Pub Date : 2021-07-28DOI: 10.1109/iccc52777.2021.9580429
Jing Zhou, Wenyi Zhang
This paper considers the bandlimited optical intensity channel (BLOIC), which is a basic channel model in optical wireless communications, like the role of the bandlimited additive white Gaussian noise channel in radio-frequency and wireline communications. We investigate achievable information rate of pulse amplitude modulation (PAM) in the BLOIC. A lower bound and an approximation for the information rate are derived, which reduce the gap between existing capacity lower and upper bounds for the BLOIC. Our methods are based on classical results on the discrete-time intersymbol interference (ISI) channels.
{"title":"New Achievability Results for the Bandlimited Optical Intensity Channel","authors":"Jing Zhou, Wenyi Zhang","doi":"10.1109/iccc52777.2021.9580429","DOIUrl":"https://doi.org/10.1109/iccc52777.2021.9580429","url":null,"abstract":"This paper considers the bandlimited optical intensity channel (BLOIC), which is a basic channel model in optical wireless communications, like the role of the bandlimited additive white Gaussian noise channel in radio-frequency and wireline communications. We investigate achievable information rate of pulse amplitude modulation (PAM) in the BLOIC. A lower bound and an approximation for the information rate are derived, which reduce the gap between existing capacity lower and upper bounds for the BLOIC. Our methods are based on classical results on the discrete-time intersymbol interference (ISI) channels.","PeriodicalId":425118,"journal":{"name":"2021 IEEE/CIC International Conference on Communications in China (ICCC)","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123031691","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-07-28DOI: 10.1109/iccc52777.2021.9580260
Zhiruo Yan, Zhi Zhang, Yue Meng
With the increase of the number of intelligent users, massive machine-type communications (mMTC), which can accommodate massive users, will play an important role. Unmanned aerial vehicle (UAV) has attracted a lot of attention due to the high mobility. However, both machine-type communications devices (MTCDs) and UAVs are battery-powered, therefore they have limited energy storage. In this paper, we focus on energy efficiency optimization in UAV-assisted mMTC networks with altitude differences. Considering the altitude differences of MTCDs, the Euclidean distances between MTCDs are in three dimensions. Besides, the altitudes of clustering centers are different, which results in the different altitudes of the hovering positions. To optimize the energy efficiency of MTCDs, a hovering positions selection algorithm based on three-dimensional clustering (3D-HPSA) is proposed. Meanwhile, a Discrete Cuckoo Search Algorithm with Genetic Mutation Operators (GMO-DCSA) is proposed to optimize the flight distance and the energy efficiency of UAV. Simulation results show that the proposed algorithms have superior performances compared with the existing works.
{"title":"Energy Efficiency Optimization for UAV-assisted mMTC Networks with Altitude Differences","authors":"Zhiruo Yan, Zhi Zhang, Yue Meng","doi":"10.1109/iccc52777.2021.9580260","DOIUrl":"https://doi.org/10.1109/iccc52777.2021.9580260","url":null,"abstract":"With the increase of the number of intelligent users, massive machine-type communications (mMTC), which can accommodate massive users, will play an important role. Unmanned aerial vehicle (UAV) has attracted a lot of attention due to the high mobility. However, both machine-type communications devices (MTCDs) and UAVs are battery-powered, therefore they have limited energy storage. In this paper, we focus on energy efficiency optimization in UAV-assisted mMTC networks with altitude differences. Considering the altitude differences of MTCDs, the Euclidean distances between MTCDs are in three dimensions. Besides, the altitudes of clustering centers are different, which results in the different altitudes of the hovering positions. To optimize the energy efficiency of MTCDs, a hovering positions selection algorithm based on three-dimensional clustering (3D-HPSA) is proposed. Meanwhile, a Discrete Cuckoo Search Algorithm with Genetic Mutation Operators (GMO-DCSA) is proposed to optimize the flight distance and the energy efficiency of UAV. Simulation results show that the proposed algorithms have superior performances compared with the existing works.","PeriodicalId":425118,"journal":{"name":"2021 IEEE/CIC International Conference on Communications in China (ICCC)","volume":"62 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121170266","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-07-28DOI: 10.1109/iccc52777.2021.9580332
Chaokun Xiao, Haomiao Huo, Wei Xu, Huan-Yao Sun, Chunjie Shu
Reconfigurable intelligent surface (RIS) is a promising technology for realizing cost-and-energy efficient wideband communication in future wireless communications. We construct a prototype of the RIS communication which realizes a new radiofrequency (RF) chain-free architecture. This experimental prototype using RIS is tested at 5.8 GHz and achieves a 20 MHz data transmission efficiently. We also propose a deep neural network-based beam alignment for the RIS communication, which validated by experiment tests with the RIS system consisting of 16×16 meta-material reflecting elements in indoor environment. The provided results show that the proposed method can achieve beam alignment in experiment tests. It improves the performance of the RIS communication with reduced overhead.
{"title":"Reconfigurable Intelligent Surface-Aided Indoor Communication With Neural Beam Alignment","authors":"Chaokun Xiao, Haomiao Huo, Wei Xu, Huan-Yao Sun, Chunjie Shu","doi":"10.1109/iccc52777.2021.9580332","DOIUrl":"https://doi.org/10.1109/iccc52777.2021.9580332","url":null,"abstract":"Reconfigurable intelligent surface (RIS) is a promising technology for realizing cost-and-energy efficient wideband communication in future wireless communications. We construct a prototype of the RIS communication which realizes a new radiofrequency (RF) chain-free architecture. This experimental prototype using RIS is tested at 5.8 GHz and achieves a 20 MHz data transmission efficiently. We also propose a deep neural network-based beam alignment for the RIS communication, which validated by experiment tests with the RIS system consisting of 16×16 meta-material reflecting elements in indoor environment. The provided results show that the proposed method can achieve beam alignment in experiment tests. It improves the performance of the RIS communication with reduced overhead.","PeriodicalId":425118,"journal":{"name":"2021 IEEE/CIC International Conference on Communications in China (ICCC)","volume":"68 12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116419573","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-07-28DOI: 10.1109/iccc52777.2021.9580396
Yuqing Jia, Lei Xie, Hui-fang Chen
Covertness is playing an increasingly important role in underwater acoustic communication (UAC). However, traditional underwater acoustic communication signals with specified characteristics cannot ensure the concealment of the communication signal. To solve the problem, a bionic covert UAC scheme based on dolphin whistle with time-delay, abbreviated as BCUAC-TD, is proposed in this paper. In the proposed BCUAC-TD scheme, we divide the time-frequency structure (TFS) into several segments uniformly to represent different symbol signals, and the time-delay is used to carry different information. Moreover, the energy compensation and the virtual time reversal mirror (VTRM) are adopted to improve the performance the demodulation. The performance of proposed BCUAC-TD scheme is evaluated by simulations under simulated and experimental channels, and the covertness and effectiveness of proposed covert communication scheme are verified.
{"title":"Bionic Covert Underwater Acoustic Communication Based on Dolphin Whistle with Time-delay","authors":"Yuqing Jia, Lei Xie, Hui-fang Chen","doi":"10.1109/iccc52777.2021.9580396","DOIUrl":"https://doi.org/10.1109/iccc52777.2021.9580396","url":null,"abstract":"Covertness is playing an increasingly important role in underwater acoustic communication (UAC). However, traditional underwater acoustic communication signals with specified characteristics cannot ensure the concealment of the communication signal. To solve the problem, a bionic covert UAC scheme based on dolphin whistle with time-delay, abbreviated as BCUAC-TD, is proposed in this paper. In the proposed BCUAC-TD scheme, we divide the time-frequency structure (TFS) into several segments uniformly to represent different symbol signals, and the time-delay is used to carry different information. Moreover, the energy compensation and the virtual time reversal mirror (VTRM) are adopted to improve the performance the demodulation. The performance of proposed BCUAC-TD scheme is evaluated by simulations under simulated and experimental channels, and the covertness and effectiveness of proposed covert communication scheme are verified.","PeriodicalId":425118,"journal":{"name":"2021 IEEE/CIC International Conference on Communications in China (ICCC)","volume":"102 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115576984","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-07-28DOI: 10.1109/iccc52777.2021.9580385
Hua-rui Zhang, Qiang Li, Yijin Zhang, Xun Li
Performance optimization of the inter-satellite link is the key to improve the performance of satellite networks. This article proposes a dynamic power allocation method for the inter-satellite link of Low Earth Orbit (LEO)/Medium Earth Orbit (MEO) satellites based on the computing power of LEO satellites. A utility function is designed according to the transmission characteristic of the inter-satellite link. The existence of the Nash Equilibrium (NE) of the utility function is proved based on the super-modular game theory. The LEO satellite obtains its balanced solution of the transmission power through the Newton iteration method. In this process, based on the initial orbit parameters of the satellite and the satellite operating time, the inter-satellite link distance is predicted through the spherical geometric relationship between the LEO/MEO satellites, so that the signal-to-interference and noise ratio (SINR) can be estimated in advance. The MEO satellite controls the penalty factor to enhance the utility of the entire network. Simulation results show that the proposed power allocation method achieves the purpose of saving power resources while improving system performance.
{"title":"Game Theory Based Power Allocation Method for Inter-satellite Links in LEO/MEO Two-layered Satellite Networks","authors":"Hua-rui Zhang, Qiang Li, Yijin Zhang, Xun Li","doi":"10.1109/iccc52777.2021.9580385","DOIUrl":"https://doi.org/10.1109/iccc52777.2021.9580385","url":null,"abstract":"Performance optimization of the inter-satellite link is the key to improve the performance of satellite networks. This article proposes a dynamic power allocation method for the inter-satellite link of Low Earth Orbit (LEO)/Medium Earth Orbit (MEO) satellites based on the computing power of LEO satellites. A utility function is designed according to the transmission characteristic of the inter-satellite link. The existence of the Nash Equilibrium (NE) of the utility function is proved based on the super-modular game theory. The LEO satellite obtains its balanced solution of the transmission power through the Newton iteration method. In this process, based on the initial orbit parameters of the satellite and the satellite operating time, the inter-satellite link distance is predicted through the spherical geometric relationship between the LEO/MEO satellites, so that the signal-to-interference and noise ratio (SINR) can be estimated in advance. The MEO satellite controls the penalty factor to enhance the utility of the entire network. Simulation results show that the proposed power allocation method achieves the purpose of saving power resources while improving system performance.","PeriodicalId":425118,"journal":{"name":"2021 IEEE/CIC International Conference on Communications in China (ICCC)","volume":"61 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116121188","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-07-28DOI: 10.1109/iccc52777.2021.9580325
Zhiping Yan, Chonglin Gu, Yue Gu, Hejiao Huang
Ensuring the security of 5G Authentication and Key Agreement (5G AKA) is utmost important in the context of the upcoming widespread use of 5G. In this paper, we focus on the formal specification and security verification of 5G AKA. We propose three attack methods including: Sequence Number (SQN) mismatch attack, Subscription Concealed Identifier (SUCI) replay attack and bogus serving network (SN) attack based on the most general assumptions on entities. For the three attacks occurred in wireless channel and SN, we also give an improved scheme by adopting challenge response mechanism and designing Unique Identifier (UNI) for the AKA protocol. The former is used to prevent an attacker with a fake SN interfering the authentication process, while the latter ensures the security of messages in wireless channel. With the advantages such as graphical nature, the simplicity of modeling and the firm mathematical foundation, Petri net is applied for the attack-driven modeling. To the best of our knowledge, this is the first time that Petri net has been introduced to validate security scheme for 5G AKA protocol in the literature.
{"title":"Security Verification and Improvement of 5G AKA Protocol Based on Petri-net","authors":"Zhiping Yan, Chonglin Gu, Yue Gu, Hejiao Huang","doi":"10.1109/iccc52777.2021.9580325","DOIUrl":"https://doi.org/10.1109/iccc52777.2021.9580325","url":null,"abstract":"Ensuring the security of 5G Authentication and Key Agreement (5G AKA) is utmost important in the context of the upcoming widespread use of 5G. In this paper, we focus on the formal specification and security verification of 5G AKA. We propose three attack methods including: Sequence Number (SQN) mismatch attack, Subscription Concealed Identifier (SUCI) replay attack and bogus serving network (SN) attack based on the most general assumptions on entities. For the three attacks occurred in wireless channel and SN, we also give an improved scheme by adopting challenge response mechanism and designing Unique Identifier (UNI) for the AKA protocol. The former is used to prevent an attacker with a fake SN interfering the authentication process, while the latter ensures the security of messages in wireless channel. With the advantages such as graphical nature, the simplicity of modeling and the firm mathematical foundation, Petri net is applied for the attack-driven modeling. To the best of our knowledge, this is the first time that Petri net has been introduced to validate security scheme for 5G AKA protocol in the literature.","PeriodicalId":425118,"journal":{"name":"2021 IEEE/CIC International Conference on Communications in China (ICCC)","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116175100","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
In this paper, we study price-based resource allocation for a cellular downlink non-orthogonal multiple access (NOMA) network with hardware impairments. The pricing and power purchase strategies between the base station (BS) and the users are modeled by the Stackelberg game. To tackle this problem, we first use a backward tracking approach to simplify the revenue maximization problem of BS as an equivalent resource allocation problem. Then the optimization problem is solved by the quadratic transform method. Finally, we propose a price-based resource allocation algorithm based on the Stackelberg game to maximize the BS's revenue. Simulation results show that compared with the existing algorithm with perfect hardware, our proposed price-based resource allocation algorithm has a better performance according to the revenue of the BS and the sum rate of users.
{"title":"Price-Based Resource Allocation in NOMA System with Hardware Impairments","authors":"Zheng-qiang Wang, Zhen Zhang, Siyu Qing, Yongjun Xu, Xiaoyu Wan, Zi-fu Fan","doi":"10.1109/iccc52777.2021.9580231","DOIUrl":"https://doi.org/10.1109/iccc52777.2021.9580231","url":null,"abstract":"In this paper, we study price-based resource allocation for a cellular downlink non-orthogonal multiple access (NOMA) network with hardware impairments. The pricing and power purchase strategies between the base station (BS) and the users are modeled by the Stackelberg game. To tackle this problem, we first use a backward tracking approach to simplify the revenue maximization problem of BS as an equivalent resource allocation problem. Then the optimization problem is solved by the quadratic transform method. Finally, we propose a price-based resource allocation algorithm based on the Stackelberg game to maximize the BS's revenue. Simulation results show that compared with the existing algorithm with perfect hardware, our proposed price-based resource allocation algorithm has a better performance according to the revenue of the BS and the sum rate of users.","PeriodicalId":425118,"journal":{"name":"2021 IEEE/CIC International Conference on Communications in China (ICCC)","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126994394","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-07-28DOI: 10.1109/ICCC52777.2021.9580239
Fan Jiang, Jin Wang, Changyin Sun
To reduce the burden on fronthaul link as well as transmission delay, this paper proposes a cooperative edge caching strategy based on the deep Q-learning (DQN) algorithm considering the cooperative caching behavior between fog access points (F-APs) for Fog Radio Access Network (F-RAN). Specifically, to obtain the desired content popularity, we first predict the user preference probability with the topic model. Furthermore, considering the coupled multi-variable nature of the optimizing problem, a deep reinforcement learning (DRL) based content caching strategy is adopted to acquire the optimal content placement policy by combining the content popularity prediction results and content popularity. Finally, numerical simulation results prove the proposed scheme can reduce the average download delay compared with the existing algorithms.
{"title":"Deep Q-Learning-Based Cooperative Caching Strategy for Fog Radio Access Networks","authors":"Fan Jiang, Jin Wang, Changyin Sun","doi":"10.1109/ICCC52777.2021.9580239","DOIUrl":"https://doi.org/10.1109/ICCC52777.2021.9580239","url":null,"abstract":"To reduce the burden on fronthaul link as well as transmission delay, this paper proposes a cooperative edge caching strategy based on the deep Q-learning (DQN) algorithm considering the cooperative caching behavior between fog access points (F-APs) for Fog Radio Access Network (F-RAN). Specifically, to obtain the desired content popularity, we first predict the user preference probability with the topic model. Furthermore, considering the coupled multi-variable nature of the optimizing problem, a deep reinforcement learning (DRL) based content caching strategy is adopted to acquire the optimal content placement policy by combining the content popularity prediction results and content popularity. Finally, numerical simulation results prove the proposed scheme can reduce the average download delay compared with the existing algorithms.","PeriodicalId":425118,"journal":{"name":"2021 IEEE/CIC International Conference on Communications in China (ICCC)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125800778","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-07-28DOI: 10.1109/iccc52777.2021.9580422
Shunan Yang, Yuan Liu
Federated learning (FL) is a distributed learning method where multiple users train and upload their local models or gradients to an edge server for artificial intelligence (AI) model training. However, the local model uploading causes information leakage on local data. Differential privacy (DP) is a random mechanism that adds uncertainty to protect privacy for dataset. In this paper, we study a multi-cell FL network where each cell is a FL system. Each user adds artificial noise in its uploaded local gradient, and the multi-cell interference is exploited to enhance the DP levels. The studied problem is formulated as a mean square error (MSE) minimization problem subject to the DP and power constraints, by controlling the transmission power on local gradient and artificial noise of each user. Our results show that multi-cell interference is beneficial to DP.
{"title":"Differentially Private Federated Learning in Multi-Cell Networks","authors":"Shunan Yang, Yuan Liu","doi":"10.1109/iccc52777.2021.9580422","DOIUrl":"https://doi.org/10.1109/iccc52777.2021.9580422","url":null,"abstract":"Federated learning (FL) is a distributed learning method where multiple users train and upload their local models or gradients to an edge server for artificial intelligence (AI) model training. However, the local model uploading causes information leakage on local data. Differential privacy (DP) is a random mechanism that adds uncertainty to protect privacy for dataset. In this paper, we study a multi-cell FL network where each cell is a FL system. Each user adds artificial noise in its uploaded local gradient, and the multi-cell interference is exploited to enhance the DP levels. The studied problem is formulated as a mean square error (MSE) minimization problem subject to the DP and power constraints, by controlling the transmission power on local gradient and artificial noise of each user. Our results show that multi-cell interference is beneficial to DP.","PeriodicalId":425118,"journal":{"name":"2021 IEEE/CIC International Conference on Communications in China (ICCC)","volume":"76 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115123262","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
In this paper, we study the integration of device-to-device communication into a non-orthogonal multiple access system. To deal with the complex co-channel interference resulting from the dense spectral reuse, we aim to maximize the sum proportional bit rate by jointly optimizing mode selection (MS) and power allocation (PA). Considering the high complexity of the original problem and the dynamics of the wireless environment, we propose an online mechanism with a double-layer structure by efficiently combining machine learning with optimization theory. In particular, when the MS scheme is given, the remaining nonconvex PA problem can be equivalently transformed into a convex one under certain manipulations. Based on the above optimum, a deep reinforcement learning-based online mechanism is designed and it constantly refines the output MS scheme generated from a deep neural network by utilizing the recent historical experiences via reinforcement learning. Finally, simulations are conducted to validate the superiority of the proposed mechanism in balancing the fundamental tradeoff between performance and online computational time.
{"title":"Joint Mode Selection And Power Allocation for NOMA Systems With D2D Communication","authors":"Rui Tang, Ruizhi Zhang, Yuanman Xia, Yihong Zhao, Jinpu He, Yu Long","doi":"10.1109/iccc52777.2021.9580380","DOIUrl":"https://doi.org/10.1109/iccc52777.2021.9580380","url":null,"abstract":"In this paper, we study the integration of device-to-device communication into a non-orthogonal multiple access system. To deal with the complex co-channel interference resulting from the dense spectral reuse, we aim to maximize the sum proportional bit rate by jointly optimizing mode selection (MS) and power allocation (PA). Considering the high complexity of the original problem and the dynamics of the wireless environment, we propose an online mechanism with a double-layer structure by efficiently combining machine learning with optimization theory. In particular, when the MS scheme is given, the remaining nonconvex PA problem can be equivalently transformed into a convex one under certain manipulations. Based on the above optimum, a deep reinforcement learning-based online mechanism is designed and it constantly refines the output MS scheme generated from a deep neural network by utilizing the recent historical experiences via reinforcement learning. Finally, simulations are conducted to validate the superiority of the proposed mechanism in balancing the fundamental tradeoff between performance and online computational time.","PeriodicalId":425118,"journal":{"name":"2021 IEEE/CIC International Conference on Communications in China (ICCC)","volume":"111 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128025653","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：