Short Term Electric Load Forecasting Based on Data Transformation and Statistical Machine Learning

Abstract

The continuous penetration of renewable energy resources (RES) into the energy mix and the transition of the traditional electric grid towards a more intelligent, flexible and interactive system, has brought electrical load forecasting to the foreground of smart grid planning and operation. Predicting the electric load is a challenging task due to its high volatility and uncertainty, either when it refers to the distribution system or to a single household. In this paper, a novel methodology is introduced which leverages the advantages of the state-of-the-art deep learning algorithms and specifically the Convolution Neural Nets (CNN). The main feature of the proposed methodology is the exploitation of the statistical properties of each time series dataset, so as to optimize the hyper-parameters of the neural network and in addition transform the given dataset into a form that allows maximum exploitation of the CNN algorithm’s advantages. The proposed algorithm is compared with the LSTM (Long Short Term Memory) technique which is the state of the art solution for electric load forecasting. The evaluation of the algorithms was conducted by employing three open-source, publicly available datasets. The experimental results show strong evidence of the effectiveness of the proposed methodology.

Hierarchical Multiobjective Distributed Deep Learning for Residential Short-Term Electric Load Forecasting

“…Some studies [26,27] use CNN, which has been used for image processing, to extract higher-level features from the input data. The authors of [27] transform load data into an image-like matrix to apply CNN.…”

“…Some studies [26,27] use CNN, which has been used for image processing, to extract higher-level features from the input data. The authors of [27] transform load data into an image-like matrix to apply CNN. The CNN-based model shows good forecasting performance; although RNN can learn longer dependencies in input time-series data, CNN can also express the relationship between consecutive time steps.…”

A Real-Time Electrical Load Forecasting in Jordan Using an Enhanced Evolutionary Feedforward Neural Network

“…The internal clustering is incorporated to enhance accuracy. STLF analysis based on the transformed data and the statistical machine learning algorithm considering the penetration of renewable energy resources is investigated in [ 30 ], a more resilient and robust grid through accurate electrical load forecasting and using the cutting edge of the machine learning techniques.…”

A Bidirectional Grid-Connected DC–AC Converter for Autonomous and Intelligent Electricity Storage in the Residential Sector

“…A wide range of techniques is already available in the literature and these techniques can be classified into two main categories [14][15][16][17][18]. Indeed, these approaches are based either on information processing methods or on optimization tactics:…”