Concurrency and Computation-Practice & Experience最新文献

{"title":"Cloud Workload Forecasting via Latency-Aware Time Series Clustering-Based Scheduling Technique","authors":"P. Sridhar,&nbsp;R. R. Sathiya","doi":"10.1002/cpe.70151","DOIUrl":"https://doi.org/10.1002/cpe.70151","url":null,"abstract":"<div>\u0000 \u0000 <p>Cloud computing is a fundamental paradigm for computing services based on the elasticity attribute, in which available resources are effectively adjusted for changing workloads over time. A critical challenge in such systems is the task scheduling problem, which aims to identify the optimal allocation of resources to maximize performance and minimize response times. To overcome these drawbacks, a novel latency-aware time series-based scheduling (LATS) algorithm has been proposed in this paper for predicting future server loads. The proposed method involves collecting workloads, preprocessing and clustering them, predicting time series, and post-processing the data. The workload data will be divided according to a historical time window during the preprocessing phase. Next, the time series data will be clustered based on the latency classes using the dynamic fuzzy c-means algorithm. The time series prediction phase utilizes the Gated Recurrent Unit (GRU), and post-processing is performed to retrieve the original data. An evaluation of the accuracy of future workload predictions was conducted based on actual requests to web servers, and the silhouette score was utilized as the metric for assessing cluster performance. The proposed model has been compared with previous approaches involving Crystal LP, SWDF, and GA-PSO approaches in terms of prediction accuracy by 31.9%, 18.74%, and 12.16%, respectively.</p>\u0000 </div>","PeriodicalId":55214,"journal":{"name":"Concurrency and Computation-Practice & Experience","volume":"37 15-17","pages":""},"PeriodicalIF":1.5,"publicationDate":"2025-06-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144315322","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"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":"Fusing the Polyhedral and Tensor Compilers to Accelerate Scientific Computing Kernels","authors":"Qingzhi Liu,&nbsp;Changbo Chen,&nbsp;Hanwen Dai","doi":"10.1002/cpe.70164","DOIUrl":"https://doi.org/10.1002/cpe.70164","url":null,"abstract":"<div>\u0000 \u0000 <p>Polyhedral compilers and tensor compilers have achieved great success on accelerating scientific computing kernels and deep learning networks, respectively. Although much work has been done to integrate techniques of the polyhedral model to tensor compilers for accelerating deep learning, leveraging the powerful auto-tuning ability of modern tensor compilers to accelerate more general scientific computing kernels is challenging and is still at its dawn. In this work, we introduce a method to accelerate a family of basic scientific computing kernels by fusing the polyhedral compiler Pluto and the tensor compiler Tensor Virtual Machine (TVM) to generate efficient implementations targeting the heterogeneous CPU/GPU platform. The fusion is done in four steps: building a polyhedral model for the loop description of a given scientific kernel; designing schedules to transform the polyhedral model to new ones to enable rectangular tiling and expose explicit parallelism; selecting a new polyhedral model and converting it to the tensor compute representation; auto-tuning the tensor compute to generate efficient implementations on both CPUs and GPUs. Shifting and padding optimizations are also considered to avoid conditionals. Experiments on 30 typical scientific computing kernels show that our method achieves <span></span><math>\u0000 <semantics>\u0000 <mrow>\u0000 <mn>3</mn>\u0000 <mo>.</mo>\u0000 <mn>31</mn>\u0000 <mo>×</mo>\u0000 </mrow>\u0000 <annotation>$$ 3.31times $$</annotation>\u0000 </semantics></math> speedup on average over a typical polyhedral compiler PPCG on GPU.</p>\u0000 </div>","PeriodicalId":55214,"journal":{"name":"Concurrency and Computation-Practice & Experience","volume":"37 15-17","pages":""},"PeriodicalIF":1.5,"publicationDate":"2025-06-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144309129","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"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":"An Android API Recommendation Approach Based on API Dependency Paths Learning","authors":"Jia Deng,&nbsp;Jianxun Liu,&nbsp;Yi Liu,&nbsp;Yiming Yin,&nbsp;Yong Xiao","doi":"10.1002/cpe.70159","DOIUrl":"https://doi.org/10.1002/cpe.70159","url":null,"abstract":"<div>\u0000 \u0000 <p>Software development plays a crucial role in the modern mobile application domain, reflecting its significance through widespread application. With the continuous evolution and vast number of Android APIs, developers need to invest considerable effort in learning how to use various suitable APIs for their projects. Unfortunately, most current recommendation methods, when representing programs as source code sequences, abstract syntax trees, or API call paths, often focus only on contextual relationships while ignoring valuable information in API dependency relationships. Moreover, existing sequence models (such as RNN, LSTM) often fail to make correct predictions for low-frequency API methods with high-frequency suffixes, as these models tend to capture the most common API sequence patterns, causing these relatively low-frequency but potentially more applicable APIs to be overlooked. To address this issue, we propose an API dependency path-based Android API recommendation method, DPAPIRec. This approach combines program analysis with deep learning, which first extracts API methods and their data flow and control flow dependency relationships from a large number of Android APPs through program analysis techniques and then obtains a comprehensive API dependency paths repository. Finally, a deep learning method is applied to learn and represent these dependency relationships to improve API recommendation accuracy. Furthermore, to better extract dependency relationships, we employ an improved attention-based LSTM model with a novel loss architecture, enhancing the global dependency relationships between APIs through a weighted mixed loss, thereby strengthening the weight of initial nodes and alleviating the problem of low-frequency APIs with high-frequency suffixes. Our experiments on the AndroZoo dataset demonstrate that DPAPIRec significantly outperforms baseline methods in Android API recommendation tasks, showing substantial improvements in both Accuracy and Mean Reciprocal Rank (MRR).</p>\u0000 </div>","PeriodicalId":55214,"journal":{"name":"Concurrency and Computation-Practice & Experience","volume":"37 15-17","pages":""},"PeriodicalIF":1.5,"publicationDate":"2025-06-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144308707","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"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":"Adaptive Deep Fuzzy Neural Network With Multi-Headed Self-Attention for Improving Performance of Social Network Representation Learning and Link Prediction","authors":"Linh Nguyen Thi My,&nbsp;Vu Nguyen,&nbsp;Tham Vo","doi":"10.1002/cpe.70165","DOIUrl":"https://doi.org/10.1002/cpe.70165","url":null,"abstract":"<div>\u0000 \u0000 <p>Link prediction has long been a fundamental task in graph data analysis, aimed at identifying potential or missing connections between nodes. This task is particularly important for understanding social dynamics and improving the robustness of networks. However, existing graph learning methods often struggle with modeling complex structures, especially in social networks where data is noisy, uncertain, as well as multi-faceted. Most traditional graph embedding architectures are limited in their ability to handle noise and effectively represent multi-view information. Likewise, there are several graph neural networks (GNNs) face challenges in integrating diverse structural perspectives and managing uncertainty, which leads to subpar performance in link prediction tasks. To overcome these challenges, we propose a novel model called AFGRL which is an attention-driven fuzzy graph representation learning. Our proposed AFGRL combines multiple types of GNNs for multi-view embedding with a multi-headed attention-enhanced fuzzy neural network. This design enables our AFGRL model to better learn richer, as well as more expressive graph representations while effectively managing uncertainty and noise. The attention mechanism integrated into our AFGRL model allows it to focus on various structural aspects of the graph—while the fuzzy logic component captures ambiguity inherent in social network data. Our model is particularly tailored for online social networks—where user relationships are dynamic and characterized by varying degrees of trust and influence. We evaluate AFGRL on several real-world and benchmark datasets, demonstrating its superior performance in link prediction compared to state-of-the-art baselines. The results confirm that our AFGRL model not only enhances predictive accuracy but also provides robust and meaningful structural representations; as a result, highlighting the value of integrating attention and fuzzy logic into graph learning frameworks.</p>\u0000 </div>","PeriodicalId":55214,"journal":{"name":"Concurrency and Computation-Practice & Experience","volume":"37 15-17","pages":""},"PeriodicalIF":1.5,"publicationDate":"2025-06-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144300516","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"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":"Enhanced Task Scheduling With Metaheuristics for Delay and Energy Optimization in Cloud-Fog Computing","authors":"Pinky,&nbsp;Karan Verma","doi":"10.1002/cpe.70163","DOIUrl":"https://doi.org/10.1002/cpe.70163","url":null,"abstract":"<div>\u0000 \u0000 <p>The growth of the Internet of Things (IoT) and its application across various industries has produced large volumes of data for processing. Tasks that require prompt responses, particularly delay-sensitive ones, are directed to the nearest fog nodes. Offloading critical tasks to the cloud reduces user-side energy consumption but increases latency due to longer transmission distances. Fog nodes, being closer to the source, minimize delay but may require more local energy. Another major issue in cloud-fog computing is allocating tasks to suitable resources according to task needs. To tackle these challenges, this study introduces a hybrid meta-heuristic approach by combining the Butterfly Swarm Optimization (BSO) algorithm with the heuristic Minimum Completion Time (MCT) initialization method. The key innovation of this work lies in the integration of MCT-based heuristic initialization with the BSO algorithm, enabling faster convergence and more efficient task scheduling by balancing energy and delay in heterogeneous cloud-fog environments. Both delay and energy consumption are reduced through the MCT-BSO algorithm, in which the fog broker effectively manages the task distribution. Simulation results show that the MCT-BSO method achieves delay reductions of approximately 20.7% to 36.3% and improvements in energy consumption ranging from 15.4% to 38.1%, significantly outperforming comparative algorithms such as Grey Wolf Optimization, Nondominated Sorting Genetic Algorithm II, and Modified Particle Swarm Optimization, particularly under high workload conditions.</p>\u0000 </div>","PeriodicalId":55214,"journal":{"name":"Concurrency and Computation-Practice & Experience","volume":"37 15-17","pages":""},"PeriodicalIF":1.5,"publicationDate":"2025-06-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144273234","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"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":"Container Placement Using Penalty-Based PSO in the Cloud Data Center","authors":"Md. Akram Khan,&nbsp;Bibudatta Sahoo,&nbsp;Sambit Kumar Mishra","doi":"10.1002/cpe.70157","DOIUrl":"https://doi.org/10.1002/cpe.70157","url":null,"abstract":"<div>\u0000 \u0000 <p>Containerization has transformed application deployment by offering a lightweight, scalable, and portable architecture for the deployment of container applications and their dependencies. In contemporary cloud computing data centers, where virtual machines (VMs) are frequently utilized to host containerized applications, the challenge of effective placement of the container has garnered significant attention. Container placement (CP) involves placing a container over the VM to execute a container. CP is a nontrivial problem in the container cloud data center (CCDC). Poor placement decisions can lead to decreased service performance or wastage of cloud resources. Efficient placement of containers within a virtual environment is critical while optimizing resource utilization and performance. This paper proposes a penalty-based particle swarm optimization (PB-PSO) CP algorithm. In the proposed algorithm, we have considered the makespan, cost, and load of the VM while making the CP decisions. We have proposed the concept of a load-balancing penalty to prevent a VM from becoming overloaded. This algorithm solves various CP challenges by varying container application sizes in heterogeneous cloud environments. The primary goal of the proposed algorithm is to minimize the makespan and computational cost of containers through efficient resource utilization. We have performed extensive simulation studies to verify the efficacy of the proposed algorithm using the CloudSim 4.0 simulator. The proposed optimization algorithm (PB-PSO) aims to minimize both the makespan and the execution monetary costs and maximize the resource utilization simultaneously. During the simulation, we observed a reduction of 10% to 15% in both execution cost and makespan. Furthermore, our algorithm achieved the most optimal cost-makespan trade-offs compared to other competing algorithms.</p>\u0000 </div>","PeriodicalId":55214,"journal":{"name":"Concurrency and Computation-Practice & Experience","volume":"37 15-17","pages":""},"PeriodicalIF":1.5,"publicationDate":"2025-06-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144264339","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"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":"An Effective Federated Learning Approach for Secure and Private Scalable Intrusion Detection on the Internet of Vehicles","authors":"Wisam Makki Alwash,&nbsp;Mustafa Kara,&nbsp;Muhammed Ali Aydin,&nbsp;Hasan Hüseyin Balik","doi":"10.1002/cpe.70160","DOIUrl":"https://doi.org/10.1002/cpe.70160","url":null,"abstract":"<div>\u0000 \u0000 <p>The rapid proliferation of connected vehicles in the Internet of Vehicles (IoV) has introduced significant data security and privacy challenges, emphasizing the need for advanced intrusion detection systems (IDS). This article proposes a federated learning-based intrusion detection system (FL-IDS), explicitly designed to identify both external network-level threats and internal vehicular cyberattacks. Federated learning enables collaborative training across distributed vehicles without sharing raw data, significantly reducing communication overhead and preserving data privacy. To further enhance privacy, differential privacy (DP) mechanisms are applied, ensuring sensitive information remains protected even during model updates. Additionally, secure communication channels are established using Secure Sockets Layer/Transport Layer Security (SSL/TLS) protocols, effectively safeguarding the integrity and authenticity of data exchanges between vehicles, roadside units, and cloud servers. Robust preprocessing methods, including data balancing, normalization, and feature selection, are combined with an adaptive federated learning strategy (FedXgbBagging) specifically designed to address the challenges posed by heterogeneous and non-independent and identically distributed (non-IID) data. Extensive evaluations on two real-world datasets, CSE-CIC-IDS2018 for network attacks and CICIoV2024 for in-vehicle Controller Area Network (CAN) bus attacks—show remarkable performance, achieving accuracy rates of 99.64% and 99.99%, respectively. The proposed FL-IDS significantly outperforms existing methods, demonstrating its robustness, adaptability, and scalability in securing IoV environments against diverse cyber threats.</p>\u0000 </div>","PeriodicalId":55214,"journal":{"name":"Concurrency and Computation-Practice & Experience","volume":"37 15-17","pages":""},"PeriodicalIF":1.5,"publicationDate":"2025-06-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144256426","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"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":"Shilling Attack Detection Method Integrating Item Temporal Information and Relational Networks","authors":"Shuguang Zhang,&nbsp;Lingjie Liu,&nbsp;Xuntao Zhi,&nbsp;Yu Cheng,&nbsp;Xinyu Zheng,&nbsp;Yunlong Wang","doi":"10.1002/cpe.70150","DOIUrl":"https://doi.org/10.1002/cpe.70150","url":null,"abstract":"<div>\u0000 \u0000 <p>Shilling attack detection is a method to identify and defend against malicious users in recommender systems, and it mainly detects shilling attackers by analyzing user behavior or item content anomalies. Items in the system subject to shilling attack often present abnormal scoring time-series information and relationship networks, but time-series data has the characteristics of large and unstable data volume, which makes it difficult to directly use raw data for detection, while detection from user relationship networks can often only solve a specific attack problem, and it is difficult to detect coordinated attack behaviors. To address the above issues, we propose a detection method called ITRN, which makes full use of item timing information and relational networks, dividing the time series of item ratings based on important points, constructing cubes for similarity measure using the second-order difference method to obtain the anomalous time intervals and the set of suspicious users, constructing a suspicious user-item bipartite graph, aggregating the higher-order neighboring information of the suspicious users using LightGCN, and then inputting these higher-order embedded inputs into the linear layer that are mapped into a scalar, and finally these scalars are input into the Sigmoid function to obtain the probability of the user being suspicious. Experiments were conducted on three datasets of varying sizes from Movielens, and the results showed that our method improved precision by approximately 0.02 and F1-measure by approximately 0.01 compared to the optimal baseline model.</p>\u0000 </div>","PeriodicalId":55214,"journal":{"name":"Concurrency and Computation-Practice & Experience","volume":"37 15-17","pages":""},"PeriodicalIF":1.5,"publicationDate":"2025-06-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144244156","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"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":"Leveraging SYCL for Heterogeneous cDTW Computation on CPU, GPU, and FPGA","authors":"Cristian Campos,&nbsp;Rafael Asenjo,&nbsp;Javier Hormigo,&nbsp;Angeles Navarro","doi":"10.1002/cpe.70142","DOIUrl":"https://doi.org/10.1002/cpe.70142","url":null,"abstract":"<p>One of the most time-consuming kernels of a recent epileptic seizure detection application is the computation of the constrained Dynamic Time Warping (cDTW) Distance Matrix. In this paper, we explore the design space of heterogeneous CPU, GPU, and FPGA implementations of this kernel using SYCL as a programming model. First, we optimize the CPU implementation leveraging the SIMD capability of SYCL and compare it with the latest C++26 SIMD library. Next, we tune the SYCL code to run on an on-chip GPU, iGPU, as well as on a discrete NVIDIA GPU, dGPU. We also develop a SYCL implementation on an Intel FPGA. On top of that, we exploit simultaneous co-processing on CPU+GPU and CPU+FPGA platforms by extending a previous heterogeneous scheduling framework to now support 2D partitioning strategies. Our evaluations demonstrate that SYCL seems well suited to exploit the SIMD capabilities of modern CPU cores and shows promising results for accelerating devices, both in terms of performance and energy efficiency. Moreover, we find that our scheduler enables the efficient co-execution of work among the computing devices, and the results demonstrate that dynamic and adaptive partitioning strategies perform efficiently with overheads below 4%.</p>","PeriodicalId":55214,"journal":{"name":"Concurrency and Computation-Practice & Experience","volume":"37 15-17","pages":""},"PeriodicalIF":1.5,"publicationDate":"2025-06-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/cpe.70142","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144244521","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"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":"Leveraging Traversal Tree for Node Pair Selection-Based Reliable IoT Network Construction","authors":"Yongqin Zhu,&nbsp;Bojiang Xie","doi":"10.1002/cpe.70131","DOIUrl":"https://doi.org/10.1002/cpe.70131","url":null,"abstract":"<div>\u0000 \u0000 <p>It is a popular practice to enhance the process of integrating new links for the purpose of strengthening IoT network resilience, as measured by traditional indicators like connectivity. Nevertheless, even in relatively small-scale networks, attempting to connect the two parts of every intended separation by adding every potential link proves to be unfeasible. Since the quantity of potential links to be taken into account will be far greater than the existing links. In practical applications, hasty methods usually lead to very unsatisfactory outcomes. We have devised a simplified approach for representing all relevant divisions. This approach relies on defining the relationship between trimmed structures and divisions. Subsequently, it can identify the nearly optimal set of cuts that encompass all recognized divisions. Consequently, this allows us to determine the optimal set of links to improve connectivity. In tests on benchmark network models, the results demonstrated that this method can attain significant improvements comparable to the optimal method. Notably, the processing time can be decreased by up to a million times in contrast to the ideal strategy, with only a slight increment in the number of added links. When contrasted with commonly used rule-of-thumb methods, which are largely ineffective in safeguarding these systems, the proposed method yields nearly flawless results in large networks.</p>\u0000 </div>","PeriodicalId":55214,"journal":{"name":"Concurrency and Computation-Practice & Experience","volume":"37 15-17","pages":""},"PeriodicalIF":1.5,"publicationDate":"2025-06-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144232359","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}