Data Stream. In: Wang, H., Zou, L., Huang, G., He, J., Pang, C., Zhang, H.L., Zhao, D., Yi, Z. (eds.) APWeb 2012 Workshops. LNCS, vol. 7234, pp. 89–94. Springer, Heidelberg (2012)
Silva, D., Yu, X., Alahakoon, D., Holmes, G.: Semi-Supervised Classification of Characterized Patterns for Demand Forecasting using Smart Electricity Meters. In: International Conference on Electrical Machines and Systems, pp. 1–6 (2011)
Nissen, S.: Neural Network Made Simple. Software 2.0 (2005)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2012 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Lee, J., Park, GL. (2012). Demand Forecast for Electric Vehicle Sharing Systems Using Movement History Archive. In: Kim, Th., Ramos, C., Abawajy, J., Kang, BH., Ślęzak, D., Adeli, H. (eds) Computer Applications for Modeling, Simulation, and Automobile. MAS ASNT 2012 2012. Communications in Computer and Information Science, vol 341. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-35248-5_17
Download citation
DOI: https://doi.org/10.1007/978-3-642-35248-5_17
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-35247-8
Online ISBN: 978-3-642-35248-5
eBook Packages: Computer ScienceComputer Science (R0)