Long-term load forecasting based on adaptive neural fuzzy inference system using real energy data

Akdemïr, Bayram; Çetinkaya, Nurettin

doi:10.1016/j.egypro.2011.12.1013

Cited by 50 publications

(19 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Up to now, several hybrid prediction models have been proposed such as combined ARIMA-support vector machine (SVM) [20][21][22], hybrid of Grey and Box-Jenkins autoregressive moving average (ARMA) models [23], hybrid of ARIMA and fuzzy logic [24], hybrid of support vector regression (SVR) and differential evolution (DE) algorithm [25], integrated ANN-genetic algorithms (GAs) [26][27][28]/ANN-particle swarm optimization (PSO) [14]/ ANN-artificial fish swarm algorithm (AFSA) [29], combined generalized linear autoregression (GLAR)-ANN [30], hybrid of artificial intelligence (AI) and ANN [31], hybrid of wavelets and ANN implemented on a decision support system [32,33], integrated ARMA-ANN [34,35], combined seasonal ARIMA-back propagation (BP) ANN [36], combination of several ANNs [15,37], hybrid model of self organization map (SOM) neural network, GAs, and fuzzy rule base (FRB) [38], combined fuzzy techniques-ANN [39][40][41], hybrid based on PSO, evolutionary algorithm (EA) and DE for training a recurrent neural network (RNN) [42].…”

Section: Introductionmentioning

confidence: 99%

Time series prediction using PSO-optimized neural network and hybrid feature selection algorithm for IEEE load data

Sheikhan

Mohammadi

2012

Neural Comput & Applic

View full text Add to dashboard Cite

Artificial neural networks have been widely used in time series prediction. In this paper, multi-layer feedforward neural networks with optimized structures, using particle swarm optimization (PSO) algorithm, are used for hourly load prediction based on load time series of IEEE Reliability Test System. To have a small and appropriate feature subset, a hybrid method is used for feature selection in this paper. This hybrid method uses the combination of genetic algorithm (GA) and ant colony optimization (ACO) algorithm. The season, day of the week, time of the day and history load are considered as load influencing factors in this study based on the mentioned standard load dataset. The optimized number of neurons in the hidden layers of multi-layer perceptron (MLP) is determined using PSO algorithm. Experimental results show that the proposed hybrid model offers superior performance, in terms of mean absolute percentage error (MAPE), in time series prediction as compared to some recent researches in this field.

show abstract

Section: Introductionmentioning

confidence: 99%

Time series prediction using PSO-optimized neural network and hybrid feature selection algorithm for IEEE load data

Sheikhan

Mohammadi

2012

Neural Comput & Applic

View full text Add to dashboard Cite

show abstract

“…Results showed that ANFIS could be used in demand forecasting with limited data. Akdemir and Çetinkaya [24] proposed an ANFIS model to forecast the annual energy demand in Turkey with use of population, income level, peak load and energy demand data for 27 years. In spite of small number of data, good results were obtained.…”

Section: Anfismentioning

confidence: 99%

Forecasting energy consumption using ensemble ARIMA–ANFIS hybrid algorithm

Barak

Sadegh

2016

International Journal of Electrical Power & Energy Systems

269

113

View full text Add to dashboard Cite

a b s t r a c tEnergy consumption is on the rise in developing economies. In order to improve present and future energy supplies, forecasting energy demands is essential. However, lack of accurate and comprehensive data set to predict the future demand is one of big problems in these countries. Therefore, using ensemble hybrid forecasting models that can deal with shortage of data set could be a suitable solution. In this paper, the annual energy consumption in Iran is forecasted using 3 patterns of ARIMA-ANFIS model. In the first pattern, ARIMA (Auto Regressive Integrated Moving Average) model is implemented on 4 input features, where its nonlinear residuals are forecasted by 6 different ANFIS (Adaptive Neuro Fuzzy Inference System) structures including grid partitioning, sub clustering, and fuzzy c means clustering (each with 2 training algorithms). In the second pattern, the forecasting of ARIMA in addition to 4 input features is assumed as input variables for ANFIS prediction. Therefore, four mentioned inputs beside ARIMA's output are used in energy prediction with 6 different ANFIS structures. In the third pattern, due to dealing with data insufficiency, the second pattern is applied with AdaBoost (Adaptive Boosting) data diversification model and a novel ensemble methodology is presented.The results indicate that proposed hybrid patterns improve the accuracy of single ARIMA and ANFIS models in forecasting energy consumption, though third pattern, used diversification model, acts better than others and model's MSE criterion was decreased to 0.026% from 0.058% of second hybrid pattern. Finally, a comprehensive comparison between other hybrid prediction models is done. IntroductionEnergy is vital important for development of every country from the social, economic and environmental perspective. It has magnificent effect on industrial and agricultural products, health, sanitary, population, education and human life quality [1].As energy is a crucial input to industrial part of country, energy demand increases along the industrial function increase. Rapid changes in industry and economy strongly affect energy consumption. Therefore, energy consumption is an important economical index that represents economic development of a city or a country [2]. According to the international energy agent report, there should be many transformations in amount and type of future energy consumption (year 2030). As over the past decade global energy consumption has increased rapidly because of population and economic growth [3,4]. According to wide growth of energy consumption in the last decade, energy demand management is very important for achieving economic success, environment preservation and suitable planning for existing resources that result in self-sufficiency and economic development. Therefore, various techniques have been used for energy demand management to forecast future energy demands accurately [4]. However, energy forecasting is difficult, because it is affected by rapid development of economy, technology, gove...

show abstract

“…Akdemir and Çetinkaya [3] employed adaptive neural fuzzy inference system (as one of the most famous artificial intelligence methods which has been widely used in literature) for long-term load forecasting. They evaluated their proposed model by means of mean absolute error and mean absolute percentage error and obtained error values 1.504313 and 0.82439, respectively.…”

Section: Literature Reviewmentioning

confidence: 99%

A Cooperative Ant Colony Optimization-Genetic Algorithm approach for construction of energy demand forecasting knowledge-based expert systems

Ghanbari

Kazemi

Mehmanpazir

et al. 2013

Knowledge-Based Systems

View full text Add to dashboard Cite

Long-term load forecasting based on adaptive neural fuzzy inference system using real energy data

Cited by 50 publications

References 18 publications

Time series prediction using PSO-optimized neural network and hybrid feature selection algorithm for IEEE load data

Time series prediction using PSO-optimized neural network and hybrid feature selection algorithm for IEEE load data

Forecasting energy consumption using ensemble ARIMA–ANFIS hybrid algorithm

A Cooperative Ant Colony Optimization-Genetic Algorithm approach for construction of energy demand forecasting knowledge-based expert systems

Contact Info

Product

Resources

About