A Hybrid Model Based on LSSVM and the Improved BFOA for Sustainability of Daily Electricity Load Forecasting in Malaysia DOI Open Access
Farah Anishah Zaini, Mohamad Fani Sulaima,

Intan Azmira binti Wan Abdul Razak

et al.

Published: June 11, 2024

: Leveraging the sustainability of power system market, researchers have developed various ML models for forecasting electricity demand. The LSSVM is well suited to handle complex non-linear load series. However, less optimal regularization parameter and Gaussian kernel function in model contributed flawed accuracy random generalization ability. Thus, these parameters need be chosen appropriately using intelligent optimization algorithms. This study proposes a hybrid based on optimized by IBFOA daily Peninsular Malaysia. introduced. sine cosine equation proposed adjust constant step size BFOA, which creates an imbalance between exploration exploitation during optimization. Finally, LSSVM-IBFOA constructed MAPE as objective function. Comparative analysis demonstrates model, achieving highest R2 (0.9880) significantly reducing error metrics (MAPE, MAE, RMSE, MSE, NRMSE) compared baseline (average reduction 27.72% 47.72%). Additionally, exhibits faster convergence higher highlighting short-term forecasting.

Language: Английский

Placement and Capacity of EV Charging Stations by Considering Uncertainties With Energy Management Strategies DOI
Fareed Ahmad, Atif Iqbal,

Imtiaz Asharf

et al.

IEEE Transactions on Industry Applications, Journal Year: 2023, Volume and Issue: 59(3), P. 3865 - 3874

Published: March 8, 2023

At the present context, Plug-in electric vehicles (PEVs) are gaining popularity in automotive industry due to their low CO2 emissions, simple maintenance, and operating costs. As number of PEVs on road increases, charging demand affects distribution network features, such as power loss, voltage profile, harmonic distortion. Furthermore, one more problem arises high peak from grid charge at station (CS). In addition, location CS also behavior EV users investors. Hence, this paper applies investor, PEV user, operator who could approach CS's optimal capacity. Integrating renewable energy sources (RESs) is suggested lower stress grid. Moreover, keep down utilize efficiently, management strategies (EMS) have been applied through control discharging battery storage system (BSS). vehicle (V2G) strategy discharge station. uncertainties related PV generation addressed by Monte Carlo Simulation (MCS) method.

Language: Английский

Citations

60
Hybrid genetic algorithm-simulated annealing based electric vehicle charging station placement for optimizing distribution network resilience DOI Creative Commons

B. Anil Kumar,

B. Jyothi,

Arvind R. Singh

et al.

Scientific Reports, Journal Year: 2024, Volume and Issue: 14(1)

Published: April 1, 2024

Abstract Rapid placement of electric vehicle charging stations (EVCSs) is essential for the transportation industry in response to growing (EV) fleet. The widespread usage EVs an strategy reducing greenhouse gas emissions from traditional vehicles. focus this study challenge smoothly integrating Plug-in EV Charging Stations (PEVCS) into distribution networks, especially when distributed photovoltaic (PV) systems are involved. A hybrid Genetic Algorithm and Simulated Annealing method (GA-SAA) used research strategically find optimal locations PEVCS order overcome integration difficulty. This paper investigates PV system situations, presenting problem as a multicriteria task with two primary objectives: power losses maintaining acceptable voltage levels. By optimizing EVCS balancing their generation, approach enhances sustainability reliability networks.

Language: Английский

Citations

38
Adaptive Hosting Capacity Forecasting in Distribution Networks with Distributed Energy Resources DOI Creative Commons
Md Tariqul Islam, M. J. Hossain, Md. Ahasan Habib

et al.

Energies, Journal Year: 2025, Volume and Issue: 18(2), P. 263 - 263

Published: Jan. 9, 2025

The sustainable integration of distributed energy resources (DER) into distribution networks requires accurate forecasting hosting capacity. network and DER variables alone do not capture the full range external influences on integration. Traditional models often overlook dynamic impacts these exogenous factors, leading to suboptimal predictions. This study introduces a Sensitivity-Enhanced Recurrent Neural Network (SERNN) model, featuring sensitivity gate within neural network’s memory cell architecture enhance responsiveness time-varying variables. dynamically adjusts model’s response based conditions, allowing for improved input variability temporal characteristics DER. Additionally, feedback mechanism model provides inputs from previous states forget gate, refined control over selection enhancing precision. Through case studies, demonstrates superior accuracy in capacity predictions compared baseline like LSTM, ConvLSTM, Bidirectional Stacked GRU. Study shows that SERNN achieves mean absolute error (MAE) 0.2030, root square (RMSE) 0.3884 an R-squared value 0.9854, outperforming best by 48 per cent MAE 71 RMSE. Feature engineering enhances performance, improving 0.9145 0.9854. also lowering 0.2030 0.2283 without increasing 0.9152 Incorporating factors such as time day input, further improves responsiveness, making more adaptable real-world conditions. advanced offers reliable framework operators, supporting intelligent planning proactive management. Ultimately, it significant step forward analysis, enabling efficient next-generation networks.

Language: Английский

Citations

2
Electric vehicle charging infrastructure planning model with energy management strategies considering EV parking behavior DOI
Salman Habib, Fareed Ahmad, Muhammad Majid Gulzar

et al.

Energy, Journal Year: 2025, Volume and Issue: 316, P. 134421 - 134421

Published: Jan. 15, 2025

Language: Английский

Citations

2
Optimal allocation of plug-in electric vehicle charging stations in the distribution network with distributed generation DOI Creative Commons
Ebunle Akupan Rene, Willy Stephen Tounsi Fokui,

Paule Kevin Nembou Kouonchie

et al.

Green Energy and Intelligent Transportation, Journal Year: 2023, Volume and Issue: 2(3), P. 100094 - 100094

Published: June 1, 2023

The transportation sector is characterized by high emissions of greenhouse gases (GHG) into the atmosphere. Consequently, electric vehicles (EVs) have been proposed as a revolutionary solution to mitigate GHG and dependence on petroleum products, which are fast depleting. EVs proliferating in many countries worldwide adoption this technology significantly dependent expansion charging stations. This study proposes use hybrid genetic algorithm particle swarm optimization (GA-PSO) for optimal allocation plug-in EV stations (PEVCS) distribution network with distributed generation (DG) volumes at selected buses. Photovoltaic (PV) systems power factor 0.95 used DGs. PVs penetrated 60% six penetration cases considered placement PEVCSs. problem formulated multi-objective minimizing active reactive losses well voltage deviation index. IEEE 33 69 bus networks test networks. simulation was performed using MATLAB results obtained validate effectiveness GA-PSO. For example, integration PEVCSs minimum still within accepted margins. network, resulting 0.973 p.u case 1, 0.982 2, 0.96 3, 0.961 4, 0.954 5, 0.965 6. sustainable means mitigating from their utilization essential concern climate change carbon-free society intensifies.

Language: Английский

Citations

41
Planning of fast charging infrastructure for electric vehicles in a distribution system and prediction of dynamic price DOI Creative Commons

K. Victor Sam Moses Babu,

Pratyush Chakraborty, Mayukha Pal

et al.

International Journal of Electrical Power & Energy Systems, Journal Year: 2023, Volume and Issue: 155, P. 109502 - 109502

Published: Sept. 22, 2023

Language: Английский

Citations

28
Artificial intelligence-based optimal EVCS integration with stochastically sized and distributed PVs in an RDNS segmented in zones DOI Creative Commons
Ebunle Akupan Rene, Willy Stephen Tounsi Fokui

Journal of Electrical Systems and Information Technology, Journal Year: 2024, Volume and Issue: 11(1)

Published: Jan. 2, 2024

Abstract The growing interest in electric vehicles (EVs) for transportation has led to increased production and government support through legislation since they offer environmental benefits such as reduced air pollution carbon emissions compared conventional combustion engine vehicles. This shift toward EV technology aligns with the goal of preserving natural environment. To fully utilize EVs, effective management power grid is crucial, particularly radial distribution network systems (RDNS) pose stress deviation system parameters from their normal. study proposes a novel strategy maximizing utilization charging stations (EVCSs) an RDNS by considering factors load voltage deviation, line losses, presence distributed solar photovoltaic at centers. research begins segmenting into zones, followed application artificial intelligence-based hybrid genetic algorithm (GA) particle swarm optimization (PSO) approach known GA–PSO. identifies optimal locations EVCSs integrated photovoltaics within network. Subsequently, employment individual GA PSO algorithms optimize EVCS placement focuses on minimizing loss enhancing voltage. effectiveness GA–PSO that separate methods. Extensive simulations using IEEE 33-node test feeders validate proposed techniques, demonstrating usefulness identifying each zone. results also highlight advantages novelty achieving stochastically sized RDNS.

Language: Английский

Citations

9
An Innovative Real-Time Recursive Framework for Techno-Economical Self-Healing in Large Power Microgrids Against Cyber–Physical Attacks Using Large Change Sensitivity Analysis DOI Creative Commons
Mehdi Zareian Jahromi, Elnaz Yaghoubi, Elaheh Yaghoubi

et al.

Energies, Journal Year: 2025, Volume and Issue: 18(1), P. 190 - 190

Published: Jan. 4, 2025

In the past, providing an online and real-time response to cyber–physical attacks in large-scale power microgrids was considered a fundamental challenge by operators managers of distribution networks. To address this issue, innovative framework is proposed paper, enabling responsiveness cyberattacks while focusing on techno-economic energy management microgrids. This leverages large change sensitivity (LCS) method receive immediate updates system’s optimal state under disturbances, eliminating need for full recalculation flow equations. significantly reduces computational complexity enhances adaptability compared traditional approaches. Additionally, optimizes operational points, including resource generation network reconfiguration, simultaneously considering technical, economic, reliability parameters—a comprehensive integration often overlooked recent studies. Performance evaluation systems, such as IEEE 33-bus, 69-bus, 118-bus networks, demonstrates that achieves optimization less than 2 s, ensuring superior efficiency, scalability, resilience. The results highlight significant improvements over state-of-the-art methods, establishing robust solution real-time, cost-effective, resilient disturbances.

Language: Английский

Citations

1
Dual-layered deep learning and optimization algorithm for electric vehicles charging infrastructure planning DOI
Bishoy E. Sedhom, Abdelfattah A. Eladl, Pierluigi Siano

et al.

International Journal of Electrical Power & Energy Systems, Journal Year: 2025, Volume and Issue: 166, P. 110545 - 110545

Published: Feb. 20, 2025

Language: Английский

Citations

1
Stochastic Modelling and Integration of Electric Vehicles in the Distribution System Using the Jaya Algorithm DOI

Mohd Owais Khan,

Sheeraz Kirmani, Mohd Rihan

et al.

IETE Journal of Research, Journal Year: 2024, Volume and Issue: 70(7), P. 6478 - 6493

Published: Jan. 5, 2024

Electric vehicles (EVs) have enormous promise for the development of future transportation systems. The widespread use EVs could negatively impact how power systems operate, particularly at distribution level. Therefore, smart charging techniques are essential to increasing EV adoption in general. connection between electricity grid and network is made electric vehicle stations (EVCS), both networks will be simultaneously impacted by operational behaviour EVs. EVCS must placed a best possible way. In this paper, an efficient approach formulated schedule so that adverse effects like increase peak demand system cost minimized. load model considering factors such as state charge, trip distance travelled, user's behaviour. proposed reduces optimizes charging. Different types considered based on their usage patterns making realistic problem formulations. technique presented work 30% 50%. addition, placement implemented alongside distributed generation IEEE 33 69 bus reduce losses improve voltage profile using metaheuristic algorithm known Jaya Algorithm. effectiveness established comparing results with published work.

Language: Английский

Citations

7