@article{TORRES19-1,

title = {Big data solar power forecasting based on deep learning and multiple data sources},

author = {J. F. Torres and A. Troncoso and I. Koprinska and Z. Wang and F. Martínez-Álvarez},

url = {https://onlinelibrary.wiley.com/doi/abs/10.1111/exsy.12394},

doi = {https://doi.org/10.1111/exsy.12394},

year  = {2019},

date = {2019-03-01},

journal = {Expert Systems},

volume = {36},

pages = {id12394},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{INFSCI2018,

title = {A novel Spark-based multi-step forecasting algorithm for big data time series},

author = {A. Galicia and J. F. Torres and F. Martínez-Álvarez and A. Troncoso},

url = {https://www.sciencedirect.com/science/article/pii/S0020025518304493},

doi = {10.1016/j.ins.2018.06.010},

year  = {2018},

date = {2018-01-01},

journal = {Information Sciences},

volume = {467},

pages = {800-818},

abstract = {This paper presents different scalable methods for predicting big time series, namely time series with a high frequency measurement. Methods are also developed to deal with arbitrary prediction horizons. The Apache Spark framework is proposed for distributed computing in order to achieve the scalability of the methods. Prediction methods have been developed using Spark’s MLlib library for machine learning. Since the library does not support multivariate regression, the prediction problem is formulated as h prediction sub-problems, where h is the number of future values to predict, that is, the prediction horizon. Furthermore, different kinds of representative methods have been chosen, such as decision trees, two tree-based ensemble techniques (Gradient-Boosted and Random Forest) and a linear regression method as a reference method for comparisons. Finally, the methodology has been tested in a real time series of electrical demand in Spain, with a time interval of ten minutes between measurements.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{ICAE2018,

title = {A scalable approach based on deep learning for big data time series forecasting},

author = {J. F. Torres and A. Galicia and A. Troncoso and F. Martínez-Álvarez},

url = {https://content.iospress.com/articles/integrated-computer-aided-engineering/ica580},

doi = {10.3233/ICA-180580},

year  = {2018},

date = {2018-01-01},

journal = {Integrated Computer-Aided Engineering},

volume = {25},

number = {4},

pages = {335-348},

abstract = {This paper presents a method based on deep learning to deal with big data times series forecasting. The deep feed forward neural network provided by the H2O big data analysis framework has been used along with the Apache Spark platform for distributed computing. Since H2O does not allow the conduction of multi-step regression, a general-purpose methodology that can be used for prediction horizons with arbitrary length is proposed here, being the prediction horizon, h, the number of future values to be predicted. The solution consists in splitting the problem into h forecasting subproblems, being h the number of samples to be simultaneously predicted. Thus, the best prediction model for each subproblem can be obtained, making easier its parallelization and adaptation to the big data context. Moreover, a grid search is carried out to obtain the optimal hyperparameters of the deep learning-based approach. Results from a real-world dataset composed of electricity consumption in Spain, with a ten-minute frequency sampling rate, from 2007 to 2016 are reported. In particular, the accuracy and runtimes versus computing resources and size of the dataset are analyzed. Finally, the performance and the scalability of the proposed method is compared to other recently published techniques, showing to be a suitable method to process big data time series.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Energy2018,

title = {Stacking ensemble learning for short-term electricity consumption forecasting},

author = {F. Divina and A. Gilson and F. Goméz-Vela and M. García-Torres and J. F. Torres},

url = {https://www.mdpi.com/1996-1073/11/4/949},

doi = {https://doi.org/10.3390/en11040949},

year  = {2018},

date = {2018-01-01},

journal = {Energies},

volume = {11},

number = {4},

pages = {949},

abstract = {The ability to predict short-term electric energy demand would provide several benefits, both at the economic and environmental level. For example, it would allow for an efficient use of resources in order to face the actual demand, reducing the costs associated to the production as well as the emission of CO 2 . To this aim, in this paper we propose a strategy based on ensemble learning in order to tackle the short-term load forecasting problem. In particular, our approach is based on a stacking ensemble learning scheme, where the predictions produced by three base learning methods are used by a top level method in order to produce final predictions. We tested the proposed scheme on a dataset reporting the energy consumption in Spain over more than nine years. The obtained experimental results show that an approach for short-term electricity consumption forecasting based on ensemble learning can help in combining predictions produced by weaker learning methods in order to obtain superior results. In particular, the system produces a lower error with respect to the existing state-of-the art techniques used on the same dataset. More importantly, this case study has shown that using an ensemble scheme can achieve very accurate predictions, and thus that it is a suitable approach for addressing the short-term load forecasting problem.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}