Scalable Forecasting Techniques Applied to Big Electricity Time Series

@inproceedings{Galicia2017ScalableFT,
  title={Scalable Forecasting Techniques Applied to Big Electricity Time Series},
  author={Antonio Galicia and Jos{\'e} F. Torres and Francisco Mart{\'i}nez-{\'A}lvarez and Alicia Troncoso Lora},
  booktitle={IWANN},
  year={2017}
}
This paper presents different scalable methods to predict time series of very long length such as time series with a high sampling frequency. The Apache Spark framework for distributed computing is proposed in order to achieve the scalability of the methods. Namely, the existing MLlib machine learning library from Spark has been used. Since MLlib does not support multivariate regression, the forecasting problem has been split into h forecasting subproblems, where h is the number of future… 
View via Publisher
eps.upo.es
16 Citations
Background Citations
5
Methods Citations
3

16 Citations

Multi-step forecasting for big data time series based on ensemble learning

Big data time series forecasting based on nearest neighbours distributed computing with Spark

Analysis and enhanced prediction of the Spanish Electricity Network through Big Data and Machine Learning techniques

A TensorFlow Approach to Data Analysis for Time Series Forecasting in the Energy-Efficiency Realm

An approach for developing EC prediction systems is introduced here by the use of artificial neural networks (ANN), and a divide-and-conquer strategy is used so that the target system’s execution switches from one to another specialized small models that forecast the EC of a building within the time range of one hour.

Batch and incremental dynamic factor machine learning for multivariate and multi-step-ahead forecasting

DFML, a machine-learning version of the dynamic factor model, a successful forecasting methodology well-known in econometrics is proposed, and it is shown that it can consistently outperform state-of-the-art methods in a number of Synthetic and real forecasting tasks.

Stacking Ensemble Learning for Short-Term Electricity Consumption Forecasting

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, and that using an ensemble scheme can achieve very accurate predictions.

Temporal Convolutional Networks Applied to Energy-Related Time Series Forecasting

The TCN proposal outperforms the forecasting accuracy of Long Short-Term Memory (LSTM) recurrent networks, which are considered the state-of-the-art in the field.

Energy load forecasting model based on deep neural networks for smart grids

The results show that the proposed ELF model has attained better generalization and outperform the existing load forecasting models based on the shallow neural network, ensemble tree bagger and generalized linear regression.

A Comparative Study of Time Series Forecasting Methods for Short Term Electric Energy Consumption Prediction in Smart Buildings

Smart buildings are equipped with sensors that allow monitoring a range of building systems including heating and air conditioning, lighting and the general electric energy consumption. Thees data…

Machine Learning Based Grain Moisture Estimation for Real-time Monitoring of High-Temperature Paddy Drying Silo

In this study, a methodology has been developed to predict under-treatment paddy moisture content based on historical patterns, internal and external environmental parameters, with a shallow neural network providing the highest accuracy and lower computational time.

References

SHOWING 1-10 OF 26 REFERENCES

A Survey on Data Mining Techniques Applied to Electricity-Related Time Series Forecasting

This work explores the application of data mining techniques to time series forecasting and reviews the latest works of time series forecast and, as case study, those related to electricity price and demand markets.

Finding Electric Energy Consumption Patterns in Big Time Series Data

The distributed version of the k-means algorithm in the Apache Spark framework is proposed in order to find patterns from a big time series, corresponding to the electricity consumptions for two buildings from a public university.

A Nearest Neighbours-Based Algorithm for Big Time Series Data Forecasting

A nearest neighbours-based strategy is adopted as the main core of the algorithm, and although some parts remain iterative, and consequently requires an enhanced implementation, execution times are considered as satisfactory.

YADING: Fast Clustering of Large-Scale Time Series Data

This paper proposes a novel end-to-end time series clustering algorithm, YADING, which automatically clusters large-scale time series with fast performance and quality results and selects L1 norm as similarity measure and the multi-density approach as the clustering method.

Addressing Big Data Time Series: Mining Trillions of Time Series Subsequences Under Dynamic Time Warping

This work shows that by using a combination of four novel ideas the authors can search and mine massive time series for the first time, and demonstrates the following unintuitive fact: in large datasets they can exactly search under Dynamic Time Warping much more quickly than the current state-of-the-art Euclidean distance search algorithms.

Time series analysis, forecasting and control

This revision of a classic, seminal, and authoritative book explores the building of stochastic models for time series and their use in important areas of application —forecasting, model specification, estimation, and checking, transfer function modeling of dynamic relationships, modeling the effects of intervention events, and process control.

MRPR: A MapReduce solution for prototype reduction in big data classification

Machine learning on big data: Opportunities and challenges

Time series analysis, forecasting and control

time series analysis san francisco state university, 6 4 introduction to time series analysis, box and jenkins time series analysis forecasting and, th15 weeks citation classic eugene garfield, proc…

PLANET: Massively Parallel Learning of Tree Ensembles with MapReduce

This paper describes PLANET: a scalable distributed framework for learning tree models over large datasets, and shows how this framework supports scalable construction of classification and regression trees, as well as ensembles of such models.