Pub Date : 2024-11-13DOI: 10.1109/TNSE.2024.3496902
Ruipeng Zhang;Yanxiang Feng;Yikang Yang;Xiaoling Li;Hengnian Li
Satellite edge computing (SEC) is important for future network deployments because of its global coverage and low-latency computing services. Nevertheless, due to data dependencies among tasks and limited buffers in satellites, a coupling exists between transmission and computation, and undesired deadlocks may arise. This paper addresses task offloading in SEC and aims to minimize service latency, energy consumption, and time window violations simultaneously. First, a mixed-integer nonlinear programming model is presented. To resolve potential deadlocks, a deadlock amending algorithm (DAA) based on Petri net with polynomial time complexity is proposed. Deadlocks in solutions are amended by finding a transition sequence that corresponding transmission and computation can be performed sequentially. By embedding DAA, we develop a learning-based deadlock-free multi-objective scheduling algorithm (LDMOSA) that combines the exploration of evolutionary algorithms with the perception of reinforcement learning. To enhance the convergence and diversity of solutions, an initialization strategy employing problem-specific constructive heuristics is designed. Then, a learning-based mechanism is used to leverage real-time information to perform adaptive operator selection during the search process. Finally, extensive experiments demonstrate the effectiveness of DAA in resolving deadlocks, and the LDMOSA outperforms state-of-the-art algorithms for task offloading in SEC.
{"title":"Learning-Based Deadlock-Free Multi-Objective Task Offloading in Satellite Edge Computing With Data-Dependent Constraints and Limited Buffers","authors":"Ruipeng Zhang;Yanxiang Feng;Yikang Yang;Xiaoling Li;Hengnian Li","doi":"10.1109/TNSE.2024.3496902","DOIUrl":"https://doi.org/10.1109/TNSE.2024.3496902","url":null,"abstract":"Satellite edge computing (SEC) is important for future network deployments because of its global coverage and low-latency computing services. Nevertheless, due to data dependencies among tasks and limited buffers in satellites, a coupling exists between transmission and computation, and undesired \u0000<italic>deadlocks</i>\u0000 may arise. This paper addresses task offloading in SEC and aims to minimize service latency, energy consumption, and time window violations simultaneously. First, a mixed-integer nonlinear programming model is presented. To resolve potential deadlocks, a deadlock amending algorithm (DAA) based on Petri net with polynomial time complexity is proposed. Deadlocks in solutions are amended by finding a transition sequence that corresponding transmission and computation can be performed sequentially. By embedding DAA, we develop a learning-based deadlock-free multi-objective scheduling algorithm (LDMOSA) that combines the exploration of evolutionary algorithms with the perception of reinforcement learning. To enhance the convergence and diversity of solutions, an initialization strategy employing problem-specific constructive heuristics is designed. Then, a learning-based mechanism is used to leverage real-time information to perform adaptive operator selection during the search process. Finally, extensive experiments demonstrate the effectiveness of DAA in resolving deadlocks, and the LDMOSA outperforms state-of-the-art algorithms for task offloading in SEC.","PeriodicalId":54229,"journal":{"name":"IEEE Transactions on Network Science and Engineering","volume":"12 1","pages":"356-368"},"PeriodicalIF":6.7,"publicationDate":"2024-11-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142880325","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}
Pub Date : 2024-11-13DOI: 10.1109/TNSE.2024.3497573
Francesco Chiti;Roberto Picchi;Laura Pierucci
Considering the scientific and economic opportunities, several public and private organizations are going to establish colonies on the Moon. In particular, lunar colonization can be a first step for deep space missions, and the initial phase is accomplished with the deployment of many Internet of Things (IoT) devices and systems. Therefore, a dedicated Earth-Moon backbone, which results from the combination of terrestrial and lunar satellite segments, must be designed. Considering that its elements are inherently mobile, to ensure the connection, the constituent devices are supposed to be programmed to properly operate during specific time intervals. The features of the Software-Defined Networking (SDN) paradigm allows achieving this aim. Moreover, the Temporal Networks (TNs) theoretical framework makes it possible to optimize the forwarding rules. In light of these principles, this paper proposes an SDN-based architecture and analyzes the overall communications scenario proposing a specific strategy to optimize the data rate. The performance was evaluated considering the End-to-End (E2E) best path duration, the number of hops, the control packets latency, the power budget and capacity. The results point out that it is feasible to establish a networking strategy on-demand to support the transmission of continuous IoT data flows with limited overhead.
{"title":"From Earth-to-Moon Networking: A Software-Defined Temporal Perspective","authors":"Francesco Chiti;Roberto Picchi;Laura Pierucci","doi":"10.1109/TNSE.2024.3497573","DOIUrl":"https://doi.org/10.1109/TNSE.2024.3497573","url":null,"abstract":"Considering the scientific and economic opportunities, several public and private organizations are going to establish colonies on the Moon. In particular, lunar colonization can be a first step for deep space missions, and the initial phase is accomplished with the deployment of many Internet of Things (IoT) devices and systems. Therefore, a dedicated Earth-Moon backbone, which results from the combination of terrestrial and lunar satellite segments, must be designed. Considering that its elements are inherently mobile, to ensure the connection, the constituent devices are supposed to be programmed to properly operate during specific time intervals. The features of the Software-Defined Networking (SDN) paradigm allows achieving this aim. Moreover, the Temporal Networks (TNs) theoretical framework makes it possible to optimize the forwarding rules. In light of these principles, this paper proposes an SDN-based architecture and analyzes the overall communications scenario proposing a specific strategy to optimize the data rate. The performance was evaluated considering the End-to-End (E2E) best path duration, the number of hops, the control packets latency, the power budget and capacity. The results point out that it is feasible to establish a networking strategy on-demand to support the transmission of continuous IoT data flows with limited overhead.","PeriodicalId":54229,"journal":{"name":"IEEE Transactions on Network Science and Engineering","volume":"12 1","pages":"369-380"},"PeriodicalIF":6.7,"publicationDate":"2024-11-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10752586","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142880411","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-11-13DOI: 10.1109/TNSE.2024.3497577
Yubin Jia;Zhao Yang Dong;Changyin Sun;Ke Meng
With the increasing integration of renewable energy into power systems, two key challenges emerge in low-carbon energy networks: the distributed topology resulting from distributed energy resources (DERs), and the fluctuations caused by the intermittency of renewable energy sources (RES). This paper proposes a distributed model predictive control (MPC) for the frequency regulation of low-carbon energy networks that encompass both conventional generators (including hydro and gas turbine power plants) and wind turbines. First, the cooperation based distributed model predictive controller of each subsystem accounts for the communication between the subsystems and global control objectives while the constraints are considered. Second, a tube-based controller containing two cascaded MPCs is proposed to deal with the system exogenous disturbance such as wind speed fluctuation. The simulation cases illustrate the efficiency and the advantages of the proposed method.
{"title":"A Tube-Based Distributed MPC Based Method for Low-Carbon Energy Networks With Exogenous Disturbances","authors":"Yubin Jia;Zhao Yang Dong;Changyin Sun;Ke Meng","doi":"10.1109/TNSE.2024.3497577","DOIUrl":"https://doi.org/10.1109/TNSE.2024.3497577","url":null,"abstract":"With the increasing integration of renewable energy into power systems, two key challenges emerge in low-carbon energy networks: the distributed topology resulting from distributed energy resources (DERs), and the fluctuations caused by the intermittency of renewable energy sources (RES). This paper proposes a distributed model predictive control (MPC) for the frequency regulation of low-carbon energy networks that encompass both conventional generators (including hydro and gas turbine power plants) and wind turbines. First, the cooperation based distributed model predictive controller of each subsystem accounts for the communication between the subsystems and global control objectives while the constraints are considered. Second, a tube-based controller containing two cascaded MPCs is proposed to deal with the system exogenous disturbance such as wind speed fluctuation. The simulation cases illustrate the efficiency and the advantages of the proposed method.","PeriodicalId":54229,"journal":{"name":"IEEE Transactions on Network Science and Engineering","volume":"12 1","pages":"381-391"},"PeriodicalIF":6.7,"publicationDate":"2024-11-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142880282","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}
Pub Date : 2024-11-11DOI: 10.1109/TNSE.2024.3496199
Yu Sun;Cheng Hu;Shipin Wen;Juan Yu;Haijun Jiang
In this article, by developing a direct error approach, the pinning passivity of leaderless fractional spatiotemporal networks and the leaderless bipartite synchronization of fractional spatiotemporal networks over a signed topological graph are investigated respectively. Above all, a fractional-order edge-based adaptive pinning strategy is designed based on the spanning tree to achieve the passivity of leaderless systems with Dirichlet boundary condition. Next, the fractional spatiotemporal networks with signed graph are discussed and some conditions are obtained to realize leaderless bipartite synchronization based on the derived passivity results and gauge transformation. Note that, the passivity and synchronization of networks are directly investigated without defining any reference state. The developed criteria are eventually verified by several illustrative examples.
{"title":"Pinning Adaptive Passivity and Bipartite Synchronization of Leaderless Fractional Spatiotemporal Networks","authors":"Yu Sun;Cheng Hu;Shipin Wen;Juan Yu;Haijun Jiang","doi":"10.1109/TNSE.2024.3496199","DOIUrl":"https://doi.org/10.1109/TNSE.2024.3496199","url":null,"abstract":"In this article, by developing a direct error approach, the pinning passivity of leaderless fractional spatiotemporal networks and the leaderless bipartite synchronization of fractional spatiotemporal networks over a signed topological graph are investigated respectively. Above all, a fractional-order edge-based adaptive pinning strategy is designed based on the spanning tree to achieve the passivity of leaderless systems with Dirichlet boundary condition. Next, the fractional spatiotemporal networks with signed graph are discussed and some conditions are obtained to realize leaderless bipartite synchronization based on the derived passivity results and gauge transformation. Note that, the passivity and synchronization of networks are directly investigated without defining any reference state. The developed criteria are eventually verified by several illustrative examples.","PeriodicalId":54229,"journal":{"name":"IEEE Transactions on Network Science and Engineering","volume":"12 1","pages":"319-331"},"PeriodicalIF":6.7,"publicationDate":"2024-11-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142880336","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}
Pub Date : 2024-11-07DOI: 10.1109/TNSE.2024.3494542
Zhiwei Zhou;Li Pan;Shijun Liu
With the proliferation of mobile phones, IoT devices, and the rising demand for computational resources, computation offloading has emerged as a promising technique for improving performance, and optimizing resource usage. It involves transferring computational tasks from local devices to edge servers. However, reducing latency and device energy consumption remains a challenge in current research. In this paper, we propose a potential game-theoretic approach to optimize computation offloading in edge computing environments. We consider heterogeneous edge servers, where each server may have different computational capabilities. By formulating the problem as a potential game, we have end devices acting as players deciding whether to execute tasks locally or on edge servers. Our framework includes utility functions capturing the latency-energy consumption trade-off. Through a detailed analysis, we introduce an innovative algorithm for potential games aiming at achieving Nash equilibrium. This algorithm demonstrates exceptional convergence properties, ensuring reliable convergence even in complex scenarios. Extensive experiments validate the convergence of our algorithm and demonstrate its better performance compared to other benchmark algorithms in terms of latency and energy consumption.
{"title":"Potential Game-Based Computation Offloading in Edge Computing With Heterogeneous Edge Servers","authors":"Zhiwei Zhou;Li Pan;Shijun Liu","doi":"10.1109/TNSE.2024.3494542","DOIUrl":"https://doi.org/10.1109/TNSE.2024.3494542","url":null,"abstract":"With the proliferation of mobile phones, IoT devices, and the rising demand for computational resources, computation offloading has emerged as a promising technique for improving performance, and optimizing resource usage. It involves transferring computational tasks from local devices to edge servers. However, reducing latency and device energy consumption remains a challenge in current research. In this paper, we propose a potential game-theoretic approach to optimize computation offloading in edge computing environments. We consider heterogeneous edge servers, where each server may have different computational capabilities. By formulating the problem as a potential game, we have end devices acting as players deciding whether to execute tasks locally or on edge servers. Our framework includes utility functions capturing the latency-energy consumption trade-off. Through a detailed analysis, we introduce an innovative algorithm for potential games aiming at achieving Nash equilibrium. This algorithm demonstrates exceptional convergence properties, ensuring reliable convergence even in complex scenarios. Extensive experiments validate the convergence of our algorithm and demonstrate its better performance compared to other benchmark algorithms in terms of latency and energy consumption.","PeriodicalId":54229,"journal":{"name":"IEEE Transactions on Network Science and Engineering","volume":"12 1","pages":"290-301"},"PeriodicalIF":6.7,"publicationDate":"2024-11-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142880333","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}
Pub Date : 2024-11-07DOI: 10.1109/TNSE.2024.3491823
Xiaojie Huang;Yingying Ren;Da-Wei Ding
This paper investigates the synchronization of complex cyber-physical networks (CCPNs) under hybrid asynchronous attacks. Firstly, a kind of hybrid asynchronous attack model consisting of DoS attacks in sensor to controller (S-C) channel, DoS attacks in controller to actuator (C-A) channel and connection attacks is proposed, which is a new generalization of traditional synchronous attack model. Secondly, a distributed controller using two combinational measurements of node states and sensor outputs is designed to obtain the synchronization criteria of CCPNs under hybrid asynchronous attacks. Then, two methods are proposed to ensure that all nodes of CCPNs are synchronized based on the designed distributed controller. Meanwhile, the duration time and frequency of attacks that the systems can tolerate are calculated. Finally, two examples are given to illustrate the effectiveness of the proposed method.
{"title":"Security Synchronization for Complex Cyber-Physical Networks Under Hybrid Asynchronous Attacks","authors":"Xiaojie Huang;Yingying Ren;Da-Wei Ding","doi":"10.1109/TNSE.2024.3491823","DOIUrl":"https://doi.org/10.1109/TNSE.2024.3491823","url":null,"abstract":"This paper investigates the synchronization of complex cyber-physical networks (CCPNs) under hybrid asynchronous attacks. Firstly, a kind of hybrid asynchronous attack model consisting of DoS attacks in sensor to controller (S-C) channel, DoS attacks in controller to actuator (C-A) channel and connection attacks is proposed, which is a new generalization of traditional synchronous attack model. Secondly, a distributed controller using two combinational measurements of node states and sensor outputs is designed to obtain the synchronization criteria of CCPNs under hybrid asynchronous attacks. Then, two methods are proposed to ensure that all nodes of CCPNs are synchronized based on the designed distributed controller. Meanwhile, the duration time and frequency of attacks that the systems can tolerate are calculated. Finally, two examples are given to illustrate the effectiveness of the proposed method.","PeriodicalId":54229,"journal":{"name":"IEEE Transactions on Network Science and Engineering","volume":"12 1","pages":"237-251"},"PeriodicalIF":6.7,"publicationDate":"2024-11-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142890212","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}
The growing integration of renewable energy sources into the power grid necessitates innovative approaches to energy system management. Integrated gas and electricity networks offer a promising solution to this challenge, enabling the efficient, reliable, and sustainable operation of energy systems. This paper presents a novel approach to the optimal scheduling of integrated gas and electricity networks, addressing the challenges posed by high penetration of renewable energy sources. First, a learning-assisted methodology is proposed to leverage Graph Convolutional Networks (GCNs) and Bayesian-based uncertainty models to enhance the accuracy and efficiency of scheduling integrated energy systems. The proposed GCN model effectively captures the complex interactions within the integrated network, facilitating accurate power and gas flow predictions. Meanwhile, the Bayesian-based model adeptly manages the inherent uncertainties associated with renewable energy generation, employing a chance-constrained approach to ensure system reliability. The effectiveness of the proposed methodology is demonstrated through extensive simulations on an IEEE 39-bus electricity network coupled with a 22-node hydrogen network. Results indicate significant improvements in computational efficiency and predictive accuracy compared to traditional model-based methods and existing data-driven techniques.
{"title":"Enhancing Integrated Gas and Electricity Networks Operation With Coupling Attention-Graph Convolutional Network Under Renewable Energy Variability","authors":"Runze Bai;Xianzhuo Sun;Wen Zhang;Jing Qiu;Yuechuan Tao;Shuying Lai;Junhua Zhao","doi":"10.1109/TNSE.2024.3493247","DOIUrl":"https://doi.org/10.1109/TNSE.2024.3493247","url":null,"abstract":"The growing integration of renewable energy sources into the power grid necessitates innovative approaches to energy system management. Integrated gas and electricity networks offer a promising solution to this challenge, enabling the efficient, reliable, and sustainable operation of energy systems. This paper presents a novel approach to the optimal scheduling of integrated gas and electricity networks, addressing the challenges posed by high penetration of renewable energy sources. First, a learning-assisted methodology is proposed to leverage Graph Convolutional Networks (GCNs) and Bayesian-based uncertainty models to enhance the accuracy and efficiency of scheduling integrated energy systems. The proposed GCN model effectively captures the complex interactions within the integrated network, facilitating accurate power and gas flow predictions. Meanwhile, the Bayesian-based model adeptly manages the inherent uncertainties associated with renewable energy generation, employing a chance-constrained approach to ensure system reliability. The effectiveness of the proposed methodology is demonstrated through extensive simulations on an IEEE 39-bus electricity network coupled with a 22-node hydrogen network. Results indicate significant improvements in computational efficiency and predictive accuracy compared to traditional model-based methods and existing data-driven techniques.","PeriodicalId":54229,"journal":{"name":"IEEE Transactions on Network Science and Engineering","volume":"12 1","pages":"277-289"},"PeriodicalIF":6.7,"publicationDate":"2024-11-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142890214","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}
Pub Date : 2024-11-07DOI: 10.1109/TNSE.2024.3493053
Jiancheng Chi;Xiaobo Zhou;Fu Xiao;Tie Qiu;C. L. Philip Chen
In the Multi-access Edge Computing (MEC)-based Industrial Internet of Things (IIoT), a key challenge is to make an efficient task-offloading decision. Machine learning methods have emerged as popular solutions to address this issue. However, in IIoT, it is common for the feature distribution of data to change significantly over time, i.e., data drift, and existing machine learning-based schemes struggle to frequent data drift, failing to maintain consistent high accuracy of task-offloading decisions. This struggle arises because they require extended retraining or extensive model adjustments, which involve significant delays and increased computational overhead due to the complex network structure. In this paper, we propose a B road learning-based task OFF loading scheme (BOFF). In BOFF, a data drift detection method based on statistical features and a sliding window is established to determine the occurrence of data drift in the system, while utilizing the Gini coefficient to enhance feature extraction and improve accuracy of task-offloading decision model under data drift. When data drift is detected, BOFF leverages its fast training and redeployment capabilities based on feature-enhanced broad learning to update the task offloading model and maintain accuracy. In the absence of significant data drift, minor changes in data distribution are addressed through incremental updates to slow the decline in model accuracy. Numerical results demonstrate that BOFF significantly improves the adaptability of data drift, ensuring high accuracy and efficiency of task offloading in dynamic IIoT environments.
{"title":"Enhancing Adaptability and Efficiency of Task Offloading by Broad Learning in Industrial IoT","authors":"Jiancheng Chi;Xiaobo Zhou;Fu Xiao;Tie Qiu;C. L. Philip Chen","doi":"10.1109/TNSE.2024.3493053","DOIUrl":"https://doi.org/10.1109/TNSE.2024.3493053","url":null,"abstract":"In the Multi-access Edge Computing (MEC)-based Industrial Internet of Things (IIoT), a key challenge is to make an efficient task-offloading decision. Machine learning methods have emerged as popular solutions to address this issue. However, in IIoT, it is common for the feature distribution of data to change significantly over time, i.e., data drift, and existing machine learning-based schemes struggle to frequent data drift, failing to maintain consistent high accuracy of task-offloading decisions. This struggle arises because they require extended retraining or extensive model adjustments, which involve significant delays and increased computational overhead due to the complex network structure. In this paper, we propose a \u0000<bold>B</b>\u0000road learning-based task \u0000<bold>OFF</b>\u0000loading scheme (BOFF). In BOFF, a data drift detection method based on statistical features and a sliding window is established to determine the occurrence of data drift in the system, while utilizing the Gini coefficient to enhance feature extraction and improve accuracy of task-offloading decision model under data drift. When data drift is detected, BOFF leverages its fast training and redeployment capabilities based on feature-enhanced broad learning to update the task offloading model and maintain accuracy. In the absence of significant data drift, minor changes in data distribution are addressed through incremental updates to slow the decline in model accuracy. Numerical results demonstrate that BOFF significantly improves the adaptability of data drift, ensuring high accuracy and efficiency of task offloading in dynamic IIoT environments.","PeriodicalId":54229,"journal":{"name":"IEEE Transactions on Network Science and Engineering","volume":"12 1","pages":"263-276"},"PeriodicalIF":6.7,"publicationDate":"2024-11-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142890156","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}
Pub Date : 2024-11-06DOI: 10.1109/TNSE.2024.3486733
Haleema Sadia;Ahmad Kamal Hassan;Ziaul Haq Abbas;Ghulam Abbas;John M. Cioffi
Intelligent reflecting surfaces (IRSs) improves beyond fifth generation (B5G) systems performance in power- and cost-efficient ways. However, maintaining the performance of multiple IRSs-enabled networks without constraining available resources is challenging. In this paper, we propose a novel IRS-assisted phase cooperative framework to maximize the sum rate of the secondary phase cooperative system ( $mathbf {SPC}_{mathcal {S}ys}$ ) located in close proximity of the primary phase cooperative system ( $mathbf {PPC}_{mathcal {S}ys}$ ). We exploit transmit beamforming (BF) at base stations (BSs) and phase shift optimization at the IRS with effective phase cooperation between BSs. The maximization problem turns out to be NP-hard, so an alternating optimization is solved for the $mathbf {PPC}_{mathcal {S}ys}$ using an exhaustive search method, i.e., the branch-reduce-and-bound (BRB) algorithm, to obtain the optimal solution for active beamformers, and phase optimization is performed using the semidefinite relaxation (SDR) approach. Further, an active BF is carried out at the $mathbf {SPC}_{mathcal {S}ys}$ transmitter by utilizing optimal phase shifts of the $mathbf {PPC}_{mathcal {S}ys}$ . For the proposed framework, the performance of the BRB algorithm is compared with sub-optimal heuristic BF approaches, including transmit minimum-mean-square-error, zero-forcing BF, and maximum-ratio-transmission. The results support the benefits of deploying IRS in wireless networks to improve sum rate performance of $mathbf {SPC}_{mathcal {S}ys}$ through effective phase cooperation. The proposed framework significantly reduces the hardware cost of the system without constraining the resources of $mathbf {PPC}_{mathcal {S}ys}$ .
{"title":"An IRS-Enabled Phase Cooperative Framework for Sum Rate Maximization in B5G Networks","authors":"Haleema Sadia;Ahmad Kamal Hassan;Ziaul Haq Abbas;Ghulam Abbas;John M. Cioffi","doi":"10.1109/TNSE.2024.3486733","DOIUrl":"https://doi.org/10.1109/TNSE.2024.3486733","url":null,"abstract":"Intelligent reflecting surfaces (IRSs) improves beyond fifth generation (B5G) systems performance in power- and cost-efficient ways. However, maintaining the performance of multiple IRSs-enabled networks without constraining available resources is challenging. In this paper, we propose a novel IRS-assisted phase cooperative framework to maximize the sum rate of the secondary phase cooperative system (\u0000<inline-formula><tex-math>$mathbf {SPC}_{mathcal {S}ys}$</tex-math></inline-formula>\u0000) located in close proximity of the primary phase cooperative system (\u0000<inline-formula><tex-math>$mathbf {PPC}_{mathcal {S}ys}$</tex-math></inline-formula>\u0000). We exploit transmit beamforming (BF) at base stations (BSs) and phase shift optimization at the IRS with effective phase cooperation between BSs. The maximization problem turns out to be NP-hard, so an alternating optimization is solved for the \u0000<inline-formula><tex-math>$mathbf {PPC}_{mathcal {S}ys}$</tex-math></inline-formula>\u0000 using an exhaustive search method, i.e., the branch-reduce-and-bound (BRB) algorithm, to obtain the optimal solution for active beamformers, and phase optimization is performed using the semidefinite relaxation (SDR) approach. Further, an active BF is carried out at the \u0000<inline-formula><tex-math>$mathbf {SPC}_{mathcal {S}ys}$</tex-math></inline-formula>\u0000 transmitter by utilizing optimal phase shifts of the \u0000<inline-formula><tex-math>$mathbf {PPC}_{mathcal {S}ys}$</tex-math></inline-formula>\u0000. For the proposed framework, the performance of the BRB algorithm is compared with sub-optimal heuristic BF approaches, including transmit minimum-mean-square-error, zero-forcing BF, and maximum-ratio-transmission. The results support the benefits of deploying IRS in wireless networks to improve sum rate performance of \u0000<inline-formula><tex-math>$mathbf {SPC}_{mathcal {S}ys}$</tex-math></inline-formula>\u0000 through effective phase cooperation. The proposed framework significantly reduces the hardware cost of the system without constraining the resources of \u0000<inline-formula><tex-math>$mathbf {PPC}_{mathcal {S}ys}$</tex-math></inline-formula>\u0000.","PeriodicalId":54229,"journal":{"name":"IEEE Transactions on Network Science and Engineering","volume":"12 1","pages":"134-144"},"PeriodicalIF":6.7,"publicationDate":"2024-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142890139","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}
Pub Date : 2024-11-05DOI: 10.1109/TNSE.2024.3492032
Tapadhir Das;Raj Mani Shukla;Shamik Sengupta
With the usage of Machine Learning (ML) algorithms in modern-day Network Intrusion Detection Systems (NIDS), contemporary network communications are efficiently protected from cyber threats. However, these ML algorithms are starting to be compromised by adversarial attacks that ambush the ML pipeline. This paper demonstrates the feasibility of an adversarial attack called the Cosine Similarity Label Manipulation (CSLM) which is geared toward compromising training labels for ML-based NIDS. The paper develops two versions of CSLM attacks: Minimum CSLM (Min-CSLM) and Maximum CSLM (Max-CSLM). We demonstrate the attacks' efficacy towards single and multi-controller Software-defined Network (SDN) setups. Results indicate that the proposed attacks provide substantial deterioration of classifier performance in single SDNs, specifically, those that utilize Random Forests (RF), which deteriorate $approx$ 50% under Min-CSLM attacks, and Support Vector Machines (SVM), which undergo $approx$ 60% deterioration from a Max-CSLM attack. We also note that RF, SVM, and Multi-layer Perceptron (MLP) classifiers are also extensively vulnerable to these attacks in Multi-controller SDN setups (MSDN) as they incur the most observed utility deterioration. MLP-based uniform MSDNs incur the most deterioration under both proposed CSLM attacks with $approx$ 28% decrease in performance, while SVM and RF-based variable MSDNs incur the most deterioration under both CSLM attacks with $approx$ 30% and $approx$ 35% decrease in performance, respectively.
{"title":"Poisoning the Well: Adversarial Poisoning on ML-Based Software-Defined Network Intrusion Detection Systems","authors":"Tapadhir Das;Raj Mani Shukla;Shamik Sengupta","doi":"10.1109/TNSE.2024.3492032","DOIUrl":"https://doi.org/10.1109/TNSE.2024.3492032","url":null,"abstract":"With the usage of Machine Learning (ML) algorithms in modern-day Network Intrusion Detection Systems (NIDS), contemporary network communications are efficiently protected from cyber threats. However, these ML algorithms are starting to be compromised by adversarial attacks that ambush the ML pipeline. This paper demonstrates the feasibility of an adversarial attack called the Cosine Similarity Label Manipulation (CSLM) which is geared toward compromising training labels for ML-based NIDS. The paper develops two versions of CSLM attacks: Minimum CSLM (Min-CSLM) and Maximum CSLM (Max-CSLM). We demonstrate the attacks' efficacy towards single and multi-controller Software-defined Network (SDN) setups. Results indicate that the proposed attacks provide substantial deterioration of classifier performance in single SDNs, specifically, those that utilize Random Forests (RF), which deteriorate \u0000<inline-formula><tex-math>$approx$</tex-math></inline-formula>\u000050% under Min-CSLM attacks, and Support Vector Machines (SVM), which undergo \u0000<inline-formula><tex-math>$approx$</tex-math></inline-formula>\u000060% deterioration from a Max-CSLM attack. We also note that RF, SVM, and Multi-layer Perceptron (MLP) classifiers are also extensively vulnerable to these attacks in Multi-controller SDN setups (MSDN) as they incur the most observed utility deterioration. MLP-based uniform MSDNs incur the most deterioration under both proposed CSLM attacks with \u0000<inline-formula><tex-math>$approx$</tex-math></inline-formula>\u000028% decrease in performance, while SVM and RF-based variable MSDNs incur the most deterioration under both CSLM attacks with \u0000<inline-formula><tex-math>$approx$</tex-math></inline-formula>\u000030% and \u0000<inline-formula><tex-math>$approx$</tex-math></inline-formula>\u0000 35% decrease in performance, respectively.","PeriodicalId":54229,"journal":{"name":"IEEE Transactions on Network Science and Engineering","volume":"12 1","pages":"252-262"},"PeriodicalIF":6.7,"publicationDate":"2024-11-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142890331","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}
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：