Diffusion Convolutional Recurrent Neural Network-Based Load Forecasting During COVID-19 Pandemic Situation

Infected by the novel coronavirus (COVID-19 – C-19) pandemic, worldwide energy generation and utilization have altered immensely. It remains unfamiliar in any case that traditional short-term load forecasting methodologies centered upon single-task, single-area, standard signals could precisely catch pattern during C-19 must be cautiously analyzed. An effectual administration finer planning power concerns remain of higher importance for precise electrical forecasting. There presents a degree unpredictability’s time series (TS) arduous doing forecast (SLF), medium-term (MLF), long-term (LLF). For excerpting local trends capturing similar patterns short medium TS, we proffer Diffusion Convolutional Recurrent Neural Network (DCRNN), which attains execution normalization employing knowledge transition betwixt disparate jobs. This as well evens portrayals if many layers stacked. The paradigms been tested actual life performing comprehensive experimentations authenticating their steadiness applicability. has computed concerning squared error, Root Mean Square Error (RMSE), Absolute Percentage (MAPE), (MAE). Consequently, proffered DCRNN 0.0534 MSE Chicago area, 0.1691 MAPE Seattle 0.0634 MAE area.