Pub Date : 2023-11-15DOI: 10.1109/TCC.2023.3333223
Yi Dou;Henry C. B. Chan
Searchable encryption is a technique that can support operations on encrypted data directly. However, searchable encryption is still vulnerable to attacks that exploit the leakages from encrypted query results. This article presents an effective multi-server searchable encryption scheme to prevent volume and access pattern leakages. To hide the volume leakage of a keyword, a new index construction is proposed to compress multiple results into one index. To prevent the attacker from observing the access pattern of injected records, the update and search phases are executed in batches, such that the server can only retrieve multiple numbers of fixed volumes. To reduce the co-occurrence leakage, we propose our index distribution algorithm. Both records and queries are dispatched among cloud servers such that the attacker cannot recover the trapdoor values by only observing one cloud server. We use the minimum $s-t$ cut algorithm to find the optimal assignment strategy that can diminish the query response time and the information disclosure at the same time. We formally analyze the security strengths and conduct evaluations. The experimental results indicate that our designs can strike a good balance between security and efficiency.
{"title":"Leakage-Suppressed Encrypted Keyword Queries Over Multiple Cloud Servers","authors":"Yi Dou;Henry C. B. Chan","doi":"10.1109/TCC.2023.3333223","DOIUrl":"10.1109/TCC.2023.3333223","url":null,"abstract":"Searchable encryption is a technique that can support operations on encrypted data directly. However, searchable encryption is still vulnerable to attacks that exploit the leakages from encrypted query results. This article presents an effective multi-server searchable encryption scheme to prevent volume and access pattern leakages. To hide the volume leakage of a keyword, a new index construction is proposed to compress multiple results into one index. To prevent the attacker from observing the access pattern of injected records, the update and search phases are executed in batches, such that the server can only retrieve multiple numbers of fixed volumes. To reduce the co-occurrence leakage, we propose our index distribution algorithm. Both records and queries are dispatched among cloud servers such that the attacker cannot recover the trapdoor values by only observing one cloud server. We use the minimum \u0000<inline-formula><tex-math>$s-t$</tex-math></inline-formula>\u0000 cut algorithm to find the optimal assignment strategy that can diminish the query response time and the information disclosure at the same time. We formally analyze the security strengths and conduct evaluations. The experimental results indicate that our designs can strike a good balance between security and efficiency.","PeriodicalId":13202,"journal":{"name":"IEEE Transactions on Cloud Computing","volume":null,"pages":null},"PeriodicalIF":6.5,"publicationDate":"2023-11-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135709782","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 : 2023-11-10DOI: 10.1109/TCC.2023.3329129
Danlin Jia;Li Wang;Natalia Valencia;Janki Bhimani;Bo Sheng;Ningfang Mi
Apache Spark is an in-memory analytic framework that has been adopted in the industry and research fields. Two memory managers, Static and Unified, are available in Spark to allocate memory for caching Resilient Distributed Datasets (RDDs) and executing tasks. However, we find that the static memory manager (SMM) lacks flexibility, while the unified memory manager (UMM) puts heavy pressure on the garbage collection of the JVM on which Spark resides. To address these issues, we design a learning-based bidirectional usage-bounded memory allocation scheme to support dynamic memory allocation with the consideration of both memory demands and latency introduced by garbage collection. We first develop an auto-tuning memory manager (ATuMm) that adopts an intuitive feedback-based learning solution. However, ATuMm is a slow learner that can only alter the states of Java Virtual Memory (JVM) Heap in a limited range. That is, ATuMm decides to increase or decrease the boundary between the execution and storage memory pools by a fixed portion of JVM Heap size. To overcome this shortcoming, we further develop a new reinforcement learning-based memory manager (Q-ATuMm) that uses a Q-learning intelligent agent to dynamically learn and tune the partition of JVM Heap. We implement our new memory managers in Spark 2.4.0 and evaluate them by conducting experiments in a real Spark cluster. Our experimental results show that our memory manager can reduce the total garbage collection time and thus further improve Spark applications’ performance (i.e., reduced latency) compared to the existing Spark memory management solutions. By integrating our machine learning-driven memory manager into Spark, we can further obtain around 1.3x times reduction in the latency.
{"title":"Learning-Based Dynamic Memory Allocation Schemes for Apache Spark Data Processing","authors":"Danlin Jia;Li Wang;Natalia Valencia;Janki Bhimani;Bo Sheng;Ningfang Mi","doi":"10.1109/TCC.2023.3329129","DOIUrl":"10.1109/TCC.2023.3329129","url":null,"abstract":"Apache Spark is an in-memory analytic framework that has been adopted in the industry and research fields. Two memory managers, Static and Unified, are available in Spark to allocate memory for caching Resilient Distributed Datasets (RDDs) and executing tasks. However, we find that the static memory manager (SMM) lacks flexibility, while the unified memory manager (UMM) puts heavy pressure on the garbage collection of the JVM on which Spark resides. To address these issues, we design a learning-based bidirectional usage-bounded memory allocation scheme to support dynamic memory allocation with the consideration of both memory demands and latency introduced by garbage collection. We first develop an auto-tuning memory manager (ATuMm) that adopts an intuitive feedback-based learning solution. However, ATuMm is a slow learner that can only alter the states of Java Virtual Memory (JVM) Heap in a limited range. That is, ATuMm decides to increase or decrease the boundary between the execution and storage memory pools by a fixed portion of JVM Heap size. To overcome this shortcoming, we further develop a new reinforcement learning-based memory manager (Q-ATuMm) that uses a Q-learning intelligent agent to dynamically learn and tune the partition of JVM Heap. We implement our new memory managers in Spark 2.4.0 and evaluate them by conducting experiments in a real Spark cluster. Our experimental results show that our memory manager can reduce the total garbage collection time and thus further improve Spark applications’ performance (i.e., reduced latency) compared to the existing Spark memory management solutions. By integrating our machine learning-driven memory manager into Spark, we can further obtain around 1.3x times reduction in the latency.","PeriodicalId":13202,"journal":{"name":"IEEE Transactions on Cloud Computing","volume":null,"pages":null},"PeriodicalIF":6.5,"publicationDate":"2023-11-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135610951","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 : 2023-11-02DOI: 10.1109/TCC.2023.3329646
Hui Sun;Guanzhong Chen;Yinliang Yue;Xiao Qin
LSM-tree-based key-value stores (KV stores) render high-performance read/write services to data-intensive applications. KV stores employ an SSTable-based Coarse-Grained Compaction (CGC) mechanism, which involves a huge amount of data that do not need to be updated, thereby bringing a high write amplification (WA) and long tail latency. To address this issue, we propose a Fine-Grained Compaction (FGC) mechanism anchored on a L og- S tructured p atched- M erge tree (LSpM-tree) - a new data organization that averts rewriting irrelevant data into disks amid compaction. A cluster, the basic unit in FGC, encloses several patches and a redirection table, where each patch has an array of KV regions. We devise three compaction modes powered by the LSpM-tree, and we implement a high-performance key-value store, named FGKV. The extensive experiments show that FGKV improves the random-write throughput by up to 121%, 36.8%, 38.6%, and 15.2% compared with LevelDB, RocksDB, LDC, and ALDC, respectively. FGKV lowers the WA of the alternative KV stores by up to 50%. FGKV boosts read performance by up to 122%, 51.4%, 96.6%, and 368%, respectively, and FGKV curbs the 99th percentile latency of LevelDB, RocksDB, LDC, and ALDC by up to 78.2%, 77.6%, 78.3%, and 73.1% under YCSB A, respectively. Moreover, FGKV is readily extended to the other KV stores.
{"title":"Improving LSM-Tree Based Key-Value Stores With Fine-Grained Compaction Mechanism","authors":"Hui Sun;Guanzhong Chen;Yinliang Yue;Xiao Qin","doi":"10.1109/TCC.2023.3329646","DOIUrl":"10.1109/TCC.2023.3329646","url":null,"abstract":"LSM-tree-based key-value stores (KV stores) render high-performance read/write services to data-intensive applications. KV stores employ an SSTable-based Coarse-Grained Compaction (CGC) mechanism, which involves a huge amount of data that do not need to be updated, thereby bringing a high write amplification (WA) and long tail latency. To address this issue, we propose a Fine-Grained Compaction (FGC) mechanism anchored on a \u0000<bold>L</b>\u0000og-\u0000<bold>S</b>\u0000tructured \u0000<bold>p</b>\u0000atched-\u0000<bold>M</b>\u0000erge tree (LSpM-tree) - a new data organization that averts rewriting irrelevant data into disks amid compaction. A cluster, the basic unit in FGC, encloses several patches and a redirection table, where each patch has an array of KV regions. We devise three compaction modes powered by the LSpM-tree, and we implement a high-performance key-value store, named FGKV. The extensive experiments show that FGKV improves the random-write throughput by up to 121%, 36.8%, 38.6%, and 15.2% compared with LevelDB, RocksDB, LDC, and ALDC, respectively. FGKV lowers the WA of the alternative KV stores by up to 50%. FGKV boosts read performance by up to 122%, 51.4%, 96.6%, and 368%, respectively, and FGKV curbs the 99th percentile latency of LevelDB, RocksDB, LDC, and ALDC by up to 78.2%, 77.6%, 78.3%, and 73.1% under YCSB A, respectively. Moreover, FGKV is readily extended to the other KV stores.","PeriodicalId":13202,"journal":{"name":"IEEE Transactions on Cloud Computing","volume":null,"pages":null},"PeriodicalIF":6.5,"publicationDate":"2023-11-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134890814","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 : 2023-10-30DOI: 10.1109/TCC.2023.3328614
Kai Peng;Peiyun Xiao;Shangguang Wang;Victor C. M. Leung
With the rapid growth of the Industrial Internet of Things, a large amount of industrial data that needs to be processed promptly. Edge computing-based computation offloading can well assist industrial devices to process these data and reduce the overall time overhead. However, there are dependencies among tasks and some tasks have high latency requirements, so completing computation offloading while considering the above factors faces important challenges. In this article, we design a computation offloading method based on a directed acyclic graph task model by modeling task dependencies. In addition to considering traditional optimization objectives in previous computation offloading problems (e.g., latency, energy consumption, etc.), we also propose an age of information (AoI) model to reflect the freshness of information and transform the task offloading problem into an optimization problem for latency, energy consumption, and AoI. To address this issue, we propose a method based on an improved dueling double deep Q-network computation offloading algorithm, named ID3CO. Specifically, it combines the advantages of deep Q-network, double deep Q-network, and dueling deep Q-network algorithms while further utilizing deep residual neural networks to improve convergence. Extensive simulations are conducted to demonstrate that ID3CO outperforms the existing baselines in terms of performance.
{"title":"AoI-Aware Partial Computation Offloading in IIoT With Edge Computing: A Deep Reinforcement Learning Based Approach","authors":"Kai Peng;Peiyun Xiao;Shangguang Wang;Victor C. M. Leung","doi":"10.1109/TCC.2023.3328614","DOIUrl":"10.1109/TCC.2023.3328614","url":null,"abstract":"With the rapid growth of the Industrial Internet of Things, a large amount of industrial data that needs to be processed promptly. Edge computing-based computation offloading can well assist industrial devices to process these data and reduce the overall time overhead. However, there are dependencies among tasks and some tasks have high latency requirements, so completing computation offloading while considering the above factors faces important challenges. In this article, we design a computation offloading method based on a directed acyclic graph task model by modeling task dependencies. In addition to considering traditional optimization objectives in previous computation offloading problems (e.g., latency, energy consumption, etc.), we also propose an age of information (AoI) model to reflect the freshness of information and transform the task offloading problem into an optimization problem for latency, energy consumption, and AoI. To address this issue, we propose a method based on an improved dueling double deep Q-network computation offloading algorithm, named ID3CO. Specifically, it combines the advantages of deep Q-network, double deep Q-network, and dueling deep Q-network algorithms while further utilizing deep residual neural networks to improve convergence. Extensive simulations are conducted to demonstrate that ID3CO outperforms the existing baselines in terms of performance.","PeriodicalId":13202,"journal":{"name":"IEEE Transactions on Cloud Computing","volume":null,"pages":null},"PeriodicalIF":6.5,"publicationDate":"2023-10-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135262391","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 : 2023-10-24DOI: 10.1109/TCC.2023.3327290
Michał Kucab;Piotr Boryło;Piotr Chołda
This article is devoted to the problems of static and runtime integrity for cloud deployments. Existing remote attestation solutions for cloud infrastructure do not cover static and dynamic attestation as a whole. They evaluate either the static or dynamic part, not considering the rest. We address this gap by proposing a runtime attestation process based on hardware CET technology, as an enhancement to static attestation enabled by SGX. We show how hardware-assisted protection for control-flow-related attacks can enhance virtual deployment security with minimal tradeoff. Our solution does not significantly increase the processing time. Moreover, a processing time can even be reduced when this mechanism is used as a default protection method against control-flow related attacks.
{"title":"Hardware-Assisted Static and Runtime Attestation for Cloud Deployments","authors":"Michał Kucab;Piotr Boryło;Piotr Chołda","doi":"10.1109/TCC.2023.3327290","DOIUrl":"10.1109/TCC.2023.3327290","url":null,"abstract":"This article is devoted to the problems of static and runtime integrity for cloud deployments. Existing remote attestation solutions for cloud infrastructure do not cover static and dynamic attestation as a whole. They evaluate either the static or dynamic part, not considering the rest. We address this gap by proposing a runtime attestation process based on hardware CET technology, as an enhancement to static attestation enabled by SGX. We show how hardware-assisted protection for control-flow-related attacks can enhance virtual deployment security with minimal tradeoff. Our solution does not significantly increase the processing time. Moreover, a processing time can even be reduced when this mechanism is used as a default protection method against control-flow related attacks.","PeriodicalId":13202,"journal":{"name":"IEEE Transactions on Cloud Computing","volume":null,"pages":null},"PeriodicalIF":6.5,"publicationDate":"2023-10-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135157477","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 : 2023-10-23DOI: 10.1109/TCC.2023.3326339
Chunlin Li;Jinguo Li;Kai Zhang;Yan Yan;Jianting Ning
Cloud-based publish-subscribe (pub-sub) services provide a decoupling method for publishers and subscribers to effectively exchange targeted information and massive data on the cloud platform. Data publishers implement fine-grained access control to set subscription privileges for outsourced data through an access policy. However, in the context of semi-honest cloud platforms, the publisher's access policy may be collected, and incomplete or incorrect subscription results may be returned (e.g., to save communication costs). Existing solutions pay little attention to protecting the data publisher's access policy and cannot provide efficient verification for local results. In this article, we propose a verifiable multi-keyword data publish-subscribe scheme with a hidden access policy (VMP/S). Specifically, VMP/S combines attribute-based keyword search and data aggregation technology to achieve secure fine-grained access control, thereby protecting the privacy of the access policy. Additionally, the scheme provides an effective method for verifying local results by using equal-length verification information to confirm the correctness of feedback subscription data. Furthermore, we introduce a novel verification method for access control to enhance subscription performance efficiency. We demonstrate that VMP/S achieves IND-CKA security and ensures the privacy of the access policy through a comprehensive security analysis. Through experimental simulations, we confirm its effectiveness.
{"title":"Verifiable Cloud-Based Data Publish-Subscribe Service With Hidden Access Policy","authors":"Chunlin Li;Jinguo Li;Kai Zhang;Yan Yan;Jianting Ning","doi":"10.1109/TCC.2023.3326339","DOIUrl":"10.1109/TCC.2023.3326339","url":null,"abstract":"Cloud-based publish-subscribe (pub-sub) services provide a decoupling method for publishers and subscribers to effectively exchange targeted information and massive data on the cloud platform. Data publishers implement fine-grained access control to set subscription privileges for outsourced data through an access policy. However, in the context of semi-honest cloud platforms, the publisher's access policy may be collected, and incomplete or incorrect subscription results may be returned (e.g., to save communication costs). Existing solutions pay little attention to protecting the data publisher's access policy and cannot provide efficient verification for local results. In this article, we propose a verifiable multi-keyword data publish-subscribe scheme with a hidden access policy (VMP/S). Specifically, VMP/S combines attribute-based keyword search and data aggregation technology to achieve secure fine-grained access control, thereby protecting the privacy of the access policy. Additionally, the scheme provides an effective method for verifying local results by using equal-length verification information to confirm the correctness of feedback subscription data. Furthermore, we introduce a novel verification method for access control to enhance subscription performance efficiency. We demonstrate that VMP/S achieves IND-CKA security and ensures the privacy of the access policy through a comprehensive security analysis. Through experimental simulations, we confirm its effectiveness.","PeriodicalId":13202,"journal":{"name":"IEEE Transactions on Cloud Computing","volume":null,"pages":null},"PeriodicalIF":6.5,"publicationDate":"2023-10-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135106395","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}
Co-location, which deploys long running applications and batch-processing applications in the same computing cluster, has become a promising way to improve resource utility for large cloud datacenters. However, co-location brings huge challenges to task scheduling because different types of workloads may affect each other. Existing works on task scheduling rarely focus on the scenario of co-location. This article presents Co-ScheRRL, a scheduling algorithm delicately designed for co-located workloads. Co-ScheRRL consists of two major mechanisms: i) a self-attention encoding mechanism which encodes and represents states of the computing cluster as a set of embedding feature vectors; ii) a deep reinforcement learning (DRL) relational reasoning mechanism which calculates and compares different scheduling actions under different co-located workloads pattern via DRL feedback reward signals based on these feature vectors. Our two mechanisms can tackle complicatedly and dynamically varying behaviors of co-located workloads. With the help of these two mechanisms, Co-ScheRRL is able to construct high-quality scheduling policies. Trace-driven simulation demonstrates that Co-ScheRRL outperforms existing scheduling algorithms in terms of makespan by more than 38.4% and throughput by more than 166.7%.
{"title":"Learning Scheduling Policies for Co-Located Workloads in Cloud Datacenters","authors":"Jialun Li;Danyang Xiao;Jieqian Yao;Yujie Long;Weigang Wu","doi":"10.1109/TCC.2023.3319383","DOIUrl":"10.1109/TCC.2023.3319383","url":null,"abstract":"Co-location, which deploys long running applications and batch-processing applications in the same computing cluster, has become a promising way to improve resource utility for large cloud datacenters. However, co-location brings huge challenges to task scheduling because different types of workloads may affect each other. Existing works on task scheduling rarely focus on the scenario of co-location. This article presents Co-ScheRRL, a scheduling algorithm delicately designed for co-located workloads. Co-ScheRRL consists of two major mechanisms: i) a self-attention encoding mechanism which encodes and represents states of the computing cluster as a set of embedding feature vectors; ii) a deep reinforcement learning (DRL) relational reasoning mechanism which calculates and compares different scheduling actions under different co-located workloads pattern via DRL feedback reward signals based on these feature vectors. Our two mechanisms can tackle complicatedly and dynamically varying behaviors of co-located workloads. With the help of these two mechanisms, Co-ScheRRL is able to construct high-quality scheduling policies. Trace-driven simulation demonstrates that Co-ScheRRL outperforms existing scheduling algorithms in terms of makespan by more than 38.4% and throughput by more than 166.7%.","PeriodicalId":13202,"journal":{"name":"IEEE Transactions on Cloud Computing","volume":null,"pages":null},"PeriodicalIF":6.5,"publicationDate":"2023-09-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135748503","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 : 2023-09-25DOI: 10.1109/TCC.2023.3319038
Shuo Wang;Zhijun Ding;Ru Yang;Changjun Jiang
The interaction process in microservice architectures is highly complex, making it very challenging to ensure correct behavioral interactions. The few related works focus only on the verification of interaction soundness in the case of a specific buffer k -value, without considering how to get the suitable buffer k -value. To solve the above problems, this article proposes a method to find the maximum k -value for microservice systems with bounded buffers, which can maximize the analysis of valuable asynchronous interaction paths while avoiding the waste of computer memory resources. Specific contributions include, first, giving the relationship between buffer k -value and asynchronous interaction paths, interaction soundness, and its proof; second, proposing an iterative detection based on the additional added paths algorithm and its correctness proof, which leads to the conclusion that finding the maximum k -value is a decidable problem; finally, validating the proposing methods on ten classical cases of microservice systems, and analyzing effectiveness and performance. The experimental results show that the method can effectively find the maximum k -value of bounded buffers compared with existing methods and thus ensure the correct behavioral interactions of microservice systems.
微服务架构中的交互过程非常复杂，因此确保正确的行为交互非常具有挑战性。为数不多的相关著作只关注特定缓冲区 k 值情况下交互合理性的验证，而没有考虑如何获得合适的缓冲区 k 值。为了解决上述问题，本文提出了一种为缓冲区有界的微服务系统寻找最大 k 值的方法，可以最大限度地分析有价值的异步交互路径，同时避免计算机内存资源的浪费。具体贡献包括：首先，给出了缓冲区k值与异步交互路径之间的关系、交互健全性及其证明；其次，提出了基于额外添加路径算法的迭代检测方法及其正确性证明，从而得出寻找最大k值是一个可解问题的结论；最后，在十个微服务系统的经典案例上验证了所提出的方法，并分析了有效性和性能。实验结果表明，与现有方法相比，该方法能有效求出有界缓冲区的最大k值，从而保证微服务系统行为交互的正确性。
{"title":"A Complex Behavioral Interaction Analysis Method for Microservice Systems With Bounded Buffers","authors":"Shuo Wang;Zhijun Ding;Ru Yang;Changjun Jiang","doi":"10.1109/TCC.2023.3319038","DOIUrl":"10.1109/TCC.2023.3319038","url":null,"abstract":"The interaction process in microservice architectures is highly complex, making it very challenging to ensure correct behavioral interactions. The few related works focus only on the verification of interaction soundness in the case of a specific buffer \u0000<italic>k</i>\u0000-value, without considering how to get the suitable buffer \u0000<italic>k</i>\u0000-value. To solve the above problems, this article proposes a method to find the maximum \u0000<italic>k</i>\u0000-value for microservice systems with bounded buffers, which can maximize the analysis of valuable asynchronous interaction paths while avoiding the waste of computer memory resources. Specific contributions include, first, giving the relationship between buffer \u0000<italic>k</i>\u0000-value and asynchronous interaction paths, interaction soundness, and its proof; second, proposing an iterative detection based on the additional added paths algorithm and its correctness proof, which leads to the conclusion that finding the maximum \u0000<italic>k</i>\u0000-value is a decidable problem; finally, validating the proposing methods on ten classical cases of microservice systems, and analyzing effectiveness and performance. The experimental results show that the method can effectively find the maximum \u0000<italic>k</i>\u0000-value of bounded buffers compared with existing methods and thus ensure the correct behavioral interactions of microservice systems.","PeriodicalId":13202,"journal":{"name":"IEEE Transactions on Cloud Computing","volume":null,"pages":null},"PeriodicalIF":6.5,"publicationDate":"2023-09-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135699997","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 : 2023-09-19DOI: 10.1109/TCC.2023.3307582
Feibo Jiang;Yubo Peng;Kezhi Wang;Li Dong;Kun Yang
This article studies a dynamic Mobile Edge Computing (MEC) system assisted by Unmanned Aerial Vehicles (UAVs) and Intelligent Reflective Surfaces (IRSs). We propose a scaleable resource scheduling algorithm to minimize the energy consumption of all UEs and UAVs in the MEC system with a variable number of UAVs. We propose a Multi-tAsk Resource Scheduling (MARS) framework based on Deep Reinforcement Learning (DRL) to solve the problem. First, we present a novel Advantage Actor-Critic (A2C) structure with the state-value critic and entropy-enhanced actor to reduce variance and enhance the policy search of DRL. Then, we present a multi-head agent with three different heads in which a classification head is applied to make offloading decisions and a regression head is presented to allocate computational resources, and a critic head is introduced to estimate the state value of the selected action. Next, we introduce a multi-task controller to adjust the agent to adapt to the varying number of UAVs by loading or unloading a part of weights in the agent. Finally, a Light Wolf Search (LWS) is introduced as the action refinement to enhance the exploration in the dynamic action space. The numerical results demonstrate the feasibility and efficiency of the MARS framework.
{"title":"MARS: A DRL-Based Multi-Task Resource Scheduling Framework for UAV With IRS-Assisted Mobile Edge Computing System","authors":"Feibo Jiang;Yubo Peng;Kezhi Wang;Li Dong;Kun Yang","doi":"10.1109/TCC.2023.3307582","DOIUrl":"10.1109/TCC.2023.3307582","url":null,"abstract":"This article studies a dynamic Mobile Edge Computing (MEC) system assisted by Unmanned Aerial Vehicles (UAVs) and Intelligent Reflective Surfaces (IRSs). We propose a scaleable resource scheduling algorithm to minimize the energy consumption of all UEs and UAVs in the MEC system with a variable number of UAVs. We propose a Multi-tAsk Resource Scheduling (MARS) framework based on Deep Reinforcement Learning (DRL) to solve the problem. First, we present a novel Advantage Actor-Critic (A2C) structure with the state-value critic and entropy-enhanced actor to reduce variance and enhance the policy search of DRL. Then, we present a multi-head agent with three different heads in which a classification head is applied to make offloading decisions and a regression head is presented to allocate computational resources, and a critic head is introduced to estimate the state value of the selected action. Next, we introduce a multi-task controller to adjust the agent to adapt to the varying number of UAVs by loading or unloading a part of weights in the agent. Finally, a Light Wolf Search (LWS) is introduced as the action refinement to enhance the exploration in the dynamic action space. The numerical results demonstrate the feasibility and efficiency of the MARS framework.","PeriodicalId":13202,"journal":{"name":"IEEE Transactions on Cloud Computing","volume":null,"pages":null},"PeriodicalIF":6.5,"publicationDate":"2023-09-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135551147","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 : 2023-09-13DOI: 10.1109/TCC.2023.3315014
Zhihua Cui;Tianhao Zhao;Linjie Wu;A. K. Qin;Jianwei Li
Cloud platforms scheduling resources based on the demand of the tasks submitted by the users, is critical to the cloud provider's interest and customer satisfaction. In this paper, we propose a multi-objective cloud task scheduling algorithm based on an evolutionary multi-factorial optimization algorithm. First, we choose execution time, execution cost, and virtual machines load balancing as the objective functions to construct a multi-objective cloud task scheduling model. Second, the multi-factor optimization (MFO) technique is applied to the task scheduling problem, and the task scheduling characteristics are combined with the multi-objective multi-factor optimization (MO-MFO) algorithm to construct an assisted optimization task. Finally, a dynamic adaptive transfer strategy is designed to determine the similarity between tasks according to the degree of overlap of the MFO problem and to control the intensity of knowledge transfer. The results of simulation experiments on the cloud task test dataset show that our method significantly improves scheduling efficiency, compared with other evolutionary algorithms (EAs), the scheduling method simplifies the decomposition of complex problems by a multi-factor approach, while using knowledge transfer to share the convergence direction among sub-populations, which can find the optimal solution interval more quickly and achieve the best results among all objective functions.
{"title":"Multi-Objective Cloud Task Scheduling Optimization Based on Evolutionary Multi-Factor Algorithm","authors":"Zhihua Cui;Tianhao Zhao;Linjie Wu;A. K. Qin;Jianwei Li","doi":"10.1109/TCC.2023.3315014","DOIUrl":"10.1109/TCC.2023.3315014","url":null,"abstract":"Cloud platforms scheduling resources based on the demand of the tasks submitted by the users, is critical to the cloud provider's interest and customer satisfaction. In this paper, we propose a multi-objective cloud task scheduling algorithm based on an evolutionary multi-factorial optimization algorithm. First, we choose execution time, execution cost, and virtual machines load balancing as the objective functions to construct a multi-objective cloud task scheduling model. Second, the multi-factor optimization (MFO) technique is applied to the task scheduling problem, and the task scheduling characteristics are combined with the multi-objective multi-factor optimization (MO-MFO) algorithm to construct an assisted optimization task. Finally, a dynamic adaptive transfer strategy is designed to determine the similarity between tasks according to the degree of overlap of the MFO problem and to control the intensity of knowledge transfer. The results of simulation experiments on the cloud task test dataset show that our method significantly improves scheduling efficiency, compared with other evolutionary algorithms (EAs), the scheduling method simplifies the decomposition of complex problems by a multi-factor approach, while using knowledge transfer to share the convergence direction among sub-populations, which can find the optimal solution interval more quickly and achieve the best results among all objective functions.","PeriodicalId":13202,"journal":{"name":"IEEE Transactions on Cloud Computing","volume":null,"pages":null},"PeriodicalIF":6.5,"publicationDate":"2023-09-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135403631","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：