Electric load forecasting by using dynamic neural network

Mordjaoui, Mourad; Haddad, Salim; Medoued, Ammar; Laouafi, Abderrezak

doi:10.1016/j.ijhydene.2017.03.101

Cited by 81 publications

(37 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…In a past paper [10], a univariate model for short-term load forecasting based on linear regression and patterns of daily cycles of load time series was proposed and compared to the performance of several regression methods in the model. Many researches have accomplished the implementation of artificial neural network (ANNs) for the electrical load forecasting [11][12][13]. Deep neural network (DNN) is a significant method developed based on ANN and its deep structure increases the feature abstraction capability of neural networks.…”

Section: Introductionmentioning

confidence: 99%

Short-Term Load Forecasting Based on Elastic Net Improved GMDH and Difference Degree Weighting Optimization

et al. 2018

View full text Add to dashboard Cite

As objects of load prediction are becoming increasingly diversified and complicated, it is extremely important to improve the accuracy of load forecasting under complex systems. When using the group method of data handling (GMDH), it is easy for the load forecasting to suffer from overfitting and be unable to deal with multicollinearity under complex systems. To solve this problem, this paper proposes a GMDH algorithm based on elastic net regression, that is, group method of data handling based on elastic net (EN-GMDH), as a short-term load forecasting model. The algorithm uses an elastic net to compress and punish the coefficients of the Kolmogorov–Gabor (K–G) polynomial and select variables. Meanwhile, based on the difference degree of historical data, this paper carries out variable weight processing on the input data of load forecasting, so as to solve the impact brought by the abrupt change of load law. Ten characteristic variables, including meteorological factors, meteorological accumulation factors, and holiday factors, are taken as input variables. Then, EN-GMDH is used to establish the relationship between the characteristic variables and the load, and a short-term load forecasting model is established. The results demonstrate that, compared with other algorithms, the evaluation index of EN-GMDH is significantly better than that of the rest algorithm models in short-term load forecasting, and the accuracy of prediction is obviously improved.

show abstract

Section: Introductionmentioning

confidence: 99%

Short-Term Load Forecasting Based on Elastic Net Improved GMDH and Difference Degree Weighting Optimization

et al. 2018

View full text Add to dashboard Cite

show abstract

“…The forecasting results indicated that the NN-based NARX model is superior to the other models because it can reuse the predicted load data for reflecting the forecast trend. Mordjaoui et al 19 proposed a dynamic NN-based electric load forecasting model and compared it to the Holt-Winters exponential smoothing (ES) and seasonal autoregressive integrated moving average (SARIMA) models. They reported that their model could achieve better mean absolute percentage error (MAPE).…”

Section: Related Studiesmentioning

confidence: 99%

A comparative analysis of artificial neural network architectures for building energy consumption forecasting

Moon

Park

Rho

et al. 2019

International Journal of Distributed Sensor Networks

View full text Add to dashboard Cite

Smart grids have recently attracted increasing attention because of their reliability, flexibility, sustainability, and efficiency. A typical smart grid consists of diverse components such as smart meters, energy management systems, energy storage systems, and renewable energy resources. In particular, to make an effective energy management strategy for the energy management system, accurate load forecasting is necessary. Recently, artificial neural network–based load forecasting models with good performance have been proposed. For accurate load forecasting, it is critical to determine effective hyperparameters of neural networks, which is a complex and time-consuming task. Among these parameters, the type of activation function and the number of hidden layers are critical in the performance of neural networks. In this study, we construct diverse artificial neural network–based building electric energy consumption forecasting models using different combinations of the two hyperparameters and compare their performance. Experimental results indicate that neural networks with scaled exponential linear units and five hidden layers exhibit better performance, on average than other forecasting models.

show abstract

“…Generally, the static neural network processes input signals from the input layer and then goes through each layer in order, and finally outputs the output results through the neurons in the output layer. The NAR and other dynamic networks can feed back the output signal to the input end, so that the output signal can participate in the next iterative training with memory function, so it can better describe the characteristics of time-varying systems with non-stationary, nonlinear and other complex mapping relationships [9], and overcome the shortcomings of the ARMA model that can only be modelled for stationary linear signals.…”

Section: Autoregressive Neural Networkmentioning

confidence: 99%

Condition Monitoring of Wind Turbine Based on Copula Function and Autoregressive Neural Network

et al. 2018

View full text Add to dashboard Cite

The traditional wind turbine fault monitoring is often based on a single monitoring signal without considering the overall correlation between signals. A global condition monitoring method based on Copula function and autoregressive neural network is proposed for this problem. Firstly, the Copula function was used to construct the binary joint probability density function of the power and wind speed in the fault-free state of the wind turbine. The function was used as the data fusion model to output the fusion data, and a fault-free condition monitoring model based on the auto-regressive neural network in the faultless state was established. The monitoring model makes a single-step prediction of wind speed and power, and statistical analysis of the residual values of the prediction determines whether the value is abnormal, and then establishes a fault warning mechanism. The experimental results show that this method can provide early warning and effectively realize the monitoring of wind turbine condition.

show abstract

Electric load forecasting by using dynamic neural network

Cited by 81 publications

References 21 publications

Short-Term Load Forecasting Based on Elastic Net Improved GMDH and Difference Degree Weighting Optimization

Short-Term Load Forecasting Based on Elastic Net Improved GMDH and Difference Degree Weighting Optimization

A comparative analysis of artificial neural network architectures for building energy consumption forecasting

Condition Monitoring of Wind Turbine Based on Copula Function and Autoregressive Neural Network

Contact Info

Product

Resources

About