Abstract: In ocean observations, the infrastructure providing wireless communication is sparsely deployed and the wireless observation nodes move very fast. The limited or even scarce wireless network resources are difficult to meet the uploading requirements of large-scale data collection. It is extremely urgent to study and solve the effective upload access control method for massive observation nodes to compete for scarce communication resources. Based on the historical data of the observation access request, the neural network is used to perform time series analysis on them, and then gets their future revenues based on probability. To maximize total revenue, this paper studies the optimization method of uploading access scheduling problem that guarantees the delay tolerance of observation data based on time series analysis. Unfortunately, it is an NP-hard problem (see in theorem 1). Therefore, the approximation algorithm of enhanced access control (P-RSA) is proposed based on the dynamic programming idea. Firstly, the wireless access requests with spatio-temporal dynamic features is a quantified. Secondly, performance parameters are generalized to “revenue”. Finally, simulation experiments are performed that the total revenues of access requests are analysed under different AP’s load conditions until the deadline. P-RSA’s effectiveness is verified by detailed simulation experiments than the existing algorithms.