• Energy Research

Deep reinforcement learning (DRL) is a promising candidate for realizing online complex system optimal control because of its high computation efficiency. However, the interpretability and reliability problems limit its engineering application in smart grid energy management. This paper for the first time designs a novel imitative learning framework to provide a reliable solution for computation-efficient grid-connected electric vehicles (GEVs) charging management in smart grids. The optimal strategies are derived by a priors optimization model based on vehicle-to-grid (V2G) cost-benefit analysis. With better interpretability and ensured optimality, the derived strategies are used to construct an experience pool for configuring the learning environment. Then, a novel imitative learning mechanism is designed to facilitate the knowledge transfer between expert experience and reinforcement learning model. Further, a novel dual actor-imitator learning network to enable flexible scheduling of V2G power of GEVs. With the dual network structure, the expert experience can be effectively utilized to enhance the training efficiency and performance of the DRL-based V2G coordinator. The effectiveness of the developed method in improving V2G benefit and mitigating battery aging is validated on a demonstrative microgrid in the UK.

Battery energy storage systems (BESS) have been extensively investigated to improve the efficiency, economy, and stability of modern power systems and electric vehicles (EVs). However, it is still challenging to widely deploy BESS in commercial and industrial applications due to the concerns of battery aging. This paper proposes an integrated battery life loss modeling and anti-aging energy management (IBLEM) method for improving the total economy of BESS in EVs. The quantification of BESS aging cost is realized by a multifactorial battery life loss quantification model established by capturing aging characteristics from cell acceleration aging tests.Meanwhile, a charging event analysis method is proposed to deploy the built life loss model in vehicle BESS management. Two BESS active anti-aging vehicle energy management models: vehicle to grid (V2G) scheduling and plug-in hybrid electric vehicle (PHEV) power distribution, are further designed, where the battery life loss quantification model is used to generate the aging cost feedback signals. The performance of the developed method is validated on a V2G peak-shaving simulation system and a hybrid electric vehicle. The work in this paper presents a practical solution to quantify and mitigate battery aging costs by optimizing energy management strategies and thus can further promote transportation electrification.

Abstract Recent developments in fuel cell (FC) and battery energy storage technologies bring a promising perspective for improving the economy and endurance of electric aircraft. However, aircraft power system configuration and power distribution strategies should be reasonably designed to enable this benefit. This paper is the first attempt to investigate the optimal energy storage system sizing and power distribution strategies for electric aircraft with hybrid FC and battery propulsion systems. First, a novel integrated energy management and parameter sizing (IEMPS) framework is established to co-design aircraft hardware and control algorithms. Under the IEMPS framework, a new real-time power distribution algorithm with a flexible ratio is established to facilitate integrated parameter optimization, which can adapt to different power system configurations. Based on the comprehensive analysis of hydrogen economy, FC aging cost, and aircraft stability, a multi-objective parameter optimization model is established to decide the size of aircraft energy storage systems and hyper-parameters in the power controller. The X-57 Maxwell, an experimental electric aircraft designed by NASA, is employed to verify the developed methods. This work provides a novel power system configuration, sizing, and power management method for future commercial aircraft design, and it can further promote the aviation electrification process.

With the popularization of electric vehicles, vehicle-to-grid (V2G) has become an indispensable technology to improve grid economy and reliability. However, battery aging should be mitigated while providing V2G services so as to protect customer benefits and mobilize their positivity. Conventional battery anti-aging V2G scheduling methods mainly offline operates and can hardly be deployed online in hardware equipment. This paper proposes a novel online battery anti-aging V2G scheduling method based on a novel two-stage parameter calibration framework. In the first stage, the V2G scheduling is modeled as an optimization problem, where the objective is to reduce grid peak-valley difference and mitigate battery aging. The online deployment of the developed optimization-based V2G scheduling is realized by a rule-based V2G coordinator in the second stage, and a novel parameter calibration method is developed to adjust controller hyper-parameters. With the parameter calibration process, the global optimality and real-time performance of V2G strategies can be simultaneously realized. The effectiveness of the proposed methodologies is verified on a practical UK distribution network. Simulation results indicate that it can effectively mitigate battery aging in providing V2G services while guaranteeing algorithm real-time performance.

The electrification of the aviation industry is a major challenge to realizing net-zero in the global energy sector. Fuel cell (FC) hybrid electric aircraft (FCHEV) demonstrate remarkable competitiveness in terms of cruise range and total economy. However, the process of simply hybridizing different power supplies together does not lead to an improvement in the aircraft economy, since a carefully designed power system topology and energy management scheme are also necessary to realize the full benefit of FCHEV. This paper provides a new approach towards the configuration of the optimal power system and proposes a novel energy management scheme for FCHEA. Firstly, four different topologies of aircraft power systems are designed to facilitate flexible power flow control and energy management. Then, an equivalent model of aircraft hydrogen consumption is formulated by analyzing the FC efficiency, FC aging, and BESS aging. Using the newly established model, the performance of aircraft can be quantitatively evaluated in detail to guide FCHEA design. The optimal aircraft energy management is realized by establishing a mathematical optimization model with the reduction of hydrogen consumption and aging costs as objectives. An experimental aircraft, NASA X-57 Maxwell, is used to provide a detailed performance evaluation of different power system topologies and validate the effectiveness of the energy management scheme. The new approach represents a guide for future power system design and energy management of electric aircraft.

The adoption of grid-connected electric vehicles (GEVs) brings a bright prospect for promoting renewable energy. An efficient vehicle-to-grid (V2G) scheduling scheme that can deal with renewable energy volatility and protect vehicle batteries from fast aging is indispensable to enable this benefit. This article develops a novel V2G scheduling method for consuming local renewable energy in microgrids by using a mixed learning framework. It is the first attempt to integrate battery protective targets in GEVs charging management in renewable energy systems. Battery safeguard strategies are derived via an offline soft-run scheduling process, where V2G management is modeled as a constrained optimization problem based on estimated microgrid and GEVs states. Meanwhile, an online V2G regulator is built to facilitate the real-time scheduling of GEVs' charging. The extreme learning machine (ELM) algorithm is used to train the established online regulator by learning rules from soft-run strategies. The online charging coordination of GEVs is realized by the ELM regulator based on real-time sampled microgrid frequency. The effectiveness of the developed models is verified on a U.K. microgrid with actual energy generation and consumption data. This article can effectively enable V2G to promote local renewable energy with battery aging mitigated, thus economically benefiting EV owns and microgrid operators, and facilitating decarbonization at low costs.

Grid-connected electric vehicles (GEVs) and energy-transportation nexus bring a bright prospect to improve the penetration of renewable energy and the economy of microgrids (MGs). However, it is challenging to determine optimal vehicle-to-grid (V2G) strategies due to the complex battery aging mechanism and volatile MG states. This article develops a novel online battery anti-aging energy management method for energy-transportation nexus by using a novel deep reinforcement learning (DRL) framework. Based on battery aging characteristic analysis and rain-flow cycle counting technology, the quantification of aging cost in V2G strategies is realized by modeling the impact of number of cycles, depth of discharge, and charge and discharge rate. The established life loss model is used to evaluate battery anti-aging effectiveness of agent actions. The coordination of GEVs charging is modeled as multiobjective learning by using a DRL algorithm. The training objective is to maximize renewable penetration while reducing MG power fluctuations and vehicle battery aging costs. The developed energy-transportation nexus energy management method is verified to be effective in optimal power balancing and battery anti-aging control on a MG in the U.K. This article provides an efficient and economical tool for MG power balancing by optimally coordinating GEVs charging and renewable energy, thus helping promote a low-cost decarbonization transition.