.png){kind=icon}
.png){kind=icon}
Return
Multiclass Learning-Aided Temporal Decomposition and Distributed Optimization for Power Systems
.png){kind=icon}
OA
AI
DOI：10.1109/TPWRS.2021.3078380.png)
.png){kind=icon}
.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Temporal decomposition is a potential approach to relieve the computation cost of power system multi-interval scheduling problems, such as economic dispatch. In this form of decomposition, the considered scheduling horizon is partitioned into several subhorizons. A subproblem is formulated for each subhorizon, and a distributed optimization algorithm strategy is used to coordinate subproblems. The main existing challenge is decomposing the scheduling horizon to gain the most time saving from distributed computing. This paper serves as an extension to our previous work and presents a machine learning-aided temporal decomposition strategy to partition a scheduling horizon optimally. We have found that the load profile, known before solving economic dispatch, significantly affects the best number of subhorizons. We have used load profiles as inputs to a learner whose goal is to assign a temporal decomposition class to each load profile. Possible decomposition classes are divisors of the considered scheduling horizon. Thus, the proposed learning procedure is a multiclass classification. We have selected Extreme Gradient Boosting that is a tree-based classification learner. Simulation results using real-world load profiles show the promising performance of the proposed algorithm.
Keywords:
Optimization
Processor scheduling
Power systems
Economics
Classification algorithms
Scheduling
Program processors
Economic dispatch
distributed optimization
temporal decomposition
multiclass classification learner
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
IF:
7.2
Papers:
1.1W
Citations:
5.0W