Search

Electric vehicles (EVs) have significant potential and sustainability in the future transportation sector due to their less pollution and low operating cost. The uncoordinated charging of these EVs may push the power delivery system towards lower performance and even at the risk of damaging the power system equipment. The proper scheduling and coordination of EVs with the system may lessen the negative impact. In this paper, a multi-objective scheduling approach for individual candidate-based EVs is proposed to relieve the distress in power delivery in the best possible way. Minimization of average demand deviation and system unbalance reduction are selected as the objectives to restore the power delivery performance. The proposed approach has been verified on a realistic three-phase power distribution infrastructure. A simple linear regression model is employed to predict the near future number of EVs in the test region. An optimizitaion algorithm based on particle swarm optimization (PSO) technique is operated to find the finest solution satisfying EV charging constraints. The stochastic nature of load demands at the node points of the test network is analyzed with the help of a probabilistic demand model and it is further incorporated into the optimization framework. It is possible to reduce the system's average demand deviation and unbalance level by 53.74% and 51.36%, respectively, with the proposed EV scheduling approach. A comparative study with the existing methods further claims the efficacy of the proposed approach. Framework for home charging schedule of distinct EVs Compliance with multi-objective power supply efficiency Probabilistic modeling of load demand from real collected data Optimization-driven solution for a test case in Mysore city in India [ABSTRACT FROM AUTHOR]

Economic and policy factors are driving the continuous increase in the adoption and usage of electrical vehicles (EVs). However, despite being a cleaner alternative to combustion engine vehicles, EVs have negative impacts on the lifespan of microgrid equipment and energy balance due to increased power demands and the timing of their usage. In our view, grid management should leverage on EV scheduling flexibility to support local network balancing through active participation in demand response programs. In this paper, we propose a model-free solution, leveraging deep Q-learning to schedule the charging and discharging activities of EVs within a microgrid to align with a target energy profile provided by the distribution system operator. We adapted the Bellman equation to assess the value of a state based on specific rewards for EV scheduling actions and used a neural network to estimate Q-values for available actions and the epsilon-greedy algorithm to balance exploitation and exploration to meet the target energy profile. The results are promising, showing the effectiveness of the proposed solution in scheduling the charging and discharging actions for a fleet of 30 EVs to align with the target energy profile in demand response programs, achieving a Pearson coefficient of 0.99. This solution also demonstrates a high degree of adaptability in effectively managing scheduling situations for EVs that involve dynamicity, influenced by various state-of-charge distributions and e-mobility features. Adaptability is achieved solely through learning from data without requiring prior knowledge, configurations, or fine-tuning. [ABSTRACT FROM AUTHOR]

The transition from internal combustion engines to electric vehicles (EVs) has received significant attention and investment due to its potential in reducing greenhouse gas emissions. The integration of EVs into electric and transport systems presents both benefits and challenges in energy management. The scheduling of EV charging can alleviate congestion in the electric system and reduce waiting times for EV owners. The use of renewable energy sources (RESs) for EV charging and supporting the grid can help mitigate the uncertainty of these energy resources. Vehicle-to-grid (V2G) technology can be used as an alternative approach in the event of sudden high consumption of the grid. Additionally, cost minimization through large-scale coordinated planning is crucial for the future of e-mobility systems. This review paper focuses on the latest trends considering the various approaches and features in coordinated EV scheduling, as well as the influence of different stakeholders, categorized as single- and multiple-charging stations (CS) and aggregator levels. By implementing coordinated EV scheduling, various methods are presented to better manage the needs and satisfaction of EV owners as well as the profit of CS and the market trends of e-mobility systems. In this regard, EV charging strategies considering V2G, uncertainty evaluation of parameters, coordinated charging management, congestion of CSs and electrical lines, route mapping, and technical and economic aspects of the system hierarchy, including consumers, CSs and aggregators, are reviewed and discussed. [ABSTRACT FROM AUTHOR]

Economic and policy factors are driving the continuous increase in the adoption and usage of electrical vehicles (EVs). However, despite being a cleaner alternative to combustion engine vehicles, EVs have negative impacts on the lifespan of microgrid equipment and energy balance due to increased power demands and the timing of their usage. In our view, grid management should leverage on EV scheduling flexibility to support local network balancing through active participation in demand response programs. In this paper, we propose a model-free solution, leveraging deep Q-learning to schedule the charging and discharging activities of EVs within a microgrid to align with a target energy profile provided by the distribution system operator. We adapted the Bellman equation to assess the value of a state based on specific rewards for EV scheduling actions and used a neural network to estimate Q-values for available actions and the epsilon-greedy algorithm to balance exploitation and exploration to meet the target energy profile. The results are promising, showing the effectiveness of the proposed solution in scheduling the charging and discharging actions for a fleet of 30 EVs to align with the target energy profile in demand response programs, achieving a Pearson coefficient of 0.99. This solution also demonstrates a high degree of adaptability in effectively managing scheduling situations for EVs that involve dynamicity, influenced by various state-of-charge distributions and e-mobility features. Adaptability is achieved solely through learning from data without requiring prior knowledge, configurations, or fine-tuning.

This paper proposes a flexible framework for scheduling and real time operation of electric vehicle charging stations (EVCS). The methodology applies a multi-objective evolutionary particle swarm optimization algorithm (EPSO) for electric vehicles (EVs) scheduling based on a day-ahead scenario. Then, real time operation is managed based on a rule-based (RB) approach. Two types of consumer were considered: EV owners with a day-ahead request for charging (scheduled consumers, SCh) and non-scheduling users (NSCh). EPSO has two main objectives: cost reduction and reduce overloading for high demand in grid. The EVCS has support by photovoltaic generation (PV), battery energy storage systems (BESS), and the distribution grid. The method allows the selection between three types of charging, distributing it according to EV demand. The model estimates SC remaining state of charge (SoC) for arriving to EVCS and then adjusts the actual difference by the RB. The results showed a profit for EVCS by the proposed technique. The proposed EPSO and RB have a fast solution to the problem that allows practical implementation.

This paper proposes a flexible framework for scheduling and real time operation of electric vehicle charging stations (EVCS). The methodology applies a multi-objective evolutionary particle swarm optimization algorithm (EPSO) for electric vehicles (EVs) scheduling based on a day-ahead scenario. Then, real time operation is managed based on a rule-based (RB) approach. Two types of consumer were considered: EV owners with a day-ahead request for charging (scheduled consumers, SCh) and non-scheduling users (NSCh). EPSO has two main objectives: cost reduction and reduce overloading for high demand in grid. The EVCS has support by photovoltaic generation (PV), battery energy storage systems (BESS), and the distribution grid. The method allows the selection between three types of charging, distributing it according to EV demand. The model estimates SC remaining state of charge (SoC) for arriving to EVCS and then adjusts the actual difference by the RB. The results showed a profit for EVCS by the proposed technique. The proposed EPSO and RB have a fast solution to the problem that allows practical implementation. [ABSTRACT FROM AUTHOR]