Wireless sensor networks (WSNs) are mostly used for monitoring the environment, however, they are usually powered by non-rechargeable batteries with limited energy. Energy harvesting is an attractive solution to the limit, which harvests energy from natural resource and provide a continuous energy supplement. Solar energy is the most popular energy resource because it has high energy intensity, therefore, sensor nodes use solar panels to convert solar energy into electricity to run themselves. Based on the characteristics of uncertainty and intermittency of solar energy, this paper proposes a plus-profile solar energy prediction algorithm (PP-Energy), which predicts future energy by looking for stored data that is most similar to the data on the day, and takes advantage of recent weather trends to reduce forecast errors. According to the predicted result, the paper further proposed an adaptive energy manage scheme (AEM). In the scheme, sensor nodes can adaptively adjust task scheduling to achieve energy neutrality, thereby wireless sensor network can work stably for a long time. The simulation results show that the proposed scheme has obvious advantages in energy prediction accuracy and energy management strategy.