A dynamic optimization method for the competition window value of LTE and wifi coexistence based on q-learning algorithm

Abstract

The present invention relates to a dynamic optimization method of LTE and WiFi coexistence competition window value based on Q-learning algorithm, belongs to the field of communication technology, comprising steps: 1, setting the state set and action set of LAA small base station; 2, initializing the state of LAA small base station 3. Calculate the initial state value of the LAA small base station; 4. Calculate the Logistic chaotic mapping sequence according to the formula, and map it to the behavior value set of the LAA small base station and randomly select a behavior a t (i); 5. Executing behavior a t After (i), get the environmental reward value r t , enter the next state s t+1 6. Update the behavioral Q-value function of the LAA small base station; 7. Let t←t+1, repeat steps 4-6 until the goal is achieved. The present invention can improve the frequency spectrum utilization rate of the channel under the condition of ensuring user fairness, expand the system capacity of the next-generation communication system at the same time, provide better service quality for users, and improve user experience.

Description

technical field [0001] The invention belongs to the technical field of communication, and relates to a dynamic optimization method for a contention window value of coexistence of LTE and WiFi based on a Q-learning algorithm. Background technique [0002] Wireless mobile communication will play an increasingly important role in the future information communication system due to its widespread use and convenient access. With the rapid development of mobile Internet and Internet of Things services, mobile data traffic has increased sharply, resulting in a shortage of licensed frequency bands. Therefore, operators hope to explore unlicensed spectrum to supplement licensed spectrum. LTE-U (LTE-Unlicensed) proposed by 3GPP is also called Licensed Assisted Access (LAA), which aims to apply LTE technology to unlicensed frequency bands while maintaining the original LTE protocol specifications as much as possible ( Such as near 5GHz), by deploying small base stations in the unlicens...

AI Technical Summary

Problems solved by technology

[0004] Currently, existing backoff mechanisms lack a dynamic learning process, such as binary exponential backoff mechanism, fixed contention window backoff mechanism, etc., and cannot flexibly adjust system parameters according to real-time scenarios, which objectively limits the improvement of spectrum utilization of coexistence system channels

Images