Open AccessChaos-GA-BP Neural Network Power Load Forecasting Based on Rough Set Theory
Author(s) -
Dianwen Li,
Xiu Ji,
Xin Tian
Publication year - 2021
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/2010/1/012132
Subject(s) - rough set , artificial neural network , power (physics) , electric power system , grasp , set (abstract data type) , compensation (psychology) , computer science , control theory (sociology) , chaos theory , data mining , artificial intelligence , chaotic , psychology , physics , control (management) , quantum mechanics , psychoanalysis , programming language
In order to accurately grasp the trend of power load changes and provide guidance for stable and efficient operation of the power system, this paper proposes a Chaos-GA-BP power load forecasting model based on rough sets. First, screen the main factors that affect power load changes, remove redundant data, and optimize the input of the prediction model; Second, rely on the BP neural network prediction model to adjust its topology, optimize weights and thresholds, and build a rough set-based Chaos-GA-BP power load forecasting model; Finally, considering the impact of severe power load fluctuations on the forecast results, rough set theory is introduced to perform forecast compensation when the slope on both sides of the peak is large. Applying the above method to a one-month power load forecast in a certain area in Northeast China, the change trend of the forecast curve closely follows the actual load curve. Compared with the traditional method, the average absolute error percentage is reduced by 2.67%. The experiment shows that this method has certain practicability.