Short-Term Forecasting of Electric Loads Using Nonlinear Autoregressive Artificial Neural Networks with Exogenous Vector Inputs

Jaime Buitrago,Shihab Asfour

doi:10.3390/en10010040

Jaime Buitrago, Shihab Asfour

Open Access

https://doi.org/10.3390/en10010040

Copy DOI

Journal: Energies	Publication Date: Jan 1, 2017
Citations: 84	License type: CC BY 4.0

Affiliation: University of Miami

Abstract

Short-term load forecasting is crucial for the operations planning of an electrical grid. Forecasting the next 24 h of electrical load in a grid allows operators to plan and optimize their resources. The purpose of this study is to develop a more accurate short-term load forecasting method utilizing non-linear autoregressive artificial neural networks (ANN) with exogenous multi-variable input (NARX). The proposed implementation of the network is new: the neural network is trained in open-loop using actual load and weather data, and then, the network is placed in closed-loop to generate a forecast using the predicted load as the feedback input. Unlike the existing short-term load forecasting methods using ANNs, the proposed method uses its own output as the input in order to improve the accuracy, thus effectively implementing a feedback loop for the load, making it less dependent on external data. Using the proposed framework, mean absolute percent errors in the forecast in the order of 1% have been achieved, which is a 30% improvement on the average error using feedforward ANNs, ARMAX and state space methods, which can result in large savings by avoiding commissioning of unnecessary power plants. The New England electrical load data are used to train and validate the forecast prediction.

Highlights

Short-term electrical load forecasting is vital for the efficient operation of electric power systems.A power grid integrates many stake holders who can be affected by an inaccurate load forecast: power generation utilizes 24-hour or 48-hour ahead forecasts for operations planning, i.e., to determine which power sources should be allocated for the 24 h; transmission grids need to know in advance the power transmission requirements in order to assign resources; end users utilize the forecast to calculate energy prices based on estimated demand
The NARX forecast was generated in closed-loop, i.e., the network was trained in open-loop by using known values of the load; the first hourly load forecast value is calculated with the trained network, and it is fed back to the input in order to obtain the second value, and so on
The approach shows that an artificial neural networks (ANN) can be trained in open-loop by using all of the available endogenous and exogenous inputs

Summary

Introduction

Short-term electrical load forecasting is vital for the efficient operation of electric power systems.A power grid integrates many stake holders who can be affected by an inaccurate load forecast: power generation utilizes 24-hour or 48-hour ahead forecasts for operations planning, i.e., to determine which power sources should be allocated for the 24 h; transmission grids need to know in advance the power transmission requirements in order to assign resources; end users utilize the forecast to calculate energy prices based on estimated demand. Short-term electrical load forecasting is vital for the efficient operation of electric power systems. Contingency planning, load shedding, management strategies and commercialization strategies are all influenced by load forecasts. Forecast errors result in increased operating costs [1]: predicting a lower load than the actual load results in utilities not committing the necessary generation units and incurring higher costs due to the use of peak power plants; on the other hand, predicting a higher load than actual will result in higher costs because unnecessary baseline units are started and not used. Reliable forecasting methods are essential for scheduling sources and load management [2].

Objectives

Methods

Results

Discussion

Conclusion