A Joint Allocation Method of Spectrum Resources and Computing Resources Based on Reinforcement Learning

Abstract

The invention discloses a joint allocation method of frequency spectrum resources and computing resources based on reinforcement learning, which belongs to the technical field of wireless communication. Using the theory of reinforcement learning, URLLC users and eMBB users in the MEC system can be used as agents to learn distributed and autonomous learning joint allocation strategies of spectrum resources and computing resources, which realizes the minimum delay while ensuring the strict time delay constraints of URLLC users. The purpose of the total cost of time delay and energy consumption of all URLLC users and eMBB users in the system; at the same time, the present invention establishes a reinforcement learning model for the joint allocation of spectrum resources and computing resources for URLLC users and eMBB users. The function can obtain the overall optimal solution and achieve good training convergence performance; the present invention designs a distributed resource allocation algorithm, each agent maintains a Q value table separately, and performs action selection according to its own criteria so that the overall Q value table The dimensionality is lower, which achieves lower algorithm complexity.

Description

technical field [0001] The invention belongs to the field of wireless communication, relates to the joint allocation of spectrum resources and computing resources, and particularly relates to a method for joint allocation of spectrum resources and computing resources of URLLC users and eMBB users in a MEC network. Background technique [0002] At its 22nd meeting, the International Telecommunication Union (ITU) clarified that 5G networks mainly cover three major application scenarios: Ultra-Reliable Low-Latency Communication (URLLC), Enhanced Mobile Broadband (eMBB) and Massive Machine Communication (mMTC). According to the 5G development strategy, the coexistence of URLLC and eMBB services will be a common scenario of 5G. The eMBB service has a large amount of data and a high data rate. The URLLC service has low latency, high reliability and high priority. URLLC users and eMBB users will inevitably compete for various resources in the system, including spectrum resources ...

AI Technical Summary

Problems solved by technology

The centralized resource allocation method assumes that the base station has real-time global channel state information, and the base station controls the allocation of spectrum resources and computing resources for all users. However, the base station needs huge signaling overhead to obtain global channel state information. In the future massive wireless device scenarios Under the circumstances, it is difficult for the base station to have real-time global information

The distributed resource allocation method is mainly completed based on game theory and decomposition technology. The game theory method models users as game players for competitive games until the Nash equilibrium state, but solving the Nash equilibrium state requires a large amount of information exchange between users, and requires It takes a lot of iterations to converge

Decomposition technology can be used to design a heuristic greedy algorithm to optimize resource allocation and unloading decisions in turn. After decomposition, repeated iterations are still required, and the complexity of the algorithm is very high.

Existing related research mainly focuses on optimizing the offloading strategy and spectrum resource allocation, assuming that the computing resources at the MEC server are evenly distributed to each user, ignoring the benefits brought by the joint allocation of spectrum resources and all computing resources

Images