Electric vehicle charge scheduling using an artificial neural network

With the integration of EVs into the power grid, smart metering using machine-to-machine (M2M) communication is likely to play an important role in real-time energy management and control. Smart devices embedded with advanced metering infrastructure (AMI) can forecast the energy demand as well as perform energy pricing in real time. In this paper, an artificial neural network (ANN) based intelligent decision-making system is presented that utilises data logged by an M2M AMI for EV charge scheduling and load management. The ANN was trained using household power consumption and EV energy demand data, and was used to decide when a vehicle should charge (G2V), or could discharge (V2G).

[1]  Jeanny Hérault,et al.  Curvilinear component analysis: a self-organizing neural network for nonlinear mapping of data sets , 1997, IEEE Trans. Neural Networks.

[2]  Antonello Monti,et al.  Demand side management verification system for electric vehicles , 2014, 2014 IEEE International Workshop on Applied Measurements for Power Systems Proceedings (AMPS).

[3]  Alessandro Moscatelli,et al.  Smart, connected and mobile: Architecting future electric mobility ecosystems , 2013, 2013 Design, Automation & Test in Europe Conference & Exhibition (DATE).

[4]  J V Tu,et al.  Advantages and disadvantages of using artificial neural networks versus logistic regression for predicting medical outcomes. , 1996, Journal of clinical epidemiology.

[5]  Sayidul Morsalin,et al.  Induction motor inter-turn fault detection using heuristic noninvasive approach by artificial neural network with Levenberg Marquardt algorithm , 2014, 2014 International Conference on Informatics, Electronics & Vision (ICIEV).

[6]  G. E. Town,et al.  Improved peak shaving in grid-connected domestic power systems combining photovoltaic generation, battery storage, and V2G-capable electric vehicle , 2016, 2016 IEEE International Conference on Power System Technology (POWERCON).

[7]  Boriana L. Milenova,et al.  Fuzzy and neural approaches in engineering , 1997 .

[8]  Martin Fodslette Meiller.  A Scaled Conjugate Gradient Algorithm for Fast Supervised Learning , 1993 .

[9]  Salman Habib,et al.  Impact analysis of vehicle-to-grid technology and charging strategies of electric vehicles on distribution networks – A review , 2015 .

[10]  Khizir Mahmud,et al.  A review of computer tools for modeling electric vehicle energy requirements and their impact on power distribution networks , 2016 .

[11]  Howard B. Demuth,et al.  Neutral network toolbox for use with Matlab , 1995 .

[12]  G. E. Town,et al.  A review of computer tools for analyzing the impact of electric vehicles on power distribution , 2015, 2015 Australasian Universities Power Engineering Conference (AUPEC).

[13]  Luigi Martirano,et al.  EV fast charging stations and energy storage technologies: A real implementation in the smart micro grid paradigm , 2015 .

[14]  D. Molina,et al.  Optimal EV charge-discharge schedule in smart residential buildings , 2012, IEEE Power and Energy Society Conference and Exposition in Africa: Intelligent Grid Integration of Renewable Energy Resources (PowerAfrica).

[15]  Willett Kempton,et al.  ELECTRIC VEHICLES AS A NEW POWER SOURCE FOR ELECTRIC UTILITIES , 1997 .