.png){kind=icon}
Return
Space tree-based graph continuous cellular automaton for unit commitment and economic dispatch optimization
.png){kind=icon}
PRE
AI
DOI：10.1016/j.ins.2026.123199.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Unit Commitment (UC) and Economic Dispatch (ED) are core issues in the power system. In this paper we try to solve both problems jointly: UC-ED problem is a large-scale mixed-integer linear programming (MILP) problem. Algorithms based on mathematical optimization cannot solve large-scale problems, models based on heuristic algorithms tend to fall into local optima, and methods based on deep learning generally cannot directly handle constraint violations. To address UC-ED problem, a new framework: Space tree-based graph continuous cellular automaton (ST-GCCA) has been proposed. It extracts fused features through an autoencoder and decision tree, then uses deep boosted regression trees to generate initial solution of UC-ED problem, and finally employs graph continuous cellular automaton (GCCA) to optimize the solution, achieving economic and secure power system dispatch. Compared with traditional algorithms, it achieves 1400x harmonic mean speedup improvement, making it possible to solve large-scale problems; compared to the most up-to-date AI approaches, it can explicitly handle safety constraints. While achieving speed improvements, it reached economic optimality and, more importantly, achieved zero constraint violations. The experimental results on the IEEE 30-bus and IEEE 118-bus test systems demonstrate our achievements, indicating that ST-GCCA can find the optimal solution to the UC-ED problem.
Keywords:
Space tree
Graph
Continuous cellular automaton
Unit commitment
Economic dispatch
Journal
IF:
6.8
Papers:
553
Citations:
6.2W
Organization
Cited Papers
ShareSaveShareSaveForgetting velocity based improved comprehensive learning particle swarm optimization for non-convex economic dispatch problems with valve-point effects and multi-fuel options.png)
ENERGY
ENERGYIF9.4
PREAI
ShareSaveShareSave
ShareSaveShareSaveShareSave
View more