scholarly journals Supercomputer power consumption prediction using machine learning, nonlinear algorithms, and statistical methods

2021 ◽  
Vol 2090 (1) ◽  
pp. 012087
Author(s):  
Jiří Tomčala
Keyword(s):  
Machine Learning ◽  
Time Series ◽  
Power Consumption ◽  
Statistical Methods ◽  
Time Series Prediction ◽  
Machine Learning Methods ◽  
Nonlinear Algorithms ◽  
Comparison Of The Results ◽  
Power Consumption Prediction ◽  
Consumption Prediction

Abstract This work describes various methods of time series prediction. It illustrates the differences between machine learning methods, nonlinear algorithms, and statistical methods in their approach to prediction, and tries to explain in depth the principles of some of the most widely used representatives of these types of prediction methods. All of these methods are then tested on a time series from the real world: the course of power consumption of a supercomputer infrastructure. The reader is gradually acquainted with data analysis, preprocessing, the principle of the methods, and finally with the prediction itself. The main benefit of the work is the final comparison of the results of this testing in terms of the accuracy of the predictions, and the time needed to calculate them.

scholarly journals Short-Term Electricity Consumption Forecasting Based on the EMD-Fbprophet-LSTM Method

2021 ◽  
Vol 2021 ◽  
pp. 1-9
Author(s):  
Guorong Zhu ◽  
Sha Peng ◽  
Yongchang Lao ◽  
Qichao Su ◽  
Qiujie Sun
Keyword(s):  
Time Series ◽  
Power Consumption ◽  
Prediction Model ◽  
Time Series Prediction ◽  
Electricity Consumption ◽  
Operating Efficiency ◽  
Short Term ◽  
Model Based ◽  
Consumption Data ◽  
Consumption Prediction

Short-term electricity consumption data reflects the operating efficiency of grid companies, and accurate forecasting of electricity consumption helps to achieve refined electricity consumption planning and improve transmission and distribution transportation efficiency. In view of the fact that the power consumption data is nonstationary, nonlinear, and greatly influenced by the season, holidays, and other factors, this paper adopts a time-series prediction model based on the EMD-Fbprophet-LSTM method to make short-term power consumption prediction for an enterprise's daily power consumption data. The EMD model was used to decompose the time series into a multisong intrinsic mode function (IMF) and a residual component, and then the Fbprophet method was used to predict the IMF component. The LSTM model is used to predict the short-term electricity consumption, and finally the prediction value of the combined model is measured based on the weights of the single Fbprophet and LSTM models. Compared with the single time-series prediction model, the time-series prediction model based on the EMD-Fbprophet-LSTM method has higher prediction accuracy and can effectively improve the accuracy of short-term regional electricity consumption prediction.

scholarly journals STL Decomposition of Time Series Can Benefit Forecasting Done by Statistical Methods but Not by Machine Learning Ones

2021 ◽  
Vol 5 (1) ◽  
pp. 42
Author(s):  
Zuokun Ouyang ◽  
Philippe Ravier ◽  
Meryem Jabloun
Keyword(s):  
Machine Learning ◽  
Time Series ◽  
Statistical Methods ◽  
Decomposition Method ◽  
Combination Method ◽  
Learning Methods ◽  
Machine Learning Methods ◽  
Time Series Decomposition

This paper aims at comparing different forecasting strategies combined with the STL decomposition method. STL is a versatile and robust time series decomposition method. The forecasting strategies we consider are as follows: three statistical methods (ARIMA, ETS, and Theta), five machine learning methods (KNN, SVR, CART, RF, and GP), and two versions of RNNs (CNN-LSTM and ConvLSTM). We conduct the forecasting test on six horizons (1, 6, 12, 18, and 24 months). Our results show that, when applied to monthly industrial M3 Competition data as a preprocessing step, STL decomposition can benefit forecasting using statistical methods but harms the machine learning ones. Moreover, the STL-Theta combination method displays the best forecasting results on four over the five forecasting horizons.

scholarly journals Identifying Spatiotemporal Patterns in Land Use and Cover Samples from Satellite Image Time Series

2021 ◽  
Vol 13 (5) ◽  
pp. 974
Author(s):  
Lorena Alves Santos ◽  
Karine Ferreira ◽  
Michelle Picoli ◽  
Gilberto Camara ◽  
Raul Zurita-Milla ◽  
...  
Keyword(s):  
Machine Learning ◽  
Land Use ◽  
Time Series ◽  
Satellite Image ◽  
Spatiotemporal Patterns ◽  
Supervised Machine Learning ◽  
Learning Methods ◽  
Self Organizing Maps ◽  
Machine Learning Methods ◽  
Land Use And Cover

The use of satellite image time series analysis and machine learning methods brings new opportunities and challenges for land use and cover changes (LUCC) mapping over large areas. One of these challenges is the need for samples that properly represent the high variability of land used and cover classes over large areas to train supervised machine learning methods and to produce accurate LUCC maps. This paper addresses this challenge and presents a method to identify spatiotemporal patterns in land use and cover samples to infer subclasses through the phenological and spectral information provided by satellite image time series. The proposed method uses self-organizing maps (SOMs) to reduce the data dimensionality creating primary clusters. From these primary clusters, it uses hierarchical clustering to create subclusters that recognize intra-class variability intrinsic to different regions and periods, mainly in large areas and multiple years. To show how the method works, we use MODIS image time series associated to samples of cropland and pasture classes over the Cerrado biome in Brazil. The results prove that the proposed method is suitable for identifying spatiotemporal patterns in land use and cover samples that can be used to infer subclasses, mainly for crop-types.

scholarly journals Time-Series Prediction of Iron and Silicon Content in Aluminium Electrolysis Based on Machine Learning

IEEE Access ◽  
2021 ◽  
Vol 9 ◽  
pp. 10699-10710
Author(s):  
Linsheng Chen ◽  
Yongming Wu ◽  
Yingbo Liu ◽  
Tiansong Liu ◽  
Xiaojing Sheng
Keyword(s):  
Machine Learning ◽  
Time Series ◽  
Silicon Content ◽  
Time Series Prediction ◽  
Aluminium Electrolysis

Pre-execution power consumption prediction of computational multithreaded workloads

2014 ◽  
Vol 17 (4) ◽  
pp. 1323-1333 ◽  
Author(s):  
Hamid Fadishei ◽  
Hossein Deldari ◽  
Mahmoud Naghibzadeh
Keyword(s):  
Power Consumption ◽  
Multithreaded Workloads ◽  
Power Consumption Prediction ◽  
Consumption Prediction
Sign in / Sign up

Export Citation Format

Share Document