In this paper, a reinforcement learning-based multibattery energy storage system(MBESS) scheduling policy is proposed to minimize the consumers ’ electricity cost. The MBESS scheduling problem is modeled as a Markov ...In this paper, a reinforcement learning-based multibattery energy storage system(MBESS) scheduling policy is proposed to minimize the consumers ’ electricity cost. The MBESS scheduling problem is modeled as a Markov decision process(MDP) with unknown transition probability. However, the optimal value function is time-dependent and difficult to obtain because of the periodicity of the electricity price and residential load. Therefore, a series of time-independent action-value functions are proposed to describe every period of a day. To approximate every action-value function, a corresponding critic network is established, which is cascaded with other critic networks according to the time sequence. Then, the continuous management strategy is obtained from the related action network. Moreover, a two-stage learning protocol including offline and online learning stages is provided for detailed implementation in real-time battery management. Numerical experimental examples are given to demonstrate the effectiveness of the developed algorithm.展开更多
An optimal sizing method is proposed in this paper for mobile battery energy storage system(MBESS)in the distribution system with renewables.The optimization is formulated as a bi-objective problem,considering the rel...An optimal sizing method is proposed in this paper for mobile battery energy storage system(MBESS)in the distribution system with renewables.The optimization is formulated as a bi-objective problem,considering the reliability improvement and energy transaction saving,simultaneously.To evaluate the reliability of distribution system with MBESS and intermittent generation sources,a new framework is proposed,which is based on zone partition and identification of circuit minimal tie sets.Both analytic and simulation methods for reliability assessment are presented and compared in the framework.Case studies on a modified IEEE benchmark system have verified the performance of the proposed approach.展开更多
基金supported by the National Key R&D Program of China (2018AAA0101400)the National Natural Science Foundation of China (61921004,62173251,U1713209,62236002)+1 种基金the Fundamental Research Funds for the Central UniversitiesGuangdong Provincial Key Laboratory of Intelligent Decision and Cooperative Control。
文摘In this paper, a reinforcement learning-based multibattery energy storage system(MBESS) scheduling policy is proposed to minimize the consumers ’ electricity cost. The MBESS scheduling problem is modeled as a Markov decision process(MDP) with unknown transition probability. However, the optimal value function is time-dependent and difficult to obtain because of the periodicity of the electricity price and residential load. Therefore, a series of time-independent action-value functions are proposed to describe every period of a day. To approximate every action-value function, a corresponding critic network is established, which is cascaded with other critic networks according to the time sequence. Then, the continuous management strategy is obtained from the related action network. Moreover, a two-stage learning protocol including offline and online learning stages is provided for detailed implementation in real-time battery management. Numerical experimental examples are given to demonstrate the effectiveness of the developed algorithm.
基金This work was supported by the National Natural Science Foundation of China(Young Scholar Program 71401017,General Program 51277016)State Key Laboratory of Alternate Electrical Power System with Renewable Energy Sources(Grant No.LAPS14002)+1 种基金Fujian regional science and technology major projects,China(2013H41010151)Hong Kong RGC Theme Based Research Scheme Grant No.T23-407/13-N.
文摘An optimal sizing method is proposed in this paper for mobile battery energy storage system(MBESS)in the distribution system with renewables.The optimization is formulated as a bi-objective problem,considering the reliability improvement and energy transaction saving,simultaneously.To evaluate the reliability of distribution system with MBESS and intermittent generation sources,a new framework is proposed,which is based on zone partition and identification of circuit minimal tie sets.Both analytic and simulation methods for reliability assessment are presented and compared in the framework.Case studies on a modified IEEE benchmark system have verified the performance of the proposed approach.
