电力系统动态等值的人工智能方法的分析-电力系统及其自动化专业论文.docxVIP

第 第 PAGE IV 页 RESEARCH ON ARTIFICIAL INTELLIGENCE IN POWER SYSTEM DYNAMIC EQUIVALENCE ABSTRACT Dynamic equivalence is a an excellent way of simplifying electrical systems, reducing the number of equations to solve while retaining the most important characteristics of the full system, which has been drawing increasing attention throughtout the world with the steady expansion of the system, important for real-time online dynamic analysis. The main works in this dissertation are as following： Study on basic theory of power system dynamic equivalence, including modeling of elementary electrical components and the algorithms to achieve it. A Novel Load Modeling Approach has been proposed, which is based on asymmetric data recording and solutions to Park equations. Its applicable to not only the normal networks, but also the systems with tie lines. A niche immune algorithm has been proposed and applied to a practical infinite-bus system, which has several advantages, such as high degree of accuracy, high speed, satisfied astringency and good robustness. In the end, the proposed algorithm and the presented method apply to Tianjin network to test their feasibility, and the static characteristic and dynamic characteristic of the obtained models are checked as well. Simulation results show that the methods proposed in this dissertation is feasible and applicable, qualified to be used in actual engineering projects. KEY WORDS: Power system, Dynamic equivalance, Evaluation method, Artificial intelligence, Immune algorithm 第 第 PAGE VI 页 目 录 摘 要 II ABSTRACTIII 目 录 V 第一章 绪论1 1.1 研究意义1 1.2 同调等值法1 1.2.1 基本原理1 1.2.2 优缺点5 1.3 模式等值法5 1.3.1 基本原理5 1.3.2 优缺点6 1.4 估计等值法6 1.4.1 基本原理6 1.4.2 优缺点7 1.5 本文的主要工作8 第二章 系统元件模型和辨识理论9 2.1 引言9 2.2 模型概述9 2.2.1 物理机理建模9 2.2.2 辨识建模10 2.3 辨识的基本原理 11 2.4 电力系统的元件模型 11 2.4.1 同步发电机模型 11 2.4.2 励磁系统模型15 2.4.3 负荷模型17 2.5 小结22 第三章 小生境免疫算法23 3.1 引言23 3.2 人工智能方法的研究23 3.2.1 人工智能方法的发展23 3.2.2 几种人工智能方法简介24 3.2.4 人工智能方法与其它方法比较 26 3.3 人工免疫