Electric vehicle hosting capacity analysis: Challenges and solutions

Renewable and Sustainable Energy Reviews, Год журнала: 2023, Номер 189, С. 113916 - 113916

Опубликована: Ноя. 1, 2023

The significant rise of electric vehicles (EVs) and distributed energy resources (DERs) poses critical challenges to the distribution systems for maintaining statutory limits technical operating constraints. This review investigates explores innovative solutions EV hosting capacity analysis in network based on existing literature industry reports published recent years (2014–2023). study emphasizes significance multiple performance constraints, scenarios, availability data, methods analysis. In addition, it provides insights into aspects, performance, practicability issues open-source commercial tools assessing capacity. also highlights industrial projects international Australian contexts, showcasing importance region-specific integration due diverse profiles, charging facilities, topologies. Based research reports, active management, flexible limits, demand response, optimal placement methods, reconfiguration are identified as promising enhancement. concludes by discussing future scopes, considering accuracy, computational time, data requirements guide researchers grid planners.

Язык: Английский

---

Remaining Useful Life Prediction of Lithium-Ion Batteries by Using a Denoising Transformer-Based Neural Network

Energies, Год журнала: 2023, Номер 16(17), С. 6328 - 6328

Опубликована: Авг. 31, 2023

In this study, we introduce a novel denoising transformer-based neural network (DTNN) model for predicting the remaining useful life (RUL) of lithium-ion batteries. The proposed DTNN significantly outperforms traditional machine learning models and other deep architectures in terms accuracy reliability. Specifically, achieved an R2 value 0.991, mean absolute percentage error (MAPE) 0.632%, RUL 3.2, which are superior to such as Random Forest (RF), Decision Trees (DT), Multilayer Perceptron (MLP), Recurrent Neural Network (RNN), Long Short-Term Memory (LSTM), Gated Unit (GRU), Dual-LSTM, DeTransformer. These results highlight efficacy providing precise reliable predictions battery RUL, making it promising tool management systems various applications.

Язык: Английский

---

An energy management system for PV-STATCOMs in power distribution networks via a complex-domain SDP relaxation

Energy Systems, Год журнала: 2025, Номер unknown

Опубликована: Фев. 18, 2025

Язык: Английский

---

Planning and Operation Objectives of Public Electric Vehicle Charging Infrastructures: A Review

Energies, Год журнала: 2023, Номер 16(14), С. 5431 - 5431

Опубликована: Июль 17, 2023

Planning public electric vehicle (EV) charging infrastructure has gradually become a key factor in the electrification of mobility and decarbonization transport sector. In order to achieve high level mobility, recent years, different studies have been presented, proposing novel practices methodologies for planning operation vehicles infrastructure. this paper, authors present an up-to-date analysis existing literature research field, organized by considering perspectives objectives principal actors/operators EV value chain. Among these actors, vehicle, operators service providers, power system (transmission distribution system) are analyzed depth. By classifying reviewed based on manifold viewpoints approach, paper aims facilitate researchers technology developers exploring state-of-the-art each actor’s perspective, identify conflicting interests synergies planning.

Язык: Английский

---

RX-ADS: Interpretable Anomaly Detection Using Adversarial ML for Electric Vehicle CAN Data

IEEE Transactions on Intelligent Transportation Systems, Год журнала: 2023, Номер 24(12), С. 14051 - 14063

Опубликована: Июль 24, 2023

Recent year has brought considerable advancements in Electric Vehicles (EVs) and associated infrastructures/communications. Intrusion Detection Systems (IDS) are widely deployed for anomaly detection such critical infrastructures. This paper presents an Interpretable Anomaly System (RX-ADS) intrusion CAN protocol communication EVs. Contributions include: 1) Feature Extractor; 2) System; 3) Explanation Generator detected anomalies. The presented approach was tested on two benchmark datasets: OTIDS Car Hacking. performance of RX-ADS compared against the state-of-the-art approaches these HIDS GIDS. showed comparable to dataset outperformed GIDS Hacking dataset. Further, proposed able generate explanations abnormal behaviors arising from various intrusions. These were later validated by information used domain experts detect Other advantages method can be trained unlabeled data; help understanding anomalies root course analysis, also with AI model debugging diagnostics, ultimately improving user trust systems.

Язык: Английский

---

Energy Management System for Smart Grid in the Presence of Energy Storage and Photovoltaic Systems

International Journal of Photoenergy, Год журнала: 2023, Номер 2023, С. 1 - 15

Опубликована: Ноя. 21, 2023

Today, the desire to use renewable energy as a source of clean and available in grid has increased. Due unpredictable behavior resources, it is necessary storage resources microgrid structure. The power generation microgrids should be selected such way that ability respond maximum demand state connected operate independently. In this article, optimal capacity economic performance based on photovoltaic battery system have been investigated. way, first, using iterative optimization method, obtained. Then, dynamic planning method used for management. simulation results show accuracy efficiency proposed solutions. controller, while automatically dynamically adapting solar cell output changes, capable responding external requests, price signals or satisfying constraints operator requests. addition, indicate by management system, can regain stability during one two cycles, occurrence PV radiation changes well ESS charge changes. And also, according voltage within defined permissible range between 0.95 1.05 pu, which result unique system.

Язык: Английский

---

Stochastic MILP Model for Merging EV Charging Stations with Active Distribution System Expansion Planning by considering Uncertainties

Electric Power Components and Systems, Год журнала: 2023, Номер unknown, С. 1 - 31

Опубликована: Дек. 27, 2023

Radial Power Distribution Networks (PDNs) often suffer from limited reliability, flexibility, and efficiency, leading to service interruptions. Planning for radial PDNs is essential enhance redundancy resilience, reduce disruptions, improve overall efficiency. However, traditional PDN planning methods have become obsolete due the proliferation of Distributed Generation (DG) resources energy storage systems. Additionally, rise Electric Vehicles (EVs) demands sophisticated charging infrastructure planning. This article presents a Mixed-Integer Linear Programming (MILP) model joint expansion Vehicle Charging Stations (EVCSs). The takes into account construction or reinforcement substations circuits, along with integration EVs, installation DGs, placement capacitor banks, all regarded as conventional options alternatives. To address uncertainties associated DG generation, loads, EV demand, our identifies optimal asset locations. We formulate this stochastic scenario-based program chance constraints Network Expansion (PDNEP), minimizing investment, operational, loss cost costs over horizon. Through two deterministic approaches, encompassing six case studies on an 18-node test system, we evaluate effectiveness model. Results are further validated 54-node confirming model's robustness. Notably, numerical findings underscore substantial reduction achieved by including EVCSs in approach, demonstrating its cost-effectiveness. In study I, where EVs charge at home during peak hours, it's worst PDN. more complex, longer computational time. 9.97% (case II) 3.96% VI) versus worst-case I). improvements range 10.47% 1.40% VI). As result, comparative analyses against consistently outperforms diverse studies. proposed adaptability underscores suitability solving PDNEP problem PND.

Язык: Английский

---

Electric Vehicle Supply Equipment Day-Ahead Power Forecast Based on Deep Learning and the Attention Mechanism

IEEE Transactions on Intelligent Transportation Systems, Год журнала: 2024, Номер 25(8), С. 9563 - 9571

Опубликована: Май 6, 2024

Transports is one of the sectors that produce highest emissions CO $_2 $ ; in last ten years, there has been a process decarbonization which led to considerable increase Electric Vehicles (EVs). However, sudden introduction large number vehicle supply equipment (EVSE) supplying electrical energy EVs could cause problems management electric grid must cope with consequent load demand. In this context, 24 hour ahead forecast power curve associated recharge becomes vital importance ensure reliability grid. paper, different Machine Learning models based on Recurrent Neural Networks (LSTM, GRU) and architectures, are compared their capability accurately predict an EV charging station day advance. A Sequence model implemented thorough analysis Attention layer detailed. The tested real world open dataset.

Язык: Английский

---

Optimal energy management via day-ahead scheduling considering renewable energy and demand response in smart grids

ISA Transactions, Год журнала: 2024, Номер unknown

Опубликована: Сен. 1, 2024

Язык: Английский

---

A Dynamic Programming Model for Joint Optimization of Electric Drayage Truck Operations and Charging Stations Planning at Ports

IEEE Transactions on Intelligent Transportation Systems, Год журнала: 2023, Номер 24(11), С. 11710 - 11719

Опубликована: Июнь 27, 2023

The adoption of electric vehicles at ports is a promising approach to achieve sustainability goals. However, realizing the full potential this strategy depends on effective coordination between infrastructure planning and operational scheduling. In paper, we propose joint optimization framework that can co-optimize these two components minimize overall system cost. To capture dynamic nature scheduling decisions, model problem using programming techniques. Our accounts for spatial temporal heterogeneities charging driving costs different truck trips. evaluate effectiveness our proposed framework, conducted an empirical study Port Los Angeles Long Beach. Specifically, aimed fulfill 5% daily 20-foot equivalent unit containers drayage trucks. identified optimal number trucks, stations, schedules required meet container throughput requirement. We also analyzed cost per as function level various scenarios. findings provide insights how determine charger supply based throughputs ports, choose appropriate ratios trucks battery sizes in fleet under price cases.

Язык: Английский

---