Machine Learning Application for Prediction of EV Charging Demand for the Scenario of Agartala, India

Adhya, Dhritiman; Pal, Arnab; Chakraborty, Ajoy Kumar; Bhattacharya, Aniruddha

doi:10.1109/icepe55035.2022.9798369

Cited by 4 publications

(2 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Similar to the results reported in [46], papers [47]- [49] also showcase the outstanding capabilities of SVR in predicting EV load. The study presented in reference [47] utilizes the Support Vector Regression (SVR) algorithm to analyze EV charging demand, taking into account various influential factors such as meteorological conditions, number of EVs, festival periods, and weeks.…”

Section: ) Support Vector Regression (Svr)supporting

confidence: 80%

“…The findings suggest that SVR surpasses other machine learning algorithms in accuracy. The work in [49] Similar to ANN-based approaches, although SVR models are capable of capturing nonlinearity in input data, they require model parameter selection and their performace is heavily dependant on the quality of input data. Unlike ANN algorithms,SVR models are easier to interpret due to the implementation of a small set of support vectors.…”

Section: ) Support Vector Regression (Svr)mentioning

confidence: 99%

See 1 more Smart Citation

Electric Vehicle Energy Demand Prediction Techniques: An In-Depth and Critical Systematic Review

Marzbani,

Osman,

Hassan

2023

IEEE Access

View full text Add to dashboard Cite

Accurate forecast of electric vehicle energy demand is vital for maintaining the stability and reliability of power systems. With the increasing prevalence of electric vehicles in transportation systems, the anticipating demand surges with precision in terms of timing and location is becoming ever more critical for utilities to guarantee sufficient supply. The intermittent and stochastic nature of electric vehicle electricity consumption is a significant challenge in accurately forecasting of electric vehicles demand. As a result, there is a growing field of research focused on developing models that can effectively capture and interpret such complex data. In improving the potential of accurate prediction models, conducting a comprehensive review of literature, examining current research overviews, and exploring potential expansions and extensions of models are all critical components. In this review, a comprehensive overview of prior research conducted for forecasting electric vehicle energy demand is presented, including a detailed examination of the benefits and drawbacks of the methods used. Additionally, potential gaps in the field are identified, and recommendations for future research directions are provided.

show abstract