SCKF-LSTM-Based Trajectory Tracking for Electricity–Gas Integrated Energy System

A novel approach of tracking the dynamic trajectories for electricity–gas interconnected networks is developed in the studies, leveraging a Kalman filter-based structure. To capture the accurate system trajectories, the Holt's exponential smoothing techniques and nonlinear dynamic equations of gas pipelines are applied to establish the power and gas system equations, respectively. Addressing the numerical challenges posed by the strongly nonlinear system, a square-root cubature Kalman technique-based tracking solution is adopted. For the effectiveness in time series prediction, the mass flow rates forecasting task of gas loads is undertaken by employing a long short-term memory network at each computation step. Consequently, a combined method for tracking the dynamic trajectories of comprehensive energy systems by combining these two algorithms is constructed. The IEEE 39-bus network as well as the GasLib-40 node gas network is integrated by gas turbine units to form the multienergy network, and two indexes are introduced for a numerical analysis of the tracking performances. The outcomes demonstrate that the suggested approach significantly improves tracking accuracy when contrasted with the reference measurements.