Kỹ thuật dự báo phụ tải cho công ty điện lực Vĩnh Long dựa vào mạng LSTM

Abstract

This paper proposes to make forecasting models to estimate the electrical load based
on the measurements of current electrical loads of the Vinh Long power company using
a Long Short-Term Memory network (LSTM). This is a method to predict future load
demands by analyzing historical data and finding dependency patterns of its time-step
observations. The LSTM network is a sort of temporal cyclic neural network that is
specifically designed to address the long-term reliance issue. Simulation results proved
that the proposed method revealed promising results using root mean square error
(RMSE). This would help to ascertain the fluctuation in electric load well in advance
and making an opportunity or scope for preparation to meet the sudden increase in load
demand thereby meeting the expectations of an active load forecasting with numerous
applications in power system arena.
Keywords: forecasting models, electrical load, LSTM network, Vinh Long power