Optimal generation scheduling in power system using frequency prediction through ANN under ABT environment

作     者：Simarjit KAUR Yajvender Pal VERMA Sunil AGRAWAL 

作者机构：Department of Electrical & Electronics Engineering UIET Panjab University Chandigarh 160014 India 

出 版 物：《Frontiers in Energy》 (能源前沿（英文版）)

年 卷 期：2013年第7卷第4期

页      面：468-478页

核心收录：

学科分类：12[管理学] 090403[农学-农药学(可授农学、理学学位）] 1201[管理学-管理科学与工程(可授管理学、工学学位)] 081104[工学-模式识别与智能系统] 08[工学] 09[农学] 0904[农学-植物保护] 0835[工学-软件工程] 0811[工学-控制科学与工程] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

主　　题：artificial neural network (ANN) frequency prediction availability-based tariff (ABT) generation scheduling (GS) 

摘      要：In a competitive and deregulated power scenario, the utilities try to maintain their real electric power generation in balance with the load demand, which creates a need for the precise real time generation scheduling （GS）. In this paper, the GS problem is solved to perform the unit commitment （UC） based on frequency prediction by using artificial neural network （ANN） with the objective to minimize the overall system cost of the state utility. The introduction of availability-based tariff （ABT） signifies the importance of frequency in GS. Under- prediction or over-prediction will result in an unnecessary commitment of generating units or buying power from central generating units at a higher cost. Therefore, an accurate frequency prediction is the first step toward optimal GS. The dependency of frequency on various parameters such as actual generation, load demand, wind power and power deficit has been considered in this paper. The proposed technique provides a reliable solution for the input parameter different from the one presented in the training data. The performance of the frequency predictor model has been evaluated based on the absolute percentage error （APE） and the mean absolute percentage error （MAPE）. The proposed predicted frequency sensitive GS model is applied to the system of Indian state of Tamilnadu, which reduces the overall system cost of the state utility by keeping off the dearer units selected based on the predicted frequency.