Probabilistic Multi-Energy Load Forecasting for Integrated Energy System Based on Bayesian Transformer Network
Chen Wang, Ying Wang, Zhetong Ding, Kaifeng Zhang
Abstract
Probabilistic multi-energy load forecasting in an integrated energy system is very complex, because it needs to consider the following three aspects simultaneously: 1) Complex coupling relationship exists between multi-energy loads. 2) The intrinsic distribution of load uncertainties and dynamic changes of the distributions should be captured. 3) The probability distribution containing sufficient information should be generated. To address these issues, this paper proposes a multi-task Bayesian neural network, Bayesian Multiple-Decoder Transformer (BMDeT), which can capture both epistemic and aleatoric uncertainty, and achieve the joint probabilistic forecasting of the multi-energy loads considering their complex coupling relationship and related uncertainties. Firstly, the proposed model adopts the one-encoder multi-decoder framework, which could catch the multi-load coupling information by one Bayesian encoder and perform respective subtasks by multiple Bayesian decoders. Specifically, the Bayesian multi-head attention mechanism is proposed to capture the complex coupling relationship and uncertainties between multi-energy loads by optimizing the distribution of network parameters. Then, a multi-task balance method based on Bayesian theory is proposed to quantify the uncertainties of different tasks by giving trainable weights. Finally, the proposed model has been verified on a real-world load data set, the results show that it has superior performance over other benchmark models.