Forecasting of Turkey’s monthly electricity demand by seasonal artificial neural network

Hamzaçebi, Çoşkun; Es, Hüseyin Avni; Çakmak, Recep

doi:10.1007/s00521-017-3183-5

Cited by 60 publications

(26 citation statements)

References 68 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The ANN models have been used in many studies for electric power forecasting [ 6 , 39 , 44 , 46 , 48 , 53 , 54 , 55 , 57 , 58 , 59 , 60 , 61 , 62 , 65 , 70 , 75 , 77 , 81 , 82 , 86 , 108 , 153 , 155 , 165 , 175 , 176 ] and have reached a forcasting accuracy with an average MAPE value of 3.781%.…”

Section: Classes Of Forecasting Modelsmentioning

confidence: 99%

A Systematic Review of Statistical and Machine Learning Methods for Electrical Power Forecasting with Reported MAPE Score

Vivas

Allende‐Cid

Salas

2020

Entropy

View full text Add to dashboard Cite

Electric power forecasting plays a substantial role in the administration and balance of current power systems. For this reason, accurate predictions of service demands are needed to develop better programming for the generation and distribution of power and to reduce the risk of vulnerabilities in the integration of an electric power system. For the purposes of the current study, a systematic literature review was applied to identify the type of model that has the highest propensity to show precision in the context of electric power forecasting. The state-of-the-art model in accurate electric power forecasting was determined from the results reported in 257 accuracy tests from five geographic regions. Two classes of forecasting models were compared: classical statistical or mathematical (MSC) and machine learning (ML) models. Furthermore, the use of hybrid models that have made significant contributions to electric power forecasting is identified, and a case of study is applied to demonstrate its good performance when compared with traditional models. Among our main findings, we conclude that forecasting errors are minimized by reducing the time horizon, that ML models that consider various sources of exogenous variability tend to have better forecast accuracy, and finally, that the accuracy of the forecasting models has significantly increased over the last five years.

show abstract

Section: Classes Of Forecasting Modelsmentioning

confidence: 99%

A Systematic Review of Statistical and Machine Learning Methods for Electrical Power Forecasting with Reported MAPE Score

Vivas

Allende‐Cid

Salas

2020

Entropy

View full text Add to dashboard Cite

show abstract

“…Segue Figura 1, representando um modelo RNA típico de camada escondida (hidden layers) [17], que foi o modelo utilizado neste trabalho. O algoritmo de treinamento LM, de acordo com [18], pode ser descrita conforme a equação (7):…”

Section: D) Modelo Suavização Exponencial Duplaunclassified

Aplicação de Inteligência Artificial e Modelos Matemáticos para Previsão de Demanda em uma indústria do ramo plástico

Lima

Corso²

2020

SCI

View full text Add to dashboard Cite

ResumoAs constantes mudanças nos hábitos dos consumidores de utensílios domésticos evidenciam a importância do gerenciamento dos estoques, a fim de reduzir o valor investido e evitar obsolescência. O planejamento estratégico das organizações depende da identificação e previsão correta das mudanças emergentes no mercado. Embora existam diferentes métodos desenvolvidos na leitura, uma das principais dificuldades que se encontra é a escolha do método mais apropriado a ser utilizado. Este estudo tem por objetivo realizar a aplicação de inteligência artificial e métodos matemáticos de previsão de demanda em uma empresa que atua no setor de plásticos e identificar qual técnica apresenta melhores resultados na acuracidade da previsão, onde foram analisadas 365 bases históricas de diferentes produtos. Apresenta-se a comparação de modelos matemáticos com o modelo Redes Neurais Artificiais (RNA). Para a utilização do modelo RNA se desenvolveu um modelo matemático de otimização capaz de encontrar a melhor quantidade de neurônios, função matemática de treinamento e delay da rede por meio de Algoritmos Genéticos, minimizando os erros de previsão. Por meio da análise dos resultados observou-se que o modelo RNA otimizado apresentou menor percentual de erro dos dados realizados quando comparados com os demais modelos aplicados nesse estudo. Desta forma aumentando a confiabilidade e aceitabilidade do modelo, podendo ser utilizado em casos similares. A performance e comparativo estatístico dos métodos foram realizados a partir do MAPE e MAE, onde constatou-se que em 95% das vezes o modelo de RNA com otimização determinou as melhores previsões. Palavras-chaveGestão de estoque, previsão de demanda; rede neural artificial. AbstractThe constant changes in the habits of household appliances consumers highlight the importance of inventory management in order to reduce the amount invested and avoid obsolescence. Strategic planning of organizations depends on identifying and accurately forecasting emerging market changes. One of the biggest difficulties with the use of demand forecasting is the choice of the forecasting method to be used. This study aims to carry out the application of artificial intelligence and mathematical methods of forecasting demand in a company that operates in the plastics sector and to identify which technique presents better results in the accuracy of the forecast, where 365 historical bases of different products were analyzed. The comparison of mathematical models with the Artificial Neural Networks (RNA) model is presented. For the use of the RNA model a mathematical optimization model was developed capable of finding the best amount of neurons and mathematical training and delay function of the network through Genetic Algorithms, minimizing the prediction errors. Through the analysis of the results it was observed that the optimized RNA model presented smaller percentage of error of the data when compared with the other models applied in this study, increasing the reliability and acceptability of the model, b...

show abstract

“…Extensive research on prediction methods has been carried out in the references. Literature [1][2][3] proposed a method of electricity forecasting considering the time lag of economic factors on load, which reflects the changes of economic situation on electricity forecasting. Literature [4] proposed a decomposition model using moving regression and smooth spline as smoothing method is proposed to decompose the time series of power demand, and two neural networks are trained to predict the decomposition results respectively.…”

Section: A Literature Reviewmentioning

confidence: 99%

Comprehensive Forecasting Method of Monthly Electricity Consumption Based on Time Series Decomposition and Regression Analysis

Luan

Pang

et al. 2020

2020 2nd International Conference on Industrial Artificial Intelligence (IAI)

View full text Add to dashboard Cite

Power consumption prediction is the basis of implementing planned power consumption and preparing production plan. It is one of the main projects in the design of industrial and mining enterprises. It is also an important link to ensure the balance between national economic needs and power supply. Due to the influence of distributed energy and the change of power demand and load characteristics of the user side compared with the past, the power consumption prediction starts to face smallscale users and is more easily disturbed by various influencing factors, so the traditional prediction method is not fully suitable for today's power consumption prediction. Firstly, STL is used to decompose the power consumption sequence of corresponding month into trend component, season component and random component. Secondly, the BP neural network model is used to predict the seasonal component of the month when the seasonal mutation and major festivals are located. ARIMA model is used to predict the trend component. The average value is used to predict the random components. Then, the predicted values of the three components are reconstructed into the final predicted values. Finally, the algorithm is compiled by R language, and the validity of the proposed method is verified by the actual monthly electricity sales data of a University Park in the north. And further consider the prediction method of economic factors.

show abstract

Forecasting of Turkey’s monthly electricity demand by seasonal artificial neural network

Cited by 60 publications

References 68 publications

A Systematic Review of Statistical and Machine Learning Methods for Electrical Power Forecasting with Reported MAPE Score

A Systematic Review of Statistical and Machine Learning Methods for Electrical Power Forecasting with Reported MAPE Score

Aplicação de Inteligência Artificial e Modelos Matemáticos para Previsão de Demanda em uma indústria do ramo plástico

Comprehensive Forecasting Method of Monthly Electricity Consumption Based on Time Series Decomposition and Regression Analysis

Contact Info

Product

Resources

About