Optimizing Electric Vehicle (EV) Charging with Integrated Renewable Energy Sources: A Cloud-Based Forecasting Approach for Eco-Sustainability

Mathematics, Journal Year: 2024, Volume and Issue: 12(17), P. 2627 - 2627

Published: Aug. 24, 2024

As electric vehicles (EVs) are becoming more common and the need for sustainable energy practices is growing, better management of EV charging station loads a necessity. The simple act folding renewable power from solar or wind in an system presents huge opportunity to make them even greener as well improve grid resiliency. This paper proposes innovative consumption forecasting approach by incorporating integrated data. optimization achieved through application SARLDNet, which enhances predictive accuracy reduces forecast errors, thereby allowing efficient allocation load stations. technique leverages comprehensive statistics alongside detailed utilization data collected over 3.5 years various locations across California. To ensure integrity, missing were meticulously addressed, quality was enhanced. Boruta employed feature selection, identifying critical predictors, improving dataset engineering elucidate trends. Empirical mode decomposition (EMD) signal extracts intrinsic functions, revealing temporal patterns significantly boosting accuracy. study introduces novel stem-auxiliary-reduction-LSTM-dense network (SARLDNet) architecture tailored robust regression analysis. combines regularization, dense output layers, LSTM-based context learning, dimensionality reduction, early extraction mitigate overfitting. performance SARLDNet benchmarked against established models including LSTM, XGBoost, ARIMA, demonstrating superior with mean absolute percentage error (MAPE) 7.2%, Root Mean Square Error (RMSE) 22.3 kWh, R2 Score 0.87. validation SARLDNet’s potential real-world applications, its enhanced reduced rates stations, reason optimism field infrastructure planning. also emphasizes role cloud enabling real-time decision support. By facilitating scalable processing, insights generated support informed planning decisions under dynamic conditions, empowering audience adopt practices.

Language: Английский

Task-Offloading Optimization Using a Genetic Algorithm in Hybrid Fog Computing for the Internet of Drones

Sensors, Journal Year: 2025, Volume and Issue: 25(5), P. 1383 - 1383

Published: Feb. 24, 2025

Research and development on task offloading over the Internet of Drones (IoD) has expanded rapidly in last few years. Task a fog IoD environment is very challenging due to high dynamics topology, which cause intermittent connections, as well stringent requirements offloading, such reduced delay. To overcome these challenges, this paper, we propose task-offloading optimization strategy using heuristic genetic algorithm (GA) with hybrid computing technology for Drones, named GA Hybrid-Fog. The proposed solution employs from edge Unmanned Aerial Vehicles (UAVs) both base stations (FBSs) UAVs (FUAVs) order optimize delays (transmission delays) guarantee higher storage processing capacity. Experimental results show that Hybrid-Fog achieves greater improvements compared other technologies (GA BS-Fog, UAV-Fog, UAV-Edge).

Language: Английский

MLGO: A machine learning-based mountain gazelle optimization algorithm for efficient resource management and load balancing in fiber wireless access networks

Optical Fiber Technology, Journal Year: 2024, Volume and Issue: 88, P. 104014 - 104014

Published: Nov. 4, 2024

Language: Английский