The present article describes the integration of a data-driven predictive demand response control for residential buildings with heat pump and on-site energy generation. The data driven control approach schedules the heating system of the building. In each day, the next 24 hours heating demand of buildings, including space heating and domestic hot water consumption, are predicted by means of a hybrid wavelet transformation and a dynamic neural network. Linear programming is implemented to define a cost-optimal schedule for the heat pump operation. Moreover, the study discusses the impact of heat demand prediction error on performance of demand response control. In addition, the option of energy trading with the electrical grid is considered in order to evaluate the possibility of increasing the profit for private householders through on-site energy generation. The results highlight that the application of the proposed predictive control could reduce the heating energy cost up to 12% in the cold Finnish climate. Furthermore, on-site energy generation declines the total energy cost and consumption about 43% and 24% respectively. The application of a data-driven control for the demand prediction brings efficiency to demand response control.

本文介绍了将数据驱动的预测性需求响应控制与具有热泵和现场能源生成功能的住宅建筑物集成在一起的方法。数据驱动控制方法可调度建筑物的供暖系统。通过混合小波变换和动态神经网络，每天预测建筑物接下来的24小时供暖需求，包括空间供暖和生活热水消耗。执行线性编程来定义热泵运行的成本最优计划。此外，研究讨论了热需求预测误差对需求响应控制性能的影响。此外，考虑与电网进行能源交易的选择，以便评估通过现场发电来增加私人家庭的利润的可能性。结果表明，在芬兰寒冷的气候中，所提出的预测控制的应用可以将热能成本降低多达12％。此外，现场发电将总能源成本和能耗分别降低了约43％和24％。数据驱动控制在需求预测中的应用为需求响应控制带来了效率。