Pub Date : 2024-11-20DOI: 10.1109/LCOMM.2024.3502716
Tao Luo;Hancheng Lu;Baolin Chong
User-centric networking is expected to be a promising technology to implement ultra-reliable and low-latency communication (URLLC). However, the densely deployed access points (APs) in a user-centric network (UCN) will involve significant hardware costs and energy consumption. To address this issue, we propose a reconfigurable intelligent surface (RIS)-aided UCN for URLLC. Then, a joint optimization problem with consideration of active beamforming at APs and passive beamforming at RISs is formulated to achieve optimal energy efficiency (EE). Since the problem is intractable and non-convex, we develop an alternating optimization algorithm based on the inner approximation framework to solve it efficiently. Numerical results verify that the proposed algorithm outperforms baseline algorithms regarding EE. Particularly, with the proposed algorithm, our RIS-aided UCN achieves up to 147% performance gains in terms of EE compared to traditional UCN.
{"title":"Energy Efficiency Optimization for URLLC in RIS-Aided User-Centric Networks","authors":"Tao Luo;Hancheng Lu;Baolin Chong","doi":"10.1109/LCOMM.2024.3502716","DOIUrl":"https://doi.org/10.1109/LCOMM.2024.3502716","url":null,"abstract":"User-centric networking is expected to be a promising technology to implement ultra-reliable and low-latency communication (URLLC). However, the densely deployed access points (APs) in a user-centric network (UCN) will involve significant hardware costs and energy consumption. To address this issue, we propose a reconfigurable intelligent surface (RIS)-aided UCN for URLLC. Then, a joint optimization problem with consideration of active beamforming at APs and passive beamforming at RISs is formulated to achieve optimal energy efficiency (EE). Since the problem is intractable and non-convex, we develop an alternating optimization algorithm based on the inner approximation framework to solve it efficiently. Numerical results verify that the proposed algorithm outperforms baseline algorithms regarding EE. Particularly, with the proposed algorithm, our RIS-aided UCN achieves up to 147% performance gains in terms of EE compared to traditional UCN.","PeriodicalId":13197,"journal":{"name":"IEEE Communications Letters","volume":"29 1","pages":"110-114"},"PeriodicalIF":3.7,"publicationDate":"2024-11-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142940867","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-11-20DOI: 10.1109/LCOMM.2024.3503754
Qin Zhang;Han Wu;Hai Li;Zhengyu Song;Shujuan Hou
In this letter, we investigate a simultaneously transmitting and reflecting reconfigurable intelligent surface (STAR-RIS) aided integrated sensing and communication (ISAC) system. Our object is to maximize the energy efficiency (EE) of the ISAC system by jointly optimizing the beamforming at the base station (BS), the transmitting/reflecting coefficient matrices of the STAR-RIS, as well as the deployment location of the STAR-RIS. Since the formulated problem is non-convex, we propose an alternative optimization scheme by decomposing the original problem into three sub-problems, where the sub-problems are solved based on semidefinite relaxation (SDR) and fractional programming. Simulation results demonstrate that the STAR-RIS aided ISAC system achieves a higher EE than conventional RIS scheme, and the location optimization for STAR-RIS can significantly improve the system EE. Furthermore, the EE declines rapidly when the radar beampattern gain threshold increases to a larger value.
{"title":"Joint Location and Beamforming Design for Energy Efficient STAR-RIS-Aided ISAC Systems","authors":"Qin Zhang;Han Wu;Hai Li;Zhengyu Song;Shujuan Hou","doi":"10.1109/LCOMM.2024.3503754","DOIUrl":"https://doi.org/10.1109/LCOMM.2024.3503754","url":null,"abstract":"In this letter, we investigate a simultaneously transmitting and reflecting reconfigurable intelligent surface (STAR-RIS) aided integrated sensing and communication (ISAC) system. Our object is to maximize the energy efficiency (EE) of the ISAC system by jointly optimizing the beamforming at the base station (BS), the transmitting/reflecting coefficient matrices of the STAR-RIS, as well as the deployment location of the STAR-RIS. Since the formulated problem is non-convex, we propose an alternative optimization scheme by decomposing the original problem into three sub-problems, where the sub-problems are solved based on semidefinite relaxation (SDR) and fractional programming. Simulation results demonstrate that the STAR-RIS aided ISAC system achieves a higher EE than conventional RIS scheme, and the location optimization for STAR-RIS can significantly improve the system EE. Furthermore, the EE declines rapidly when the radar beampattern gain threshold increases to a larger value.","PeriodicalId":13197,"journal":{"name":"IEEE Communications Letters","volume":"29 1","pages":"140-144"},"PeriodicalIF":3.7,"publicationDate":"2024-11-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142938510","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
In this letter, we propose a novel communication system for multiple Non-Orthogonal Multiple Access (NOMA)-based end-users, leveraging a mixed THz-RF wireless communication approach. The THz link serves as the backhaul communication link and is characterized by an $alpha -mu $ fading channel, path loss, absorption loss, and pointing errors. The sub-6 GHz RF carrier has been utilized for end-user connectivity. We incorporate hardware impairments (HI), channel state information (CSI) and, successive interference cancellation (SIC) errors at the receiver to capture realistic operating conditions. We have presented a mathematical framework for outage probability and average bit error rate and the asymptotic results to evaluate the proposed system’s effectiveness. The results are analyzed for various system parameters to provide further insights into system performance. Further, Monte Carlo simulations are performed to validate the analytical results.
{"title":"THz-RF Cooperative NOMA Communication System Incorporating Practical Constraints","authors":"Isha Khirwar;Akash Gupta;Aryan Bansal;Parul Garg;Bharat Verma","doi":"10.1109/LCOMM.2024.3503727","DOIUrl":"https://doi.org/10.1109/LCOMM.2024.3503727","url":null,"abstract":"In this letter, we propose a novel communication system for multiple Non-Orthogonal Multiple Access (NOMA)-based end-users, leveraging a mixed THz-RF wireless communication approach. The THz link serves as the backhaul communication link and is characterized by an \u0000<inline-formula> <tex-math>$alpha -mu $ </tex-math></inline-formula>\u0000 fading channel, path loss, absorption loss, and pointing errors. The sub-6 GHz RF carrier has been utilized for end-user connectivity. We incorporate hardware impairments (HI), channel state information (CSI) and, successive interference cancellation (SIC) errors at the receiver to capture realistic operating conditions. We have presented a mathematical framework for outage probability and average bit error rate and the asymptotic results to evaluate the proposed system’s effectiveness. The results are analyzed for various system parameters to provide further insights into system performance. Further, Monte Carlo simulations are performed to validate the analytical results.","PeriodicalId":13197,"journal":{"name":"IEEE Communications Letters","volume":"29 1","pages":"135-139"},"PeriodicalIF":3.7,"publicationDate":"2024-11-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142938511","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-11-20DOI: 10.1109/LCOMM.2024.3504372
Ali Amhaz;Mohamed Elhattab;Sanaa Sharafeddine;Chadi Assi
This letter examines a NOMA downlink scenario where the UAV is deployed to concurrently assist in communication and sensing functionalities, empowering ISAC technology. In this regard and with the goal of maximizing the average achievable rate, we formulate an optimization problem to determine the UAV trajectory, and beamforming vectors at the transmitting base station and UAV, while at the same time satisfy the quality of service constraints for communication users and sensing for a moving target in terms of Cramer Rao bound (CRB) metric. The formulated problem showed to be non-convex and hard to be solved because of the high coupling between the variables as well as the randomness in the environment due to the channels variations and the mobility of the target. For that reason, we adopted a reinforcement learning algorithm, namely, deep deterministic policy gradient (DDPG) approach to deal with the aforementioned problems. Numerical results proved the superiority of the presented model over traditional UAV trajectory benchmarks and the ability to gain knowledge from the environment.
{"title":"UAV-Assisted NOMA for Enhancing ISAC: A Deep Reinforcement Learning Solution","authors":"Ali Amhaz;Mohamed Elhattab;Sanaa Sharafeddine;Chadi Assi","doi":"10.1109/LCOMM.2024.3504372","DOIUrl":"https://doi.org/10.1109/LCOMM.2024.3504372","url":null,"abstract":"This letter examines a NOMA downlink scenario where the UAV is deployed to concurrently assist in communication and sensing functionalities, empowering ISAC technology. In this regard and with the goal of maximizing the average achievable rate, we formulate an optimization problem to determine the UAV trajectory, and beamforming vectors at the transmitting base station and UAV, while at the same time satisfy the quality of service constraints for communication users and sensing for a moving target in terms of Cramer Rao bound (CRB) metric. The formulated problem showed to be non-convex and hard to be solved because of the high coupling between the variables as well as the randomness in the environment due to the channels variations and the mobility of the target. For that reason, we adopted a reinforcement learning algorithm, namely, deep deterministic policy gradient (DDPG) approach to deal with the aforementioned problems. Numerical results proved the superiority of the presented model over traditional UAV trajectory benchmarks and the ability to gain knowledge from the environment.","PeriodicalId":13197,"journal":{"name":"IEEE Communications Letters","volume":"29 2","pages":"249-253"},"PeriodicalIF":3.7,"publicationDate":"2024-11-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143403992","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-11-19DOI: 10.1109/LCOMM.2024.3502152
Zonglong Chen;Songkang Huang;Ming Jiang
The high Doppler effect and severe multipath delay are among the major challenges in air-to-ground (A2G) communication scenarios, where the maximum multipath delay may exceed the duration of one or more orthogonal frequency division multiplexing (OFDM) symbols, resulting in severe inter-symbol interference (ISI). In this letter, we propose a new frame structure constituted by grouped training sequences (GTSs), OFDM symbols and guard interval (GI). Specifically, two GTSs are respectively prefixed and postfixed to several cyclic-prefix-free OFDM symbols for Doppler frequency offset (DFO) and multipath delay estimation. Moreover, a two-path serial ISI cancellation (TSIC) algorithm is designed to recover the transmitted signal. Compared with existing algorithms, the new scheme can reduce errors and increase the spectral efficiency of the system.
{"title":"Two-Path Serial Inter-Symbol-Interference Cancellation for Air-to-Ground Communication","authors":"Zonglong Chen;Songkang Huang;Ming Jiang","doi":"10.1109/LCOMM.2024.3502152","DOIUrl":"https://doi.org/10.1109/LCOMM.2024.3502152","url":null,"abstract":"The high Doppler effect and severe multipath delay are among the major challenges in air-to-ground (A2G) communication scenarios, where the maximum multipath delay may exceed the duration of one or more orthogonal frequency division multiplexing (OFDM) symbols, resulting in severe inter-symbol interference (ISI). In this letter, we propose a new frame structure constituted by grouped training sequences (GTSs), OFDM symbols and guard interval (GI). Specifically, two GTSs are respectively prefixed and postfixed to several cyclic-prefix-free OFDM symbols for Doppler frequency offset (DFO) and multipath delay estimation. Moreover, a two-path serial ISI cancellation (TSIC) algorithm is designed to recover the transmitted signal. Compared with existing algorithms, the new scheme can reduce errors and increase the spectral efficiency of the system.","PeriodicalId":13197,"journal":{"name":"IEEE Communications Letters","volume":"29 1","pages":"100-104"},"PeriodicalIF":3.7,"publicationDate":"2024-11-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142940873","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-11-18DOI: 10.1109/LCOMM.2024.3499956
Loc X. Nguyen;Kitae Kim;Ye Lin Tun;Sheikh Salman Hassan;Yan Kyaw Tun;Zhu Han;Choong Seon Hong
Semantic Communication (SemCom), notable for ensuring quality of service by jointly optimizing source and channel coding, effectively extracts data semantics, eliminates redundant information, and mitigates noise effects from wireless channel. However, most studies overlook multiple user scenarios and resource availability, limiting real-world applications. This letter addresses this gap by focusing on downlink communication from a base station to multiple users with varying computing capacities. Users employ variants of Swin transformer models for source decoding and a simple architecture for channel decoding. We propose a novel training procedure FRENCA, incorporating transfer learning and knowledge distillation to improve low-computing users’ performance. Extensive simulations validate the proposed methods.
{"title":"Optimizing Multi-User Semantic Communication via Transfer Learning and Knowledge Distillation","authors":"Loc X. Nguyen;Kitae Kim;Ye Lin Tun;Sheikh Salman Hassan;Yan Kyaw Tun;Zhu Han;Choong Seon Hong","doi":"10.1109/LCOMM.2024.3499956","DOIUrl":"https://doi.org/10.1109/LCOMM.2024.3499956","url":null,"abstract":"Semantic Communication (SemCom), notable for ensuring quality of service by jointly optimizing source and channel coding, effectively extracts data semantics, eliminates redundant information, and mitigates noise effects from wireless channel. However, most studies overlook multiple user scenarios and resource availability, limiting real-world applications. This letter addresses this gap by focusing on downlink communication from a base station to multiple users with varying computing capacities. Users employ variants of Swin transformer models for source decoding and a simple architecture for channel decoding. We propose a novel training procedure FRENCA, incorporating transfer learning and knowledge distillation to improve low-computing users’ performance. Extensive simulations validate the proposed methods.","PeriodicalId":13197,"journal":{"name":"IEEE Communications Letters","volume":"29 1","pages":"90-94"},"PeriodicalIF":3.7,"publicationDate":"2024-11-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142940875","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-11-18DOI: 10.1109/LCOMM.2024.3501956
Amin Mohajer;Javad Hajipour;Victor C. M. Leung
Network slicing and computation offloading play a pivotal role in enabling edge service providers to handle dynamic service demands effectively. However, traffic fluctuations and resource diversity pose significant challenges, often constrained by static configurations lacking flexibility. To overcome these limitations, this letter presents FlexSlice, a dynamic offloading framework designed to optimize resource allocation in mobile edge networks. Our approach leverages a sparse multi-head graph attention mechanism for precise traffic prediction, capturing complex spatio-temporal dependencies to enhance network slicing decisions. Additionally, we present an adaptive offloading strategy based on the twin delayed deep deterministic policy gradient algorithm, which incorporates twin critics and prioritized experience replay to improve decision-making under dynamic conditions. Simulation results confirm FlexSlice’s outstanding performance and adaptability in diverse operational scenarios, achieving higher profits and reliable quality of service.
{"title":"Dynamic Offloading in Mobile Edge Computing With Traffic-Aware Network Slicing and Adaptive TD3 Strategy","authors":"Amin Mohajer;Javad Hajipour;Victor C. M. Leung","doi":"10.1109/LCOMM.2024.3501956","DOIUrl":"https://doi.org/10.1109/LCOMM.2024.3501956","url":null,"abstract":"Network slicing and computation offloading play a pivotal role in enabling edge service providers to handle dynamic service demands effectively. However, traffic fluctuations and resource diversity pose significant challenges, often constrained by static configurations lacking flexibility. To overcome these limitations, this letter presents FlexSlice, a dynamic offloading framework designed to optimize resource allocation in mobile edge networks. Our approach leverages a sparse multi-head graph attention mechanism for precise traffic prediction, capturing complex spatio-temporal dependencies to enhance network slicing decisions. Additionally, we present an adaptive offloading strategy based on the twin delayed deep deterministic policy gradient algorithm, which incorporates twin critics and prioritized experience replay to improve decision-making under dynamic conditions. Simulation results confirm FlexSlice’s outstanding performance and adaptability in diverse operational scenarios, achieving higher profits and reliable quality of service.","PeriodicalId":13197,"journal":{"name":"IEEE Communications Letters","volume":"29 1","pages":"95-99"},"PeriodicalIF":3.7,"publicationDate":"2024-11-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142940876","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-11-15DOI: 10.1109/LCOMM.2024.3499745
Amirhassan Babazadeh Darabi;Sinem Coleri
Diffusion models offer a promising alternative to Deep Reinforcement Learning (DRL) for resource allocation in wireless networks due to their capability to model complex data distributions with greater accuracy, yet their potential remains largely unexplored. This letter proposes a diffusion model-based approach for Wireless Networked Control Systems (WNCSs) to minimize power consumption by optimizing the sampling period, blocklength, and packet error probability within the finite blocklength regime. The problem is simplified to optimizing blocklength through optimality conditions, and a dataset of channel gains and optimal blocklengths is generated via an optimization theory-based solution. The Denoising Diffusion Probabilistic Model (DDPM) is employed to generate optimal blocklength values, conditioned on channel state information (CSI). The core idea is to train the diffusion model to generate blocklength values from noise, essentially replicating the process by which the optimization solution is derived. Extensive simulations reveal that the proposed approach surpasses existing DRL-based methods, achieving near-optimal performance in terms of total power consumption. Additionally, the proposed method reduces critical constraint violations by up to eighteen times, further highlighting the enhanced accuracy of the solution.
{"title":"Diffusion Model Based Resource Allocation Strategy in Ultra-Reliable Wireless Networked Control Systems","authors":"Amirhassan Babazadeh Darabi;Sinem Coleri","doi":"10.1109/LCOMM.2024.3499745","DOIUrl":"https://doi.org/10.1109/LCOMM.2024.3499745","url":null,"abstract":"Diffusion models offer a promising alternative to Deep Reinforcement Learning (DRL) for resource allocation in wireless networks due to their capability to model complex data distributions with greater accuracy, yet their potential remains largely unexplored. This letter proposes a diffusion model-based approach for Wireless Networked Control Systems (WNCSs) to minimize power consumption by optimizing the sampling period, blocklength, and packet error probability within the finite blocklength regime. The problem is simplified to optimizing blocklength through optimality conditions, and a dataset of channel gains and optimal blocklengths is generated via an optimization theory-based solution. The Denoising Diffusion Probabilistic Model (DDPM) is employed to generate optimal blocklength values, conditioned on channel state information (CSI). The core idea is to train the diffusion model to generate blocklength values from noise, essentially replicating the process by which the optimization solution is derived. Extensive simulations reveal that the proposed approach surpasses existing DRL-based methods, achieving near-optimal performance in terms of total power consumption. Additionally, the proposed method reduces critical constraint violations by up to eighteen times, further highlighting the enhanced accuracy of the solution.","PeriodicalId":13197,"journal":{"name":"IEEE Communications Letters","volume":"29 1","pages":"85-89"},"PeriodicalIF":3.7,"publicationDate":"2024-11-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142940870","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-11-12DOI: 10.1109/LCOMM.2024.3496534
Nguyen Tien Hoa;Can Thi Thanh Hai;Hoang Le Hung;Nguyen Cong Luong;Dusit Niyato
In this letter, we investigate a joint edge computing and semantic communication in the UAV-enabled network. Therein, a UAV executes tasks offloaded from ground user equipments (UEs). Meanwhile, it acts as an IoT device to provide image data to a Metaverse platform through a ground base station (BS). A semantic communication (SemCom) technique is implemented at the UAV to extract scene graphs from captured images. The UAV then transmits the scene graphs (rather than the orignal images) to the BS. The small size of the scene graphs allows the UAV to transmit multiple images to the BS within a short duration. However, the scene graph extraction consumes computing resource, which may reduce the performance of the task offloading of the UEs. Therefore, we aim to optimize the UAV’s computing resource allocation and the fractions of the tasks offloaded from the UEs to achieve the min-max between i) the total latency of image collection, scene graph extraction, and scene graph communication, and ii) the computation offloading latency over the ground UEs. Given the dynamics and uncertainty of the wireless channels, the distances between the UAV and UEs, and the computing resources of the UEs, we leverage the Advantage Actor-Critic (A2C) and Proximal Policy Optimization (PPO) to solve it.
{"title":"Joint Edge Computing and Semantic Communication in UAV-Enabled Networks","authors":"Nguyen Tien Hoa;Can Thi Thanh Hai;Hoang Le Hung;Nguyen Cong Luong;Dusit Niyato","doi":"10.1109/LCOMM.2024.3496534","DOIUrl":"https://doi.org/10.1109/LCOMM.2024.3496534","url":null,"abstract":"In this letter, we investigate a joint edge computing and semantic communication in the UAV-enabled network. Therein, a UAV executes tasks offloaded from ground user equipments (UEs). Meanwhile, it acts as an IoT device to provide image data to a Metaverse platform through a ground base station (BS). A semantic communication (SemCom) technique is implemented at the UAV to extract scene graphs from captured images. The UAV then transmits the scene graphs (rather than the orignal images) to the BS. The small size of the scene graphs allows the UAV to transmit multiple images to the BS within a short duration. However, the scene graph extraction consumes computing resource, which may reduce the performance of the task offloading of the UEs. Therefore, we aim to optimize the UAV’s computing resource allocation and the fractions of the tasks offloaded from the UEs to achieve the min-max between i) the total latency of image collection, scene graph extraction, and scene graph communication, and ii) the computation offloading latency over the ground UEs. Given the dynamics and uncertainty of the wireless channels, the distances between the UAV and UEs, and the computing resources of the UEs, we leverage the Advantage Actor-Critic (A2C) and Proximal Policy Optimization (PPO) to solve it.","PeriodicalId":13197,"journal":{"name":"IEEE Communications Letters","volume":"29 1","pages":"80-84"},"PeriodicalIF":3.7,"publicationDate":"2024-11-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142940941","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","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：