Design of High Speed Adaptive Load Shedding for Industrial Cogeneration System

摘要

This paper presents transient stability analysis and enhancement of Industrial Cogeneration Plant (ICP) interconnected with Public Power Company (PPC) for quality and reliability of power supply. If difference between In-plant generation and demand in islanded system is large, the speed and accuracy of load shedding is extremely important to achieve stable operation. This paper presents prompt load shedding technique for ICP in which load-generation difference is huge. In this paper load shedding scheme is configured in to three stages, User defined Knowledge base (UDKB) generation, Artificial Neural Network configuration, and online implementation. The purpose of the proposed scheme is to accomplish high speed and adaptive load shedding by real-time measurement and UDKB. By selecting the total power import, total in-plant generation, spinning reserve, total demand and frequency decay rate as the input neurons of the ANN, the minimum amount of load shedding is determined to maintain the stability of islanded systems. Transient stability analysis has been performed with the help of ETAP software, to prepare the training data set for ANN, by considering all possible contingency and combination of generation and load scenarios which affect system stability. Artificial Neural Network (ANN) has been implemented on MATLAB.