“Optimizing And Predicting Energy Consumption In Electric Vehicles Using Deep Learning: A Comparative Study Of GRU And LSTM Models”
Abstract
In this paper, we present a deep learning approach, using the Gated Recurrent Unit (GRU) model, for predicting energy consumption in electric vehicles (EVs) energy consumption. The adoption of electric vehicles in the market still faces challenges due to their limited driving range, in addition to the time required for charging batteries. Each time, before starting a journey, the driver has to assess whether the available charge on the battery is enough or not. Frequently, this estimation is based on the travelling distance and past consumption. There are two aspects that can have a very significant influence on the battery consumption: the route and the driving style. For the current study, we predict power consumption (kilowatt-hours per 100 kilometers). In this, combinedly utilizes three individual base machine learning algorithms, i.e., Linear regression, Random Forest (RF), and Support Vector Mechanism (SVMs), and Two Deep Learning technique as LSTM and The Gated Recurrent Unit (GRU) to predict the EVs’ energy consumption. Tackling the challenge of predicting EVs’ energy consumption, the data were collected from Volkswagen_e_golf-n (30 e-vehicles data). EVs energy consumption in terms of energy efficiency (kilowatt-hours per 100 kilometers) was estimated using several important variables as Trip distance (Km), consumption (kWh), Rural/ Urban, road condition, Temperature condition, park heating, average speed (Km/Hr.), Driving style, and Target consumption as kilowatt-hours per 100 kilometers.
The prediction results demonstrate that GRU is more robust in predicting EVs’ energy consumption. The results also indicate that the accuracy of predictive models for EVs energy consumption can be reasonably accomplished by adopting GRU techniques. The GRU model achieved a mean squared error of X, outperforming Linear Regression (Y), Random Forest (Z), and LSTM (W), thus demonstrating superior accuracy in predicting energy consumption. The adoption rate of electric vehicles is likely to increase as charging infrastructure becomes more widespread and accessible. These results can significantly aid in improving EV range estimations, potentially encouraging broader adoption of electric vehicles.
References
2. A Weis and P Jaramillo., "Estimating the potential of controlled plug-in hybrid electric vehicle charging to reduce operational and capacity expansion costs for electric power systems with high wind penetration," Appl. Energy, vol. 115, p. 190–204., 2014.
3. [Online]. Available: https: www.goldmansachs.com/insights.
4. J. Axscn, K. S. Kurani, and A. Burke, "Arc batteries ready for plug in hybrid buyers?" Tra11sp. Policy, vol. 17, no. 3, pp. 173-182, May 2010.
5. E. arassirnhan and C. Johnson, "The role of demand-side incentives and charging infrastructure on plug-in electric vehicle adoption: analysis of S States," E1111iro11. Res. lei/., vol. 13, no. 7, p. 074032 Jul. 2018.
6. G. Wager, J. Whale, and T. Braunl, "Driving electric vehicles at highway speeds: The effect of higher driving speeds on energy consumption and driving range for electric vehicles in Australia," Renew. Sustain. Energy Rev., vol. 63, pp. 158-165, ep. 2016.
7. 4.S. Hochreiter and J. Schmidhuber, “Long short-term memory,” Neural computation, vol. 9, no. 8, pp. 1735–1780, 1997
8. R. Fu, Z. Zhang, and L. Li, “Using LSTM and GRU neural network methods for traffic flow prediction,” in 31st IEEE Youth Academic Annual Conference of Chinese Association of Automation (YAC), 2016, pp. 324–328.
9. H. Sak, A. Senior, and F. Beaufays, “Long short-term memory recurrent neural network architectures for large scale acoustic modeling,” in Fifteenth annual conference of the international speech communication association, 2014.
10. K. Cho, B. Van Marienburg, C. Gulches, D. Bahdanau, F. Bougares, H. Schwenk, and Y. Bengio, “Learning phrase representations using RNN encoder-decoder for statistical machine translation,” arXiv preprint arXiv:1406.1078, 2014.
11. W. Waag, S. Käbitz, and D. U. Sauer, “Experimental investigation of the lithium-ion battery impedance characteristic at various conditions and aging states and its influence on the application,” Applied Energy, vol. 102, no. 0, pp. 885 – 897, 2013.
12. C. Burgos-Mellado, M. E. Orchard, M. Kazerani, R. C????rdenas, and D. S????ez, “Particle-filtering based estimation of maximum available power state in lithium-ion batteries,” Journal of Applied Energy, vol. 161, no. 0, pp. 349 – 363, 2016.
13. G. Oh and H. Peng, “Eco-driving at signalized intersections: What is possible in the real-world?” in 2018 21st International Conference on Intelligent Transportation Systems (ITSC). IEEE, 2018, pp. 3674–3679
14. M. Kubiˇ cka, J. Klus´ aˇcek, A. Sciarretta, A. Cela, H. Mounier, L. Thibault, and S.-I. Niculescu, “Performance of current eco-routing methods,” in 2016 IEEE Intelligent Vehicles Symposium (IV). IEEE, 2016, pp. 472 477.
15. G. De Nunzio, L. Thibault, and A. Sciarretta, “Model-based eco-routing strategy for electric vehicles in large urban networks,” in Comprehensive Energy Management–Eco Routing & Velocity Profiles. Springer, 2017, pp. 81–99.
16. R. Carlson, M. Duoba, D. Bocci, and H. Lohse-Busch, “On-road evaluation of advanced hybrid electric vehicles over a wide range of ambient temperatures.” Argonne National Lab. (ANL), Argonne, IL (United States), Tech. Rep., 2007.
17. F. H. Administration, “Highway performance monitoring system field manual,” 2010.
