The invention discloses a power grid loss influence quantization model by charge, network and source coordination control-based factors. the featured steps comprises: model data are prepared; a BP neural network model is built; the neural network is trained by input data; influences of each grid loss factor on power grid loss is quantized; and the model can be additionally used for predication of power grid predication. The specific implementation steps can be seen as figures in the abstract. Influences of grid influence factors on the grid loss can be quantized, and evidence is provided for a power grid department to make effective loss reduction measures.