Energy conservation and carbon reduction in building energy is an important way to achieve the global goal of ‘carbon neutrality’. Common low‐carbon operation strategies of buildings rely on price incentives to guide users’ behaviour, which is difficult to make users aware of the impact of their energy consumption behaviour on carbon emissions. In this paper, the power system's dynamic carbon emission factors (CEF) were used to release information on energy consumption and carbon emission to building users. At the same time, the differential effects of building envelope and external temperature in the Building Information Modelling were considered. An optimisation method of building low‐carbon energy consumption strategy considering both the building and power carbon emission was established to improve the comprehensive carbon reduction ability of the building and power system. The simulation results show that the proposed method effectively coordinates the building virtual energy storage and demand response. By incorporating the dynamic energy carbon transaction cost into the objective function, the target signal of carbon reduction is transmitted to users so that the volatility of the renewable Energy and other random energy behaviours can be considered in the dynamic CEF.

In order to reduce the peak load on the power grid, various types of demand response (DR) programs have been developed rapidly, and an increasing number of residents have participated in the DR. The change in residential electricity consumption behavior increases the randomness of electricity load power, which makes residential load forecasting relatively difficult. Aiming at increasing the accuracy of residential load forecasting, an innovative electricity consumption pattern clustering is implemented in this paper. Six categories of residential load are clustered considering the power consumption characteristics of high-energy-consuming equipment, using the entropy method and criteria importance though intercrieria correlation (CRITIC) method. Next, based on the clustering results, the residential load is predicted by the fully-connected deep neural network (FDNN). Compared with the prediction result without clustering, the method proposed in this paper improves the accuracy of the prediction by 5.21%, which is demonstrated in the simulation.