GMDH-Based Semi-Supervised Feature Selection for Electricity Load Classification Forecasting

Abstract

With the development of smart power grids, communication network technology and sensor technology, there has been an exponential growth in complex electricity load data. Irregular electricity load fluctuations caused by the weather and holiday factors disrupt the daily operation of the power companies. To deal with these challenges, this paper investigates a day-ahead electricity peak load interval forecasting problem. It transforms the conventional continuous forecasting problem into a novel interval forecasting problem, and then further converts the interval forecasting problem into the classification forecasting problem. In addition, an indicator system influencing the electricity load is established from three dimensions, namely the load series, calendar data, and weather data. A semi-supervised feature selection algorithm is proposed to address an electricity load classification forecasting issue based on the group method of data handling (GMDH) technology. The proposed algorithm consists of three main stages: (1) training the basic classifier; (2) selectively marking the most suitable samples from the unclassified label data, and adding them to an initial training set; and (3) training the classification models on the final training set and classifying the test samples. An empirical analysis of electricity load dataset from four Chinese cities is conducted. Results show that the proposed model can address the electricity load classification forecasting problem more efficiently and effectively than the FW-Semi FS (forward semi-supervised feature selection) and GMDH-U (GMDH-based semi-supervised feature selection for customer classification) models.

Short-Term Load Forecasting Based on Elastic Net Improved GMDH and Difference Degree Weighting Optimization

“…The group method of data handling (GMDH), also known as the polynomial neural network, is a self-organizing and inductive evolutionary algorithm. It fits complex nonlinear laws through the selection and weight adjustment of multilayer neurons [27][28][29][30][31]. Therefore, the input variables of the GMDH algorithm can be as comprehensive and extensive as possible, which is suitable for dealing with multidimensional and complex variables.…”

The effect of driver variables on the estimation of bivariate probability density of peak loads in long-term horizon

“…Wind power ramp forecasting [21] Group method of data handling (GMDH) Day-ahead electricity peak load interval forecasting short-term forecasting purposes (i.e., 5-min). This model is based on extreme learning machine and quantile regression.…”

Towards Modified Entropy Mutual Information Feature Selection to Forecast Medium-Term Load Using a Deep Learning Model in Smart Homes

“…Today, MTLF is a method used in the smart grid for electricity price and load forecasting, although it has not gained full explorations. Contrarily, STLF is widely studied in [ 8 , 9 , 10 , 11 , 12 , 13 , 14 , 15 , 16 , 24 ], which imperatively introduce competitiveness in the electricity markets. Several methods of load forecasting begin from the conventional time series analysis to computational intelligence such as machine learning.…”

“…Note that FS is a method used in selecting the important feature variables that are necessary and efficient to train a forecasting model. Other applications of FS methods in STLF and VSTLF are given in [ 8 , 9 , 10 , 11 , 12 , 13 , 14 , 15 , 16 , 17 , 18 ]. Efficient FS methods enhance forecasting accuracy and make the forecasting model faster to train with less complexity.…”