Search

Advancing bidirectional voltage source inverters in the on-board chargers of electric vehicles is vital for smart grid electric power management. These electric vehicle inverters play a crucial role in actively contributing to active/reactive power flow control in vehicle-to-grid and grid-to-vehicle applications. In this research, a proof-of-concept, model-free reinforcement learning-based agent/controller is introduced that eliminates the need for system identification or linearization techniques for control design. The goal is to dynamically control user-specified active and reactive electric vehicle on-board charger power outputs in all four quadrants for three-phase grid-connected electric vehicle voltage source inverters. A Twin-Delayed Deep Deterministic Policy Gradient deep-reinforcement learning-based controller was designed (1) to smoothly learn continuous control variables and to generate deterministic actions from the learned control policy, (2) to avoid exhaustive system identification techniques associated with nonlinearities involved in the on-board charger of electric vehicles, and (3) to ultimately track continuous active and reactive powers across all four-quadrant operation modes, ensuring safe and minimal steady-state errors. In this paper, a Markov Decision Process framework was established, encompassing the environment, actions, states, and a unique reward function. The minimal steady state error achieved in active and reactive power reference tracking across all four quadrant operation modes substantiates the trained agent’s capacity to sustain tracking accuracy and stability across a variety of operational settings. This research could potentially pave the way for any type of electric vehicle to actively play a role in smart grid management, especially through vehicle-to-grid and grid-to-vehicle capabilities.

Electric vehicle aggregators (EVAs) that utilize vehicle-to-grid (V2G) technologies can function as both controllable loads and virtual power plants, providing key energy management services to the distribution system operator (DSO). EVAs can also balance the grid’s reactive power as a virtual static VAR compensator (SVC) and provide voltage stability by utilizing advanced electric vehicle (EV) chargers that are capable of four-quadrant operations to provide reactive power management. Finally, managed charging can benefit EVAs themselves by minimizing power factor penalties in their electricity bills. In this paper, we propose a novel EV charging scheduling algorithm based on a hierarchical distributed optimization framework that minimizes peak load and provides reactive power compensation for the DSO by collaboration with EVAs that manage both the active and the reactive charging and discharging power of participating EVs. Utilizing the alternative direction method of multipliers (ADMM), the proposed distributed optimization approach scales well with increased EV charging infrastructure by balancing active and reactive power while decreasing computational burden. In our proposed hierarchical approach, each EVA schedules the active and reactive EV charging and discharging power for 1) reactive power compensation in order to minimize power factor penalty and electricity cost accrued by the EVA, 2) satisfaction of each EV’s energy demand at minimal charging cost, and 3) peak shaving and load management for the DSO. When compared with an uncoordinated charging model, the efficacy of this proposed model is successfully demonstrated through a 300% decreased peak EV load for the DSO, 28% lower electricity costs for EV users, and 98.55% smaller power factor penalty, along with 17.58% lower overall electricity costs, for EVAs. The performance of our approach is validated in a case study with 50 EVs at multiple EVAs in an IEEE 13-bus test case and compared the results with uncoordinated EV charging.

The deployment of medium-duty and heavy-duty (MDHD) electric vehicles (EVs), characterized by their substantial battery capacity and high charging power demand, poses a potential threat to voltage stability within distribution networks. One possible solution to voltage instability is reactive power compensation from charging MDHD EVs. However, this process must be carefully facilitated in order to be effective. This paper introduces an innovative distribution network voltage stability solution by first identifying the network’s weakest buses and then utilizing a metaheuristic algorithm to schedule reactive power compensation from MDHD EVs. In the paper, multiple metaheuristic algorithms, including genetic algorithms, particle swarm optimization, moth flame optimization, salp swarm algorithms, whale optimization, and grey wolf optimization, are subjected to rigorous evaluation concerning their efficacy in terms of voltage stability improvement, power loss reduction, and computational efficiency. The proposed methodology optimizes power flow with the salp swarm algorithm, which was determined to be the most effective tool, to mitigate voltage fluctuations and enhance overall stability. The simulation results, conducted on a modified IEEE 33 bus distribution system, convincingly demonstrate the algorithm’s efficacy in augmenting voltage stability and curtailing power losses, supporting the reliable and efficient integration of MDHD EVs into distribution networks.

Modern distribution systems are confronted by increasing penetration of distributed energy resources, making state estimation a critical application for distribution systems. However, existing state estimation schemes are often time-consuming and therefore, hard to scale up for large systems. In this context, this paper has proposed using a surrogate model to accelerate state estimations. Long-short-term memory (LSTM) recurrent neural networks have been applied to produce a fast yet coarse surrogate of the system states, which captures the temporal correlations between consecutive states. We have further applied an autoencoder to reduce the input size of LSTM networks, thereby shrinking LSTM network size and increasing the scalability of the proposed method. The surrogate states from LSTM are then fed into the forward/backward sweep state estimator as initial values. As a result, the state estimation convergence is accelerated by the LSTM surrogates. The proposed method is tested on IEEE 123-bus and 8500-node three-phase unbalanced test systems. Experimental results show that the proposed LSTM networks significantly reduce the computational time of distribution systems state estimation.

With an increased number of plug-in electric vehicles (PEVs) on the roads, PEV charging infrastructure is gaining an ever-more important role in simultaneously meeting the needs of drivers and those of the local distribution grid. However, the current approach to charging is not well suited to scaling with the PEV market. If PEV adoption continues, charging infrastructure will have to overcome its current shortcomings such as unresponsiveness to grid constraints, low degree of autonomy, and high cost, in order to provide a seamless and configurable interface from the vehicle to the power grid. Among the tasks a charging station will have to accomplish will be PEV identification, charging authorization, dynamic monitoring, and charge control. These will have to be done with a minimum of involvement at a maximum of convenience for a user. The system proposed in this work allows charging stations to become more responsive to grid constraints and gain a degree of networked autonomy by automatically identifying and authorizing vehicles, along with monitoring and controlling all charging activities via an RFID mesh network consisting of charging stations and in-vehicle devices. The proposed system uses a ZigBee mesh network of in-vehicle monitoring devices which simultaneously serve as active RFID tags and remote sensors. The system outlined lays the groundwork for intelligent charge-scheduling by providing access to vehicle’s State of Charge (SOC) data as well as vehicle/driver IDs, allowing a custom charging schedule to be generated for a particular driver and PEV. The approach presented would allow PEV charging to be conducted effectively while observing grid constraints and meeting the needs of PEV drivers.

With the rapid development of wind turbine, photovoltaicand battery technologies, renewable energy resources such as wind and solar become the most common distributedgenerations (DG) that are being integrated into microgrids. One key impediment is to determine the sizes and placements of DGs within which the microgrid can achieve its maximum potential benefits. The objective of the paper is to study and propose an approach to find the optimal sizes and placements of DGs in a microgrid. The authors propose a comprehensive objective function with practical constraints which take all the important factors that will impact the reliability of the power grid into account. To solve the optimization problem, genetic algorithm (GA) is used and compared with a mathematical optimization method nonlinear programming. The proposed model is tested on a real microgrid, i.e. Jeju Island, to evaluate and validate the performances of the approach. The simulation results present the optimal configuration of DGs for Jeju Island power grid. The analysis on results shows that GA maintains a delicate balance between performance and complexity. It is concluded that GA performs better not only in accuracy, stability, but also in computation time.

WINSmartEV is a software based plug-in electric vehicle (PEV) monitoring, control, and management system. It not only incorporates intelligence at every level so that charge scheduling can avoid grid bottlenecks, but it also multiplies the number of PEVs that can be plugged into a single circuit. This paper proposes, designs, and executes many upgrades to WINSmartEV. These upgrades include new hardware that makes the level 1 and level 2 chargers faster, more robust, and more scalable. It includes algorithms that provide a more optimal charge scheduling for the level 2 (EVSE) and an enhanced vehicle monitoring/identification module (VMM) system that can automatically identify PEVs and authorize charging.