To address the shortcomings of adaptability and convergence of traditional energy storage scheduling under source-load fluctuations

this paper proposes a multi-objective optimal scheduling strategy based on an improved TD3 algorithm. Based on the TD3 algorithm

a prioritized experience replay mechanism is introduced

a multi-objective reward function that takes into account economy

energy storage loss and power grid fluctuations is constructed

and a three-layer intelligent energy storage scheduling framework is established. Verification is carried out based on a microgrid simulation example

and the results show that the proposed algorithm significantly improves the convergence speed

can reduce system operation costs

cut the peak value of power grid interaction power

and meanwhile reduce the loss caused by frequent start-stop of energy storage.