Deep Learning based Short Term Load Prediction in Smart Grids

Short-term load prediction as a basic work of operation and control in power system plays an important role for power operation and scheduling, motor start-stop, etc. 5th generation (5G) communications technologies make the size of data in smart grids larger, compared to non-5G equipped smart grid. To cope with this challenge, we propose a daily time step-by-step load prediction method based on deep learning. A deep cycle neural network (DCNN) model is established for the total daily load and hourly load of users. Through simulation, superiority of our work is proved.