Abstract: Source detection of Wireless Sensor Network (WSN) would encounter problems of lacks of processing power and energy. To overcome these problems, an adaptive compressive sensing algorithm based on energy balance is proposed. Unlike the traditional adaptive compressive sensing algorithms, the proposed algorithm not only takes into account the reconstruction performance, but also considers the energy balance of the nodes when chooses the measurement vector. It prevents some nodes from the excessive consumption of energy and leading to the destruction of the whole network structure. At the same time in order to meet the needs of different application scenarios, the adaptive compressive sensing algorithm is combined with the energy balance based compressive sensing algorithm, and flexible configuration purpose is achieved by choosing the threshold. The simulations show that the proposed algorithm can extend the survival time of the network and consider both the energy consumption and convergence.