ABSTRACT With the increase in resource heterogeneity and dynamic workloads, cloud environments have become more complex, making it challenging to efficiently manage diverse resources. Limited availability and improper allocation often result in task failures, particularly when systems lack the capacity to meet strict deadlines. To address this challenge, effective task allocation algorithms with integrated fault tolerance are essential. This paper presents DTRM that is, Deadline Constrained Task Allocation using Resubmission and preemptive Migration, a novel task allocation algorithm for heterogeneous cloud environments, designed specifically for deadline‐constrained independent tasks. Unlike existing approaches, DTRM introduces a hybrid fault‐tolerant strategy that combines reactive resubmission and proactive preemptive migration, thereby minimizing task failures under deadline constraints. The algorithm operates in three phases: (i) classification of tasks and VMs according to task length and computation power, (ii) prioritization of tasks based on execution time and deadlines, and (iii) allocation to the most suitable VM category. By aligning task requirements with VM capabilities, DTRM achieves better utilization and reduces task rejection. Simulation results on varying task sizes and VM counts demonstrate that DTRM consistently outperforms baseline algorithms such as FCFS, SJF, Priority‐based scheduling, DyMaxMin, RADL, and FTTA. Specifically, DTRM significantly improves makespan reduction, task acceptance, speedup, and efficiency, validating its potential for real‐world deployment in large‐scale cloud environments where meeting deadlines is critical.

The expansion of the Internet has resulted in a change in the flow of information. With the vast amount of digital information generated online, it is easy for users to feel overwhelmed. Finding the specific information can be a challenge, and it can be difficult to distinguish credible sources from unreliable ones. This has made recommender system (RS) an integral part of the information services framework. These systems alleviate users from information overload by analyzing users’ past preferences and directing only desirable information toward users. Traditional RSs use approaches like collaborative and content-based filtering to generate recommendations. Recently, these systems have evolved to a whole new level, intuitively optimizing recommendations using deep network models. graph neural networks (GNNs) have become one of the most widely used approaches in RSs, capturing complex relationships between users and items using graphs. In this survey, we provide a literature review of the latest research efforts done on GNN-based RSs. We present an overview of RS, discuss its generalized pipeline and evolution with changing learning approaches. Furthermore, we explore basic GNN architecture and its variants used in RSs, their applications, and some critical challenges for future research.

Summary In distributed systems, tuple space is one of the coordination models that significantly maximizes system performance against failure due to its space and time decoupling features. With the growing popularity of distributed computing and increasing complexity in the network, host and link failure occurs frequently, resulting in poor system performance. This article proposes a fault‐tolerant model named Tuple Space Replication (TSR) for tuple space coordination in distributed environments. The model introduces a multi‐agent system that consists of multiple hosts. Each host in a multi‐agent system comprises an agent space with a tuple space for coordination. In this model, we introduce three novel fault‐tolerant algorithms for tuple space primitives to provide coordination among hosts with tolerance to multiple links and hosts failure. The first algorithm is given for out() operation to insert tuples in the tuple space. The second algorithm is presented for rdp() operation to read any tuple from the tuple space. The third algorithm is given for inp() operation to delete or withdraw tuples from the tuple space. These algorithms use less number of messages to ensure consistency in the system. The message complexity of the proposed algorithms is analyzed and found O(n) for out(), O(1) for rdp(), and O(n) for inp() operations which is comparable and better than existing works, where n is the number of hosts. The testbed experiment reveals that the proposed TSR model gives performance improvement up to 88%, 70.94%, and 63.80% for out(), rdp(), and inp() operations compared to existing models such as FT‐SHE, LBTS, DEPSPACE, and E‐DEPSPACE.

Abstract Fault tolerance is crucial in ensuring smooth working of distributed and cloud computing. It is challenging to implement because of the constantly changing infrastructure and complex configurations in distributed and cloud computing. Implementation of various fault tolerance methods require domain‐specific knowledge as well as in‐depth understanding of the existing techniques and approaches. Recent surveys on fault tolerance in cloud and distributed environments exist, but they have limitations. This article systematically reviews fault tolerance approaches in distributed and cloud computing and discusses their taxonomy. Based on the taxonomy provided, fault‐tolerance approaches are divided into four types, that is, reactive approaches, proactive approaches, adaptive approaches, and hybrid approaches. Reactive approaches provide a preventive measure after the occurrence of faults in the system. Proactive approaches prevent the system or minimize failure effects by predicting in advance. The adaptive approaches predict, learn, and adapt the changes to deal with new faults in the system. The hybrid approaches combine reactive, proactive, and adaptive approaches. The objective of this article is to give a better understanding of handling faults using suitable approaches and further compare them on various parameters. The paper also presents a promising research direction based on the challenges and issues in multiple approaches.

Abstract The advancements in computing and storage capabilities of machines and their fusion with new technologies like the Internet of Thing (IoT), 5G networks, and artificial intelligence, to name a few, has resulted in a paradigm shift in the way computing is done in a cloud environment. In addition, the ever‐increasing user demand for cloud services and resources has resulted in cloud service providers (CSPs) expanding the scale of their data center facilities. This has increased energy consumption leading to more carbon dioxide emission levels. Hence, it becomes all the more important to design scheduling algorithms that optimize the use of cloud resources with minimum energy consumption. This paper surveys state‐of‐the‐art algorithms for scheduling workflow tasks to cloud resources with a focus on reducing energy consumption. For this, we categorize different workflow scheduling algorithms based on the scheduling approaches used and provide an analytical discussion of the algorithms covered in the paper. Further, we provide a detailed classification of different energy‐efficient strategies used by CSPs for energy saving in data centers. Finally, we describe some of the popular real‐world workflow applications as well as highlight important emerging trends and open issues in cloud computing for future research directions.

Summary In multiprocessor environments, the scheduling algorithms play a significant role in maximizing system performance. In this paper, we propose a clustering‐based task scheduling algorithm called Edge Priority Scheduling (EPS) for multiprocessor environments. The proposed algorithm extends the idea of edge zeroing heuristic and uses the concept of edge priority to minimize the makespan of the task graph. The complexity of the EPS algorithm is O(|V||E|(|V| + |E|)), where |E| represents the number of edges and |V| denotes the number of nodes in the task graph. The experiments are performed for random task graphs and the task graphs generated from some representative real‐world applications such as Gaussian Elimination and Fast Fourier Transform. The performance of the EPS algorithm is compared with six well‐known algorithms such as EZ (Edge Zeroing), LC (Linear Clustering), CPPS (Cluster Pair Priority Scheduling), DCCL (Dynamic Computation Communication Load), RDCC (Randomized Dynamic Computation Communication), and LOCAL. The results show that the EPS algorithm outperforms the compared algorithms in terms of the normalized schedule length and speedup.