Architecture and Key Technologies of Hybrid-Intelligence-Based Decision-Making of Operation Modes for New Type Power Systems

With the construction of new type power systems, the number of operating scenarios and computational workload that need to be considered in analyzing operation modes increases greatly, the safety and stability mechanism becomes more complex, the uncertainty of the safe operation boundary increases,...

Full description

Saved in:
Bibliographic Details
Main Authors: Qinglai GUO, Jian LAN, Yanzhen ZHOU, Zhengcheng WANG, Hongtai ZENG, Hongbin SUN
Format: Article
Language:zho
Published: State Grid Energy Research Institute 2023-09-01
Series:Zhongguo dianli
Subjects:
Online Access:https://www.electricpower.com.cn/CN/10.11930/j.issn.1004-9649.202308102
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:With the construction of new type power systems, the number of operating scenarios and computational workload that need to be considered in analyzing operation modes increases greatly, the safety and stability mechanism becomes more complex, the uncertainty of the safe operation boundary increases, and the difficulty of adjusting operating mode increases significantly. The traditional decision-making method based on human experience is facing major challenges. Artificial intelligence provides new solutions but still faces challenges such as insufficient samples, poor interpretability, low exploration efficiency, etc. Focusing on the specific problems of the operation mode decision-making of the new type power systems, this paper proposes a research framework for operation mode decision-making of the new type power systems based on hybrid intelligence. The analysis and discussion are carried out from four aspects: sample generation of operation mode, analysis of the safety boundary and stability influencing factors, intelligent adjusting of operation mode, model interpretability and update, which provide a feasible technology path for applying hybrid intelligence to new type power systems.
ISSN:1004-9649