Future Generation Computer Systems-The International Journal of Escience最新文献

{"title":"A protocol generation model for protocol-unknown IoT devices","authors":"Zheng Gao ,&nbsp;Danfeng Sun ,&nbsp;Kai Wang ,&nbsp;Jia Wu ,&nbsp;Huifeng Wu","doi":"10.1016/j.future.2024.107638","DOIUrl":"10.1016/j.future.2024.107638","url":null,"abstract":"<div><div>The rapid growth of Internet of Things (IoT) applications depends on the deployment of numerous heterogeneous devices, and the deployed devices require various communication protocols to be accessed. Matching the correct protocol for accessed devices, particularly those with unknown protocols, is a complex and challenging task due to the diversity of device types, the growing number of protocols, and the reliance on domain-specific knowledge. To address these challenges, we propose a Device Clustering and Deep Reinforcement Learning-based Protocol Generation Model (DCDPM). The DCDPM generates the best-matched protocol for protocol-unknown IoT devices using only device basic information (DBI). The DCDPM employs a two-stage device clustering mechanism based on DBI similarity density to generate device clusters, and extracts protocol features from these clusters. Furthermore, a Weight Twin Delay-DDPG (WTD-DDPG), an enhanced deep reinforcement learning (DRL) method, is developed to determine the optimal weights for identifying the optimal device cluster. The WTD-DDPG addresses issues related to continuous action space and Q-value overestimation. Lastly, a feature-original fusion mechanism is designed to further enhance protocol matching by fusing the extracted protocol features with the original protocols within the optimal device cluster. Experimental validation of the DCDPM is conducted within two distinct scenarios: a communication base station and a copper smelting production line. A device library containing 1296 devices is created and 130 devices are tested. Experimental results demonstrate that DCDPM outperforms existing methods in terms of protocol matching rate, hit rate, and network traffic consumption.</div></div>","PeriodicalId":55132,"journal":{"name":"Future Generation Computer Systems-The International Journal of Escience","volume":"166 ","pages":"Article 107638"},"PeriodicalIF":6.2,"publicationDate":"2024-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142873862","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"FedCOLA: Federated learning with heterogeneous feature concatenation and local acceleration for non-IID data","authors":"Wu-Chun Chung,&nbsp;Chien-Hu Peng","doi":"10.1016/j.future.2024.107674","DOIUrl":"10.1016/j.future.2024.107674","url":null,"abstract":"<div><div>Federated Learning (FL) is an emerging training framework for machine learning to protect data privacy without accessing the original data from each client. However, the participating clients have different computing resources in FL. Clients with insufficient resources may not cooperate in the training due to hardware limitations. The restricted computing speeds may also slow down the overall computing time. In addition, the Non-IID problem happens when data distributions of the clients are varied, which results in lower performance for training. To overcome these problems, this paper proposes a FedCOLA approach to adapt various data distributions among heterogeneous clients. By introducing the feature concatenation and local update mechanism, FedCOLA supports different clients to train the model with different layers. Both communication load and time delay during collaborative training can be reduced. Combined with the adaptive auxiliary model and the personalized model, FedCOLA further improves the testing accuracy under various Non-IID data distributions. To evaluate the performance, this paper considers the effects and analysis of different Non-IID data distributions on distinct methods. The empirical results show that FedCOLA improves the accuracy by 5%, reduces 57% rounds to achieve the same accuracy, and reduces the communication load by 77% in the extremely imbalanced data distribution. Compared with the state-of-the-art methods in a real deployment of heterogeneous clients, FedCOLA reduces the time consumption by 70% to achieve the same accuracy and by 30% to complete 200 training rounds. In conclusion, the proposed FedCOLA not only accommodates various Non-IID data distributions but also supports the heterogeneous clients to train the model of different layers with a significant reduction of the time delay and communication load.</div></div>","PeriodicalId":55132,"journal":{"name":"Future Generation Computer Systems-The International Journal of Escience","volume":"166 ","pages":"Article 107674"},"PeriodicalIF":6.2,"publicationDate":"2024-12-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142825315","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"PHiFL-TL: Personalized hierarchical federated learning using transfer learning","authors":"Afsaneh Afzali,&nbsp;Pirooz Shamsinejadbabaki","doi":"10.1016/j.future.2024.107672","DOIUrl":"10.1016/j.future.2024.107672","url":null,"abstract":"<div><div>Federated Learning is a collaborative machine learning (ML) framework designed to train a globally shared model without accessing participants’ private data. However, due to the statistical heterogeneity in the participants’ data, federated learning faces significant challenges. This approach generates a similar output for all participants, without adapting the model to each individual. Consequently, the global model performs poorly on each participant's task. To mitigate these issues, personalized federated learning methods aim to reduce the negative effects caused by data heterogeneity. Previous personalized approaches have relied on a single central server. However, in federated learning based on a client-server architecture, the central server's workload becomes a bottleneck. In our paper, we propose a Personalized Hierarchical Federated Learning approach (PHiFL-TL). First, PHiFL-TL trains a global shared model using hierarchical federated learning. Next, it constructs relatively personalized models through transfer learning. We demonstrate the effectiveness of PHiFL-TL on non-identical and independent data partitions from MNIST and FEMNIST datasets.</div></div>","PeriodicalId":55132,"journal":{"name":"Future Generation Computer Systems-The International Journal of Escience","volume":"166 ","pages":"Article 107672"},"PeriodicalIF":6.2,"publicationDate":"2024-12-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142825316","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Quantum machine learning algorithms for anomaly detection: A review","authors":"Sebastiano Corli ,&nbsp;Lorenzo Moro ,&nbsp;Daniele Dragoni ,&nbsp;Massimiliano Dispenza ,&nbsp;Enrico Prati","doi":"10.1016/j.future.2024.107632","DOIUrl":"10.1016/j.future.2024.107632","url":null,"abstract":"<div><div>The advent of quantum computers has justified the development of quantum machine learning algorithms, based on the adaptation of the principles of machine learning to the formalism of qubits. Among such quantum algorithms, anomaly detection represents an important problem crossing several disciplines from cybersecurity, to fraud detection to particle physics. We summarize the key concepts involved in quantum computing, introducing the formal concept of quantum speed up. The survey provides a structured map of anomaly detection based on quantum machine learning. We have grouped existing algorithms according to the different learning methods, namely quantum supervised, quantum unsupervised and quantum reinforcement learning, respectively. We provide an estimate of the hardware resources to provide sufficient computational power in the future. The survey provides a systematic and compact understanding of the techniques belonging to each category. We eventually provide a discussion on the computational complexity of the learning methods in real application domains.</div></div>","PeriodicalId":55132,"journal":{"name":"Future Generation Computer Systems-The International Journal of Escience","volume":"166 ","pages":"Article 107632"},"PeriodicalIF":6.2,"publicationDate":"2024-12-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142825317","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Uncertainty-aware scheduling for effective data collection from environmental IoT devices through LEO satellites","authors":"Haoran Xu ,&nbsp;Xiaodao Chen ,&nbsp;Xiaohui Huang ,&nbsp;Geyong Min ,&nbsp;Yunliang Chen","doi":"10.1016/j.future.2024.107656","DOIUrl":"10.1016/j.future.2024.107656","url":null,"abstract":"<div><div>Low Earth Orbit (LEO) satellites have been widely used to collect sensing data from ground-based IoT devices. Comprehensive and timely collection of sensor data is a prerequisite for conducting analysis, decision-making, and other tasks, ultimately enhancing services such as geological hazard monitoring and ecological environment monitoring. To improve the efficiency of data collection, many models and scheduling methods have been proposed, but they did not fully consider the practical scenarios of collecting data from remote areas with limited ground network coverage, particularly in addressing the uncertainties in data transmission caused by complex environments. To cope with the above challenges, this paper first presents a mathematical representation of the real-world scenario for data collection from geographically distributed IoT devices through LEO satellites, based on a full consideration of uncertainties in transmission rates. Then, a Cross-entropy-based transmission scheduling method (CETSM) and an uncertainty-aware transmission scheduling method (UATSM) are proposed to enhance the volume of collected data and mitigate the impact of uncertainty on the data uplink transmission rate. The CETSM achieved an average increase in total data collection ranging from 7.24% to 16.69% compared to the other five benchmark methods across eight scenarios. Moreover, UATSM performs excellently in the Monte Carlo-based evaluation module, achieving an average data collection completion rate of 96.1% and saving an average of 19.8% in energy costs, thereby obtaining a good balance between energy consumption and completion rate.</div></div>","PeriodicalId":55132,"journal":{"name":"Future Generation Computer Systems-The International Journal of Escience","volume":"166 ","pages":"Article 107656"},"PeriodicalIF":6.2,"publicationDate":"2024-12-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142825318","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"PSPL: A Ponzi scheme smart contracts detection approach via compressed sensing oversampling-based peephole LSTM","authors":"Lei Wang ,&nbsp;Hao Cheng ,&nbsp;Zihao Sun ,&nbsp;Aolin Tian ,&nbsp;Zhonglian Yang","doi":"10.1016/j.future.2024.107655","DOIUrl":"10.1016/j.future.2024.107655","url":null,"abstract":"<div><div>Decentralized Finance (DeFi) utilizes the key principles of blockchain to improve the traditional finance system with greater freedom in trade. However, due to the absence of access restrictions in the implementation of decentralized finance protocols, effective regulatory measures are crucial to ensuring the healthy development of DeFi ecosystems. As a prominent DeFi platform, Ethereum has witnessed an increase in fraudulent activities, with the Ponzi schemes causing significant user losses. With the growing sophistication of Ponzi scheme fraud methods, existing detection techniques fail to effectively identify Ponzi schemes timely. To mitigate the risk of investor deception, we propose PSPL, a compressed sensing oversampling-based Peephole LSTM approach for detecting Ethereum Ponzi schemes. First, we identify Ethereum representative Ponzi schemes’ features by analyzing smart contracts’ codes and user accounts’ temporal transaction information based on the popular XBlock dataset. Second, to address the class imbalance and few-shot learning challenges, we leverage the compressed sensing approach to oversample the Ponzi Scheme samples. Third, peephole LSTM is employed to effectively capture long sequence variations in the fraud features of Ponzi schemes, accurately identifying hidden Ponzi schemes during the transaction process in case fraudulent features are exposed. Finally, experimental results demonstrate the effectiveness and efficiency of PSPL.</div></div>","PeriodicalId":55132,"journal":{"name":"Future Generation Computer Systems-The International Journal of Escience","volume":"166 ","pages":"Article 107655"},"PeriodicalIF":6.2,"publicationDate":"2024-12-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142825322","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"AISAW: An adaptive interference-aware scheduling algorithm for acceleration of deep learning workloads training on distributed heterogeneous systems","authors":"Yushen Bi ,&nbsp;Yupeng Xi ,&nbsp;Chao Jing","doi":"10.1016/j.future.2024.107642","DOIUrl":"10.1016/j.future.2024.107642","url":null,"abstract":"<div><div>Owing to the widespread application of artificial intelligence, deep learning (DL) has attracted considerable attention from both academia and industry. The DL workload-training process is a key step in determining the quality of DL-based applications. However, owing to the limited computational power of conventionally centralized clusters, it is more beneficial to accelerate workload training while placing them in distributed heterogeneous systems. Unfortunately, current scheduling algorithms do not account for the various capabilities of nodes and the limited network bandwidth, which leads to poor performance in distributed heterogeneous systems. To address this problem, we propose an adaptive interference-aware scheduling algorithm for accelerating DL workloads (called AISAW). By doing so, we initially established a predictive model consisting of a job performance model and an interference-aware model to reduce the impact of job co-location. Subsequently, to improve the system efficiency, we developed an adaptive priority-aware allocation scheme (APS) to find the optimal performance match in terms of adaptively allocating DL jobs to computing nodes. In addition, under the constraint of network bandwidth, we devised a deadline-aware overhead minimization dynamic migration scheme (DOMS) to avoid the high overhead caused by frequent job migration. Finally, we conducted experiments on real distributed heterogeneous systems deployed with several GPU-based servers. The results demonstrate that AISAW is capable of improving the system efficiency by decreasing the makespan and average JCT by at least 23.86% and 13.02%, respectively, compared to state-of-the-art algorithms such as Gandiva, Tiresias, and MLF-H.</div></div>","PeriodicalId":55132,"journal":{"name":"Future Generation Computer Systems-The International Journal of Escience","volume":"166 ","pages":"Article 107642"},"PeriodicalIF":6.2,"publicationDate":"2024-12-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142825323","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Automated generation of deployment descriptors for managing microservices-based applications in the cloud to edge continuum","authors":"James DesLauriers ,&nbsp;Jozsef Kovacs ,&nbsp;Tamas Kiss ,&nbsp;André Stork ,&nbsp;Sebastian Pena Serna ,&nbsp;Amjad Ullah","doi":"10.1016/j.future.2024.107628","DOIUrl":"10.1016/j.future.2024.107628","url":null,"abstract":"<div><div>With the emergence of Internet of Things (IoT) devices collecting large amounts of data at the edges of the network, a new generation of hyper-distributed applications is emerging, spanning cloud, fog, and edge computing resources. The automated deployment and management of such applications requires orchestration tools that take a deployment descriptor (e.g. Kubernetes manifest, Helm chart or TOSCA) as input, and deploy and manage the execution of applications at run-time. While most deployment descriptors are prepared by a single person or organisation at one specific time, there are notable scenarios where such descriptors need to be created collaboratively by different roles or organisations, and at different times of the application’s life cycle. An example of this scenario is the modular development of digital twins, composed of the basic building blocks of data, model and algorithm. Each of these building blocks can be created independently from each other, by different individuals or companies, at different times. The challenge here is to compose and build a deployment descriptor from these individual components automatically. This paper presents a novel solution to automate the collaborative composition and generation of deployment descriptors for distributed applications within the cloud-to-edge continuum. The implemented solution has been prototyped in over 25 industrial use cases within the DIGITbrain project, one of which is described in the paper as a representative example.</div></div>","PeriodicalId":55132,"journal":{"name":"Future Generation Computer Systems-The International Journal of Escience","volume":"166 ","pages":"Article 107628"},"PeriodicalIF":6.2,"publicationDate":"2024-12-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142825326","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A sampling-based acceleration method for heterogeneous chiplet NoC simulations","authors":"Ruoting Xiong ,&nbsp;Wei Ren ,&nbsp;Chengzhuo Zhang ,&nbsp;Tao Li ,&nbsp;Geyong Min","doi":"10.1016/j.future.2024.107643","DOIUrl":"10.1016/j.future.2024.107643","url":null,"abstract":"<div><div>To tackle the challenges posed by Moore’s Law, Chiplet technology emerges as a promising solution. Chiplets comprising CPUs and accelerators are connected by Networks-on-Chip (NoC) for large-scale integration and efficient communications. However, the slow simulation speed of NoCs has become a bottleneck, limiting the overall performance of chiplet simulations. Existing solutions only focus on accelerating NoC simulation in homogeneous architecture. In this paper, we introduce a novel TOPSIS-based Heterogeneous Trace Score-sampling method (THTS) for faster NoC simulation in heterogeneous architecture. THTS enables quick and accurate sampling of representative NoC traces. Additionally, we propose a weight exploration model to further enhance sampling accuracy. Compared with the traditional NoC sampling method (NoCLabs), THTS reduces the error of the average packet latency by 22.17% and the total simulation time by 1.6 folds. THTS estimates the NoC performance with an average loss less than 5%, while speeding up the NoC simulation by up to 3 times. In addition, under different weight space sizes, the time required for the weight exploration model to solve the optimal weight vector is within seconds, remarkably speeding up the solution process. Notably, the predicted NoC simulation error under the optimal weight is only 1.42%.</div></div>","PeriodicalId":55132,"journal":{"name":"Future Generation Computer Systems-The International Journal of Escience","volume":"166 ","pages":"Article 107643"},"PeriodicalIF":6.2,"publicationDate":"2024-12-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142825327","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"IoVST: An anomaly detection method for IoV based on spatiotemporal feature fusion","authors":"Jinhui Cao ,&nbsp;Xiaoqiang Di ,&nbsp;Jinqing Li ,&nbsp;Keping Yu ,&nbsp;Liang Zhao","doi":"10.1016/j.future.2024.107636","DOIUrl":"10.1016/j.future.2024.107636","url":null,"abstract":"<div><div>In the Internet of Vehicles (IoV) based on Cellular Vehicle-to-Everything (C-V2X) wireless communication, vehicles inform surrounding vehicles and infrastructure of their status by broadcasting basic safety messages, enhancing traffic management capabilities. Since anomalous vehicles can broadcast false traffic messages, anomaly detection is crucial for IoV. State-of-the-art methods typically utilize deep detection models to capture the internal spatial features of each message and the timing relationships of all messages in a sequence. However, since existing work neglects the local spatiotemporal relationship between messages broadcasted by the same vehicle, the spatiotemporal features of message sequences are not accurately described and extracted, resulting in inaccurate anomaly detection. To tackle these issues, a message attribute graph model (MAGM) is proposed, which accurately describes the spatiotemporal relationship of messages in the sequence using attribute graphs, including the internal spatial features of messages, the temporal order relationship of all messages, and the temporal order relationship of messages from the same vehicle. Furthermore, an anomaly detection method for IoV based on spatiotemporal feature fusion (IoVST) is proposed to detect anomalies accurately. IoVST aggregates the local spatiotemporal features of MAGM based on Transformer and extracts the global spatiotemporal features of message sequences through global time encoding and the self-attention mechanism. We conducted experimental evaluations on the VeReMi extension dataset. The F1 score and accuracy of IoVST are 1.68% and 1.92% higher than the optimal baseline method. The detection of every message can be accomplished in 0.7185 ms. In addition, the average accuracy of IoVST in four publicly available network intrusion detection datasets is 7.77% higher than the best baseline method, proving that our method can be applied well to other networks such as traditional IT networks, the Internet of Things, and industrial control networks.</div></div>","PeriodicalId":55132,"journal":{"name":"Future Generation Computer Systems-The International Journal of Escience","volume":"166 ","pages":"Article 107636"},"PeriodicalIF":6.2,"publicationDate":"2024-12-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142790055","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}