Massive MIMO system has attracted attention due to it's significant improvement in system capacity and spectrum utilization. Pilot pollution greatly limited the performance of Massive MIMO system. To optimize the pilot pollution in Massive MIMO system. In this paper, a pilot allocation scheme based on machine learning algorithm and users' angle of arrival is proposed. The scheme firstly classified all users according to whether the users' angle of arrival overlaps with each other. It randomly assigned pilot sequences to users whose angle of arrival do not overlap with each other. Secondly, it used machine learning algorithm to classify users whose angle of arrival overlap with each other into interfering group and non-interfering groups based on users' location information. We assign orthogonal pilots to users in the interfering group and randomly assign pilot sequences to users in the non-interfering group. Simulation results show that when the number of antenna reached 300, the pilot efficiency can be increased by about 11.67%. The pilot allocation scheme proposed in this paper can effectively suppress the impact of pilot pollution on the performance of Massive MIMO system, improve pilot efficiency and reduce pilot overhead.

Memory allocation and management of real-time task and sub real-time task have been becoming the hot problem that people concern all the time. Page coloring technology is a kind of practical method which can realize isolation of cache space. This article aimed at the problem of cache resource competition caused by shared memory on multi-core real-time system, to solve the collision of cache visit, put forward the scheme of cache space isolation based on page coloring technology and the realization method. The problem that data collide with the visit on cache can be finally avoided, by dividing the shared cache space.