Home Electric Vehicle Charge Scheduling Using Machine Learning Technique

  title={Home Electric Vehicle Charge Scheduling Using Machine Learning Technique},
  author={Prasanta Kumar Mohanty and Premalata Jena and Narayana Prasad Padhy},
  journal={2020 IEEE International Conference on Power Systems Technology (POWERCON)},
  • P. Mohanty, P. Jena, N. Padhy
  • Published 14 September 2020
  • Engineering, Computer Science
  • 2020 IEEE International Conference on Power Systems Technology (POWERCON)
With the help of artificial intelligence and advanced metering infrastructure (AMI), the analysis of electric vehicle integration will play a vital role in the future smart grid. Because getting data from smart appliances, processing that data using advanced techniques to get the desired output in near real-time is going to be a significant advantage of the smart grid. In this paper, a machine learning technique called support vector machine(SVM) is used to analyze the home charge scheduling… 

Using Smart Meter Data and Machine Learning to Identify Residential Light-duty Electric Vehicles

The growing adoption of electric vehicles (EVs) poses new challenges to power grids. To upgrade the grids with the increasing demand from charging EVs and from the change in customers consumption

Deep Learning-based Energy Optimization for Electric Vehicles Integrated Smart Micro Grid

A novel two-stage approach based on deep learning to reduce overall energy cost for sharing EVs integrated MG by forecasting its state and optimizing EVs scheduling and results show that the joint design of forecasting and optimization reduces the overall energy consumption and the payment to the external grid.

SV2G-ET: A Secure Vehicle-to-Grid Energy Trading Scheme Using Deep Reinforcement Learning

The experimental results prove the efficacy of the proposed SV2G-ET scheme that leads to improved scalability, saving the EVs charging cost, low ET data storage cost, and increased EV owner’s profit.



Scheduling of Electrical Vehicles considering uncertainty of PV generations in Smart Homes

  • H. MehdipoorS. Jadid
  • Engineering
    2014 19th Conference on Electrical Power Distribution Networks (EPDC)
  • 2014
Utilization of electric vehicles, especially Plug-in Hybrid Electric Vehicles with capability of power injection to the electrical system at the critical times, is one of the transportation system's

Optimal EV charge-discharge schedule in smart residential buildings

The work in this paper provides an approach to generate the optimal charge/discharge schedule for an EV plugged into a smart building. The building is assumed to be equipped with local solar

Demand side management verification system for electric vehicles

An EV schedule verification system based on artificial neural networks that verifies if the COS schedules can be directly applied or if some modifications are necessary and is tested on two sample distribution systems.

Definition and Evaluation of Model-Free Coordination of Electrical Vehicle Charging With Reinforcement Learning

A new Markov decision process (MDP) formulation in the RL framework is proposed, to jointly coordinate a set of charging stations, and an optimal charging policy is learned using a batch RL algorithm, fitted $Q$ -iteration.

A review of computer tools for analyzing the impact of electric vehicles on power distribution

  • K. MahmudG. Town
  • Computer Science
    2015 Australasian Universities Power Engineering Conference (AUPEC)
  • 2015
This paper reviews the various computer tools that have been reported for modeling the impacts of electrical vehicles on the power distribution grid. Forty four computer tools have been identified

Electric Vehicle Vision 2030 Challenges and Solutions

Implementation of hundred percent Electric Vehicles (EV) by 2030 is one of the most challenging visions for developing countries, especially for India with higher population growth, shortage in

Smart, connected and mobile: Architecting future electric mobility ecosystems

How and to what extent electric mobility will be integrated into the Internet of Energy (IoE) and Smart grid infrastructure to provide novel energy management solutions is discussed.

A comparison of methods for multiclass support vector machines

Decomposition implementations for two "all-together" multiclass SVM methods are given and it is shown that for large problems methods by considering all data at once in general need fewer support vectors.

10 Decision Boundary of the V2G case for training set data