Dynamic Time Warping and FFT: A Data Preprocessing Method for Electrical Load Forecasting
Journal Title: International Journal of Advanced Computer Science & Applications - Year 2018, Vol 9, Issue 2
Abstract
For power suppliers, an important task is to accurately predict the short-term load. Thus many papers have introduced different kinds of artificial intelligent models to improve the prediction accuracy. In recent years, Random Forest Regression (RFR) and Support Vector Machine (SVM) are widely used for this purpose. However, they can not perform well when the sample data set is too noisy or with too few pattern feature. It is usually difficult to tell whether a regression algorithm can accurately predict the future load from the historical data set before trials. Here we demonstrate a method which estimates the similarity between time series by Dynamic Time Warping (DTW) combined with Fast Fourier Transform (FFT). Results show this is a simple and fast method to filter the raw large electrical load data set and improve the learning result before looping through all learning processes.
Authors and Affiliations
Juan Huo
Keywords
Related Articles
- EP ID EP269279
- DOI 10.14569/IJACSA.2018.090201
- Views 132
- Downloads 0
Using GIS for Retail Location Assessment at Jeddah City
GIS software has different useful tools that can be used for sites, demographic and competitive analysis. These tools enable retail and market researchers to find solutions related to many retail planning issues. The aim...
Dist-Coop: Distributed Cooperative Transmission in UWSNs using Optimization Congestion Control and Opportunistic Routing
One of the real issues in UWSN is congestion control. The need is to plan an optimized congestion control scheme which enhances the network life time and in addition limits the usage of energy in data transmission from s...
Miniaturisation of a 2-Bits Reflection Phase Shifter for Phased Array Antenna based on Experimental Realisation
In this paper, a controllable reflection type Phase Shifter (PS) is designed, simulated and implemented. The structure of the 2-bits PS consists of branch line coupler, delay lines and six GaAs FET switches controlled in...
Boosted Decision Trees for Lithiasis Type Identification
Several urologic studies showed that it was important to determine the lithiasis types, in order to limit the recurrence residive risk and the renal function deterioration. The difficult problem posed by urologists for c...
Comparison between Commensurate and Non-commensurate Fractional Systems
This article deals with fractional systems that rep-resent better physical process and guarantee a very small number of parameters that can reduces the computation time. It focuses in particular on the state-space repres...