Open AccessApplication of BP Dual Network Model Considering Internal and External Factors in Short-Term Load Forecasting
Author(s) -
Xiaoliang Yang,
Hongyuan Ren,
Hongbao Zhao
Publication year - 2020
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 - 10.1088/1742-6596/1631/1/012137
Subject(s) - computer science , dual (grammatical number) , artificial neural network , term (time) , volatility (finance) , power grid , electricity , smart grid , scheduling (production processes) , electrical load , grid , artificial intelligence , mathematical optimization , power (physics) , econometrics , engineering , economics , mathematics , art , physics , geometry , literature , quantum mechanics , electrical engineering
In the reform of electricity sales, the accuracy of short-term load forecasting is very important for power grid operation scheduling, user demand response and pricing mechanism. Based on the theory of internal and external factors, the paper accurately extracted temperature, humidity, entropy of peak load and load volatility as the main influencing factors. Based on the artificial intelligence learning method, it introduced experts’ experience to build a dual neural network short-term load prediction model, simulated load characteristics from multiple angles, and accurately predicted the trend. The simulation results show that the improved short-term load prediction model is more suitable to deal with dynamic problems due to its fast convergence speed and high prediction accuracy.