As energy-intensive entities, data centers are associated with significant environmental impacts, making their sustainability a subject of growing interest in recent years. In this article, we revisit data center sustainability and propose a forward-looking vision for improving data center sustainability. We argue that data center sustainability encompasses more than just energy efficiency and must be evaluated and optimized through a multi-faceted approach. To this end, we first present an overview of the sustainability metrics from five aspects. After that, we demonstrate the sustainability status of the latest data centers utilizing publicly available data center sustainability ratings. Furthermore, we examine the evolution of data center sustainability standards in Singapore to highlight several trending features. Based on the analysis, we identify several key elements of sustainable data centers. We then propose the Cognitive Digital Twin (CDT) architecture, which incorporates a digital twin engine for system-wide simulation and a decision engine for optimal control to improve data center sustainability. A case study is performed to optimize the chiller plant efficiency of a production data center in Singapore. The results demonstrate that the CDT can improve chiller plant energy efficiency by 5%, indicating around 140 metric tons of annual carbon emission savings.
{"title":"Data Center Sustainability: Revisits and Outlooks","authors":"Zhiwei Cao;Xin Zhou;Xiangyu Wu;Zhaomeng Zhu;Tracy Liu;Jeffery Neng;Yonggang Wen","doi":"10.1109/TSUSC.2023.3281583","DOIUrl":"10.1109/TSUSC.2023.3281583","url":null,"abstract":"As energy-intensive entities, data centers are associated with significant environmental impacts, making their sustainability a subject of growing interest in recent years. In this article, we revisit data center sustainability and propose a forward-looking vision for improving data center sustainability. We argue that data center sustainability encompasses more than just energy efficiency and must be evaluated and optimized through a multi-faceted approach. To this end, we first present an overview of the sustainability metrics from five aspects. After that, we demonstrate the sustainability status of the latest data centers utilizing publicly available data center sustainability ratings. Furthermore, we examine the evolution of data center sustainability standards in Singapore to highlight several trending features. Based on the analysis, we identify several key elements of sustainable data centers. We then propose the Cognitive Digital Twin (CDT) architecture, which incorporates a digital twin engine for system-wide simulation and a decision engine for optimal control to improve data center sustainability. A case study is performed to optimize the chiller plant efficiency of a production data center in Singapore. The results demonstrate that the CDT can improve chiller plant energy efficiency by 5%, indicating around 140 metric tons of annual carbon emission savings.","PeriodicalId":13268,"journal":{"name":"IEEE Transactions on Sustainable Computing","volume":"9 3","pages":"236-248"},"PeriodicalIF":3.9,"publicationDate":"2023-03-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"88809223","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-03-31DOI: 10.1109/TSUSC.2023.3263510
Xinghao Yang;Yongshun Gong;Weifeng Liu;James Bailey;Dacheng Tao;Wei Liu
Deep learning models are known immensely brittle to adversarial text examples. Existing text adversarial attack strategies can be roughly divided into character-level, word-level, and sentence-level attacks. Despite the success brought by recent text attack methods, how to induce misclassification with minimal text modifications while keeping the lexical correctness, syntactic soundness, and semantic consistency is still a challenge. In this paper, we devise a Bigram and Unigram-based adaptive Semantic Preservation Optimization (BU-SPO) approach which attacks text documents not only at a unigram word level but also at a bigram level to avoid generating meaningless sentences. We also present a hybrid attack strategy that collects substitution words from both synonyms and sememe candidates, to enrich the potential candidate set. Besides, a Semantic Preservation Optimization (SPO) method is devised to determine the word substitution priority and reduce the perturbation cost. Furthermore, we constrain the SPO with a semantic Filter (dubbed SPOF) to improve the semantic similarity. To estimate the effectiveness of our proposed methods, BU-SPO and BU-SPOF, we attack four victim deep learning models trained on three text datasets. Experimental results demonstrate that our approaches accomplish the highest semantics consistency and attack success rates by making minimal word modifications compared with competitive methods.
{"title":"Semantic-Preserving Adversarial Text Attacks","authors":"Xinghao Yang;Yongshun Gong;Weifeng Liu;James Bailey;Dacheng Tao;Wei Liu","doi":"10.1109/TSUSC.2023.3263510","DOIUrl":"https://doi.org/10.1109/TSUSC.2023.3263510","url":null,"abstract":"Deep learning models are known immensely brittle to adversarial text examples. Existing text adversarial attack strategies can be roughly divided into character-level, word-level, and sentence-level attacks. Despite the success brought by recent text attack methods, how to induce misclassification with minimal text modifications while keeping the lexical correctness, syntactic soundness, and semantic consistency is still a challenge. In this paper, we devise a Bigram and Unigram-based adaptive Semantic Preservation Optimization (BU-SPO) approach which attacks text documents not only at a unigram word level but also at a bigram level to avoid generating meaningless sentences. We also present a hybrid attack strategy that collects substitution words from both synonyms and sememe candidates, to enrich the potential candidate set. Besides, a Semantic Preservation Optimization (SPO) method is devised to determine the word substitution priority and reduce the perturbation cost. Furthermore, we constrain the SPO with a semantic Filter (dubbed SPOF) to improve the semantic similarity. To estimate the effectiveness of our proposed methods, BU-SPO and BU-SPOF, we attack four victim deep learning models trained on three text datasets. Experimental results demonstrate that our approaches accomplish the highest semantics consistency and attack success rates by making minimal word modifications compared with competitive methods.","PeriodicalId":13268,"journal":{"name":"IEEE Transactions on Sustainable Computing","volume":"8 4","pages":"583-595"},"PeriodicalIF":3.9,"publicationDate":"2023-03-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"138558208","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-03-30DOI: 10.1109/TSUSC.2023.3263232
Bo Yin;Weilong Zeng;Peng Zhang;Xuetao Wei
The data query service is urgently required in sustainable-storage blockchain, where full nodes store the entire transaction data while light nodes only store block headers. Queries invariably seek data with multiple attributes. However, no existing method provides a unified authenticated data structure (ADS) to support complex query operators (e.g., range queries and data object queries) on multiattribute blockchain data. In this paper, we propose a framework EAQ that effectively supports both fast data queries on multiple attributes and authentication of the query result. We propose a new ADS, called the MR $^{Bloom}$ -tree, based on the Bloom filter (BF) and Merkle R-tree. We prove the decomposability of BFs, which enables the BF to be seamlessly incorporated with the Merkle R-tree. This ADS enables range-level search using multidimensional attribute ranges and object-level search using BFs. This ADS also supports querying and proving inexistent data objects. To reduce storage overhead, we improve the MR $^{Bloom}$ -tree using the suppressed BF structure, which constructs only one BF independent of the number of attributes. To manage string attributes, we transform them into discrete numerical attributes using density-based clustering to represent similar items with close numerical values. Experiments show that the proposed framework achieves promising results.
{"title":"EAQ: Enabling Authenticated Complex Query Services in Sustainable-Storage Blockchain","authors":"Bo Yin;Weilong Zeng;Peng Zhang;Xuetao Wei","doi":"10.1109/TSUSC.2023.3263232","DOIUrl":"https://doi.org/10.1109/TSUSC.2023.3263232","url":null,"abstract":"The data query service is urgently required in sustainable-storage blockchain, where full nodes store the entire transaction data while light nodes only store block headers. Queries invariably seek data with multiple attributes. However, no existing method provides a unified authenticated data structure (ADS) to support complex query operators (e.g., range queries and data object queries) on multiattribute blockchain data. In this paper, we propose a framework EAQ that effectively supports both fast data queries on multiple attributes and authentication of the query result. We propose a new ADS, called the MR\u0000<inline-formula><tex-math>$^{Bloom}$</tex-math></inline-formula>\u0000-tree, based on the Bloom filter (BF) and Merkle R-tree. We prove the decomposability of BFs, which enables the BF to be seamlessly incorporated with the Merkle R-tree. This ADS enables range-level search using multidimensional attribute ranges and object-level search using BFs. This ADS also supports querying and proving inexistent data objects. To reduce storage overhead, we improve the MR\u0000<inline-formula><tex-math>$^{Bloom}$</tex-math></inline-formula>\u0000-tree using the suppressed BF structure, which constructs only one BF independent of the number of attributes. To manage string attributes, we transform them into discrete numerical attributes using density-based clustering to represent similar items with close numerical values. Experiments show that the proposed framework achieves promising results.","PeriodicalId":13268,"journal":{"name":"IEEE Transactions on Sustainable Computing","volume":"8 3","pages":"435-447"},"PeriodicalIF":3.9,"publicationDate":"2023-03-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"50400595","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The integration of conventional sources with the grid has many challenges, like carbon emission, optimal cost of the system, and power quality issues. All these shortcomings create a non-sustainability in the environment, which is of great concern. In order to overcome such issues, a hybrid system is designed that is composed of various components or sources like wind energy, solar photovoltaic energy, thermal energy, and battery energy storage with the purpose of providing an environmentally friendly, economically viable, sustainable, and reliable solution. The objective is to reduce the carbon capture, carbon utilization, and carbon footprint. The carbon footprint is measured as the optimal difference between carbon capture (CC) and its utilization (CU), and carbon emission is represented as loss of carbon emission (LCE). Another objective is to reduce the optimal size of components, the distortion level, and the optimal cost in terms of loss of cost of energy (LCOE) for the various values of loss of power supply probability (LPSP). All the above objectives are accomplished by designing a nonlinear multi-objective problem. The designed nonlinear multi-objective function is based on a hybrid hysteresis fuzzy algorithm. The proposed algorithm is a combination of both fuzzy logic controllers and the hysteresis band method. The effectiveness of the proposed topology is tested on an IEEE standard 9 bus system. It is observed that a nonlinear hybrid hysteresis fuzzy algorithm provides a reliable and sustainable solution for optimal cost with a reduced effective carbon footprint and minimal distortion by maintaining the proper balance between carbon capturing and carbon utilization. The average values of LCOE,LCE, CU, and CC with the proposed method for various LPSP are found to be 0.5926 $/KWh, 70.64 g CO2/kWh, 89 g CO2/kWh, and 159 g CO2/kWh, which are the least among all methods.
传统电源与电网的集成面临许多挑战，如碳排放、系统的最佳成本和电能质量问题。所有这些缺点造成了环境的不可持续性，这引起了人们的极大关注。为了克服这些问题，设计了一种由风能、太阳能光伏、热能和电池储能等各种组件或来源组成的混合系统，目的是提供一种环境友好、经济可行、可持续和可靠的解决方案。目标是减少碳捕获、碳利用和碳足迹。碳足迹被测量为碳捕获（CC）和碳利用（CU）之间的最佳差异，碳排放被表示为碳排放损失（LCE）。另一个目标是针对不同的电源损耗概率（LPSP）值，降低组件的最佳尺寸、失真水平和能量损耗（LCOE）方面的最佳成本。所有上述目标都是通过设计一个非线性多目标问题来实现的。所设计的非线性多目标函数基于混合滞后模糊算法。所提出的算法是模糊逻辑控制器和滞后带方法的结合。所提出的拓扑结构的有效性在IEEE标准9总线系统上进行了测试。观察到，非线性混合滞后模糊算法通过保持碳捕获和碳利用之间的适当平衡，为优化成本提供了可靠和可持续的解决方案，同时减少了有效碳足迹，并将失真降至最低。对于各种LPSP，采用所提出的方法的LCOE、LCE、CU和CC的平均值分别为0.5926$/KWh、70.64 g CO2/KWh、89 g CO2/Wh和159 g CO2/kW，这是所有方法中最小的。
{"title":"An Effective Optimal Economic Sustainable Clean Energy Solution With Reduced Carbon Capturing/Carbon Utilization/ Carbon Footprint for Grid Integrated Hybrid System","authors":"Abhinav Saxena;Aseem Chandel;Amit Kumar Dash;Shailendra Kumar Gupta;Sampath Kumar V;J. P. Pandey","doi":"10.1109/TSUSC.2023.3262982","DOIUrl":"https://doi.org/10.1109/TSUSC.2023.3262982","url":null,"abstract":"The integration of conventional sources with the grid has many challenges, like carbon emission, optimal cost of the system, and power quality issues. All these shortcomings create a non-sustainability in the environment, which is of great concern. In order to overcome such issues, a hybrid system is designed that is composed of various components or sources like wind energy, solar photovoltaic energy, thermal energy, and battery energy storage with the purpose of providing an environmentally friendly, economically viable, sustainable, and reliable solution. The objective is to reduce the carbon capture, carbon utilization, and carbon footprint. The carbon footprint is measured as the optimal difference between carbon capture (CC) and its utilization (CU), and carbon emission is represented as loss of carbon emission (LCE). Another objective is to reduce the optimal size of components, the distortion level, and the optimal cost in terms of loss of cost of energy (LCOE) for the various values of loss of power supply probability (LPSP). All the above objectives are accomplished by designing a nonlinear multi-objective problem. The designed nonlinear multi-objective function is based on a hybrid hysteresis fuzzy algorithm. The proposed algorithm is a combination of both fuzzy logic controllers and the hysteresis band method. The effectiveness of the proposed topology is tested on an IEEE standard 9 bus system. It is observed that a nonlinear hybrid hysteresis fuzzy algorithm provides a reliable and sustainable solution for optimal cost with a reduced effective carbon footprint and minimal distortion by maintaining the proper balance between carbon capturing and carbon utilization. The average values of LCOE,LCE, CU, and CC with the proposed method for various LPSP are found to be 0.5926 $/KWh, 70.64 g CO2/kWh, 89 g CO2/kWh, and 159 g CO2/kWh, which are the least among all methods.","PeriodicalId":13268,"journal":{"name":"IEEE Transactions on Sustainable Computing","volume":"8 3","pages":"385-399"},"PeriodicalIF":3.9,"publicationDate":"2023-03-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"50400596","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-03-29DOI: 10.1109/TSUSC.2023.3278655
Yuepeng Li;Deze Zeng
Task offloading to edge servers has become a promising solution to tackle the computation resource poverty of the end devices. However, the zero-trust edge computing platform is highly challenged by the growing concern on security and privacy. Thus, Trust Execution Environment (TEE), like TrustZone, is advocated to empower edge clouds to enable secure task offloading. To explore TrustZone, the inevitable involvement of data encryption and decryption operations makes existing offloading strategies not applicable any more, especially when the task dependency is considered. In addition, TrustZone has distinguishable task scheduling paradigm as one CPU core does not allow multitask coexist at the same time. Taking the above issues into consideration, we investigate a dependency-aware task offloading problem for makespan minimization in TrustZone empowered edge clouds. By inventing an extended graph to describe the task execution process, we provide a formal statement to the problem and prove its NP-hardness. We then propose a Customized List Scheduling (CLS) based approximate algorithm and theoretically analyze its achievable performance. Extensive testbed based experiment results show that our approximation algorithm can effectively reduce the makespan and significantly outperforms existing state-of-the-art offloading approaches in TrustZone empowered edge clouds.
{"title":"Dependency-Aware Task Scheduling in TrustZone Empowered Edge Clouds for Makespan Minimization","authors":"Yuepeng Li;Deze Zeng","doi":"10.1109/TSUSC.2023.3278655","DOIUrl":"https://doi.org/10.1109/TSUSC.2023.3278655","url":null,"abstract":"Task offloading to edge servers has become a promising solution to tackle the computation resource poverty of the end devices. However, the zero-trust edge computing platform is highly challenged by the growing concern on security and privacy. Thus, Trust Execution Environment (TEE), like TrustZone, is advocated to empower edge clouds to enable secure task offloading. To explore TrustZone, the inevitable involvement of data encryption and decryption operations makes existing offloading strategies not applicable any more, especially when the task dependency is considered. In addition, TrustZone has distinguishable task scheduling paradigm as one CPU core does not allow multitask coexist at the same time. Taking the above issues into consideration, we investigate a dependency-aware task offloading problem for makespan minimization in TrustZone empowered edge clouds. By inventing an extended graph to describe the task execution process, we provide a formal statement to the problem and prove its NP-hardness. We then propose a Customized List Scheduling (CLS) based approximate algorithm and theoretically analyze its achievable performance. Extensive testbed based experiment results show that our approximation algorithm can effectively reduce the makespan and significantly outperforms existing state-of-the-art offloading approaches in TrustZone empowered edge clouds.","PeriodicalId":13268,"journal":{"name":"IEEE Transactions on Sustainable Computing","volume":"8 3","pages":"423-434"},"PeriodicalIF":3.9,"publicationDate":"2023-03-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"50280161","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-03-23DOI: 10.1109/TSUSC.2023.3279111
Zhuotao Lian;Weizheng Wang;Zhaoyang Han;Chunhua Su
The rapid growth of artificial intelligence (AI), blockchain technology, and edge computing services have enabled the Internet of Medical Things (IoMT) to provide various healthcare services to patients, including neural network-based disease diagnosis, heart rate monitoring, and fall detection. Generally, end devices should transmit the collected patient data to a centralized server for further model training, but at the same time, the patient's privacy may be at risk. In addition, due to the diversity of patient conditions, a one-size-fits-all model cannot meet personalized healthcare needs. To address the above challenges, we propose a blockchain-based personalized federated learning (FL) system that enables clients to participate in personalized model training without directly uploading private data. We further realize the decentralized FL by combining blockchain technology, which improves the security level of the system. Finally, we verify the reliable performance of our system on different datasets through simulation experiments.
{"title":"Blockchain-Based Personalized Federated Learning for Internet of Medical Things","authors":"Zhuotao Lian;Weizheng Wang;Zhaoyang Han;Chunhua Su","doi":"10.1109/TSUSC.2023.3279111","DOIUrl":"10.1109/TSUSC.2023.3279111","url":null,"abstract":"The rapid growth of artificial intelligence (AI), blockchain technology, and edge computing services have enabled the Internet of Medical Things (IoMT) to provide various healthcare services to patients, including neural network-based disease diagnosis, heart rate monitoring, and fall detection. Generally, end devices should transmit the collected patient data to a centralized server for further model training, but at the same time, the patient's privacy may be at risk. In addition, due to the diversity of patient conditions, a one-size-fits-all model cannot meet personalized healthcare needs. To address the above challenges, we propose a blockchain-based personalized federated learning (FL) system that enables clients to participate in personalized model training without directly uploading private data. We further realize the decentralized FL by combining blockchain technology, which improves the security level of the system. Finally, we verify the reliable performance of our system on different datasets through simulation experiments.","PeriodicalId":13268,"journal":{"name":"IEEE Transactions on Sustainable Computing","volume":"8 4","pages":"694-702"},"PeriodicalIF":3.9,"publicationDate":"2023-03-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76181749","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-03-22DOI: 10.1109/TSUSC.2023.3278464
Zhuoqun Xia;Dan Yin;Ke Gu;Xiong Li
Data classification of users’ electricity consumption provides an in-depth analysis for users’ electricity consumption status, which plays a vital role in the management and distribution of electric energy. So, some data classification methods have been proposed to solve the classification problem of electricity consumption data. However, plaintext-based data classification may bring about the privacy leakage of electricity consumption data. In this paper, we propose a privacy-preserving classification scheme for electricity consumption data under fog computing-based smart metering system, which is based on convolutional neural network (CNN) model with fully homomorphic method (CKKS). The target of our proposed scheme is to solve the leakage problem of private electricity consumption data during the classification procedure. In our scheme, an improved K-means-based labeling algorithm is constructed to process historical electricity consumption data, which is used as the sample data to train the CNN classification model by cloud server. Also, the fog nodes are only permitted to obtain the related ciphertext parameters of the trained CNN model, and perform the classification of ciphertext-based electricity consumption data generated by fully homomorphic method. Based on the classical testing data, the experimental results show that our proposed classification scheme can provide the high classification accuracy of electricity data while protecting the privacy of electricity data.
{"title":"Privacy-Preserving Electricity Data Classification Scheme Based on CNN Model With Fully Homomorphism","authors":"Zhuoqun Xia;Dan Yin;Ke Gu;Xiong Li","doi":"10.1109/TSUSC.2023.3278464","DOIUrl":"10.1109/TSUSC.2023.3278464","url":null,"abstract":"Data classification of users’ electricity consumption provides an in-depth analysis for users’ electricity consumption status, which plays a vital role in the management and distribution of electric energy. So, some data classification methods have been proposed to solve the classification problem of electricity consumption data. However, plaintext-based data classification may bring about the privacy leakage of electricity consumption data. In this paper, we propose a privacy-preserving classification scheme for electricity consumption data under fog computing-based smart metering system, which is based on convolutional neural network (CNN) model with fully homomorphic method (CKKS). The target of our proposed scheme is to solve the leakage problem of private electricity consumption data during the classification procedure. In our scheme, an improved K-means-based labeling algorithm is constructed to process historical electricity consumption data, which is used as the sample data to train the CNN classification model by cloud server. Also, the fog nodes are only permitted to obtain the related ciphertext parameters of the trained CNN model, and perform the classification of ciphertext-based electricity consumption data generated by fully homomorphic method. Based on the classical testing data, the experimental results show that our proposed classification scheme can provide the high classification accuracy of electricity data while protecting the privacy of electricity data.","PeriodicalId":13268,"journal":{"name":"IEEE Transactions on Sustainable Computing","volume":"8 4","pages":"652-669"},"PeriodicalIF":3.9,"publicationDate":"2023-03-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"84551622","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-03-20DOI: 10.1109/TSUSC.2023.3259522
Jing Bi;Haisen Ma;Haitao Yuan;Jia Zhang
Currently, cloud computing service providers face big challenges in predicting large-scale workload and resource usage time series. Due to the difficulty in capturing nonlinear features, traditional forecasting methods usually fail to achieve high prediction performance for resource usage and workload sequences. Besides, there is much noise in original time series of resources and workloads. If these time series are not de-noised by smoothing algorithms, the prediction results can fail to meet the providers’ requirements. To do so, this work proposes a hybrid prediction model named VAMBiG that integrates V ariational mode decomposition, an A daptive Savitzky-Golay (SG) filter, a M ulti-head attention mechanism, Bi directional and G rid versions of Long and Short Term Memory (LSTM) networks. VAMBiG adopts a signal decomposition method named variational mode decomposition to decompose complex and non-linear original time series into low-frequency intrinsic mode functions. Then, it adopts an adaptive SG filter as a data pre-processing tool to eliminate noise and extreme points in such functions. Afterwards, it adopts bidirectional and grid LSTM networks to capture bidirectional features and dimension ones, respectively. Finally, it adopts a multi-head attention mechanism to explore importance of different data dimensions. VAMBiG aims to predict resource usage and workloads in highly variable traces in clouds. Extensive experimental results demonstrate that it achieves higher-accuracy prediction than several advanced prediction approaches with datasets from Google and Alibaba cluster traces.
{"title":"Accurate Prediction of Workloads and Resources With Multi-Head Attention and Hybrid LSTM for Cloud Data Centers","authors":"Jing Bi;Haisen Ma;Haitao Yuan;Jia Zhang","doi":"10.1109/TSUSC.2023.3259522","DOIUrl":"https://doi.org/10.1109/TSUSC.2023.3259522","url":null,"abstract":"Currently, cloud computing service providers face big challenges in predicting large-scale workload and resource usage time series. Due to the difficulty in capturing nonlinear features, traditional forecasting methods usually fail to achieve high prediction performance for resource usage and workload sequences. Besides, there is much noise in original time series of resources and workloads. If these time series are not de-noised by smoothing algorithms, the prediction results can fail to meet the providers’ requirements. To do so, this work proposes a hybrid prediction model named VAMBiG that integrates \u0000<underline>V</u>\u0000ariational mode decomposition, an \u0000<underline>A</u>\u0000daptive Savitzky-Golay (SG) filter, a \u0000<underline>M</u>\u0000ulti-head attention mechanism, \u0000<underline>Bi</u>\u0000directional and \u0000<underline>G</u>\u0000rid versions of Long and Short Term Memory (LSTM) networks. VAMBiG adopts a signal decomposition method named variational mode decomposition to decompose complex and non-linear original time series into low-frequency intrinsic mode functions. Then, it adopts an adaptive SG filter as a data pre-processing tool to eliminate noise and extreme points in such functions. Afterwards, it adopts bidirectional and grid LSTM networks to capture bidirectional features and dimension ones, respectively. Finally, it adopts a multi-head attention mechanism to explore importance of different data dimensions. VAMBiG aims to predict resource usage and workloads in highly variable traces in clouds. Extensive experimental results demonstrate that it achieves higher-accuracy prediction than several advanced prediction approaches with datasets from Google and Alibaba cluster traces.","PeriodicalId":13268,"journal":{"name":"IEEE Transactions on Sustainable Computing","volume":"8 3","pages":"375-384"},"PeriodicalIF":3.9,"publicationDate":"2023-03-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"50280164","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
In medical cloud computing, more medical data owners are preferred to outsource their sensitive data to the cloud after encryption. Meanwhile, dynamic searchable symmetric encryption (DSSE) provides the capability for data users to query over the dynamically-updated encrypted database. To reduce update leakage, a secure DSSE scheme usually requires forward and backward privacy. However, existing multi-client DSSE schemes with forward and backward privacy require the data owner to keep online to respond to per-query interaction from data users. To address this issue, we propose a multi-client non-interactive DSSE scheme with forward and backward privacy, namely MCNI. The core design of MCNI is leveraging time range queries to achieve non-interactive forward privacy since the past queries cannot be used to search the newly-added timestamps. To enable efficient time range queries, we convert the timestamp and time range into the boolean wildcard form and develop Boolean Wildcard Matching (BWM) algorithm that formulates the match as a dot product calculation problem. Finally, we combine the polynomial fitting technique, time range query, and random matrix multiplication technique to achieve efficient keyword searches without revealing sensitive information. Theoretical analysis and extensive experiments demonstrate the security and effectiveness of our proposed scheme, respectively.
{"title":"Non-Interactive DSSE for Medical Data Sharing With Forward and Backward Privacy","authors":"Hanqi Zhang;Chang Xu;Liehuang Zhu;Chuan Zhang;Rongxing Lu;Yunguo Guan;Kashif Sharif","doi":"10.1109/TSUSC.2023.3277876","DOIUrl":"10.1109/TSUSC.2023.3277876","url":null,"abstract":"In medical cloud computing, more medical data owners are preferred to outsource their sensitive data to the cloud after encryption. Meanwhile, dynamic searchable symmetric encryption (DSSE) provides the capability for data users to query over the dynamically-updated encrypted database. To reduce update leakage, a secure DSSE scheme usually requires forward and backward privacy. However, existing multi-client DSSE schemes with forward and backward privacy require the data owner to keep online to respond to per-query interaction from data users. To address this issue, we propose a multi-client non-interactive DSSE scheme with forward and backward privacy, namely MCNI. The core design of MCNI is leveraging time range queries to achieve non-interactive forward privacy since the past queries cannot be used to search the newly-added timestamps. To enable efficient time range queries, we convert the timestamp and time range into the boolean wildcard form and develop Boolean Wildcard Matching (BWM) algorithm that formulates the match as a dot product calculation problem. Finally, we combine the polynomial fitting technique, time range query, and random matrix multiplication technique to achieve efficient keyword searches without revealing sensitive information. Theoretical analysis and extensive experiments demonstrate the security and effectiveness of our proposed scheme, respectively.","PeriodicalId":13268,"journal":{"name":"IEEE Transactions on Sustainable Computing","volume":"8 4","pages":"682-693"},"PeriodicalIF":3.9,"publicationDate":"2023-03-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"78460915","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-03-15DOI: 10.1109/TSUSC.2023.3276206
Pengfei Sun;Leixiao Li;Jianxiong Wan
With the swift development of express delivery industry, the increasingly attention has been shifted to express delivery mechanism design. Generally, the revenue of the courier is the difference between the users’ express fee and the courier's pickup cost. In order to improve the revenue of courier without increasing the user's express fee, this paper presents a low-cost package pickup covering system to find an optimal Hamiltonian pickup tour for the courier over a subset of packages, where packages who are not on the tour should be covered exactly by one package on the tour. A billing rule discounting the express fee to incentivize users to deliver their packages is also proposed. We formulate Low-cost Package Pickup Covering (LPPC) problem to maximize the revenue of the courier. Considering the complexity of LPPC , we propose a Low-cost Package Pickup Covering Mechanism (LPPCM) to solve the LPPC problem including problem transformation, hardness analyzing, Attention Model based on Encoder-Decoder Architecture (AMEDA) model design and model training. AMEDA is trained by a deep reinforcement learning algorithm in an unsupervised manner and it can directly output the solution based on the given instances. Through extensive simulations, we demonstrate that the average revenue of courier for AMEDA is at least 10.1% higher than the traditional heuristic local search and is 18.5% lower than the optimal solution on average. AMEDA provides a desired trade-off between the execution time and solution quality, which is well suited for the large-scale tasks which require quick decisions.
{"title":"LPPCM: A Low-Cost Package Pickup Covering Mechanism for Cooperative Express Services","authors":"Pengfei Sun;Leixiao Li;Jianxiong Wan","doi":"10.1109/TSUSC.2023.3276206","DOIUrl":"10.1109/TSUSC.2023.3276206","url":null,"abstract":"With the swift development of express delivery industry, the increasingly attention has been shifted to express delivery mechanism design. Generally, the revenue of the courier is the difference between the users’ express fee and the courier's pickup cost. In order to improve the revenue of courier without increasing the user's express fee, this paper presents a low-cost package pickup covering system to find an optimal Hamiltonian pickup tour for the courier over a subset of packages, where packages who are not on the tour should be covered exactly by one package on the tour. A billing rule discounting the express fee to incentivize users to deliver their packages is also proposed. We formulate \u0000<italic>Low-cost Package Pickup Covering (LPPC)</i>\u0000 problem to maximize the revenue of the courier. Considering the complexity of \u0000<italic>LPPC</i>\u0000, we propose a \u0000<italic>Low-cost Package Pickup Covering Mechanism (LPPCM)</i>\u0000 to solve the \u0000<italic>LPPC</i>\u0000 problem including problem transformation, hardness analyzing, \u0000<italic>Attention Model based on Encoder-Decoder Architecture (AMEDA)</i>\u0000 model design and model training. \u0000<italic>AMEDA</i>\u0000 is trained by a deep reinforcement learning algorithm in an unsupervised manner and it can directly output the solution based on the given instances. Through extensive simulations, we demonstrate that the average revenue of courier for \u0000<italic>AMEDA</i>\u0000 is at least 10.1% higher than the traditional heuristic local search and is 18.5% lower than the optimal solution on average. \u0000<italic>AMEDA</i>\u0000 provides a desired trade-off between the execution time and solution quality, which is well suited for the large-scale tasks which require quick decisions.","PeriodicalId":13268,"journal":{"name":"IEEE Transactions on Sustainable Computing","volume":"9 3","pages":"386-395"},"PeriodicalIF":3.9,"publicationDate":"2023-03-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"84759466","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：