Next Day Load Curve Forecasting Using Wavelet Analysis with Neural Network

Senjyu, Tomonobu; Tamaki, Y.; Takara, H.; Uezato, K.

doi:10.1080/15325000290085398

Cited by 14 publications

(8 citation statements)

References 3 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Figure 1 shows the first-scale decomposition progress, as a result, time signal S(n) is decomposed into its detailed cD1(n) and smoothed cA1(n) signals ESN with wavelet in load forecasting using filter HiF_D and LoF_D, respectively. The decomposition procedure is repeated until a predefined decomposition level, which can produce a set of signals representing the original signal Kim et al, 2002;Senjyu et al, 2002). Suppose cðtÞ [ L 2 ðRÞ is a mother wavelet, a series of sub-wavelets can be developed though dilating and translating the cðtÞ:…”

Section: The Principle Of Wavelet Analysismentioning

confidence: 99%

See 1 more Smart Citation

Echo state network with wavelet in load forecasting

Niu

Wang

et al. 2012

Kybernetes

View full text Add to dashboard Cite

Purpose -The purpose of this paper is to improve the accuracy of short time load forecasting to ensure the economical and safe operation of power systems. The traditional neural network applied in time series like load forecasting, easily plunges into local optimum and has a complicated learning process, leading to relatively slow calculating speed. On the basis of existing literature, the authors carried out studies in an effort to optimize a new recurrent neural network by wavelet analysis to solve the previous problems. Design/methodology/approach -The main technique the authors applied is referred to as echo state network (ESN). Detailed information has been acquired by the authors using wavelet analysis. After obtaining more information from original time series, different reservoirs can be built for each subsequence. The proposed method is tested by using hourly electricity load data from a southern city in China. In addition, some traditional methods are also applied for the same task, as contrast. Findings -The experiment has led the authors to believe that the optimized model is encouraging and performs better. Compared with standard ESN, BP network and SVM, the experimental results indicate that WS-ESN improves the prediction accuracy and has less computing consumption. Originality/value -The paper develops a new method for short time load forecasting. Wavelet decomposition is employed to pre-process the original load data. The approximate part associated with low frequencies and several detailed parts associated with high frequencies components give expression to different information from original data. According to this, suitable ESN is chosen for each sub-sequence, respectively. Therefore, the model combining the advantages of both ESN and wavelet analysis improves the result for short time load forecasting, and can be applied to other time series problem.

show abstract

Section: The Principle Of Wavelet Analysismentioning

confidence: 99%

“…using filter HiF_D and LoF_D, respectively. The decomposition procedure is repeated until a predefined decomposition level, which can produce a set of signals representing the original signal (An et al, 2011;Kim et al, 2002;Senjyu et al, 2002).…”

Section: Esn With Wavelet In Load Forecastingmentioning

confidence: 99%

Echo state network with wavelet in load forecasting

Niu

Wang

et al. 2012

Kybernetes

View full text Add to dashboard Cite

show abstract

“…Another approach for STWSF based on fuzzy ARTMAP (FA) technique has been explored by Haque and Meng (2011). A method based on wavelet transform (WT) has shown an excellent performance in nonstationary signal analysis and nonlinear function modelling, as reported in other forecasting applications such as wind power forecasting , electricity price forecasting (Conejo et al 2005), and load curve forecasting (Senjyu et al 2002). In spite of a significant body of research in this area, wind speed forecasting is a complex process to model and predict because wind speed is highly volatile, nonlinear, and exhibits ill-behaved time-series.…”

Section: Introductionmentioning

confidence: 99%

Wind speed forecast model for wind farm based on a hybrid machine learning algorithm

Haque

Mandal

Meng

et al. 2013

International Journal of Sustainable Energy

View full text Add to dashboard Cite

This paper presents a new strategy for wind speed forecasting based on a hybrid machine learning algorithm, composed of a data filtering technique based on wavelet transform (WT) and a soft computing model based on the fuzzy ARTMAP (FA) network. The prediction capability of the proposed hybrid WT + FA model is demonstrated by an extensive comparison with some other existing wind speed forecasting methods. The results show a significant improvement in forecasting error through the application of a proposed hybrid WT + FA model. The proposed wind speed forecasting strategy is applied to real data acquired from the North Cape wind farm located in PEI, Canada.

show abstract

“…Avdakovic et al ( ) used both linear regression and WTC to study the properties of UK power consumption and found that the WTC approach provides insight into the properties of the impact of the main factors on power consumption [9]. Furthermore, Khoa et al ( ); Senjyu et al ( ); Zhang et al ( ) successfully apply the wavelet analysis in conjunction with neural networks to forecast the electricity consumption [10][11][12]. Hence, in this study, we applied the WTC of examining the relationship between the electricity demand and the weather variables such as air temperature, relative humidity, solar radiation, and wind speed in Niamey.…”

Section: Introductionmentioning

confidence: 99%

Wavelet Analysis of Daily Energy Demand and Weather Variables

2019

View full text Add to dashboard Cite

In this paper, we applied the Wavelet Transform Coherence (WTC) and phase analysis to analyze the relationship between the daily electricity demand (DED) and weather variables such as temperature, relative humidity, wind speed, and radiation. The DED data presents both seasonal fluctuations and increasing trend while the weather variables depict only seasonal variation. The results obtained from the WTC and phase analysis permit us to detect the period of time when the DED significantly correlates with the weather variables. We found a strong seasonal interdependence between the air temperature and DED for a periodicity of 256-512 days and 128-256 days. The relationship between the humidity and DED also shows a significant interdependence for a periodicity of 256-512 days with average coherence equal to 0.8. Regarding the radiation and wind speed, the correlation is low with average coherence less than 0.5. These results provide an insight into the properties of the impacts of weather variables on electricity demand on the basis of which power planners can rely to improve their forecasting and planning of electricity demand.

show abstract

Next Day Load Curve Forecasting Using Wavelet Analysis with Neural Network

Cited by 14 publications

References 3 publications

Echo state network with wavelet in load forecasting

Echo state network with wavelet in load forecasting

Wind speed forecast model for wind farm based on a hybrid machine learning algorithm

Wavelet Analysis of Daily Energy Demand and Weather Variables

Contact Info

Product

Resources

About