No abstract

In order to improve network performance, including reducing computation delay, transmission delay and bandwidth consumption, edge computing and caching technologies are introduced to the fifth-generation wireless network (5G). However, the volume of edge resources is limited, while the number and complexity of tasks in the network are increasing sharply. Therefore, how to provide the most efficient service for network users with limited resources is an urgent problem to be solved. Thus, improving the utilization rate of communication, computing and caching resources in the network is an important issue. The diversification of network resources brings difficulties to network management. The joint resource allocation problem is difficult to be solved by traditional approaches. With the development of Artificial Intelligence (AI) technology, these AI algorithms have been applied to joint resource allocation problems to solve complex decision-making problems. In this paper, we first summarize the AI-based joint resources allocation schemes. Then, an AI-assisted intelligent wireless network architecture is proposed. Finally, based on the proposed architecture, we use deep Q-network (DQN) algorithm to figure out the complex and high-dimensional joint resource allocation problem. Simulation results show that the algorithm has good convergence characteristics, proposed architecture and the joint resource allocation scheme achieve better performance compared to other resource allocation schemes. INDEX TERMS Artificial intelligence, deep Q-network, resource management, edge computing and caching, the fifth-generation wireless network (5G).

In machine learning method, the number of training samples is an exceedingly important factor determining the learning system's robustness. In our previous researches (Liu et al.,

No abstract

The influence on total employment and employment structure of China has been studied in this paper. Based on the historical data of information industry, total employment and industry employment from 1990 to 2008, the results show that the development of information industry not only expands the amount of total employment, but also plays certain role in optimizing employment structure by the empirical study. The study suggests that the relationship between development of information industry and total employment growth is not a simple linear relationship but meets the dual logarithmic function, and has a strong positive correlation. The study also suggests that the development of information industry has a strong affect on the optimization of the employment structure.