基于深度神经网络的短期电网负荷预测模型研究

Research on Short-term Grid Load Forecasting Model Based on Deep Neural Network

随着分布式光伏装机容量的增加,已对全网负荷变化产生影响,现有负荷预测模式尚未考虑分布式光伏并网影响,电网负荷变化日趋复杂,亟需提高预测精度。构建了一种短期用电负荷预测模型,为了进一步提升预测精度,提出了一种基于深度神经网络和ResBlock迭代的短期负荷预测方法,学习不同用电量之间行为,建立内在时空的相关性。仿真结果表明,所提的负荷预测算法相比于传统方式准确性有明显的提高,在未来能源预测方面有较好的应用前景。

With the increase of distributed photovoltaic installed capacity,the load change of the whole grid has been affected.However,the impact of distributed photovoltaic grid connection has not yet been considered in the existing load forecasting model,and the load change of the grid is becoming increasingly complex.Therefore,it is urgent to improve the forecasting accuracy.Therefore,a short-term load forecasting model was constructed.In order to further improve the forecasting accuracy,a short-term load forecasting method based on deep neural network and ResBlock iteration was proposed to learn the behavior between different power consumption,so as to establish the inherent space-time correlation.The simulation results show that the accuracy of the proposed load forecasting algorithm is significantly improved compared with the traditional method,and it has a good application prospect in the future energy forecasting.