发电技术 ›› 2018, Vol. 39 ›› Issue (3): 204-212.DOI: 10.12096/j.2096-4528.pgt.2018.031

• 能源互联网 • 上一篇    下一篇

人工智能在电力系统中应用的近期研究热点介绍

朱永利1(),石鑫2,*(),王刘旺3   

  1. 1 新能源电力系统国家重点实验室(华北电力大学), 河北省 保定市 071003
    2 上海交通大学大数据工程技术研究中心, 上海市 闵行区 200240
    3 国网浙江省电力有限公司电力科学研究院, 浙江省 杭州市 310014
  • 收稿日期:2018-03-12 出版日期:2018-06-30 发布日期:2018-07-27
  • 通讯作者: 石鑫
  • 作者简介:朱永利(1963),男,教授,博士生导师,研究方向为网络化监控与智能信息处理、电力设备监测大数据处理, yonglipw@163.com|王刘旺(1988),男,博士,从事云计算、大数据及人工智能技术在电力系统的应用
  • 基金资助:
    国家自然科学基金项目(51677072)

Recent Research Hotspot Introduction on the Application of Artificial Intelligence in Power System

Yongli ZHU1(),Xin SHI2,*(),Liuwang WANG3   

  1. 1 State Key Laboratory of Alternate Electrical Power Systems with Renewable Energy Sources(North China Electric Power University), Baoding 071003, Hebei Provicne, China
    2 Research Center for Big Data Engineering Technology, Shanghai Jiao Tong University, Minhang District, Shanghai 200240, China
    3 State Grid Zhejiang Electric Power Company Electric Power Research Institute, Hangzhou 310014, Zhejiang Province, China
  • Received:2018-03-12 Published:2018-06-30 Online:2018-07-27
  • Contact: Xin SHI
  • Supported by:
    National Natural Science Foundation of China(51677072)

摘要:

大数据驱动下的新一代人工智能由传统知识表示转向深度、自主知识学习,不再需要人的过多干预,展现出了更加智能的一面。近年来,深度学习成为人工智能研究热点。该文重点介绍了深度学习的特点、原理及其在电力系统中的应用研究现状,分析了新一代智能方法研究趋势及在应用过程中存在的问题,并提供了基于分布式机器学习和增量学习的解决方法,旨在为相关研究工作者提供参考。

关键词: 电力系统, 人工智能, 深度学习, 大数据

Abstract:

The new generation of artificial intelligence driven by big data has shifted from traditional knowledge representation to deep and autonomous learning. It no longer requires too much human intervention and shows a smarter side. In recent years, deep learning (DL) has become the hotspot of artificial intelligence. This paper focuses on the characteristics, principles and the current application status of DL in the power system. It also analyzes the research trends and problems in the application process of the new generation artificial intelligence, and provides solutions based on distributed machine learning and incremental learning methods. This paper is written for providing references for researchers involved in the field.

Key words: power system, artificial intelligence, deep learning, big data