Input Vector Comparison for Hourly Load Forecast of Small Load Area Using Artificial Neural Network

Tasre, Mohan B.; Ghate, Vilas N.; Bedekar, Prashant P.

doi:10.1109/csnt.2012.63

Cited by 5 publications

(3 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, the justification of the choices for the input vector is often absent [19]- [22], and the model architecture is often not systematically argued or commented in a clarified way [18], [23]- [26]. The input vector is often defined in an arbitrary way, mainly based on experience [24], [25] or reproduces sets of variables used in previous publications [23], [27], [20]. As to the number of neurons on the hidden layer, a common practice is to choose the structure that causes the lowest training error by a trial-and-error scheme [19], [21], [25], [28], [29].…”

Section: Introductionmentioning

confidence: 99%

Neural Network-Based Model Design for Short-Term Load Forecast in Distribution Systems

Ding¹,

Benoît²,

Foggia³

et al. 2016

IEEE Trans. Power Syst.

181

View full text Add to dashboard Cite

Accurate forecasts of electrical substations are mandatory for the efficiency of the Advanced Distribution Automation functions in distribution systems. The paper describes the design of a class of machine-learning models, namely neural networks, for the load forecasts of medium-voltage/low-voltage substations. We focus on the methodology of neural network model design in order to obtain a model that has the best achievable predictive ability given the available data. Variable selection and model selection are applied to electrical load forecasts to ensure an optimal generalization capacity of the neural network model. Real measurements collected in French distribution systems are used to validate our study. The results show that the neural network-based models outperform the time series models and that the design methodology guarantees the best generalization ability of the neural network model for the load forecasting purpose based on the same data.Index Terms-Model design, machine learning, neural network, short-term load forecast, variable selection, virtual leave-one-out.

show abstract

Section: Introductionmentioning

confidence: 99%

Neural Network-Based Model Design for Short-Term Load Forecast in Distribution Systems

Ding¹,

Benoît²,

Foggia³

et al. 2016

IEEE Trans. Power Syst.

181

View full text Add to dashboard Cite

show abstract

“…Except predicting algorithm, the input selection of predicting methods cannot be ignored. Researchers always choose input variables by experience or simplified criterion . In order to obtain all the potential influence variables, considers amount of input variables, which contains load demand of several weeks ahead and climate parameters of several weeks ahead.…”

Section: Introductionmentioning

confidence: 99%

Short‐term building load forecast based on a data‐mining feature selection and LSTM‐RNN method

Sun

Jiang

Wang

et al. 2020

IEEJ Transactions Elec Engng

View full text Add to dashboard Cite

Short‐term load forecast for individual electric customers is becoming increasingly important in the grid operation, since the power system is becoming a more interactive and intelligent system. Accurate short‐term load forecast for industrial or commercial electric buildings is more challenging due to the complicated load characteristics and numerous influence variables. In this paper, we consider maximizing the relevancy and minimizing the redundancy criterion to select effectively feature variables, which influence the building load consumption, and then a deep learning technique—long‐short memory recurrent neural network is proposed to predict the load consumption. This novel strategy captures distinct load characteristics, choosing accurate input variables, and shows a great forecasting performance as demonstrated by three different types of city building load in China. © 2020 Institute of Electrical Engineers of Japan. Published by John Wiley & Sons, Inc.

show abstract

“…PSO is used to control parameters in BP. Finally, ANN uses to forecast load demand in hourly basis (Tasre et al, 2012).…”

Section: Load Demandmentioning

confidence: 99%

A Review of Considered Factors to Penetrate Renewable Energy Resources in Electrical Power System

Giyatno

2015

KEn

View full text Add to dashboard Cite

ABSTRACT:As an increasing of load demand, scarcity of fossil fuel and penetration of greenhouse gasses (GHG) effect, utilization of renewable energy resources (RER) such as wind, solar, biomass and tidal are rising drastically. Distributed generation (DG) is a technology giving opportunity to integrate RER into power system network. These integrations are needed optimal long term planning. Those planning, hopefully, can increase reliability of electrical power system network while saving environment from GHG with minimum infestation, operation and maintenance cost. The aim of this paper is reviewing factors should be consider when preparing, operating and evaluating electrical power system with integration of RER. By this planning, it is expected that its integration is effective and efficient in a lifetime of project. Finally, this review can help government, researcher, engineer and private sector to make policies to preparing hybrid power system-DGs.

show abstract

Input Vector Comparison for Hourly Load Forecast of Small Load Area Using Artificial Neural Network

Cited by 5 publications

References 14 publications

Neural Network-Based Model Design for Short-Term Load Forecast in Distribution Systems

Neural Network-Based Model Design for Short-Term Load Forecast in Distribution Systems

Short‐term building load forecast based on a data‐mining feature selection and LSTM‐RNN method

A Review of Considered Factors to Penetrate Renewable Energy Resources in Electrical Power System

Contact Info

Product

Resources

About