In this study, a new technique is proposed to forecast short-term electrical load. Load forecasting is an integral part of power system planning and operation. Precise forecasting of load is essential for unit commitment, capacity planning, network augmentation and demand side management. Load forecasting can be generally categorized into three classes such as short-term, midterm and long-term. Short-term forecasting is usually done to predict load for next few hours to few weeks. In the literature, various methodologies such as regression analysis, machine learning approaches, deep learning methods and artificial intelligence systems have been used for short-term load forecasting. However, existing techniques may not always provide higher accuracy in short-term load forecasting. To overcome this challenge, a new approach is proposed in this paper for short-term load forecasting. The developed method is based on the integration of convolutional neural network (CNN) and long short-term memory (LSTM) network. The method is applied to Bangladesh power system to provide short-term forecasting of electrical load. Also, the effectiveness of the proposed technique is validated by comparing the forecasting errors with that of some existing approaches such as long short-term memory network, radial basis function network and extreme gradient boosting algorithm. It is found that the proposed strategy results in higher precision and accuracy in short-term load forecasting.

/pdf/a-short-term-load-forecasting-method-using-integrated-cnn-3oizzesogt.pdf

A Short-Term Load Forecasting Method Using Integrated CNN and LSTM Network

Short term electricity load forecasting using hybrid prophet-LSTM model optimized by BPNN

District Heater Load Forecasting Based on Machine Learning and Parallel CNN-LSTM Attention

District heater load forecasting based on machine learning and parallel CNN-LSTM attention

Prediction of electricity generation from a combined cycle power plant based on a stacking ensemble and its hyperparameter optimization with a grid-search method

Load forecasting procedure is one of the most vital factors to make the selection of unit commitment, economic dispatch, relaxation, spinning reserve capacity and schedule device maintenance. Energy providers, related organizations in power generation, transmission system and policy makers of a country are dependent on the scale of future electricity demand. Short term load forecasting (STLF) procedure is considered one of the most complex and accuracy defining factors of the electrical power system. However, conventional forecasting strategies may not always fulfill the precise result demand in the issue of STLF. In this research work, a viable strategy for the issue of STLF procedure using long short term memory network (LSTM), a special type of recurrent neural network is presented. The forecasting outcomes on time series electrical load data of Bangladesh represent that the developed strategy has the ability to obtain higher precision and accuracy in STLF. Evaluation parameters of proposed network are also compared with the outcomes of conventional regression model and obtained superior outputs.

Highly Efficient Short Term Load Forecasting Scheme Using Long Short Term Memory Network

In this research work, a novel methodology for the issue of short-term load forecasting (STLF) procedure using convolutional neural network (CNN) is presented. The forecasting outcomes of the proposed CNN model in the field of STLF is compared with the outcomes of autoregressive integrated moving average (ARIMA) model that are most frequently used in time series forecasting arena. Mean average error (MAE), root mean square error (RMSE), mean absolute percentage error (MAPE) have been defined as accuracy evaluation parameters which evaluated the performance of both proposed CNN model and ARIMA model. Results obtained from the developed network appear that the strategy has the ability to obtain higher precision and accuracy in load forecasting.

Short Term Electric Load Forecasting Using High Precision Convolutional Neural Network

In this research work, an improved short-term electrical load forecasting technique is developed. Short-term load forecasting plays a key role in scheduling of generating units and spinning reserve evaluation. It essentially estimates the near-future electricity demand, which helps to ensure seamless operation of all three stages of a power system – generation, transmission and distribution. There are a number of strategies for short-term load forecasting. However, conventional methods may not provide precise forecasting outcomes. Therefore, it is necessary to develop a more accurate technique to predict short-term electrical load. To this end, a convolutional long short term memory network (Conv-LSTM) is developed in this paper, which results in good forecasting precision. The developed methodology is applied to the electric load data of Bangladesh power system. Further, the performance of the proposed technique is compared to that of the conventional linear regression based forecasting algorithm in terms of different error metrics. Simulation results reveal that the proposed approach provides better forecasting and outperforms the conventional algorithm.

An Effective Short-Term Load Forecasting Methodology Using Convolutional Long Short Term Memory Network

This paper investigates the optimized model and the behavior of a variable speed wind energy conversion system (WECS) based on permanent magnet synchronous generator (PMSG). Models and equations that describe different components of the WECS are addressed and their implementations into PSCAD/EMTDC are described. There are different types of synchronous generators, but the PMSG is chosen because the elimination of gearbox and introduction of variable speed control would even further increase the availability of the system. The proposed model has a set of IGBT converter-inverter connected through a DC bus associated with the maximum power point tracking (MPPT) system. Three models for the converter-inverter set have been used and their performances have been compared. Simulation results show that the controllers can extract maximum power and regulate the voltage and frequency under varying wind conditions. The controllers show very good dynamic and transient performances.

Shafiul Hasan Rafi

Papers

A Short-Term Load Forecasting Method Using Integrated CNN and LSTM Network

Highly Efficient Short Term Load Forecasting Scheme Using Long Short Term Memory Network

Short Term Electric Load Forecasting Using High Precision Convolutional Neural Network

An Effective Short-Term Load Forecasting Methodology Using Convolutional Long Short Term Memory Network

Optimization of a direct-drive wind power generation system by using PMSG