Deep dive into hybrid networks: A comparative study and novel architecture for efficient power prediction

Abstract

The prediction of electric power consumption (PC) and power generation (PG) plays an important role in the management, trading, and storage of energy, and in saving resources. Traditional approaches based on machine learning (ML) are subject to several issues arising from the use of handcrafted feature extraction, the requirement to learn the nonlinear relationships between output and input sequences, and inadequate adjustability to real-world scenarios. Similarly, the performance of deep-plane hybrid networks decreases when their depth increases. There is a need for more robust models in the energy forecasting domain that have high accuracy and strong generalizability to real-world implementations. To tackle the problems described above and to obtain a robust model, we propose a hybrid network based on a dilated depthwise separable convolutional neural network (DDSCNN) and a bidirectional gated recurrent unit (BGRU) in which a skip connection strategy is used to forecast short-term power production and consumption. In our framework, the obtained data are passed through a preprocessing stage for cleaning, and the refined data are input to the residual DDSCNN block to extract spatial features. These features are then fed to the residual BGRU block to learn the sequential and temporal patterns from them, and finally, dense layers are included at the end of the model to forecast the power. A comprehensive ablation study is conducted on various spatiotemporal hybrid models, and the best performer in terms of accuracy is selected using six power datasets. The root mean square error (RMSE) values obtained by the proposed model for the Korea south east solar power (KSESP), Australia Alice Springs solar power (AASSP), and Korea Yeongam solar power (KYSP) datasets are 0.8335, 0.2317, and 0.0954, respectively. Similarly, the RMSE values for the Korea south east wind power (KSEWP), individual household electric power consumption (IHEPC), and advanced institute of convergence technology (AICT) datasets are recorded as 0.5596, 0.1054, and 0.1068, respectively.