基于热特性及供热参数预测的热力站调控方法研究
Regulation method of heating substations based on thermalcharacteristics and heating parameter prediction
摘要：
基于预测的热力站调控对实现供热系统的节能降耗和按需供热具有重要意义,但是输入数据的质量影响预测结果的准确性,而模型复杂度则限制了实际应用推广。针对这2个问题,提出了一种融合建筑热特性k值及BiGRU预测供热参数的调控方法。为了提高预测模型输入数据的质量,利用历史数据回归得到热力站的综合热特性k值,并根据k值对热力站进行分组,将每组热力站供热参数的平均值作为预测模型的输入。然后,基于BiGRU建立每组热力站的供热参数预测模型,用于指导热力站的运行调控。实际案例分析结果表明,预测值与各热力站的实际供热参数的均方根误差(RMSE)不大于0.53 ℃,平均绝对百分比误差(MAPE)小于1.5%,验证了该方法的有效性,为实现按需供热提供了理论基础。
Abstract：
Prediction-based heating substation regulation is of great significance to realize energy saving, consumption reduction and on-demand heating in heating systems, but the quality of input data affects the accuracy of prediction results, and the complexity of the model limits the practical application and promotion. To solve these two problems, a regulation method is proposed to integrate the k value of building thermal characteristics and BiGRU to predict the heating parameters. To improve the quality of the input data of the prediction model, the k value of the comprehensive thermal characteristics of the heating substations is obtained by regression of historical data, and the heating substations are grouped according to the k value, and the average value of the heating parameters of each group of heating substations is used as the input of the prediction model. Then, based on BiGRU, the prediction model of heating parameters of each group of heating substations is established to guide the operation and regulation of heating substations. The results of the actual case analysis show that the RMSE between the predicted value and the actual heating parameters of each heating substation is not more than 0.53 ℃, and the MAPE is less than 1.5%, which verifies the effectiveness of the method and provides a theoretical basis for the realization of on-demand heating.
Keywords:on-demand heating; heating substation; regulation; thermal characteristic; heating parameter; prediction; BiGRU