Localization for Energy Interconnection Systems With Uncertainties via Maximum Entropy Adaptive Dynamic Programming

This article addresses the critical challenge of high localization error in long-distance energy interconnection systems (EISs), where conventional methods face significant limitations due to the increased uncertainties of time-dependent information. A novel localization framework is proposed based on the maximum entropy adaptive dynamic programming (MEADP) algorithm to tackle this challenge. This framework transforms the long-distance localization problem into a consistency issue concerning the attenuation of negative pressure waves (NPWs), thereby reducing reliance on time-based information. To address measurement noise, a hybrid data fusion algorithm driven by both model and data is developed to reduce the variance of predicted NPWs using a Kalman filter. At the core of the framework lies the MEADP algorithm, which incorporates entropy regularization in the policy improvement to encourage exploration and prevent convergence to suboptimal solutions. Moreover, the algorithm employs a policy network based on the $\beta $ -distribution, enabling dynamic adjustment of action probabilities to adhere to physical constraints and maintain feasible operational limits. Finally, the proposed framework is validated through experiments with pipelines exceeding 350 km in length.