For the sake of accurate energy resource allocation in smart buildings with hybrid solar energy and main electrical grid, an uncertainty-aware minority-game based energy management system (UAMG-EMS) is introduced in this paper. Multiple agents are deployed in the building, and are able to consider two types of uncertainties: (i) stochastic noise from energy meters/sensors; and (ii) uncertain working behaviors from load side. Firstly, agents can perform Kalman Filter based error-correction algorithm to reduce the stochastic noise coming from energy meters/sensors. Moreover, agents can have supervised learning to predict uncertain energy profiles. Afterwards, agents can play a modified minority game based energy management to allocate the limited solar energy resource. To extend the scalability of agents for the entire building, K-means based classifier is applied to characterize the types of agents and hence can reduce the number of agents for large-scale buildings. Compared with the conventional minority-game based energy management system (MG-EMS) without considering uncertainty, our UAMG-EMS shows about 37% reduction of unbalance in fair solar energy allocation, and also about 23% reduction of noise influence merely based on inaccurate energy meters/sensors.