Autocorrelation and partial autocorrelation functions to improve neural networks models on univariate time series forecasting

Flores, João Henrique Ferreira; Engel, Paulo Martins; Pinto, Rafael C.

doi:10.1109/ijcnn.2012.6252470

Cited by 52 publications

(28 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…After data preprocessing, ANN input parameters were selected from historical data. Many prediction papers selected the input based on the significance of the data from the autocorrelation function (ACF) (Flores et al, 2012;Sfetsos and Coonick, 2000). Fig.…”

Section: Resultsmentioning

confidence: 99%

Data Preprocessing for Load Forecasting using Artificial Neural Network

Ferraz

Azeredo

et al. 2020

Anais Do Simpósio Brasileiro De Sistemas Elétricos 2020

View full text Add to dashboard Cite

An accurate demand forecasting is essential for planning the electric dispatch in power system, contributing financially to electricity companies and helping in the security and continuity of electricity supply. In addition, it is evident that the distributed energy resource integration in the electric power system has been increasing recently, mostly from the photovoltaic generation, resulting in a gradual change of the load curve profile. Therefore, the 24 hours ahead prediction of the electrical demand of Campina Grande, Brazil, was realized from artificial neural network with a focus on the data preprocessing. Thus, the time series variations, such as hourly, diary and seasonal, were reduced in order to obtain a better demand prediction. Finally, it was compared the results between the forecasting with the preprocessing application and the prediction without the preprocessing stage. Based on the results, the first methodology presented lower mean absolute percentage error with 7.95% against 10.33% of the second one.

show abstract

Section: Resultsmentioning

confidence: 99%

Data Preprocessing for Load Forecasting using Artificial Neural Network

Ferraz

Azeredo

et al. 2020

Anais Do Simpósio Brasileiro De Sistemas Elétricos 2020

View full text Add to dashboard Cite

show abstract

“…The output layer has a single neuron with a multiplication unit. For all the methods, the number of significant inputs is calculated using the autocorrelation and partial autocorrelation of the series (Flores et al, 2012). The interested readers may go through (Flores et al, 2012) to have a detailed description on selection of significant inputs of ANN for univariate TSF using autocorrelation and partial autocorrelation functions.…”

Section: Experimental Setup and Simulation Resultsmentioning

confidence: 99%

“…For all the methods, the number of significant inputs is calculated using the autocorrelation and partial autocorrelation of the series (Flores et al, 2012). The interested readers may go through (Flores et al, 2012) to have a detailed description on selection of significant inputs of ANN for univariate TSF using autocorrelation and partial autocorrelation functions. We have considered 11 univariate time series datasets (as mentioned in Table 2) from the Time Series Data Library (Hyndman, 2010) for analysing the effectiveness of the proposed method with other methods.…”

Section: Experimental Setup and Simulation Resultsmentioning

confidence: 99%

Nonlinear time series forecasting using a novel self-adaptive TLBO-MFLANN model

Panigrahi

Behera

2019

IJCISTUDIES

View full text Add to dashboard Cite

In this paper, we have proposed a multiplicative FLANN (MFLANN) model for time series forecasting. In addition, an improved version of teaching learning based optimisation (TLBO), called self-adaptive TLBO (SATLBO) has been proposed to train the MFLANN model. The proposed SATLBO uses the gradient descent learning algorithm in the teacher phase while uses the past experience to adapt the learners parameters. This unique integration of SATLBO with gradient descent learning algorithm is used to determine the near optimal weight set of MFLANN. The proposed method is implemented in MATLAB environment and the obtained results are compared with other methods (DE-based MFLANN, TLBO-based MFLANN, CRO-based MFLANN, Jaya-based MFLANN and ETLBO-JPSNN) considering 11 benchmark univariate time series datasets. Extensive statistical analysis on obtained results indicated that the proposed SATLBO-MFLANN method is better and statistically significant in comparison to its counterparts.

show abstract

“…where P (A|B) is the best linear projection of A on B. Although both AC and PAC functions measures linear correlation, they can still be used for feature selection of nonlinear prediction methods, such as neural network techniques, as discussed in [42]. Thus, PAC function is used here for feature lag selection.…”

Section: Startmentioning

confidence: 99%

Data-Driven Mitigation of Energy Scheduling Inaccuracy in Renewable-Penetrated Grids: Summerside Electric Use Case

Farrokhabadi¹

2019

Energies

View full text Add to dashboard Cite

This paper presents findings on mitigating the negative impact of renewable energy resources variability on the energy scheduling problem, in particular for island grids and microgrids. The methods and findings presented in this paper are twofold. First, data obtained from the City of Summerside in the province of Prince Edward Island, Canada, is leveraged to demonstrate the effectiveness of state-of-the-art time series predictors in mitigating energy scheduling inaccuracy. Second, the outcome of the time series prediction analysis is used to propose a novel data-driven battery energy storage system (BESS) sizing study for energy scheduling purposes. The proposed probabilistic method accounts for intra-interval variations of generation and demand, thus mitigating the trade-off between time resolution of the problem formulation and the solution accuracy. In addition, as part of the sizing study, a BESS management strategy is proposed to minimize energy scheduling inaccuracies, and is then used to obtain the optimal BESS size. Finally, the paper presents quantitative analyses of the impact of both the energy predictors and the BESS on the supplied energy cost using the actual data of the Summerside Electric grid. The paper reveals the significant potential for reducing energy cost in renewable-penetrated grids and microgrids through state-of-the-art predictors combined with applications of properly-sized energy storage systems.

show abstract

Autocorrelation and partial autocorrelation functions to improve neural networks models on univariate time series forecasting

Cited by 52 publications

References 12 publications

Data Preprocessing for Load Forecasting using Artificial Neural Network

Data Preprocessing for Load Forecasting using Artificial Neural Network

Nonlinear time series forecasting using a novel self-adaptive TLBO-MFLANN model

Data-Driven Mitigation of Energy Scheduling Inaccuracy in Renewable-Penetrated Grids: Summerside Electric Use Case

Contact Info

Product

Resources

About