The current research work is mainly based on the decomposition of the total load of the family house into the electrical level load, and less research on the bus load of the high voltage level. To solve this problem, ia bus load composition decomposition algorithm based on bi-directional long short-term memory(Bi-LSTM) is proposed. Firstly, Bi-LSTM is constructed on the basis of LSTM. Secondly, bus load and its corresponding external information sources (such as date type, weather, et al) are used as input of Bi-LSTM after training. Finally, taking the mean relative error between the predicted value and the target value of the building power load decomposed by the network as the evaluation index. The experimental results show that the method can effectively identify the bus load with unknown components. Compared with the traditional recurrent neural network and long-term and short-term memory network, the proposed algorithm has better identification ability.