A Fuzzy-Logic-Based Load Balancing Scheme for a Satellite–Terrestrial Integrated Network
With the development of communication systems, users are becoming more widely distributed and require higher speed networks. A satellite–terrestrial integrated network could provide seamless coverage for these users. In previous studies of load balancing, initial access and load balancing are decide...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-09-01
|
| Series: | Electronics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2079-9292/11/17/2752 |
| _version_ | 1797495774367449088 |
|---|---|
| author | Yuehong Gao Haotian Yang Xiaoqi Wang Yihao Chen Chenyang Li Xin Zhang |
| author_facet | Yuehong Gao Haotian Yang Xiaoqi Wang Yihao Chen Chenyang Li Xin Zhang |
| author_sort | Yuehong Gao |
| collection | DOAJ |
| description | With the development of communication systems, users are becoming more widely distributed and require higher speed networks. A satellite–terrestrial integrated network could provide seamless coverage for these users. In previous studies of load balancing, initial access and load balancing are decided on based on signal reception and are performed reactively after the overloading occurs, which may not work well in satellite–terrestrial integrated networks. Therefore, this paper proposes a fuzzy-logic-based load balancing scheme. In this scheme, a fuzzy evaluation metric to pre-evaluate the user’s impact on overload is presented. The fuzzy logic system is constructed based on adaptive neuro fuzzy system, which takes the user’s signal reception, speed and data requirement as inputs. Then, the fuzzy-logic- and reinforcement-learning-based access is proposed to give an access decision for all users in the network to prevent overloading. Due to the large dimensions of action space, the reinforcement learning model is trained by the proposed fuzzy, deep, deterministic policy gradient. Next, the fuzzy-logic-based offloading algorithm is proposed to balance load after overloading. A simulation platform is established to evaluate the performance. Simulation results indicate that the proposed scheme can ensure load balance for a longer time than base line schemes while ensuring data rate of users. |
| first_indexed | 2024-03-10T01:55:25Z |
| format | Article |
| id | doaj.art-dab1e6f682c9416293bd12a3b676355a |
| institution | Directory Open Access Journal |
| issn | 2079-9292 |
| language | English |
| last_indexed | 2024-03-10T01:55:25Z |
| publishDate | 2022-09-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Electronics |
| spelling | doaj.art-dab1e6f682c9416293bd12a3b676355a2023-11-23T12:59:22ZengMDPI AGElectronics2079-92922022-09-011117275210.3390/electronics11172752A Fuzzy-Logic-Based Load Balancing Scheme for a Satellite–Terrestrial Integrated NetworkYuehong Gao0Haotian Yang1Xiaoqi Wang2Yihao Chen3Chenyang Li4Xin Zhang5School of Information and Communication Engineering, Beijing University of Posts and Telecommunications, Beijing 100876, ChinaSchool of Information and Communication Engineering, Beijing University of Posts and Telecommunications, Beijing 100876, ChinaSchool of Information and Communication Engineering, Beijing University of Posts and Telecommunications, Beijing 100876, ChinaSchool of Information and Communication Engineering, Beijing University of Posts and Telecommunications, Beijing 100876, ChinaSchool of Information and Communication Engineering, Beijing University of Posts and Telecommunications, Beijing 100876, ChinaSchool of Information and Communication Engineering, Beijing University of Posts and Telecommunications, Beijing 100876, ChinaWith the development of communication systems, users are becoming more widely distributed and require higher speed networks. A satellite–terrestrial integrated network could provide seamless coverage for these users. In previous studies of load balancing, initial access and load balancing are decided on based on signal reception and are performed reactively after the overloading occurs, which may not work well in satellite–terrestrial integrated networks. Therefore, this paper proposes a fuzzy-logic-based load balancing scheme. In this scheme, a fuzzy evaluation metric to pre-evaluate the user’s impact on overload is presented. The fuzzy logic system is constructed based on adaptive neuro fuzzy system, which takes the user’s signal reception, speed and data requirement as inputs. Then, the fuzzy-logic- and reinforcement-learning-based access is proposed to give an access decision for all users in the network to prevent overloading. Due to the large dimensions of action space, the reinforcement learning model is trained by the proposed fuzzy, deep, deterministic policy gradient. Next, the fuzzy-logic-based offloading algorithm is proposed to balance load after overloading. A simulation platform is established to evaluate the performance. Simulation results indicate that the proposed scheme can ensure load balance for a longer time than base line schemes while ensuring data rate of users.https://www.mdpi.com/2079-9292/11/17/2752load balancingfuzzy logicreinforcement learningsatellite–terrestrial network |
| spellingShingle | Yuehong Gao Haotian Yang Xiaoqi Wang Yihao Chen Chenyang Li Xin Zhang A Fuzzy-Logic-Based Load Balancing Scheme for a Satellite–Terrestrial Integrated Network Electronics load balancing fuzzy logic reinforcement learning satellite–terrestrial network |
| title | A Fuzzy-Logic-Based Load Balancing Scheme for a Satellite–Terrestrial Integrated Network |
| title_full | A Fuzzy-Logic-Based Load Balancing Scheme for a Satellite–Terrestrial Integrated Network |
| title_fullStr | A Fuzzy-Logic-Based Load Balancing Scheme for a Satellite–Terrestrial Integrated Network |
| title_full_unstemmed | A Fuzzy-Logic-Based Load Balancing Scheme for a Satellite–Terrestrial Integrated Network |
| title_short | A Fuzzy-Logic-Based Load Balancing Scheme for a Satellite–Terrestrial Integrated Network |
| title_sort | fuzzy logic based load balancing scheme for a satellite terrestrial integrated network |
| topic | load balancing fuzzy logic reinforcement learning satellite–terrestrial network |
| url | https://www.mdpi.com/2079-9292/11/17/2752 |
| work_keys_str_mv | AT yuehonggao afuzzylogicbasedloadbalancingschemeforasatelliteterrestrialintegratednetwork AT haotianyang afuzzylogicbasedloadbalancingschemeforasatelliteterrestrialintegratednetwork AT xiaoqiwang afuzzylogicbasedloadbalancingschemeforasatelliteterrestrialintegratednetwork AT yihaochen afuzzylogicbasedloadbalancingschemeforasatelliteterrestrialintegratednetwork AT chenyangli afuzzylogicbasedloadbalancingschemeforasatelliteterrestrialintegratednetwork AT xinzhang afuzzylogicbasedloadbalancingschemeforasatelliteterrestrialintegratednetwork AT yuehonggao fuzzylogicbasedloadbalancingschemeforasatelliteterrestrialintegratednetwork AT haotianyang fuzzylogicbasedloadbalancingschemeforasatelliteterrestrialintegratednetwork AT xiaoqiwang fuzzylogicbasedloadbalancingschemeforasatelliteterrestrialintegratednetwork AT yihaochen fuzzylogicbasedloadbalancingschemeforasatelliteterrestrialintegratednetwork AT chenyangli fuzzylogicbasedloadbalancingschemeforasatelliteterrestrialintegratednetwork AT xinzhang fuzzylogicbasedloadbalancingschemeforasatelliteterrestrialintegratednetwork |