Vector Method for Singular Spectrum Analysis (SSA) of Electricity Consumption

Author(s):  
D.V. Antonenkov ◽  
D.A. Pavluchenko ◽  
D.V. Orlov ◽  
Denis B. Solovev
2017 ◽  
Vol 3 (1) ◽  
pp. 13-22
Author(s):  
Yogo Aryo Jatmiko ◽  
Rini Luciani Rahayu ◽  
Gumgum Darmawan

The Holt-Winters method is used to model data with seasonal patterns, whether trends or not. There are two methods of forecasting in Singular Spectrum Analysis (SSA), namely recurrent method (R-forecasting) and vector method (V-forecasting). The recurrent method performs continuous continuation (with the help of LRF), whereas the vector method corresponds to the L-continuation. Different methods of course make a difference in the accuracy of forecast results. To see the difference between the three methods is done by looking at the comparison of accuracy and reliability of forecast results. To measure the accuracy of forecasting used Mean Absolute Percentage Error (MAPE) and to measure the reliability of forecasting results is done by tracking signal. Applications are done on Indonesian red onion production from January 2006 to December 2015. Forecasting of both methods in SSA uses window length L = 39 and grouping r = 8. With α = 0.1, β = 0.001 and γ = 0.5, Holt-Winters additive method gives better result with MAPE 13,469% than SSA method.   Keywords: 


DYNA ◽  
2015 ◽  
Vol 82 (190) ◽  
pp. 138-146 ◽  
Author(s):  
Moises Lima de Menezes ◽  
Reinaldo Castro Souza ◽  
José Francisco Moreira Pessanha

Singular Spectrum Analysis (SSA) is a non-parametric technique that allows the decomposition of a time series into signal and noise. Thus, it is a useful technique to trend extraction, smooth and filter a time series. The effect on performance of both Box and Jenkins' and Holt-Winters models when applied to the time series filtered by SSA is investigated in this paper. Three different methodologies are evaluated in the SSA approach: Principal Component Analysis (PCA), Cluster Analysis and Graphical Analysis of Singular Vectors. In order to illustrate and compare the methodologies, in this paper, we also present the main results of a computational experiment with the monthly residential consumption of electricity in Brazil.


Sensors ◽  
2021 ◽  
Vol 21 (4) ◽  
pp. 1403
Author(s):  
Xin Jin ◽  
Xin Liu ◽  
Jinyun Guo ◽  
Yi Shen

Geocenter is the center of the mass of the Earth system including the solid Earth, ocean, and atmosphere. The time-varying characteristics of geocenter motion (GCM) reflect the redistribution of the Earth’s mass and the interaction between solid Earth and mass loading. Multi-channel singular spectrum analysis (MSSA) was introduced to analyze the GCM products determined from satellite laser ranging data released by the Center for Space Research through January 1993 to February 2017 for extracting the periods and the long-term trend of GCM. The results show that the GCM has obvious seasonal characteristics of the annual, semiannual, quasi-0.6-year, and quasi-1.5-year in the X, Y, and Z directions, the annual characteristics make great domination, and its amplitudes are 1.7, 2.8, and 4.4 mm, respectively. It also shows long-period terms of 6.09 years as well as the non-linear trends of 0.05, 0.04, and –0.10 mm/yr in the three directions, respectively. To obtain real-time GCM parameters, the MSSA method combining a linear model (LM) and autoregressive moving average model (ARMA) was applied to predict GCM for 2 years into the future. The precision of predictions made using the proposed model was evaluated by the root mean squared error (RMSE). The results show that the proposed method can effectively predict GCM parameters, and the prediction precision in the three directions is 1.53, 1.08, and 3.46 mm, respectively.


2020 ◽  
Vol 14 (3) ◽  
pp. 295-302
Author(s):  
Chuandong Zhu ◽  
Wei Zhan ◽  
Jinzhao Liu ◽  
Ming Chen

AbstractThe mixture effect of the long-term variations is a main challenge in single channel singular spectrum analysis (SSA) for the reconstruction of the annual signal from GRACE data. In this paper, a nonlinear long-term variations deduction method is used to improve the accuracy of annual signal reconstructed from GRACE data using SSA. Our method can identify and eliminate the nonlinear long-term variations of the equivalent water height time series recovered from GRACE. Therefore the mixture effect of the long-term variations can be avoided in the annual modes of SSA. For the global terrestrial water recovered from GRACE, the peak to peak value of the annual signal is between 1.4 cm and 126.9 cm, with an average of 11.7 cm. After the long-term and the annual term have been deducted, the standard deviation of residual time series is between 0.9 cm and 9.9 cm, with an average of 2.1 cm. Compared with the traditional least squares fitting method, our method can reflect the dynamic change of the annual signal in global terrestrial water, more accurately with an uncertainty of between 0.3 cm and 2.9 cm.


Sign in / Sign up

Export Citation Format

Share Document