Feature Selection Using Genetic Algorithm and Bayesian Hyper-parameter Optimization for LSTM in Short-Term Load Forecasting

2021 ◽  
pp. 69-79
Author(s):  
Nguyen Nhat Anh ◽  
Nguyen Hoang Quoc Anh ◽  
Nguyen Xuan Tung ◽  
Nguyen Thi Ngoc Anh
Keyword(s):  
Genetic Algorithm ◽  
Feature Selection ◽  
Parameter Optimization ◽  
Load Forecasting ◽  
Short Term ◽  
Short Term Load Forecasting

An intelligent approach towards very short-term load forecasting

2021 ◽  
Vol 0 (0) ◽  
Author(s):  
Uttamarani Pati ◽  
Papia Ray ◽  
Arvind R. Singh
Keyword(s):  
Genetic Algorithm ◽  
Feature Selection ◽  
Load Forecasting ◽  
Dew Point ◽  
Short Term ◽  
Spinning Reserve ◽  
Feature Selection Technique ◽  
Selection Technique ◽  
Load Demand ◽  
Short Term Load Forecasting

Abstract Very short term load forecasting (VSTLF) plays a pivotal role in helping the utility workers make proper decisions regarding generation scheduling, size of spinning reserve, and maintaining equilibrium between the power generated by the utility to fulfil the load demand. However, the development of an effective VSTLF model is challenging in gathering noisy real-time data and complicates features found in load demand variations from time to time. A hybrid approach for VSTLF using an incomplete fuzzy decision system (IFDS) combined with a genetic algorithm (GA) based feature selection technique for load forecasting in an hour ahead format is proposed in this research work. This proposed work aims to determine the load features and eliminate redundant features to form a less complex forecasting model. The proposed method considers the time of the day, temperature, humidity, and dew point as inputs and generates output as forecasted load. The input data and historical load data are collected from the Northern Regional Load Dispatch Centre (NRLDC) New Delhi for December 2009, January 2010 and February 2010. For validation of proposed method efficacy, it’s performance is further compared with other conventional AI techniques like ANN and ANFIS, which are integrated with genetic algorithm-based feature selection technique to boost their performance. These techniques’ accuracy is tested through their mean absolute percentage error (MAPE) and normalized root mean square error (nRMSE) value. Compared to other conventional AI techniques and other methods provided through previous studies, the proposed method is found to have acceptable accuracy for 1 h ahead of electrical load forecasting.

scholarly journals A novel genetic-algorithm-based neural network for short-term load forecasting

2003 ◽  
Vol 50 (4) ◽  
pp. 793-799 ◽  
Author(s):  
S.H. Ling ◽  
F.H.F. Leung ◽  
H.K. Lam ◽  
Yim-Shu Lee ◽  
P.K.S. Tam
Keyword(s):  
Neural Network ◽  
Genetic Algorithm ◽  
Load Forecasting ◽  
Short Term ◽  
Short Term Load Forecasting

Short-Term Load Forecasting Based on GA-Elman Model

2014 ◽  
Vol 986-987 ◽  
pp. 520-523
Author(s):  
Wen Xia You ◽  
Jun Xiao Chang ◽  
Zi Heng Zhou ◽  
Ji Lu
Keyword(s):  
Neural Network ◽  
Genetic Algorithm ◽  
Relative Error ◽  
Bp Neural Network ◽  
Load Forecasting ◽  
Short Term ◽  
Elman Neural Network ◽  
Learning Efficiency ◽  
Multiple Layer ◽  
Short Term Load Forecasting

Elman Neural Network is a typical neural-network which shares the characteristics of multiple-layer and dynamic recurrent, and it’s more suitable than BP Neural Network when it’s applied to forecast the short-term load with periodicity and similarity. To solve the problem that Elman Neural Network lacks learning efficiency, GA-Elman model is established by optimizing the weights and thresholds using Genetic Algorithm. An example is then given to prove the effectiveness of GA-Elman model, using the load data of a certain region. Relative error and MSE have been considered as criterions to analyze the results of load forecasting. By comparing the results calculated by BP, Elman and GA-Elman model, the effectiveness of GA-Elman model is verified, which will improve the accuracy of short-term load forecasting.

Sign in / Sign up

Export Citation Format

Share Document