UAV has been widely used in forest fire monitoring because of its small size, simple structure and simple operation. Due to the complex environment in the forest fire scene, the UAV needs to make attitude adjustment to reduce the influence of these factors when performing tasks. Meanwhile, the optimization of energy consumption should be considered due to the limited carrying energy of the UAV. Therefore, this paper discusses the UAV attitude adjustment strategy based on energy consumption optimization in the forest fire scene, establishes the UAV energy consumption model, and puts forward the energy model optimization problem combined with the UAV attitude adjustment. The optimization problem is transformed into Markov decision process, and the Deep Q network (DQN) enhancement algorithm is used to realize the effective attitude adjustment of UAV. The simulation results show that the proposed scheme can effectively realize the UAV monitoring task under the circumstance of forest fire environment with limited energy.