Pub Date : 2024-10-14DOI: 10.1109/TSC.2024.3479926
Shihao Shen;Yicheng Feng;Mengwei Xu;Yuanming Ren;Xiaofei Wang;Victor C.M. Leung;Wenyu Wang
Deploying Latency-Critical (LC) services and Best-Effort (BE) services together is expected to improve resource utilization in edge clouds. However, co-locating LC and BE services on edge clouds presents unique challenges. Unlike cloud datacenters, edge clouds are heterogeneous, resource-constrained, and geographically distributed, leading to fiercer competition for resources and greater difficulty in balancing fluctuating co-located workloads. Due to the lack of consideration for the characteristics of edge environments, previous solutions designed for cloud datacenters are no longer applicable. To address these challenges, we introduce Tango , a harmonious scheduling framework for Kubernetes -based edge cloud systems with mixed services. Tango incorporates novel components and mechanisms for elastic resource allocation on the edge, as well as two traffic scheduling algorithms that efficiently manage distributed edge resources. Tango fosters harmony not only by supporting compatible mixed services but also by offering collaborative solutions that complement each other. Based on a non-intrusive design for Kubernetes , Tango further enhances it with automatic scaling and traffic scheduling capabilities. Compared to state-of-the-art approaches, experiments on large-scale hybrid edge clouds, driven by real workload traces, show that Tango improves system resource utilization by 36.9%, QoS-guarantee satisfaction rate by 11.3%, and throughput by 47.6%.
{"title":"Tango: Harmonious Optimization for Mixed Services in Kubernetes-Based Edge Clouds","authors":"Shihao Shen;Yicheng Feng;Mengwei Xu;Yuanming Ren;Xiaofei Wang;Victor C.M. Leung;Wenyu Wang","doi":"10.1109/TSC.2024.3479926","DOIUrl":"10.1109/TSC.2024.3479926","url":null,"abstract":"Deploying Latency-Critical (LC) services and Best-Effort (BE) services together is expected to improve resource utilization in edge clouds. However, co-locating LC and BE services on edge clouds presents unique challenges. Unlike cloud datacenters, edge clouds are heterogeneous, resource-constrained, and geographically distributed, leading to fiercer competition for resources and greater difficulty in balancing fluctuating co-located workloads. Due to the lack of consideration for the characteristics of edge environments, previous solutions designed for cloud datacenters are no longer applicable. To address these challenges, we introduce \u0000<italic>Tango</i>\u0000, a harmonious scheduling framework for \u0000<italic>Kubernetes</i>\u0000-based edge cloud systems with mixed services. \u0000<italic>Tango</i>\u0000 incorporates novel components and mechanisms for elastic resource allocation on the edge, as well as two traffic scheduling algorithms that efficiently manage distributed edge resources. \u0000<italic>Tango</i>\u0000 fosters harmony not only by supporting compatible mixed services but also by offering collaborative solutions that complement each other. Based on a non-intrusive design for \u0000<italic>Kubernetes</i>\u0000, \u0000<italic>Tango</i>\u0000 further enhances it with automatic scaling and traffic scheduling capabilities. Compared to state-of-the-art approaches, experiments on large-scale hybrid edge clouds, driven by real workload traces, show that \u0000<italic>Tango</i>\u0000 improves system resource utilization by 36.9%, QoS-guarantee satisfaction rate by 11.3%, and throughput by 47.6%.","PeriodicalId":13255,"journal":{"name":"IEEE Transactions on Services Computing","volume":"17 6","pages":"4354-4367"},"PeriodicalIF":5.5,"publicationDate":"2024-10-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142439671","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 : 2024-10-14DOI: 10.1109/TSC.2024.3479912
Ahmed Alharbi;Hai Dong;Xun Yi;Prabath Abeysekara
We propose a novel approach to effectively detect cloned identities of social-sensor cloud service providers (i.e. social media users) in the face of incomplete non-privacy-sensitive profile data. Named ICD-IPD, the proposed approach first extracts account pairs with similar usernames or screen names from a given set of user accounts collected from a social media. It then learns a multi-view representation associated with a given account and extracts two categories of features for every single account. These two categories of features include profile and Weighted Generalised Canonical Correlation Analysis (WGCCA)-based features that may potentially contain missing values. To counter the impact of such missing values, a missing value imputer will next impute the missing values of the aforementioned profile and WGCCA-based features. After that, the proposed approach further extracts two categories of augmented features for each account pair identified previously, namely, 1) similarity and 2) differences-based features. Finally, these features are concatenated and fed into a Light Gradient Boosting Machine classifier to detect identity cloning. We evaluated and compared the proposed approach against the existing state-of-the-art identity cloning approaches and other machine or deep learning models atop a real-world dataset. The experimental results show that the proposed approach outperforms the state-of-the-art approaches and models in terms of Precision, Recall and F1-score.
{"title":"Cloned Identity Detection in Social-Sensor Clouds Based on Incomplete Profiles","authors":"Ahmed Alharbi;Hai Dong;Xun Yi;Prabath Abeysekara","doi":"10.1109/TSC.2024.3479912","DOIUrl":"10.1109/TSC.2024.3479912","url":null,"abstract":"We propose a novel approach to effectively detect cloned identities of social-sensor cloud service providers (i.e. social media users) in the face of incomplete non-privacy-sensitive profile data. Named ICD-IPD, the proposed approach first extracts account pairs with similar usernames or screen names from a given set of user accounts collected from a social media. It then learns a multi-view representation associated with a given account and extracts two categories of features for every single account. These two categories of features include profile and Weighted Generalised Canonical Correlation Analysis (WGCCA)-based features that may potentially contain missing values. To counter the impact of such missing values, a missing value imputer will next impute the missing values of the aforementioned profile and WGCCA-based features. After that, the proposed approach further extracts two categories of augmented features for each account pair identified previously, namely, 1) similarity and 2) differences-based features. Finally, these features are concatenated and fed into a Light Gradient Boosting Machine classifier to detect identity cloning. We evaluated and compared the proposed approach against the existing state-of-the-art identity cloning approaches and other machine or deep learning models atop a real-world dataset. The experimental results show that the proposed approach outperforms the state-of-the-art approaches and models in terms of Precision, Recall and F1-score.","PeriodicalId":13255,"journal":{"name":"IEEE Transactions on Services Computing","volume":"17 6","pages":"3227-3240"},"PeriodicalIF":5.5,"publicationDate":"2024-10-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142439673","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 : 2024-10-14DOI: 10.1109/TSC.2024.3479909
Yao Zhao;Youyang Qu;Yong Xiang;Feifei Chen;Md Palash Uddin;Longxiang Gao
M obile E dge C omputing (MEC) is an emerging technology, where App vendors are allowed to cache multiple data replicas on geographically distributed edge servers to serve adjacent mobile subscribers. However, this benefit introduces an extra workload for edge servers and App vendors, as they must audit the integrity of multiple data replicas periodically considering various threats caused by distributed and dynamic MEC environments. The large-scale growth of data replicas certainly is a challenge to design more efficient E dge D ata I ntegrity (EDI) verification approaches. Existing solutions are mostly limited to improving efficiency by optimizing proof generation and verification methods, while the improvement is still far from satisfactory due to adopting indiscriminate inspection philosophy (checking all data replicas without discrimination). In this paper, we make the first attempt to abstract a pre-processing phase and correspondingly study the U nreliable data R eplica S election (URS) problem. It can be seamlessly integrated into existing EDI solutions by solving the URS problem at the start of each verification round. Such pre-selection can significantly enhance overall EDI verification efficiency by incorporating the cache service Q uality o f S ervice (QoS) and verification success rate, especially in scenarios with a large number of data replicas. Specifically, we first formalize the URS problem as a constrained optimization problem, and further prove its $mathcal {NP}$ -hardness. To address the problem efficiently, we transform it into an easy-to-handle form and develop a P riority-based approach named URS-P. Both theoretical analysis and experimental evaluation validate the effectiveness and efficiency of our proposed solution.
移动边缘计算（MEC）是一项新兴技术，应用程序供应商可以在地理分布的边缘服务器上缓存多个数据副本，以服务相邻的移动用户。然而，这一优势为边缘服务器和应用程序供应商带来了额外的工作负载，因为他们必须定期审核多个数据副本的完整性，考虑分布式和动态MEC环境造成的各种威胁。数据副本的大规模增长无疑是设计更有效的边缘数据完整性（EDI）验证方法的挑战。现有的解决方案大多局限于通过优化证明生成和验证方法来提高效率，而由于采用无差别检查（无差别检查所有数据副本）的理念，改进效果还远远不能令人满意。本文首次尝试抽象一个预处理阶段，并对不可靠数据副本选择（URS）问题进行了相应的研究。通过在每个验证轮开始时解决URS问题，它可以无缝地集成到现有的EDI解决方案中。通过结合缓存服务QoS （Quality of service）和验证成功率，这种预选可以显著提高EDI验证的整体效率，特别是在数据副本大量的场景中。具体而言，我们首先将URS问题形式化为约束优化问题，并进一步证明其$mathcal {NP}$ -硬度。为了有效地解决这个问题，我们将其转换为易于处理的表单，并开发了一种名为URS-P的基于优先级的方法。理论分析和实验验证了该方法的有效性和高效性。
{"title":"Winning at the Starting Line: Unreliable Data Replica Selection for Edge Data Integrity Verification","authors":"Yao Zhao;Youyang Qu;Yong Xiang;Feifei Chen;Md Palash Uddin;Longxiang Gao","doi":"10.1109/TSC.2024.3479909","DOIUrl":"10.1109/TSC.2024.3479909","url":null,"abstract":"<u>M</u>\u0000obile \u0000<u>E</u>\u0000dge \u0000<u>C</u>\u0000omputing (MEC) is an emerging technology, where App vendors are allowed to cache multiple data replicas on geographically distributed edge servers to serve adjacent mobile subscribers. However, this benefit introduces an extra workload for edge servers and App vendors, as they must audit the integrity of multiple data replicas periodically considering various threats caused by distributed and dynamic MEC environments. The large-scale growth of data replicas certainly is a challenge to design more efficient \u0000<u>E</u>\u0000dge \u0000<u>D</u>\u0000ata \u0000<u>I</u>\u0000ntegrity (EDI) verification approaches. Existing solutions are mostly limited to improving efficiency by optimizing proof generation and verification methods, while the improvement is still far from satisfactory due to adopting indiscriminate inspection philosophy (checking all data replicas without discrimination). In this paper, we make the first attempt to abstract a pre-processing phase and correspondingly study the \u0000<u>U</u>\u0000nreliable data \u0000<u>R</u>\u0000eplica \u0000<u>S</u>\u0000election (URS) problem. It can be seamlessly integrated into existing EDI solutions by solving the URS problem at the start of each verification round. Such pre-selection can significantly enhance overall EDI verification efficiency by incorporating the cache service \u0000<u>Q</u>\u0000uality \u0000<u>o</u>\u0000f \u0000<u>S</u>\u0000ervice (QoS) and verification success rate, especially in scenarios with a large number of data replicas. Specifically, we first formalize the URS problem as a constrained optimization problem, and further prove its \u0000<inline-formula><tex-math>$mathcal {NP}$</tex-math></inline-formula>\u0000 -hardness. To address the problem efficiently, we transform it into an easy-to-handle form and develop a \u0000<u>P</u>\u0000riority-based approach named URS-P. Both theoretical analysis and experimental evaluation validate the effectiveness and efficiency of our proposed solution.","PeriodicalId":13255,"journal":{"name":"IEEE Transactions on Services Computing","volume":"17 6","pages":"4481-4493"},"PeriodicalIF":5.5,"publicationDate":"2024-10-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142439674","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 : 2024-10-14DOI: 10.1109/TSC.2024.3479935
Hamta Sedghani;Federica Filippini;Danilo Ardagna
Nowadays, Artificial Intelligence (AI) applications are becoming increasingly popular in a wide range of industries, mainly thanks to Deep Neural Networks (DNNs) that needs powerful resources. Cloud computing is a promising approach to serve AI applications thanks to its high processing power, but this sometimes results in an unacceptable latency because of long-distance communication. Vice versa, edge computing is close to where data are generated and therefore it is becoming crucial for their timely, flexible, and secure management. Given the more distributed nature of the edge and the heterogeneity of its resources, efficient component placement and resource allocation approaches become critical in orchestrating the application execution. In this paper, we formulate the resource selection and AI applications component placement problem in a computing continuum as a Mixed Integer Non-Linear Problem (MINLP), and we propose a design-time tool for its efficient solution. We first propose a Random Greedy algorithm to minimize the cost of the placement while guaranteeing some response time performance constraints. Then, we develop some heuristic methods such as Local Search, Tabu Search, Simulated Annealing and Genetic Algorithms, to improve the initial solutions provided by the Random Greedy. To evaluate our proposed approach, we designed an extensive experimental campaign, comparing the heuristics methods with one another and then the best heuristic against Best Cost Performance Constraint (BCPC) algorithm, a state-of-the-art approach. The results demonstrate that our proposed approach finds lower-cost solution than BCPC (27.6% on average) under the same time limit in large-scale systems. Finally, during the validation in a real edge system including FaaS resources our approach finds the globally optimal solution, suffering a deviation of around 12% between actual and predicted costs.
{"title":"SPACE4AI-D: A Design-Time Tool for AI Applications Resource Selection in Computing Continua","authors":"Hamta Sedghani;Federica Filippini;Danilo Ardagna","doi":"10.1109/TSC.2024.3479935","DOIUrl":"10.1109/TSC.2024.3479935","url":null,"abstract":"Nowadays, Artificial Intelligence (AI) applications are becoming increasingly popular in a wide range of industries, mainly thanks to Deep Neural Networks (DNNs) that needs powerful resources. Cloud computing is a promising approach to serve AI applications thanks to its high processing power, but this sometimes results in an unacceptable latency because of long-distance communication. Vice versa, edge computing is close to where data are generated and therefore it is becoming crucial for their timely, flexible, and secure management. Given the more distributed nature of the edge and the heterogeneity of its resources, efficient component placement and resource allocation approaches become critical in orchestrating the application execution. In this paper, we formulate the resource selection and AI applications component placement problem in a computing continuum as a Mixed Integer Non-Linear Problem (MINLP), and we propose a design-time tool for its efficient solution. We first propose a Random Greedy algorithm to minimize the cost of the placement while guaranteeing some response time performance constraints. Then, we develop some heuristic methods such as Local Search, Tabu Search, Simulated Annealing and Genetic Algorithms, to improve the initial solutions provided by the Random Greedy. To evaluate our proposed approach, we designed an extensive experimental campaign, comparing the heuristics methods with one another and then the best heuristic against Best Cost Performance Constraint (BCPC) algorithm, a state-of-the-art approach. The results demonstrate that our proposed approach finds lower-cost solution than BCPC (27.6% on average) under the same time limit in large-scale systems. Finally, during the validation in a real edge system including FaaS resources our approach finds the globally optimal solution, suffering a deviation of around 12% between actual and predicted costs.","PeriodicalId":13255,"journal":{"name":"IEEE Transactions on Services Computing","volume":"17 6","pages":"4324-4339"},"PeriodicalIF":5.5,"publicationDate":"2024-10-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142439672","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 : 2024-10-11DOI: 10.1109/TSC.2024.3478768
Mohammad Reza Jabbarpour;Bahman Javadi;Philip H.W. Leong;Rodrigo N. Calheiros;David Boland
Low Earth Orbit (LEO) satellite constellations have diverse applications, including earth observation, communication services, navigation, and positioning. These constellations have evolved into a valuable data source; however, their use in a ground station (GS) for analysis via machine learning algorithms presents challenges due to constraints on power consumption, communication bandwidth, and onboard computing capabilities. While the combination of Federated Learning (FL) and Orbital Edge Computing has been employed to address these challenges, its heavy reliance on the GS for model aggregation and edge resource limitations remains a research challenge. This article presents FedOrbit, a novel energy-efficient and decentralised FL method to optimise communication with the GS and reduce power consumption. FedOrbit utilises reinforcement learning for cluster formation, satellite visiting patterns for master satellite selection, and block minifloat arithmetic for power reduction. Extensive performance evaluation under Walker Delta-based LEO constellation configurations and different datasets reveals that FedOrbit can maintain high accuracy while significantly reduce communication demand, power consumption and training time in comparison to state-of-the-art FL approaches. The proposed technique can also reduce the training time by 5× compared with the centralised FL approaches. In addition, the utilisation of block minifloat representation as low-precision arithmetic enhanced the energy consumption by 3.5× compared with the single-precision (FP32) format.
{"title":"FedOrbit: Energy Efficient Federated Learning for Orbital Edge Computing Using Block Minifloat Arithmetic","authors":"Mohammad Reza Jabbarpour;Bahman Javadi;Philip H.W. Leong;Rodrigo N. Calheiros;David Boland","doi":"10.1109/TSC.2024.3478768","DOIUrl":"10.1109/TSC.2024.3478768","url":null,"abstract":"Low Earth Orbit (LEO) satellite constellations have diverse applications, including earth observation, communication services, navigation, and positioning. These constellations have evolved into a valuable data source; however, their use in a ground station (GS) for analysis via machine learning algorithms presents challenges due to constraints on power consumption, communication bandwidth, and onboard computing capabilities. While the combination of Federated Learning (FL) and Orbital Edge Computing has been employed to address these challenges, its heavy reliance on the GS for model aggregation and edge resource limitations remains a research challenge. This article presents FedOrbit, a novel energy-efficient and decentralised FL method to optimise communication with the GS and reduce power consumption. FedOrbit utilises reinforcement learning for cluster formation, satellite visiting patterns for master satellite selection, and block minifloat arithmetic for power reduction. Extensive performance evaluation under Walker Delta-based LEO constellation configurations and different datasets reveals that FedOrbit can maintain high accuracy while significantly reduce communication demand, power consumption and training time in comparison to state-of-the-art FL approaches. The proposed technique can also reduce the training time by 5× compared with the centralised FL approaches. In addition, the utilisation of block minifloat representation as low-precision arithmetic enhanced the energy consumption by 3.5× compared with the single-precision (FP32) format.","PeriodicalId":13255,"journal":{"name":"IEEE Transactions on Services Computing","volume":"17 6","pages":"3657-3671"},"PeriodicalIF":5.5,"publicationDate":"2024-10-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142415694","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}
Accurate and reliable service quality prediction has become a key issue in service recommendation and network measurement scenarios. However, traditional methods for time-aware QoS prediction face two main challenges: (I) data sparsity makes it difficult to estimate and recover global information from the limited known data; (II) shallow learning models struggle to represent the intricate relationships between objects, and thus suffer poor prediction performance. To this end, we propose a time-aware QoS prediction framework that combines the merits of graph modeling, graph representation learning, and contrastive learning. First, a novel graph schema is proposed to capture the complex interactions between user-service-slots. Then, a prediction model is developed leveraging a graph convolutional network to learn the node representations by aggregating feature information from neighboring nodes. Finally, a novel contrastive learning strategy is used to improve the robustness of node representation. Experimental results on a large-scale dataset demonstrated that our proposed method significantly outperforms the state-of-the-art prediction methods on response time and throughput prediction tasks.
{"title":"Effective Graph Modeling and Contrastive Learning for Time-Aware QoS Prediction","authors":"Hao Wu;Shuting Tian;Binbin Jin;Yiji Zhao;Lei Zhang","doi":"10.1109/TSC.2024.3478836","DOIUrl":"10.1109/TSC.2024.3478836","url":null,"abstract":"Accurate and reliable service quality prediction has become a key issue in service recommendation and network measurement scenarios. However, traditional methods for time-aware QoS prediction face two main challenges: (I) data sparsity makes it difficult to estimate and recover global information from the limited known data; (II) shallow learning models struggle to represent the intricate relationships between objects, and thus suffer poor prediction performance. To this end, we propose a time-aware QoS prediction framework that combines the merits of graph modeling, graph representation learning, and contrastive learning. First, a novel graph schema is proposed to capture the complex interactions between user-service-slots. Then, a prediction model is developed leveraging a graph convolutional network to learn the node representations by aggregating feature information from neighboring nodes. Finally, a novel contrastive learning strategy is used to improve the robustness of node representation. Experimental results on a large-scale dataset demonstrated that our proposed method significantly outperforms the state-of-the-art prediction methods on response time and throughput prediction tasks.","PeriodicalId":13255,"journal":{"name":"IEEE Transactions on Services Computing","volume":"17 6","pages":"3513-3526"},"PeriodicalIF":5.5,"publicationDate":"2024-10-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142415698","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 : 2024-10-11DOI: 10.1109/TSC.2024.3478796
Juncheng Pu;Xiaodong Fu;Hai Dong;Pengcheng Zhang;Li Liu
Federated learning provides privacy protection to the collaborative training of global model based on distributed private data. The local private data is often in the presence of long-tailed distribution in reality, which downgrades the performance and causes biased results. In this paper, we propose a dynamic adaptive federated learning optimization algorithm with the Grey Wolf Optimizer and Markov Chain, named FedWolf, to solve the problems of performance degradation and result bias caused by the local long-tailed data. FedWolf is launched with a set of randomly initialized parameters instead of a shared parameter employed by existing methods. Then multi-level participants are elected based on the F1 scores calculated from the uploaded parameters. A dynamic weighting strategy based on the participant level is used to adaptively update parameters without artificial control. The above parameter updating is modelled as a Markov Process. After all communication rounds are completed, the future performance (including the probability of each participant is elected as different participant level) of participants is predicted through the historical Markov states. Finally, the probability of each participant is elected as the level 1 is used as the contribution weight and the global model is obtained through dynamic contribution weight aggregating. We introduce the Gini index to evaluate the bias of classification results. Extensive experiments are conducted to validate the effectiveness of FedWolf in solving the problems of performance cracks and categorization result bias as well as the robustness of adaptive parameter updating in resisting outliers and malicious users.
{"title":"Dynamic Adaptive Federated Learning on Local Long-Tailed Data","authors":"Juncheng Pu;Xiaodong Fu;Hai Dong;Pengcheng Zhang;Li Liu","doi":"10.1109/TSC.2024.3478796","DOIUrl":"10.1109/TSC.2024.3478796","url":null,"abstract":"Federated learning provides privacy protection to the collaborative training of global model based on distributed private data. The local private data is often in the presence of long-tailed distribution in reality, which downgrades the performance and causes biased results. In this paper, we propose a dynamic adaptive federated learning optimization algorithm with the Grey Wolf Optimizer and Markov Chain, named FedWolf, to solve the problems of performance degradation and result bias caused by the local long-tailed data. FedWolf is launched with a set of randomly initialized parameters instead of a shared parameter employed by existing methods. Then multi-level participants are elected based on the F1 scores calculated from the uploaded parameters. A dynamic weighting strategy based on the participant level is used to adaptively update parameters without artificial control. The above parameter updating is modelled as a Markov Process. After all communication rounds are completed, the future performance (including the probability of each participant is elected as different participant level) of participants is predicted through the historical Markov states. Finally, the probability of each participant is elected as the level 1 is used as the contribution weight and the global model is obtained through dynamic contribution weight aggregating. We introduce the Gini index to evaluate the bias of classification results. Extensive experiments are conducted to validate the effectiveness of FedWolf in solving the problems of performance cracks and categorization result bias as well as the robustness of adaptive parameter updating in resisting outliers and malicious users.","PeriodicalId":13255,"journal":{"name":"IEEE Transactions on Services Computing","volume":"17 6","pages":"3485-3498"},"PeriodicalIF":5.5,"publicationDate":"2024-10-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142415536","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 : 2024-10-11DOI: 10.1109/TSC.2024.3478822
Xikang Zhu;Wenbin Yao;Yingying Hou;Shigang Li;Juanjuan Luo;Zhibin Huang;Shengdong Fu
The combination of edge computing and replication technology provides service guarantee for edge applications. However, optimizing replica creation and placement to enhance system performance is challenging due to the limited resources available at the edge. In this context, effective replica management becomes crucial for efficient and reliable edge computing. This study proposes a real-time dynamic replica management model to address the challenges of replica creation and placement in the edge computing environment. Firstly, we design a prediction-based dynamic proactive replica creation algorithm. This algorithm integrates data popularity and node load, utilizing fuzzy membership functions to model data and node states, effectively handling the state uncertainty in certain conditions. It also defines overheating and undercooling similarities to assess the trend of state changes, thereby determining the optimal timing for replica creation. To prevent latency in replica creation, the algorithm employs an Long Short-Term Memory (LSTM) model with a deviation feedback mechanism, which helps prevent lag in replica creation and minimizes unnecessary replica generation. Secondly, we formula replica placement as a multi-objective optimization problem considering the node load and access degree. We use a joint optimization replica placement algorithm that combines Evolutionary Gradient Search (EGS) and Sorting Genetic Algorithm-II to solve the multi-objective replica placement problem. Finally, we conduct extensive experiments on the replica management model. The results demonstrate significant improvements in average response time, effective network utilization rate, storage space utilization rate, and system load balancing, which validate the effectiveness of the proposed method.
边缘计算与复制技术的结合为边缘应用提供了服务保障。然而，由于边缘可用资源有限，优化副本创建和放置以增强系统性能是具有挑战性的。在这种情况下，有效的副本管理对于高效可靠的边缘计算至关重要。本研究提出了一种实时动态副本管理模型，以解决边缘计算环境中副本创建和放置的挑战。首先，设计了一种基于预测的动态主动副本创建算法。该算法将数据流行度和节点负载相结合，利用模糊隶属函数对数据和节点状态进行建模，有效处理特定条件下的状态不确定性。它还定义了过热和过冷的相似性，以评估状态变化的趋势，从而确定创建副本的最佳时机。为了避免副本创建延迟，该算法采用了LSTM （Long short - short Memory）模型，该模型具有偏差反馈机制，避免了副本创建延迟，减少了不必要的副本生成。其次，考虑节点的负载和访问度，将副本的放置作为一个多目标优化问题。采用一种结合进化梯度搜索（EGS）和排序遗传算法- ii的联合优化副本放置算法来解决多目标副本放置问题。最后，我们对副本管理模型进行了大量的实验。结果表明，该方法在平均响应时间、有效网络利用率、存储空间利用率和系统负载均衡等方面均有显著改善，验证了该方法的有效性。
{"title":"RDRM: Real-Time Dynamic Replica Management With Joint Optimization for Edge Computing","authors":"Xikang Zhu;Wenbin Yao;Yingying Hou;Shigang Li;Juanjuan Luo;Zhibin Huang;Shengdong Fu","doi":"10.1109/TSC.2024.3478822","DOIUrl":"10.1109/TSC.2024.3478822","url":null,"abstract":"The combination of edge computing and replication technology provides service guarantee for edge applications. However, optimizing replica creation and placement to enhance system performance is challenging due to the limited resources available at the edge. In this context, effective replica management becomes crucial for efficient and reliable edge computing. This study proposes a real-time dynamic replica management model to address the challenges of replica creation and placement in the edge computing environment. Firstly, we design a prediction-based dynamic proactive replica creation algorithm. This algorithm integrates data popularity and node load, utilizing fuzzy membership functions to model data and node states, effectively handling the state uncertainty in certain conditions. It also defines overheating and undercooling similarities to assess the trend of state changes, thereby determining the optimal timing for replica creation. To prevent latency in replica creation, the algorithm employs an Long Short-Term Memory (LSTM) model with a deviation feedback mechanism, which helps prevent lag in replica creation and minimizes unnecessary replica generation. Secondly, we formula replica placement as a multi-objective optimization problem considering the node load and access degree. We use a joint optimization replica placement algorithm that combines Evolutionary Gradient Search (EGS) and Sorting Genetic Algorithm-II to solve the multi-objective replica placement problem. Finally, we conduct extensive experiments on the replica management model. The results demonstrate significant improvements in average response time, effective network utilization rate, storage space utilization rate, and system load balancing, which validate the effectiveness of the proposed method.","PeriodicalId":13255,"journal":{"name":"IEEE Transactions on Services Computing","volume":"17 6","pages":"4183-4196"},"PeriodicalIF":5.5,"publicationDate":"2024-10-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142415696","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 : 2024-10-11DOI: 10.1109/TSC.2024.3478841
Zhao Tong;Jiaxin Deng;Jing Mei;Yuanyang Zhang;Keqin Li
The widespread adoption of the Internet of Things (IoT) has increased demand for task processing via mobile edge computing (MEC). In this study, we designed a directed acyclic graph (DAG) task offloading workflow in MEC. Traditional task offloading often does not simultaneously take into account task upload delay and task communication delay, failing to accurately reflect real-world issues. The constraints between task execution delay, upload delay and communication delay were introduced to model system response time and energy consumption for optimization. To satisfy task dependencies, the edge rank_u sorting (ERS) algorithm is used to generate specific offloading queues. A federated deep q-network (FDQN) algorithm addresses the offloading issue. It is different from the traditional approach of uploading task information data to the edge and facing data privacy risks. FDQN deploies the model locally and only collects model parameters for aggregation to update the local model. The algorithm improves the performance and stability of the model while protecting user privacy. To automatically tune hyperparameters for multiple devices, we used the tree of parzen estimators (TPE) algorithm, and named the whole process federated DQN with automated hyperparameter optimization (FDAHO). Experimental results show that FDAHO outperforms other algorithms in scenarios of different task number, task types, and user numbers, with consideration of benchmarks.
{"title":"Multi-Objective DAG Task Offloading in MEC Environment Based on Federated DQN With Automated Hyperparameter Optimization","authors":"Zhao Tong;Jiaxin Deng;Jing Mei;Yuanyang Zhang;Keqin Li","doi":"10.1109/TSC.2024.3478841","DOIUrl":"10.1109/TSC.2024.3478841","url":null,"abstract":"The widespread adoption of the Internet of Things (IoT) has increased demand for task processing via mobile edge computing (MEC). In this study, we designed a directed acyclic graph (DAG) task offloading workflow in MEC. Traditional task offloading often does not simultaneously take into account task upload delay and task communication delay, failing to accurately reflect real-world issues. The constraints between task execution delay, upload delay and communication delay were introduced to model system response time and energy consumption for optimization. To satisfy task dependencies, the edge rank_u sorting (ERS) algorithm is used to generate specific offloading queues. A federated deep q-network (FDQN) algorithm addresses the offloading issue. It is different from the traditional approach of uploading task information data to the edge and facing data privacy risks. FDQN deploies the model locally and only collects model parameters for aggregation to update the local model. The algorithm improves the performance and stability of the model while protecting user privacy. To automatically tune hyperparameters for multiple devices, we used the tree of parzen estimators (TPE) algorithm, and named the whole process federated DQN with automated hyperparameter optimization (FDAHO). Experimental results show that FDAHO outperforms other algorithms in scenarios of different task number, task types, and user numbers, with consideration of benchmarks.","PeriodicalId":13255,"journal":{"name":"IEEE Transactions on Services Computing","volume":"17 6","pages":"3999-4012"},"PeriodicalIF":5.5,"publicationDate":"2024-10-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142415697","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 : 2024-10-11DOI: 10.1109/TSC.2024.3478730
Gang Sun;Yuhui Wang;Hongfang Yu;Mohsen Guizani
Space-Air-Ground Integrated Networks (SAGIN) is considered as the key structure of the next generation network. The space satellites and air nodes are potential candidates to assist and offload the computing tasks. An Unmanned Aerial Vehicle (UAV) collects computing tasks from IoT devices and then makes online offloading decisions. However, UAVs belonging to different service providers compete for computing resources from ground base stations during task scheduling, resulting in extremely long queue delays and load imbalance. In this paper, we designed a task scheduling algorithm based on Proportional Fairness-Aware Auction with Proximal Policy Optimization (PFAPPO), which decouples the task scheduling process in competitive scenarios into two parts: resource allocation and task offloading decision-making. We first propose an auction algorithm to allocate computing resources reasonably to each UAV, after resource allocation is completed, the UAV learns its available computing resources at each offloading destination. Based on the heterogeneous characteristics of the tasks, the UAV makes intelligent offloading decisions using the distributed deep reinforcement learning PPO algorithm. The simulation results show that our proposed PFAPPO has obvious performance improvement compared with existing methods in terms of system profit, load balancing, and system fairness.
{"title":"Proportional Fairness-Aware Task Scheduling in Space-Air-Ground Integrated Networks","authors":"Gang Sun;Yuhui Wang;Hongfang Yu;Mohsen Guizani","doi":"10.1109/TSC.2024.3478730","DOIUrl":"10.1109/TSC.2024.3478730","url":null,"abstract":"Space-Air-Ground Integrated Networks (SAGIN) is considered as the key structure of the next generation network. The space satellites and air nodes are potential candidates to assist and offload the computing tasks. An Unmanned Aerial Vehicle (UAV) collects computing tasks from IoT devices and then makes online offloading decisions. However, UAVs belonging to different service providers compete for computing resources from ground base stations during task scheduling, resulting in extremely long queue delays and load imbalance. In this paper, we designed a task scheduling algorithm based on Proportional Fairness-Aware Auction with Proximal Policy Optimization (PFAPPO), which decouples the task scheduling process in competitive scenarios into two parts: resource allocation and task offloading decision-making. We first propose an auction algorithm to allocate computing resources reasonably to each UAV, after resource allocation is completed, the UAV learns its available computing resources at each offloading destination. Based on the heterogeneous characteristics of the tasks, the UAV makes intelligent offloading decisions using the distributed deep reinforcement learning PPO algorithm. The simulation results show that our proposed PFAPPO has obvious performance improvement compared with existing methods in terms of system profit, load balancing, and system fairness.","PeriodicalId":13255,"journal":{"name":"IEEE Transactions on Services Computing","volume":"17 6","pages":"4125-4137"},"PeriodicalIF":5.5,"publicationDate":"2024-10-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142415695","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：