Uncertainties in model predictive control for decentralized autonomous demand side management of electric vehicles DOI Creative Commons
Muhandiram Arachchige Subodha Tharangi Ireshika, Peter Kepplinger

Journal of Energy Storage, Journal Year: 2024, Volume and Issue: 83, P. 110194 - 110194

Published: Jan. 28, 2024

Optimal scheduling of electric vehicle charging is a non-trivial problem associated with multiple sources uncertainties. These uncertainties are often neglected in demand-side management studies assuming perfect predictions, which practice unrealistic. In this paper, we propose model predictive control framework for the residential vehicles to account associated. The evaluations performed considering decentralized algorithm proposed literature, aims exploit flexibility fill valleys demand curve order flatten aggregated load. performance method evaluated response uncertainty non-elastic load, demand, and user behavior. results show that variance reduced by factor 4.8 predictive-based presence all three considered relative uncontrolled charging. Under prediction, reduction 7.5, thereby indicating viable solution against Moreover, study provides an overview degree overestimations desired outcomes realized under assumptions predictions different uncertain parameters, demonstrating most significant impact arises from mobility usage.

Language: Английский

A state-of-the-art comparative review of load forecasting methods: Characteristics, perspectives, and applications DOI Creative Commons

Mahmudul Hasan,

Zannatul Mifta,

Sumaiya Janefar Papiya

et al.

Energy Conversion and Management X, Journal Year: 2025, Volume and Issue: unknown, P. 100922 - 100922

Published: Feb. 1, 2025

Language: Английский

Citations

1
Review of peak load management strategies in commercial buildings DOI
Darwish Darwazeh, Jean Duquette,

Burak Gunay

et al.

Sustainable Cities and Society, Journal Year: 2021, Volume and Issue: 77, P. 103493 - 103493

Published: Nov. 2, 2021

Language: Английский

Citations

49
Design and development of Residential Sector Load Prediction model during COVID-19 Pandemic using LSTM based RNN DOI Open Access

A. Ajitha,

Maitri Goel,

Mohit Assudani

et al.

Electric Power Systems Research, Journal Year: 2022, Volume and Issue: 212, P. 108635 - 108635

Published: July 14, 2022

Language: Английский

Citations

31
A Survey on Data-Driven Runoff Forecasting Models Based on Neural Networks DOI
Ziyu Sheng,

Shiping Wen,

Zhong-kai Feng

et al.

IEEE Transactions on Emerging Topics in Computational Intelligence, Journal Year: 2023, Volume and Issue: 7(4), P. 1083 - 1097

Published: March 31, 2023

As an important branch of time series forecasting, runoff forecasting provides a reliable decision-making basis for the rational use water resources, economic development and ecological management river basins. With revolution computing power, data-driven model has become mainstream method. This survey will introduce explore several types existing neural network forecasting: convolutional (CNN), recurrent (RNN) Transformer. The advantages limitations these referenced models are also discussed. In addition, this paper discusses future improvement directions from three accuracy, robustness interpretability. Through plug-and-play lightweight attention mechanism modules, ensemble methods, forward-looking interpretability potential can be further tapped to improve overall performance.

Language: Английский

Citations

22
Uncertainties in model predictive control for decentralized autonomous demand side management of electric vehicles DOI Creative Commons
Muhandiram Arachchige Subodha Tharangi Ireshika, Peter Kepplinger

Journal of Energy Storage, Journal Year: 2024, Volume and Issue: 83, P. 110194 - 110194

Published: Jan. 28, 2024

Optimal scheduling of electric vehicle charging is a non-trivial problem associated with multiple sources uncertainties. These uncertainties are often neglected in demand-side management studies assuming perfect predictions, which practice unrealistic. In this paper, we propose model predictive control framework for the residential vehicles to account associated. The evaluations performed considering decentralized algorithm proposed literature, aims exploit flexibility fill valleys demand curve order flatten aggregated load. performance method evaluated response uncertainty non-elastic load, demand, and user behavior. results show that variance reduced by factor 4.8 predictive-based presence all three considered relative uncontrolled charging. Under prediction, reduction 7.5, thereby indicating viable solution against Moreover, study provides an overview degree overestimations desired outcomes realized under assumptions predictions different uncertain parameters, demonstrating most significant impact arises from mobility usage.

Language: Английский

Citations

7