As PV is considered prospective for decarbonizing the building sector, the self-consumption of on-site PV generation, which is susceptible to the temporal mismatch between solar radiation and energy demand, greatly affects the overall performance of improving building autonomy. As an important way to lessen the dependence of the decentralized PV energy system on the grid, internal flexibility from buildings is receiving increasing attention. This research sought to contribute to our understanding of the flexibility potential of Building Thermal Mass (BTM). In this aim, the load-shifting potential of BTM and the impacts on the self-consumption of rooftop PV generation were evaluated in a single-family residential building. To ensure a satisfying accuracy, this research proposed a novel framework that integrates multi-agent system and resistance-capacitance modelling techniques. The proposed methods represent the thermal network by means of circuit analogy and perform indoor thermal control based on stochastic occupant behaviours and appliance usage. The proposed BTM modelling framework is of great potential in flexibility estimation of BTM and could be used to assist the demand-side management.