Electricity Load Forecasting Using Artificial Neural Network in Matlab

Introduction

The electricity power consumption is a non-linear process. Artificial Neural Networks have the capability to predict future data based on the data fed for training as it can recognize the pattern in it. This will in turn enable us to maintain a good power management and in the needy times we can use renewable resources of energy like wind energy or solar energy.

Methodology

This example demonstrates building and validating a short term forecasting of electricity loadmodel with MATLAB. The models take into account multiple sources of information including temperatures and holidays in constructing a day-ahead load forecaster. This script uses Neural Networks. Bayesian regularization algorithm is used in this forecasting section

Abstract:

Electrical load forecasting is one of the important parts for smart grid system. The reliable prediction of the load demand contributes to the efficient and economical operations and planning. The artificial neural network is used extensively in load demand forecasting. The nonlinear nature of the electrical load demand conforms to the ability of the artificial neural network in calculating the nonlinear relationship of inputs and outputs. Among many models of neural networks, radial basis neural networks yield superior performance in small error and fast simulation time. However, it is challenge to design the radial basis neural networks. The excessive numbers of hidden neurons lead to lacking of generalization or so called overfitting problems. This paper proposes an approach to design the radial basis neural networks that use as least numbers of hidden neurons as possible. The error criterion is optimized based on modified genetic algorithm as the numbers of hidden neurons are incrementally increased. Simulation results of short term load forecasting are calculated in Matlab, and compared to the orthogonal least square error method. The proposed approach gives better results with the same numbers of hidden neurons.

ELECTRICITY LOAD FORECASTING -AN MARKET CASE STUDY - MATLAB

Electricity Load Forecasting -An Market Case Study ,This is a case study of how MATLAB can be used to forecast short-term electricity loads for the Australian market using Sydney temperature and NSW historical load data sets. Nonlinear regression and neural network modeling techniques are used to demonstrate accurate modeling using historical, seasonal, day-of-the week, and temperature data.

Highlights include:

• Forecasting short-term electricity loads and prices
• Accessing data from regional wholesale electricity markets
• “White-box” modeling using customisable algorithms and viewable-source functions
• Automatic Report Publishing

This case study is for practitioners at power generators, utilities or energy trading groups whose focus is transmission planning, distribution operations, derivative valuation, or quantitative analysis. Familiarity with MATLAB is not required.

Related Projects

Payment