Multi-step forecasting influences systems of energy management a lot, but traditional methods are unable to obtain important feature information because of the complex composition of features, which causes prediction errors. There are numerous types of data to forecast in the energy sector; we present the following datasets for comparison in the paper: electricity demand, PV production, and heating, ventilation, and air conditioning load. For a detailed comparison, we took both classical and modern forecasting methods: Bayesian ridge, Ridge regression, Linear regression, ARD regression, LightGBM, RF, Bi-RNN, Bi-LSTM, Bi-GRU, and XGBoost.