Short-Term Electricity-Load Forecasting Using a TSK-Based Extreme Learning Machine with Knowledge Representation

Abstract

This paper discusses short-term electricity-load forecasting using an extreme learning machine (ELM) with automatic knowledge representation from a given input-output data set. For this purpose, we use a Takagi-Sugeno-Kang (TSK)-based ELM to develop a systematic approach to generating if-then rules, while the conventional ELM operates without knowledge information. The TSK-ELM design includes a two-phase development. First, we generate an initial random-partition matrix and estimate cluster centers for random clustering. The obtained cluster centers are used to determine the premise parameters of fuzzy if-then rules. Next, the linear weights of the TSK fuzzy type are estimated using the least squares estimate (LSE) method. These linear weights are used as the consequent parameters in the TSK-ELM design. The experiments were performed on short-term electricity-load data for forecasting. The electricity-load data were used to forecast hourly day-ahead loads given temperature forecasts; holiday information; and historical loads from the New England ISO. In order to quantify the performance of the forecaster, we use metrics and statistical characteristics such as root mean squared error (RMSE) as well as mean absolute error (MAE), mean absolute percent error (MAPE), and R-squared, respectively. The experimental results revealed that the proposed method showed good performance when compared with a conventional ELM with four activation functions such sigmoid, sine, radial basis function, and rectified linear unit (ReLU). It possessed superior prediction performance and knowledge information and a small number of rules.

A Hybrid BA-ELM Model Based on Factor Analysis and Similar-Day Approach for Short-Term Load Forecasting

“…(2) The temperature. As people use temperature-adjusting devices to adapt to the temperature, in a previous study [23][24][25], temperature was considered as an essential input feature and the forecasting results were accurate enough. In this paper, the maximum temperature, the minimum temperature and the average temperature are selected as factors.…”

“…In addition, there are still many other external weather factors that may also potentially influence the power load. Only Energies 2018, 11, 1282 3 of 18 considering the temperature as the input variable may be not enough [23][24][25], and other meteorological factors such as humidity, visibility and air pressure etc. also should be taken into consideration.…”

Short-Term Load Forecasting with Improved CEEMDAN and GWO-Based Multiple Kernel ELM

“…erefore, they have become more and more popular in energy forecasting. Typical AI models include support-vector regression (SVR) and its extension least-squares SVR (LSSVR) [5,6], artificial neural network (ANN) [7][8][9], extreme learning machine (ELM) [10], sparse Bayesian learning (SBL) [11,12], deep learning [13] (stacked denoising autoencoders (SDAs) [14], deep belief network (DBN) [15], convolutional neural network (CNN) [16], and long short-term memory (LSTM)) [17]), and nature-inspired optimization algorithms [18,19]. For example, Chen et al put forward a new SVR model that used the temperature before demand response as additional input variables for STLF [6].…”

“…Kulkarni et al proposed a spiking neural network to forecast short-term load with consideration of weather variables [8]. Yoem and Kwak used an ELM with knowledge representation for STLF, and the experimental results indicated good performance of the approach [10]. Han et al presented time-dependency CNN and cycle-based LSTM for STLF by mapping the load data as pixels and rearranging them into a 2-D image, and the extensive experiments demonstrated that the proposed models were superior to the compared models in terms of computation complexity [13].…”

Static and Dynamic Networking of Smart Meters Based on the Characteristics of the Electricity Usage Information

“…Referring to [24], the connection weight γ between the hidden layer and the output layer can be obtained by solving the least square solution of the equations listed as follows:…”