Rethinking weather station selection for electric load forecasting using genetic algorithms

Moreno-Carbonell, Santiago; Sánchez‐Úbeda, Eugenio F.; Muñoz, Antonio

doi:10.1016/j.ijforecast.2019.08.008

Cited by 19 publications

(8 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We have selected stations located at the country capitals, whenever the amount of available data and the existing missing data in the period of interest for our case study (January 1980 to December 2019) are reasonable. It should be noted that in order to better select the reference temperature for electric load forecasting, methods such as those described in Reference [31] or Reference [32] would provide better results in terms of error. However, Appendix A.…”

Section: Abbreviationsmentioning

confidence: 99%

Time Series Decomposition of the Daily Outdoor Air Temperature in Europe for Long-Term Energy Forecasting in the Context of Climate Change

2020

Self Cite

View full text Add to dashboard Cite

Temperature is widely known as one of the most important drivers to forecast electricity and gas variables, such as the load. Because of that reason, temperature forecasting is and has been for years of great interest for energy forecasters and several approaches and methods have been published. However, these methods usually do not consider temperature trend, which causes important error increases when dealing with medium- or long-term estimations. This paper presents several temperature forecasting methods based on time series decomposition and analyzes their results and the trends of 37 different European countries, proving their annual average temperature increase and their different behaviors regarding trend and seasonal components.

show abstract

Section: Abbreviationsmentioning

confidence: 99%

Time Series Decomposition of the Daily Outdoor Air Temperature in Europe for Long-Term Energy Forecasting in the Context of Climate Change

2020

Self Cite

View full text Add to dashboard Cite

show abstract

“…Another way to classify the related work is the mathematical techniques used to forecasting, for example, Artificial Neural Networks (ANN) [8,9,27], Bagged Regression Trees (BRT) [8], Support Vector Machines (SVM) [9,28], Multiple Regression Models (Linear and Non-linear) [10,14,17,19,23,30], Genetic Algorithms (GA) [12], Fuzzy [18,29], Simulation [20], Decision Tree [24], Particle Swarm Optimization [28,29].…”

Section: Related Workmentioning

confidence: 99%

“…Other related works are focusing on some devices like Energy Management Systems (EMS) [8], weather station [12], microgrid [13].…”

Section: Related Workmentioning

confidence: 99%

Forecasting Electricity Consumption Using Weather Data in an Edge-Fog-Cloud Data Analytics Architecture

Olivares-Rojas

Reyes-Archundia

Gnecchi

et al. 2020

Advances on P2P, Parallel, Grid, Cloud and Internet Computing

View full text Add to dashboard Cite

The forecasting of electricity consumption is a well-study research problem; however, electricity consumption is a complex model because it depends on many factors, and its accuracy is not always accurate. The accuracy of this forecasting impact; for example, in the utilities in the bulk generation of electricity and in the end-user at economical prices. This work shows the implementation of a forecasting model considering weather data across the smart metering system infrastructure using and edge-fog-cloud architecture for data analytics. The results show that using weather data across edge-fog-cloud architecture is an excellent alternative to forecast electricity consumption.

show abstract

“…The simplest way to integrate the temperature into the model when information is available from several stations, is to average the temperature of all or choose them based on experience. However, various studies have recently shown that this is not the most adequate method [6][7][10] [12]. In [10], a review of different methods of selection and combination of meteorological stations for load forecasting is carried out.…”

Section: Introductionmentioning

confidence: 99%

A Method for Weather Station Selection Based on Wavelet Squared Coherence for Electric Load Forecasting

Boya

Ardila-Rey

2020

IEEE Access

View full text Add to dashboard Cite

This paper presents a new method for selection and combination of weather stations based on Wavelet Squared Coherence (WSC) that seeks to improve the performance of forecast models for the electric load. An Average Coherence Index (ACI) is obtained from WSC and used as an indicator of the relationship between the temperature of a weather station and the load of an area served by a utility. The ACI is used to categorize stations and select the best combination of stations for a forecast model. The method is validated with data from 18 load zones and 11 weather stations, offering a lower Mean Absolute Percentage Error (MAPE) than similar methods.

show abstract

Rethinking weather station selection for electric load forecasting using genetic algorithms

Cited by 19 publications

References 26 publications

Time Series Decomposition of the Daily Outdoor Air Temperature in Europe for Long-Term Energy Forecasting in the Context of Climate Change

Time Series Decomposition of the Daily Outdoor Air Temperature in Europe for Long-Term Energy Forecasting in the Context of Climate Change

Forecasting Electricity Consumption Using Weather Data in an Edge-Fog-Cloud Data Analytics Architecture

A Method for Weather Station Selection Based on Wavelet Squared Coherence for Electric Load Forecasting

Contact Info

Product

Resources

About