Yuzheng Ren;Haijun Zhang;Fei Richard Yu;Wei Li;Pincan Zhao;Ying He
{"title":"Industrial Internet of Things With Large Language Models (LLMs): An Intelligence-Based Reinforcement Learning Approach","authors":"Yuzheng Ren;Haijun Zhang;Fei Richard Yu;Wei Li;Pincan Zhao;Ying He","doi":"10.1109/TMC.2024.3522130","DOIUrl":"https://doi.org/10.1109/TMC.2024.3522130","url":null,"abstract":"Large Language Models (LLMs), as advanced AI technologies for processing and generating natural language text, bring substantial benefits to the Industrial Internet of Things (IIoT) by enhancing efficiency, decision-making, and automation. Nevertheless, their deployment faces significant obstacles due to high computational and energy demands, which often exceed the capabilities of many industrial devices. To overcome these challenges, edge-cloud collaboration has become increasingly essential, assisting in offloading LLMs tasks to reduce the computational load. However, traditional reinforcement learning (RL)-based strategies for LLMs task offloading encounter difficulties with generalization ability and defining explicit, appropriate reward functions. Therefore, in this paper, we propose a novel framework for offloading LLMs inference tasks in IIoT, utilizing a Decentralized Identifier (DID)-based identity management system for trusted task offloading. Furthermore, we introduce an intelligence-based RL (IRL) approach, which sidesteps the need for defining specific reward functions. Instead, it uses “intelligence” as a metric to evaluate cognitive improvements and adapt to varying environmental preferences, significantly improving generalizability. In our experiments, we employ the GPT-J-6B model and utilize the Human Eval dataset to assess its ability to tackle programming challenges, demonstrating the superior performance of our proposed solution compared to existing methods.","PeriodicalId":50389,"journal":{"name":"IEEE Transactions on Mobile Computing","volume":"24 5","pages":"4136-4152"},"PeriodicalIF":7.7,"publicationDate":"2024-12-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143783234","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Yuxiao Song;Daojing He;Minghui Dai;Sammy Chan;Kim-Kwang Raymond Choo;Mohsen Guizani
{"title":"Blockchain Assisted Trust Management for Data-Parallel Distributed Learning","authors":"Yuxiao Song;Daojing He;Minghui Dai;Sammy Chan;Kim-Kwang Raymond Choo;Mohsen Guizani","doi":"10.1109/TMC.2024.3521443","DOIUrl":"https://doi.org/10.1109/TMC.2024.3521443","url":null,"abstract":"Machine learning models can support decision-making in mobile terminals (MTs) deployments, but their training generally requires massive datasets and abundant computation resources. This is challenging in practice due to the resource constraints of many MTs. To address this issue, data-parallel distributed learning can be conducted by offloading computation tasks from MTs to the edge-layer nodes. To facilitate the establishment of trust, one can leverage trust management, say to use trust values derived from local model quality and evaluations by other nodes as access criteria. Nonetheless, security and performance considerations remain unsolved. In this paper, we propose a blockchain-assisted dynamic trust management scheme for distributed learning, which comprises nodes attributes registration, trust calculation, information saving, and block writing. The proof of stake (PoS) consensus mechanism is leveraged to enable efficient consensus among the nodes using trust values as stakes. The incentive mechanism and corresponding dynamic optimization are then proposed to further improve system performance and security. The reinforcement-learning approach is leveraged to provide the optimal strategy for nodes’ local iterations and selection. Simulations and security analysis demonstrate that our proposed scheme can achieve an optimal trade-off between efficiency and quality of distributed learning while maintaining system security.","PeriodicalId":50389,"journal":{"name":"IEEE Transactions on Mobile Computing","volume":"24 5","pages":"3826-3843"},"PeriodicalIF":7.7,"publicationDate":"2024-12-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143777917","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Taming Event Cameras With Bio-Inspired Architecture and Algorithm: A Case for Drone Obstacle Avoidance","authors":"Danyang Li;Jingao Xu;Zheng Yang;Yishujie Zhao;Hao Cao;Yunhao Liu;Longfei Shangguan","doi":"10.1109/TMC.2024.3521044","DOIUrl":"https://doi.org/10.1109/TMC.2024.3521044","url":null,"abstract":"Fast and accurate obstacle avoidance is crucial to drone safety. Yet existing on-board sensor modules such as frame cameras and radars are ill-suited for doing so due to their low temporal resolution or limited field of view. This paper presents <i>BioDrone</i>, a new design paradigm for drone obstacle avoidance using stereo event cameras. At the heart of BioDrone are three simple yet effective system designs inspired by the mammalian visual system, namely, a chiasm-inspired event filtering, a lateral geniculate nucleus (LGN)-inspired event matching, and a dorsal stream-inspired obstacle tracking. We implement BioDrone on FPGA through software-hardware co-design and deploy it on an industrial drone. In comparative experiments against two state-of-the-art event-based systems, BioDrone consistently achieves an obstacle detection rate of <inline-formula><tex-math>$> $</tex-math></inline-formula>90%, and an obstacle tracking error of <inline-formula><tex-math>$<$</tex-math></inline-formula>5.8 cm across all flight modes with an end-to-end latency of <inline-formula><tex-math>$<$</tex-math></inline-formula>6.4 ms, outperforming both baselines by over 44%.","PeriodicalId":50389,"journal":{"name":"IEEE Transactions on Mobile Computing","volume":"24 5","pages":"4202-4216"},"PeriodicalIF":7.7,"publicationDate":"2024-12-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143783278","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Shanshan Jiang;Xue Wang;Junhao Lin;Chongwen Huang;Zhihong Qian;Zhu Han
{"title":"A Delay-Oriented Joint Optimization Approach for RIS-Assisted MEC-MIMO System","authors":"Shanshan Jiang;Xue Wang;Junhao Lin;Chongwen Huang;Zhihong Qian;Zhu Han","doi":"10.1109/TMC.2024.3521012","DOIUrl":"https://doi.org/10.1109/TMC.2024.3521012","url":null,"abstract":"In the paper, we propose a joint optimization algorithm based on the block coordinate descent (JOABCD) algorithm for reflective intelligent surface (RIS) assisted MEC-MIMO systems. First, we define the delay minimization function for both single user with multi-antenna and multiple users with single-antenna scenarios. Since the optimization function is an NP-hard problem, we decompose it into two subproblems: computing setting and communication setting using the block coordinate descent (BCD) iterative algorithm. The subproblem of resource allocation is solved using a bisection method, while the subproblem of transmit power and phase shift matrix is solved alternately. The optimal simulation results show that the JOABCD algorithm can realize a lower time latency and a higher sum achievable rate compared with the existing methods.","PeriodicalId":50389,"journal":{"name":"IEEE Transactions on Mobile Computing","volume":"24 5","pages":"4263-4277"},"PeriodicalIF":7.7,"publicationDate":"2024-12-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143783235","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Multi-Modal Federated Learning Based Resources Convergence for Satellite-Ground Twin Networks","authors":"Yongkang Gong;Haipeng Yao;Zehui Xiong;Dongxiao Yu;Xiuzhen Cheng;Chau Yuen;Mehdi Bennis;Mérouane Debbah","doi":"10.1109/TMC.2024.3521399","DOIUrl":"https://doi.org/10.1109/TMC.2024.3521399","url":null,"abstract":"Satellite-ground twin networks (SGTNs) are regarded as a promising service paradigm, which can provide mega access services and powerful computation offloading capabilities via cloud-fog automation functions. Specifically, cloud-fog automation technologies are collaboratively leveraged to enable dense connectivity, pervasive computing, and intelligent control in terrestrial industrial cyber-physical systems, whose system-level privacy security can be strengthened via blockchain based consensus protocol. Moreover, digital twin (DT) can shorten the gap between physical unities and digital space to enable instant data mapping in SGTNs environments. However, complex multi-modal network environments, such as stochastic task size, dynamic low earth orbit location, and time-varying channel gains, hinder better performance metrics in terms of energy consumption, throughput and privacy overhead. Hence, we establish a SGTN integrated cloud-fog automation model to transfer task data to low earth orbit satellites, and then execute broad communication access, powerful computation offloading, and efficient twin control. Next, we propose a Lyapunov stability theory based multi-modal federated learning (LST-MMFL) method to optimize the battery energy, the size of block, computation frequency, and the number of twin control for minimizing the total energy consumption and privacy overhead. Furthermore, we design a novel blockchain based transaction verification protocol to strengthen privacy security, derive performance upper bounds of SGTN model, and fulfill the long-term average task as well as energy queue constraints. Finally, massive simulation results show that the proposed LST-MMFL algorithm outperforms existing state-of-the-art benchmarks in line with energy consumption, available battery level, networked control and privacy protection overhead.","PeriodicalId":50389,"journal":{"name":"IEEE Transactions on Mobile Computing","volume":"24 5","pages":"4104-4117"},"PeriodicalIF":7.7,"publicationDate":"2024-12-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143783279","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"mmFruit: A Contactless and Non-Destructive Approach for Fine-Grained Fruit Moisture Sensing Using Millimeter-Wave Technology","authors":"Fahim Niaz;Jian Zhang;Muhammad Khalid;Muhammad Younas;Ashfaq Niaz","doi":"10.1109/TMC.2024.3520914","DOIUrl":"https://doi.org/10.1109/TMC.2024.3520914","url":null,"abstract":"Wireless sensing offers a promising approach for non-destructive and contactless identification of the moisture content in fruits. Traditional methods assess fruit quality based on external features, such as color, shape, size, and texture. However, fruits often appear perfect externally while being rotten inside. Thus, accurately measuring internal conditions is crucial. This paper introduces mmFruit, a non-destructive and ubiquitous system that employs mmWave signals for precise and robust moisture level sensing in thin and thick pericarp fruits. We propose a novel dual incidence moisture estimation model for regular moisture monitoring to achieve high granularity and eliminate fruit type and size dependency. Additionally, we leverage unique reflection responses across different mmWave frequencies to provide discriminative information about fruit moisture levels. Our comprehensive theoretical model demonstrates how fruits’ refractive index, attenuation factor, and elasticity can be estimated by eliminating fruit type dependency. We developed an electric field distribution model utilizing two receiving antennas to address the challenge of varying fruit sizes through a differential approach, aiming to improve overall robustness. mmFruit integrates a customized Spatial-invariant network (SpI-Net) to eliminate interference from different frequencies and locations, ensuring stable moisture monitoring regardless of target displacement. Extensive experiments were conducted over a month in varied environments on seven types of fruits with thin and thick pericarps (apple, pear, peach, mango, orange, dragon fruit, and watermelon). The results demonstrate that mmFruit achieves a commendable RMSE of 0.276 in moisture estimation. It accurately distinguishes fruits with minor moisture level differences (0% to 7%) with 93.6% accuracy and higher moisture differences (45% to 65%) with over 95.1% accuracy, even in scenarios involving diverse displacements and rotations.","PeriodicalId":50389,"journal":{"name":"IEEE Transactions on Mobile Computing","volume":"24 5","pages":"4022-4039"},"PeriodicalIF":7.7,"publicationDate":"2024-12-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143783282","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Yunwei Wang;Xinghua Li;Yinbin Miao;Qiuyun Tong;Ximeng Liu;Robert H. Deng
{"title":"PLRQ: Practical and Less Leakage Range Query Over Encrypted Mobile Cloud Data","authors":"Yunwei Wang;Xinghua Li;Yinbin Miao;Qiuyun Tong;Ximeng Liu;Robert H. Deng","doi":"10.1109/TMC.2024.3521366","DOIUrl":"https://doi.org/10.1109/TMC.2024.3521366","url":null,"abstract":"As a fundamental service in mobile cloud computing, range query has attracted extensive attention. But the existing secure range query schemes not only leak data privacy but also have low query efficiency. To address those issues, we first design a novel range-matched code to convert the range query into code set matching, which aims to hide the order relationship of outsourced data as well as the index of most significant different bit. Based on the designed range-matched code, we propose a <underline>P</u>ractical and <underline>L</u>ess Leakage <underline>R</u>ange <underline>Q</u>uery scheme over encrypted mobile cloud data (PLRQ) by integrating XOR filter and multiset hash function. Security analysis shows that PLRQ achieves semantic security and avoids data privacy leakage. Extensive experiments using real datasets demonstrate that, compared with two state-of-the-art solutions-RngMatch and LSRQ, our proposed PLRQ improves the query efficiency both by 2 orders of magnitude, and reduces the storage cost on Cloud Service Provider by about 79.5% and 73.6% respectively.","PeriodicalId":50389,"journal":{"name":"IEEE Transactions on Mobile Computing","volume":"24 5","pages":"4183-4201"},"PeriodicalIF":7.7,"publicationDate":"2024-12-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143783236","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Daliang Xu;Wangsong Yin;Hao Zhang;Xin Jin;Ying Zhang;Shiyun Wei;Mengwei Xu;Xuanzhe Liu
{"title":"EdgeLLM: Fast On-Device LLM Inference With Speculative Decoding","authors":"Daliang Xu;Wangsong Yin;Hao Zhang;Xin Jin;Ying Zhang;Shiyun Wei;Mengwei Xu;Xuanzhe Liu","doi":"10.1109/TMC.2024.3513457","DOIUrl":"https://doi.org/10.1109/TMC.2024.3513457","url":null,"abstract":"Generative tasks, such as text generation and question answering, are essential for mobile applications. Given their inherent privacy sensitivity, executing them on devices is demanded. Nowadays, the execution of these generative tasks heavily relies on the Large Language Models (LLMs). However, the scarce device memory severely hinders the scalability of these models. We present <monospace>EdgeLLM</monospace>, an efficient on-device LLM inference system for models whose sizes exceed the device's memory capacity. <monospace>EdgeLLM</monospace> is built atop speculative decoding, which delegates most tokens to a smaller, memory-resident (draft) LLM. <monospace>EdgeLLM</monospace> integrates three novel techniques: (1) Instead of generating a fixed width and depth token tree, <monospace>EdgeLLM</monospace> proposes compute-efficient branch navigation and verification to pace the progress of different branches according to their accepted probability to prevent the wasteful allocation of computing resources to the wrong branch and to verify them all at once efficiently. (2) It uses a self-adaptive fallback strategy that promptly initiates the verification process when the smaller LLM generates an incorrect token. (3) To not block the generation, <monospace>EdgeLLM</monospace> proposes speculatively generating tokens during large LLM verification with the compute-IO pipeline. Through extensive experiments, <monospace>EdgeLLM</monospace> exhibits impressive token generation speed which is up to 9.3× faster than existing engines.","PeriodicalId":50389,"journal":{"name":"IEEE Transactions on Mobile Computing","volume":"24 4","pages":"3256-3273"},"PeriodicalIF":7.7,"publicationDate":"2024-12-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143564041","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Yang Xiao;Huihan Yu;Ying Yang;Yixing Wang;Jun Liu;Nirwan Ansari
{"title":"Adaptive Joint Routing and Caching in Knowledge-Defined Networking: An Actor-Critic Deep Reinforcement Learning Approach","authors":"Yang Xiao;Huihan Yu;Ying Yang;Yixing Wang;Jun Liu;Nirwan Ansari","doi":"10.1109/TMC.2024.3521247","DOIUrl":"https://doi.org/10.1109/TMC.2024.3521247","url":null,"abstract":"By integrating the software-defined networking (SDN) architecture with the machine learning-based knowledge plane, knowledge-defined networking (KDN) is revolutionizing established traffic engineering (TE) methodologies. This paper investigates the challenging joint routing and caching problem in KDN-based networks, managing multiple traffic flows to improve long-term quality-of-service (QoS) performance. This challenge is formulated as a computationally expensive non-convex mixed-integer non-linear programming (MINLP) problem, which exceeds the capacity of heuristic methods to achieve near-optimal solutions. To address this issue, we present DRL-JRC, an actor-critic deep reinforcement learning (DRL) algorithm for adaptive joint routing and caching in KDN-based networks. DRL-JRC orchestrates the optimization of multiple QoS metrics, including end-to-end delay, packet loss rate, load balancing index, and hop count. During offline training, DRL-JRC employs proximal policy optimization (PPO) to smooth the policy optimization process. In addition, the learned policy can be seamlessly integrated with conventional caching solutions during online execution. Extensive experiments demonstrate the comprehensive superiority of DRL-JRC over baseline methods in various scenarios. Meanwhile, DRL-JRC consistently outperforms the heuristic baseline under partial policy deployment during execution. Compared to the average performance of the baseline methods, DRL-JRC reduces the end-to-end delay by 51.14% and the packet loss rate by 40.78%.","PeriodicalId":50389,"journal":{"name":"IEEE Transactions on Mobile Computing","volume":"24 5","pages":"4118-4135"},"PeriodicalIF":7.7,"publicationDate":"2024-12-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143783276","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Ankur Nahar;Nishit Bhardwaj;Debasis Das;Sajal K. Das
{"title":"A Hypergraph Approach to Deep Learning Based Routing in Software-Defined Vehicular Networks","authors":"Ankur Nahar;Nishit Bhardwaj;Debasis Das;Sajal K. Das","doi":"10.1109/TMC.2024.3520657","DOIUrl":"https://doi.org/10.1109/TMC.2024.3520657","url":null,"abstract":"Software-Defined Vehicular Networks (SDVNs) revolutionize modern transportation by enabling dynamic and adaptable communication infrastructures. However, accurately capturing the dynamic communication patterns in vehicular networks, characterized by intricate spatio-temporal dynamics, remains a challenge with traditional graph-based models. Hypergraphs, due to their ability to represent multi-way relationships, provide a more nuanced representation of these dynamics. Building on this hypergraph foundation, we introduce a novel hypergraph-based routing algorithm. We jointly train a model that incorporates Convolutional Neural Networks (CNN) and Gated Recurrent Units (GRU) using a Deep Deterministic Policy Gradient (DDPG) approach. This model carefully extracts spatial and temporal traffic matrices, capturing elements such as location, time, velocity, inter-dependencies, and distance. An integrated attention mechanism refines these matrices, ensuring precision in capturing vehicular dynamics. The culmination of these components results in routing decisions that are both responsive and anticipatory. Through detailed empirical experiments using a testbed, simulations with OMNeT++, and theoretical assessments grounded in real-world datasets, we demonstrate the distinct advantages of our methodology. Furthermore, when benchmarked against existing solutions, our technique performs better in model interpretability, delay minimization, rapid convergence, reducing complexity, and minimizing memory footprint.","PeriodicalId":50389,"journal":{"name":"IEEE Transactions on Mobile Computing","volume":"24 5","pages":"3844-3859"},"PeriodicalIF":7.7,"publicationDate":"2024-12-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143777766","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}