Short-term load forecast of electrical power system by radial basis function neural network and new stochastic search algorithm

Abedinia, Oveis; Amjady, Nima

doi:10.1002/etep.2160

Cited by 59 publications

(50 citation statements)

References 40 publications

(79 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Energy forecasting methods are classified based on different aspects. From the time duration point of view, energy forecasting is divided into four categories: long‐term, midterm, short‐term, and very short‐term . This paper focuses on long‐term energy forecasting.…”

Section: Proposed Methods For Energy Forecastingmentioning

confidence: 99%

“…Recently, some methods have been proposed in literature such as neural networks or wavelet analysis method, which will be used for comparison with the proposed method. The neural networks method is an advanced method that uses a pattern recognition model to predict load . This method is based on the concept of the neural networks of “learning from the past” in order to predict the future.…”

Section: Proposed Methods For Energy Forecastingmentioning

confidence: 99%

“…It is also possible to improve the results by using a suitable data filtering . So, by using MRMRMS method, the forecasting becomes more accurate .…”

Section: Comparison Of the Proposed Methods With Other Methods For Loamentioning

confidence: 99%

See 2 more Smart Citations

A new combined method for future energy forecasting in electrical networks

Baesmat

Shiri

2018

Int Trans Electr Energ Syst

View full text Add to dashboard Cite

Summary Growing the industry and population in a region leads to the growth of required amount of electrical energy. Electrical companies should provide high quality energy according to the demand of customers. Load is an effective parameter of any system, and the network programmers should consider the annual load growth of the system and predict the required energy for each region by investigating previously recorded data of consumed electrical energy and stochastic analysis. In this paper, a new combined method for long‐term energy forecasting is proposed. This method, which combines the land‐consumption method and curve fitting based on generalization method, in addition to having simple calculations, takes into account the saturation. Moreover, loads from detailed formal program provided by the relevant institutes have been used, which results in better coordination between all organizations in charge of energy predictions and development of the countries. A suitable filtering method is also employed for input data to improve the method accuracy. To show the effectiveness of the proposed method, the results of different methods have been compared with those of the proposed method as well as real data. Then, real data of former 11 years of consumed energy gathered from Shiraz Electrical Distribution Company subscribers are employed and the energy for future 11 years is forecasted.

show abstract

Section: Proposed Methods For Energy Forecastingmentioning

confidence: 99%

Section: Proposed Methods For Energy Forecastingmentioning

confidence: 99%

See 1 more Smart Citation

A new combined method for future energy forecasting in electrical networks

Baesmat

Shiri

2018

Int Trans Electr Energ Syst

View full text Add to dashboard Cite

show abstract

“…The validity of the proposed method has been verified using historical locational marginal prices in the PJM US market. Focusing on the same market, Abedinia and Amjady have tried a radial basis function ANN based on a stochastic search algorithm to forecast short‐term loads. It is noticeable that the list of main forecasting models of electricity prices before 2014 can be found in the state‐of‐art paper of Weron …”

Section: Previous Researchmentioning

confidence: 99%

Stochastic modelling of the price‐volume relationship in electricity markets: Evidence from the Nordic energy exchange

Saâdaoui

Mrad

2017

Int Trans Electr Energ Syst

View full text Add to dashboard Cite

Summary The analysis of the interactions between price and transaction volume, conducted as part of a financial market, is one of the central themes of the financial theory. However, with the emergence of power exchanges and despite the expansion of the research sphere in this context, this issue had not been sufficiently addressed. This is due to not only the lack of concepts in theory but also to the peculiarity of price dynamics. The purpose of this paper is to shed light on the nature of the relationship between price changes and trading volume in the Nordic power market (Nord Pool), which is one of the largest energy markets worldwide. Through statistical timing analysis of the price‐volume covariation, we reconsider this joint modelling, but only settling for daily observations, which makes the specificity of this work. Contrary to most comparable works, which were based on high frequency data, we chose to omit intraday observations to circumvent the repercussion of the daily seasonality on one side and ensure more lucidity and clairvoyance to a wider horizon on the other. The empirical results go in line with our expectations and provide support for the claim that there exists a significant reciprocal causality between prices and trading volume.

show abstract

“…Owners of renewable resources need to predict the uncertainties for optimal planning such as photovoltaic voltage/power generation [2], market price [3], and load forecasting [4], wind farm power generation/wind speed (WS) [5][6][7][8][9]. In [7], firstly, historical data of WF is decomposed using wavelet transform (WT) and then WF power generation is predicted by artificial neural network (ANN).…”

Section: Introductionmentioning

confidence: 99%