Deep learning-based load forecasting considering data reshaping using MATLAB\Simulink

Abstract

Load forecasting is a nonlinear problem and complex task that plays a key role in power system planning, operation, and control. A recent study proposed a deep learning approach called historical data augmentation (HDA) to improve the accuracy of the load forecasting model by dividing the input data into several yearly sub-datasets. When the original data is associated with high time step changes from 1 year to another, the approach was not found as effective as it should be for long-term forecasting because the time-series information is disconnected by the approach between the end of 1-year sub-data and the beginning of the next-year sub-data. Alternatively, this paper proposes the use of 2-year sub-dataset in order to connect the two ends of the yearly subsets. A correlation analysis is conducted to show how the yearly datasets are correlated to each other. In addition, a Simulink-based program is introduced to simulate the problem which has an advantage of visualizing the algorithm. To increase the model generalization, several inputs are considered in the model including load demand profile, weather information, and some important categorical data such as week-day and weekend data that are embedded using onehot encoding technique. The deep learning methods used in this study are the long short-term memory (LSTM) and gated rest unit (GRU) neural networks which have been increasingly employed in the recent years for time series and sequence problems. To provide a theoretical background on these models, a new picturized detail is presented. The proposed method is applied to the Kurdistan regional load demands and compared with classical methods of data inputting demonstrating improvements in both the model accuracy and training time.

Application of Deep Learning Gated Recurrent Unit in Hybrid Shunt Active Power Filter for Power Quality Enhancement

“…An RNN architecture consists of neural networks with feedback. RNN has the capability of reaching the history value using the present scenario, but there exist gradient issues that vanish and explode [37]. The weight computation and updating in the training process are performed in proportion to the gradient of the error concerning the weight.…”

“…LSTM is capable of holding long-term dependencies for a short duration [37]. The main working ideas of the LSTM are the ability of the delay cells to hold the data and the ability of the information flow gate to permits the information flow to and from the memory units.…”

“…This is performed using the sigmoid function. The mathematical relationship between gate outputs is given in Equations ( 5)-( 10) [37].…”

“…Previous hidden state Hp is taken as cell state. GRU network takes less training time as compared to LSTM to become trained for the nonlinear relationships of sequential data due to lesser network parameters [37]. The equations of dependencies within the cells are given in Equations ( 11)-( 14) [38].…”

“…The study suggested that transfer learning can extend this application to different domains. The load behavior is forecasted using a deep learning model and is deployed in MATLAB/Simulink with the "predict" blocks [37]. This method demonstrated improvement in accuracy and training time.…”