摘要
新一代人工智能技术因其具有高维状态智能感知和快速决策的能力,在推动未来电网数字化、信息化以及智能化方面将发挥重要作用,然而其固有的可解释性差、脆弱性等缺点也限制了人工智能技术在电力系统的进一步应用。首先,介绍了混合增强智能技术以及其在自动驾驶、工业机器人等领域的应用发展。结合电力系统特征和人工智能技术特点分析和总结了电力系统对混合增强智能的需求。其次,围绕数据处理、模型训练和模型应用等方面分析了人机协同混合增强智能应用中涉及的关键技术。在此基础上,设计和分析了混合增强智能技术在电力系统暂态稳定评估、电网断面潮流调控等典型场景的应用,可为后续工程应用提供参考借鉴。最后,对混合增强智能在电力系统中应用所面临的挑战进行了分析和展望,旨在推动和丰富混合智能技术在电力系统的应用方面的基础理论与关键技术的发展。
The new generation of artificial intelligence(AI)technology will play an important role in promoting the digitalization,informatization and intelligence of the future power grids due to its high-dimensional state intelligent perception and rapid decision-making capabilities.However,its inherent shortcomings such as the poor interpretability and fragility also limit the further applications of the AI technology in power systems.This paper firstly introduces the hybrid-augmented intelligence(HAI)technology and its application development in the fields of vehicle autonomous driving and industrial robots.Combining the characteristics of the power system and the AI technology,the requirements of the power systems for the HAI are analyzed and summarized.Secondly,the key technologies involved in the human-machine collaborative HAI are analyzed in terms of the data processing,the model training and the model application.On this basis,the application of the HAI technology in the typical scenarios,such as the power system transient stability assessment and the grid section power flow regulation,is designed and analyzed,which provides a reference for the subsequent engineering applications.Finally,the challenges faced by the application of the HAI in power systems are analyzed and prospected,aiming to promote and enrich the development of the basic theories and the key technologies of the hybrid intelligence in power systems.
作者
范士雄
郭剑波
马士聪
赵泽宁
王铁柱
FAN Shixiong;GUO Jianbo;MA Shicong;ZHAO Zening;WANG Tiezhu(China Electric Power Research Institute,Haidian District,Beijing 100192,China)
出处
《电网技术》
EI
CSCD
北大核心
2023年第10期4081-4091,共11页
Power System Technology
基金
中国电科院青年科学家项目(52420023000Z)。
关键词
人工智能
混合增强智能
人在回路
电力系统
机器学习
人机协同
artificial intelligence
hybrid-augmented intelligence
human-in-the-loop
power system
machine learning
human-machine collaboration
