Multilayer Perceptron (MLP) and Autoregressive Integrated Moving Average (ARIMA) Models in Multivariate Input Time Series Data: Solar Irradiance Forecasting

Devi Munandar


Solar irradiance needs to estimate power consumptions for requiring of saving energy. The demand accomplished with providing facilities to predict. Time series data is a dataset that has complex problems. Using multilayer perceptron (MLP) and autoregressive integrated moving average (ARIMA) with multivariate input to solve the problem of predicting solar irradiance. The dataset is collected from solar irradiance sensor by an online monitoring station with 10 minutes data interval for 18 months. Prediction experimented with t, t-2, and t-6 data inputs that represent t as the day to get the predictive model (t+1). In ARIMA model, optimization was obtained in the input parameter (t-6) and ARIMA(1,1,2) with minimum RMSE is 43.91 W/m2, whereas MLP model used single layer, 10 neurons and using relu activation function to predict with minimum RMSE is 8.68 W/m2 using (t) input parameter. The deep learning model is better than the statistical model in this experiment. RMSE, MSE, MAE, MAPE, and R2, are used as an evaluation for model performance.


MLP, ARIMA; performance of evaluation; time series; forecasting; multivariate input.

Full Text:



Xinghua Fan, Li Wang, Shasha Li, Predicting chaotic coal prices using a multi-layer perceptron network model, In Resources Policy, Volume 50, 2016, Pages 86-92, ISSN 0301-4207.

Ramón Velo, Paz López, Francisco Maseda, Wind speed estimation using multilayer perceptron, In Energy Conversion and Management, Volume 81, 2014, Pages 1-9, ISSN 0196-8904.

Kumar Abhishek, M.P. Singh, Saswata Ghosh, Abhishek Anand, Weather Forecasting Model using Artificial Neural Network, In Procedia Technology, Volume 4, 2012, Pages 311-318, ISSN 2212-0173.

Kahina Dahmani, Gilles Notton, Cyril Voyant, Rabah Dizene, Marie Laure Nivet, Christophe Paoli, Wani Tamas, Multilayer Perceptron approach for estimating 5-min and hourly horizontal global irradiation from exogenous meteorological data in locations without solar measurements, In Renewable Energy, Volume 90, 2016, Pages 267-282, ISSN 0960-1481.

Ján VaÅ¡Äák, Rudolf JakÅ¡a, Juraj KoÅ¡Äák, Ján AdamÄák, Local weather prediction system for a heating plant using cognitive approaches, Computers in Industry, Volume 74, December 2015, Pages 110-118, ISSN 0166-3615.

Seydou Traore, Yufeng Luo, Guy Fipps, Deployment of artificial neural network for short-term forecasting of evapotranspiration using public weather forecast restricted messages, In Agricultural Water Management, Volume 163, 2016, Pages 363-379, ISSN 0378-3774.

Diana A. Bonilla Cardona, Nadia Nedjah, Luiza M. Mourelle, Online phoneme recognition using multi-layer perceptron networks combined with recurrent non-linear autoregressive neural networks with exogenous inputs, Neurocomputing, Volume 265, 2017, Pages 78-90, ISSN 0925-2312.

Mengjiao Qin, Zhihang Li, Zhenhong Du, Red tide time series forecasting by combining ARIMA and deep belief network, Knowledge-Based Systems, Volume 125, 2017, Pages 39-52, ISSN 0950-7051.

Abass Gibrilla, Geophrey Anornu, Dickson Adomako, Trend analysis and ARIMA modelling of recent groundwater levels in the White Volta River basin of Ghana, Groundwater for Sustainable Development, Volume 6, 2018, Pages 150-163, ISSN 2352-801X.

Kanika Taneja, Shamshad Ahmad, Kafeel Ahmad, S.D. Attri, Time series analysis of aerosol optical depth over New Delhi using Box–Jenkins ARIMA modeling approach, Atmospheric Pollution Research, Volume 7, Issue 4, 2016, Pages 585-596, ISSN 1309-1042.

S. Chattopadhyay, G. Chattopadhyay, Univariate modelling of summer-monsoon rainfall time series: comparison between ARIMA and ARNN ,CR Geoscience, 342 (2010), pp. 100-107.

George E. P. Box, Gwilym M. Jenkins, Gregory C. Reinsel, Greta M. Ljung, Time Series Analysis: Forecasting and Control, 5th Edition, ISBN: 978-1-118-67502-1, Jun 2015.

Parag Sen, Mousumi Roy, Parimal Pal, Application of ARIMA for forecasting energy consumption and GHG emission: A case study of an Indian pig iron manufacturing organization, Energy, Volume 116, Part 1, 2016, Pages 1031-1038, ISSN 0360-5442.

Arindrajit Pal, Jyoti Prakash Singh, Paramartha Dutta, Path length prediction in MANET under AODV routing: Comparative analysis of ARIMA and MLP model, Egyptian Informatics Journal, Volume 16, Issue 1, 2015, Pages 103-111, ISSN 1110-8665.



  • There are currently no refbacks.

Published by INSIGHT - Indonesian Society for Knowledge and Human Development