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...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:IEEE transactions on industrial informatics Jg. 21; H. 6; S. 4296 - 4305
Hauptverfasser: Chen, Liang, Li, Yang, Cai, Jun, Gu, Songlin, Yan, Ying
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Piscataway IEEE 01.06.2025
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Schlagworte:
Algorithms
Current measurement
Dynamical systems
Electricity
Gas pipelines
Gas turbines
Integrated energy system (IES)
Integrated energy systems
Kalman filters
Long short term memory
long short-term memory (LSTM)
Mass flow rate
Mathematical models
Nonlinear dynamics
Nonlinear systems
Numerical analysis
Pipelines
Power system dynamics
Predictive models
Smoothing methods
square-root cubature Kalman filter (SCKF)
Tracking
Trajectory tracking
Vectors
ISSN:1551-3203, 1941-0050
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung: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.
Bibliographie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:1551-3203
1941-0050
DOI:10.1109/TII.2024.3523544