137
Views
1
CrossRef citations to date
0
Altmetric
Research Article

A GBDT-BCO Technique based Cost Reduction and Energy Management between Electric Vehicle and Electricity Distribution System

&
Received 28 Dec 2020, Accepted 14 Jul 2021, Published online: 19 Aug 2021
 

ABSTRACT

This work presents an energy management system for the performance of electric vehicle charging station (EVCS) based on the distribution system (DS) with a hybrid approach. The proposed hybrid strategy is the consolidation of the gradient boosting decision tree (GBDT) algorithm and the border collie optimization (BCO), thus it is called GBDT-BCO. The major contribution of this manuscript is cost reduction and energy management interaction among electric vehicles and distribution system. The proposed system consists of electric vehicles (EV) with bi-directional energy exchange through charging and grid-to-vehicle and vehicle-to-household operating modes, energy storage systems (ESS) through peak cutting, photovoltaic (PV) favors the sale of energy to the grid, which are deemed the energy management system (EMS). Power is predicted by GBDT approach. For diminishing the operating cost of power, the proposed system is incorporated with photovoltaic, including energy storage systems, and the cost is reduced by optimizing the BCO. System stability is improved through the use of time-based predictions (e.g. usage time). The proposed GBDT-BCO approach reduces the cost of the system and maintains the needed power output during the integration of EVCS with distribution system. The efficiency of GBDT-BCO approach is likened to existing approaches and assessed with dissimilar test cases and time periods. The experimental results show that the proposed GBDT-BCO approach offers best solutions likened to existing process and increases the advantages of the distribution system for the entire cases assumed. The efficiency of the proposed and existing techniques is also analyzed. GA’s efficiency achieved is 47%, PSO reaches 56%, GA-PSO reaches 77%, and the proposed technique reaches 89%.

Additional information

Notes on contributors

Arumugam Vijayakumar

Vijayakumar Arumugam received B.E degree in Electrical and Electronics Engineering from Shanmugha Colleege of Engineering (Presently known as SASTRA Deemed University), Thanjavur, in 1991. The institution was then affiliated to Bharathidasan University Trichy, Tamilnadu.  He received M.E Degree in Power Electronics and Drives from the same institution in 1999. He was awarded Ph.D degree by Anna University, Chennai, India in 2016.  His research interests include power quality and power electronics. He is having 25 years of teaching experience and  at present working as Professor of EEE department in Anjalai Ammal Mahalingam Engineering College, Kovilveni, Tiruvarur district.

Dharmaligam Uma

Uma Dharmaligam  received her B.E degree in Electrical and Electronics Engineering from Alagappa Chettiar Government College of Engineering & Technology,  Karaikudi in 1995. The institution was then affiliated to Madurai Kamaraj University Madurai, Tamilnadu . She received M.E Degree in Power Electronics and Drives from Shanmugha Colleege of Engineering (Presently known as SASTRA Deemed University), in 1999. He was awarded Ph.D degree by SASTRA Deemed University, Thanjavur, India in 2018.  His research interests include electrical machines, power quality and power electronics and drives. She is having 25 years of teaching experience and at present working as Senior Assistant Professor in school EEE, in SASTRA Deemed University, Thanjavur.

Log in via your institution

Log in to Taylor & Francis Online

PDF download + Online access

  • 48 hours access to article PDF & online version
  • Article PDF can be downloaded
  • Article PDF can be printed
USD 61.00 Add to cart

* Local tax will be added as applicable

Related Research

People also read lists articles that other readers of this article have read.

Recommended articles lists articles that we recommend and is powered by our AI driven recommendation engine.

Cited by lists all citing articles based on Crossref citations.
Articles with the Crossref icon will open in a new tab.