Mid-Term Load Forecasting Based on Neural Network Algorithm: a Comparison of Models

Bunnoon, Pituk

doi:10.7763/ijcee.2011.v3.388

Cited by 13 publications

(4 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Using feature selection method, 10 features related to past loads are selected i.e., 1,2,3,4,6,7,8,14,26 and 28 days before the forecasting day. In addition, some other features such as holidays, day type of a week, and month of a year have been taken into account in inputs by binary features.…”

Section: Simulation Resultsmentioning

confidence: 99%

“…In literatures, the time horizon of MTLF are not considered the same. For instance, authors in [5] believe that the forecasting term of MTLF is 1 to 12 months ahead of time while, the load forecast within 3 months to 3 years is suggested by [6] as the medium-term time horizon. However, in another point of view, MTLF is carried out by [7] for a period between one to several years.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Medium-Term Load Forecasting Using Support Vector Regression, Feature Selection, and Symbiotic Organism Search Optimization

Zare-Noghabi

Shabanzadeh

Sangrody

2019

2019 IEEE Power &Amp; Energy Society General Meeting (PESGM)

View full text Add to dashboard Cite

An accurate load forecasting has always been one of the main indispensable parts in the operation and planning of power systems. Among different time horizons of forecasting, while short-term load forecasting (STLF) and long-term load forecasting (LTLF) have respectively got benefits of accurate predictors and probabilistic forecasting, medium-term load forecasting (MTLF) requires more attentions due to its vital role in power system operation and planning such as optimal scheduling of generation units, robust planning programs for customer service, and economic supply. In this study, a hybrid method, composed of Support Vector Regression (SVR) and Symbiotic Organism Search Optimization (SOSO) method, is proposed for MTLF. In the proposed forecasting model, SVR is the main part of the forecasting algorithm while SOSO is embedded into it to optimize the parameters of SVR. In addition, a minimum redundancy-maximum relevance feature selection algorithm is applied in the preprocessing of input data. The proposed method is tested on EUNITE competition dataset and compared with some previous works to demonstrate its high performance.

show abstract

Section: Simulation Resultsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Medium-Term Load Forecasting Using Support Vector Regression, Feature Selection, and Symbiotic Organism Search Optimization

Zare-Noghabi

Shabanzadeh

Sangrody

2019

2019 IEEE Power &Amp; Energy Society General Meeting (PESGM)

View full text Add to dashboard Cite

show abstract

“…Output is solar radiation. The AND and OR operators are used to correlate the input variables (Bunnoon, 2011). The third phase is the fuzzy inference engine which includes the application of the membership functions of inputs and the fuzzy rules base to maintain the membership function of output.…”

Section: Figure (1)mentioning

confidence: 99%

The Prediction of Solar Radiation Using Fuzzy Logic: a Case Study

MOHAMMED

2018

juod

View full text Add to dashboard Cite

Solar energy is used in many applications such as producing agricultural food, renewable energy, and heating and lighting systems… etc. Nowadays, countries all over the world, especially the developing countries are facing a great challenge which is providing sustainable energy for consumers. Electricity is the most common type of energy that is used by consumers in which oil or nuclear power is used to produce sufficient amount of electricity for the constant increase of the population in the present. However, both oil and nuclear energy negatively affect the global warming; therefore, solar energy is aspired by many countries to decrease the effects of the global warming and produce renewable sources of energy. The aim of this study is to predict the use of solar radiation for solar energy to produce electricity in Duhok city due to the fact that "national electricity" is not enough for the great number of consumers; as a result, people depend on "local or private generators" which mainly depend on oil to produce electricity. Fuzzy logic approach is used to estimate the solar radiation. The four fuzzy systems are created using the available data in Duhok City in 2016. Daily observations for temperature, humidity and wind speed for four seasons are analyzed to estimate the solar radiation. The predicted outputs of fuzzy logic system are compared with the actual solar radiation. In addition, the fuzzy system approach is evaluated using Mean Absolute Percentage Error (MAPE) and Absolute Percentage Error (APE). The outcomes of MAPE and APE are 5. 86%, 1.54%, 2.76% and 1.52 for four seasons (winter, summer, spring and fall), respectively. According to the results, the performance of fuzzy system is reasonably effective in predicting the solar radiation.

show abstract

“…Tsekouras et al (2006) use an adaptive ANN, which properly transforms the input variables to differences or relative differences, in order to predict energy values not included in the training set. Another example of yearly mid-term load forecasting is described in Bunnoon (2011). An ANN is used to forecast a year ahead the grid demand based on different factors, such as temperature, humidity, wind speed, rainfall, industrial index and consumer price index.…”

Section: Artificial Neural Network In Electrical Applicationsmentioning

confidence: 99%

Artificial recurrent neural networks for the distributed control of electrical grids with photovoltaic electricity

Avila¹

View full text Add to dashboard Cite

Realizando el acto de defensa y lectura de la Tesis en la E.T.S.I.T., Madrid, el día de de 2016.Acuerdan otorgar la calificación de:Y, para que conste, se extiende firmada por los componentes del tribunal, la presente diligencia ResumenEl sistema eléctrico actual no ha evolucionado desde sus orígenes. Esto ha hecho que emerjan diferentes problemas los cuales son necesarios afrontar para incrementar el rendimiento de las redes eléctricas. Uno de estos problemas es el crecimiento de la demanda, mientras que otros, como las Tecnologías de la Información y las Comunicaciones (TIC) o la Generación Distribuida (GD), se han desarrollado dentro de la red eléctrica recientemente sin ser propiamente integradas dentro de ella. Esta Tesis afronta los problemas derivados del manejo y la operación de las redes eléctricas existentes y su evolución hacia lo que se considera la red eléctrica del futuro o Smart Grid (SG).El SG nace de la convergencia de cinco aspectos: i) la red eléctrica, ii) TICs, iii) energías renovables, iv) almacenamiento eléctrico y v) Gestión de la Demanda Eléctrica (GDE). Esta Tesis consiste en un primer paso hacia el SG uniendo e integrando los cinco aspectos claves para su desarrollo y despliegue en el futuro cercano. Para ello, la mejora del estado de la red eléctrica se consigue a través del suavizado del consumo agregado. Para lograr este objetivo, se propone el uso de un algoritmo que procese la información proveniente de las TICs para que todas las partes de la red eléctrica se puedan beneficiar. Algunos de estos beneficios son: mejor uso de las infraestructuras, reducción de su tamaño, mayor eficiencia, reducción de costes e integración de GD, entre otros. El algoritmo propuesto está basado en una aproximación distribuida en la que los usuarios son hechos partícipes de sus decisiones, siendo capaces de manejar sus flujos de potencia con este objetivo. El algoritmo se ha implementado siguiendo una estrategia basada en la GDE combinada con el control automático de la demanda que ayude a integrar los Recursos Energéticos Distribuidos (RED) (energías renovables y sistemas de almacenamiento eléctrico), que lo conducen hacia un concepto innovador denominado Gestión de la Activa de la Demanda Eléctrica (GADE).En esta Tesis, una aproximación basada en la Inteligencia Artificial (IA) ha sido utilizada para implementar el algoritmo propuesto. Este algoritmo ha sido construido utilizando Redes Neuronales Artificiales (RNAs), más concretamente Redes Neuronales Recurrentes (RNRs). El uso de RNAs ha sido motivado por las ventajas de trabajar con sistemas distribuidos, adaptativos y no lineales. Y la elección de las RNRs se ha basado en sus propiedades dinámicas, las cuales encajan perfectamente con el comportamiento dinámico no lineal de la red eléctrica. Además, un controlador neural es utilizado para manejar cada elemento de la red eléctrica, incrementado la eficiencia global a través del suavizado del consumo agregado y maximizando el autoconsumo de los RED disponibles. Sin embargo, no existe ningún tipo de...

show abstract

Mid-Term Load Forecasting Based on Neural Network Algorithm: a Comparison of Models

Cited by 13 publications

References 20 publications

Medium-Term Load Forecasting Using Support Vector Regression, Feature Selection, and Symbiotic Organism Search Optimization

Medium-Term Load Forecasting Using Support Vector Regression, Feature Selection, and Symbiotic Organism Search Optimization

The Prediction of Solar Radiation Using Fuzzy Logic: a Case Study

Artificial recurrent neural networks for the distributed control of electrical grids with photovoltaic electricity

Contact Info

Product

Resources

About