The traditional MapReduce frameworks were originally designed for processing data within a single cluster and are not suitable for handling geo-distributed data. Consequently, alternative approaches such as Hierarchical and Geo-Hadoop have been proposed to address this limitation. However, these approaches still face challenges in efficiently managing inter-cluster data transfer, particularly considering the heterogeneity of clusters and varying bandwidth among them. Moreover, the need to transmit results to a central global reducer for geo-distributed MapReduce operations adds unnecessary complexity. To tackle these issues, we introduce Extended Cross-MapReduce (ECMR), a framework that integrates resource heterogeneity and network links in geo-distributed MapReduce workflows. ECMR optimizes data management and determines the necessary data volume for generating final results. To enhance performance, ECMR leverages the overlap between data transfer and execution time by utilizing multiple global reducers and grouping temporary results that require data transfer over the Internet. In ECMR, we propose a bipartite graph and extend the Gale-Shapley algorithm to determine the optimal number of clusters and select the most suitable locations for global reducers. Through extensive experimental evaluations conducted on a real testbed, we demonstrate the effectiveness of our proposed ECMR method. The results exhibit significant improvements over traditional Hierarchical and Geo-Hadoop approaches, achieving reductions of up to 81% and 85% in overall makespan, respectively.

Identifying motifs within sets of protein sequences constitutes a pivotal challenge in proteomics, imparting insights into protein evolution, function prediction, and structural attributes. Motifs hold the potential to unveil crucial protein aspects like transcription factor binding sites and protein-protein interaction regions. However, prevailing techniques for identifying motif sequences in extensive protein collections often entail significant time investments. Furthermore, ensuring the accuracy of obtained results remains a persistent motif discovery challenge. This paper introduces an innovative approach-a branch and bound algorithm-for exact motif identification across diverse lengths. This algorithm exhibits superior performance in terms of reduced runtime and enhanced result accuracy, as compared to existing methods. To achieve this objective, the study constructs a comprehensive tree structure encompassing potential motif evolution pathways. Subsequently, the tree is pruned based on motif length and targeted similarity thresholds. The proposed algorithm efficiently identifies all potential motif subsequences, characterized by maximal similarity, within expansive protein sequence datasets. Experimental findings affirm the algorithm's efficacy, highlighting its superior performance in terms of runtime, motif count, and accuracy, in comparison to prevalent practical techniques.

Scheduling workflows in cloud environments is an important issue that many types of research have been conducted in this field. However, these approaches often focus on single workflow scheduling while the need for scheduling multiple workflows is growing. This study aims at presenting a cloud broker for executing Deadline-constrained Periodic scientific Workflows (BDPW). BDPW acts as a Workflow as a Service (WaaS) broker and uses both reserved and on-demand resources in order to minimize the monetary cost of renting resources from a cloud provider. Furthermore, BDPW uses container technology by executing multiple containerized tasks on the same Virtual Machine (VM) to decrease the provisioning delay of VMs. The proposed broker uses a hybrid scheduling method, i.e., static planning and dynamic scheduling. The static planner uses resource leveling problem (RLP) to provide a scheduling plan and also recognizes the number of reserved resources that should be leased from a provider. Then, the dynamic scheduler tries to assign tasks to the reserved resources based on the primary static plan and leases on-demand instances if necessary. Also, it may make changes to the primary plan due to uncertainties in the task runtimes. The experimental results in CloudSim show that BDPW outperforms baseline algorithms in terms of monetary cost.

SUMMARY: Topology determination is one of the most important intermediate steps toward building the atomic structure of proteins from their medium-resolution cryo-electron microscopy (cryo-EM) map. The main goal in the topology determination is to identify correct matches (i.e. assignment and direction) between secondary structure elements (SSEs) (α-helices and β-sheets) detected in a protein sequence and cryo-EM density map. Despite many recent advances in molecular biology technologies, the problem remains a challenging issue. To overcome the problem, this article proposes a linear programming-based topology determination (LPTD) method to solve the secondary structure topology problem in three-dimensional geometrical space. Through modeling of the protein's sequence with the aid of extracting highly reliable features and a distance-based scoring function, the secondary structure matching problem is transformed into a complete weighted bipartite graph matching problem. Subsequently, an algorithm based on linear programming is developed as a decision-making strategy to extract the true topology (native topology) between all possible topologies. The proposed automatic framework is verified using 12 experimental and 15 simulated α-β proteins. Results demonstrate that LPTD is highly efficient and extremely fast in such a way that for 77% of cases in the dataset, the native topology has been detected in the first rank topology in <2 s. Besides, this method is able to successfully handle large complex proteins with as many as 65 SSEs. Such a large number of SSEs have never been solved with current tools/methods. AVAILABILITY AND IMPLEMENTATION: The LPTD package (source code and data) is publicly available at https://github.com/B-Behkamal/LPTD. Moreover, two test samples as well as the instruction of utilizing the graphical user interface have been provided in the shared readme file. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

Heterogeneous multi-core processors (HMP) with the same instruction set architecture (ISA) integrate complex high performance big cores with power efficient small cores on the same chip. In comparison with homogeneous architectures, HMPs have been shown to significantly increase energy efficiency. However, current techniques to exploit the energy efficiency of HMPs do not consider fair usage of resources that leads to reduced performance predictability, a longer makespan, starvation, and QoS degradation. The effect of different cluster voltage and frequency levels on fairness is another issue neglected by previous task scheduling algorithms. The present study investigates both the fairness problem and energy efficiency in HMPs. This article proposes a heterogeneous fairness-aware energy efficient framework (HFEE) that employs DVFS to meet fairness constraints and provide energy efficient scheduling. The proposed framework is implemented and evaluated on a real heterogeneous multi-core processor. The experimental results indicate that the introduced technique can significantly improve energy efficiency and fairness when compared to Linux standard scheduler and two energy efficient and fairness-aware schedulers.

BACKGROUND: Infectious diseases are a cruel assassin with millions of victims around the world each year. Understanding infectious mechanism of viruses is indispensable for their inhibition. One of the best ways of unveiling this mechanism is to investigate the host-pathogen protein-protein interaction network. In this paper we try to disclose many properties of this network. We focus on human as host and integrate experimentally 32,859 interaction between human proteins and virus proteins from several databases. We investigate different properties of human proteins targeted by virus proteins and find that most of them have a considerable high centrality scores in human intra protein-protein interaction network. Investigating human proteins network properties which are targeted by different virus proteins can help us to design multipurpose drugs. RESULTS: As host-pathogen protein-protein interaction network is a bipartite network and centrality measures for this type of networks are scarce, we proposed seven new centrality measures for analyzing bipartite networks. Applying them to different virus strains reveals unrandomness of attack strategies of virus proteins which could help us in drug design hence elevating the quality of life. They could also be used in detecting host essential proteins. Essential proteins are those whose functions are critical for survival of its host. One of the proposed centralities named diversity of predators, outperforms the other existing centralities in terms of detecting essential proteins and could be used as an optimal essential proteins' marker. CONCLUSIONS: Different centralities were applied to analyze human protein-protein interaction network and to detect characteristics of human proteins targeted by virus proteins. Moreover, seven new centralities were proposed to analyze host-pathogen protein-protein interaction network and to detect pathogens' favorite host protein victims. Comparing different centralities in detecting essential proteins reveals that diversity of predator (one of the proposed centralities) is the best essential protein marker.

While GPUs are meantime omnipresent for many scientific and technical computations, they still continue to evolve as processors. An important recent feature is the ability to execute multiple kernels concurrently via queue streams. However, experiments show that different parameters including the behavior of kernels, the order of kernel launches and other execution configurations, e.g., the number of concurrent thread blocks, may result in different execution time for concurrent kernel execution. Since kernels may have different resource requirements, they can be classified into different classes, which are traditionally assumed as either memory-bound or compute-bound. However, a kernel may belong to the different classes on different hardware according to the hardware resources. In this paper, the definition of kernel mix intensity is introduced. Based on this, a scheduling framework called concurrent CUDA (cCUDA) is proposed to co-schedule the concurrent kernels more efficiently. It first profiles and ranks kernels with different execution behaviors and then takes the kernel resource requirements into account to partition thread blocks of different kernels and overlap them to better utilize the GPU resources. Experimental results on real hardware demonstrate performance improvement in terms of execution time of up to 1.86x, and an average speedup of 1.28x for a wide range of kernels. cCUDA is available at https://github.com/kshekofteh/cCUDA.

Graphics Processing Units (GPUs) are vastly used for running massively parallel programs. GPU kernels exhibit different behavior at runtime and can usually be classified in a simple form as either “compute-bound” or “memory-bound.” Recent GPUs are capable of concurrently running multiple kernels, which raises the question of how to most appropriately schedule kernels to achieve higher performance. In particular, co-scheduling of compute-bound and memory-bound kernels seems promising. However, its benefits as well as drawbacks must be determined along with which kernels should be selected for a concurrent execution. Classifying kernels can be performed online by instrumentation based on performance counters. This work conducts a thorough analysis of the metrics collected from various benchmarks from Rodinia and CUDA SDK. The goal is to find the minimum number of effective metrics that enables online classification of kernels with a low overhead. This study employs a wrapper-based feature selection method based on the Fisher feature selection criterion. The results of experiments show that to classify kernels with a high accuracy, only three and five metrics are sufficient on a Kepler and a Pascal GPU, respectively. The proposed method is then utilized for a runtime scheduler. The results show an average speedup of 1.18× and 1.1× compared with a serial and a random scheduler, respectively.

Predicting β-sheet topology (β-topology) is one of the most critical intermediate steps towards protein structure and function prediction. The β-topology prediction problem is defined as the determination of the optimal arrangement of β-strand interactions within protein β-sheets. Significant efforts have been made to predict β-topologies. However, due to the inaccurate determination of interactions among β-strands and the huge topological space of proteins with a large number of β-strands, more efficient methods are required to improve both the accuracy and speed of β-topology prediction. In order to attain higher accuracy, the current paper introduces a bidirectional strand-strand interaction graph and considers all possible orientations (parallel and antiparallel) and orders of β-strand pairwise interactions. For the first time, the β-topology prediction is transformed into a maximum weight disjoint path cover solution by conserving all potential topologies. Moreover, to manage the computation time, a set of candidate β-sheets is generated and an optimization process is applied to select a subset of maximum score disjoint β-sheets as a predicted β-topology. The proposed method is comprehensively compared with state-of-the-art methods. The experimental results on the BetaSheet916 and BetaSheet1452 datasets reveal that the current study's approach enhances performance measurements as well as reduces the runtime.

Organizing sensor nodes into a clustered architecture is an effective method for load balancing and prolonging the network lifetime. However, a serious drawback of the clustering approach is the imposed energy overhead caused by the “global” clustering operations in every round of the global round-based policy (GRBP). To mitigate this problem, this paper proposes a hierarchical clustering-task scheduling policy (HCSP), which triggers node-driven clustering as opposed to GRBP's time-driven clustering. Based on HCSP, each cluster is reconfigured only once at each local super round. Therefore, the cluster reconfiguration frequency varies on-demand and may differ from one cluster to another throughout the network lifetime. However, in order to refresh the entire network structure, global clustering is performed at the end of every global hyper round. Accordingly, HCSP aims to achieve a more flexible, energy-efficient, and scalable clustering-task scheduling than that of GRBP. This policy mitigates the clustering overhead, which is the worst disadvantage of clustering approaches. Energy consumption calculations and extensive simulations show the effectiveness of HCSP in saving energy and in prolonging the network lifetime.

Prolonging the network life cycle is an essential requirement for many types of Wireless Sensor Network (WSN) applications. Dynamic clustering of sensors into groups is a popular strategy to maximize the network lifetime and increase scalability. In this strategy, to achieve the sensor nodes' load balancing, with the aim of prolonging lifetime, network operations are split into rounds, i.e., fixed time intervals. Clusters are configured for the current round and reconfigured for the next round so that the costly role of the cluster head is rotated among the network nodes, i.e., Round-Based Policy (RBP). This load balancing approach potentially extends the network lifetime. However, the imposed overhead, due to the clustering in every round, wastes network energy resources. This paper proposes a distributed energy-efficient scheme to cluster a WSN, i.e., Dynamic Hyper Round Policy (DHRP), which schedules clustering-task to extend the network lifetime and reduce energy consumption. Although DHRP is applicable to any data gathering protocols that value energy efficiency, a Simple Energy-efficient Data Collecting (SEDC) protocol is also presented to evaluate the usefulness of DHRP and calculate the end-to-end energy consumption. Experimental results demonstrate that SEDC with DHRP is more effective than two well-known clustering protocols, HEED and M-LEACH, for prolonging the network lifetime and achieving energy conservation.

In hybrid cloud model, organizations can keep their sensitive information and critical applications in the private cloud and move other data and applications to a public cloud, if necessary. To maintain data privacy in workflow applications, we present a budget constrained hybrid cloud scheduler (BCHCS) which is a static heuristic scheduling algorithm. It is able to make decisions about scheduling sensitive tasks on private cloud and uses public cloud's resources for non-sensitive tasks, such that the makespan is minimized, while the budget limitation imposed by the user is satisfied. Experimental results show that the proposed method guarantees the execution of sensitive tasks on private cloud while achieving at least 7 percent lower makespan and higher success rate in comparison to similar existing techniques.

Network functions virtualization provides opportunities to design, deploy, and manage networking services. It utilizes cloud computing virtualization services that run on high-volume servers, switches, and storage hardware to virtualize network functions. Virtualization techniques can be used in IP multimedia subsystem (IMS) cloud computing to develop different networking functions (e.g., load balancing and call admission control). IMS network signaling happens through session initiation protocol (SIP). An open issue is the control of overload that occurs when an SIP server lacks sufficient CPU and memory resources to process all messages. This paper proposes a virtual load balanced call admission controller (VLB-CAC) for the cloud-hosted SIP servers. VLB-CAC determines the optimal “call admission rates” and “signaling paths” for admitted calls along with the optimal allocation of CPU and memory resources of the SIP servers. This optimal solution is derived through a new linear programming model. This model requires some critical information of SIP servers as input. Further, VLB-CAC is equipped with an autoscaler to overcome resource limitations. The proposed scheme is implemented in smart applications on virtual infrastructure (SAVI) which serves as a virtual testbed. An assessment of the numerical and experimental results demonstrates the efficiency of the proposed work.

Although the growth in the scale and complexity is the response of High Performance Computing (HPC) systems like computational grids to the ever-increasing demand for high processing capacity, it also makes these systems considerable energy consumers. In fact, high energy consumption is the new challenge in front of performance improvement of HPC systems and thus power management is now a necessity for them. One of the major components that can have a great role in the power-saving process is the scheduler. In this paper, a new power-aware scheduling algorithm is proposed by incorporating the characteristics of both job and resource into the job mapping and ordering, and frequency-setting decision steps. In addition to the analytical study, the proposed scheduler has been evaluated based on results obtained from experiments in different resources heterogeneity levels and workload conditions. The results show the greater capability of the proposed scheduling algorithm in comparison with other related approaches.

Abstract This paper presents a new model of support vector machines (SVMs) that handle data with tolerance and uncertainty. The constraints of the SVM are converted to fuzzy inequality. Giving more relaxation to the constraints allows us to consider an importance degree for each training samples in the constraints of the SVM. The new method is called relaxed constraints support vector machines (RSVMs). Also, the fuzzy SVM model is improved with more relaxed constraints. The new model is called fuzzy RSVM. With this method, we are able to consider importance degree for training samples both in the cost function and constraints of the SVM, simultaneously. In addition, we extend our method to solve one‐class classification problems. The effectiveness of the proposed method is demonstrated on artificial and real‐life data sets.

Recently, utility Grids have emerged as a new model of service provisioning in heterogeneous distributed systems. In this model, users negotiate with service providers on their required Quality of Service and on the corresponding price to reach a Service Level Agreement. One of the most challenging problems in utility Grids is workflow scheduling, i.e., the problem of satisfying the QoS of the users as well as minimizing the cost of workflow execution. In this paper, we propose a new QoS-based workflow scheduling algorithm based on a novel concept called Partial Critical Paths (PCP), that tries to minimize the cost of workflow execution while meeting a user-defined deadline. The PCP algorithm has two phases: in the deadline distribution phase it recursively assigns subdeadlines to the tasks on the partial critical paths ending at previously assigned tasks, and in the planning phase it assigns the cheapest service to each task while meeting its subdeadline. The simulation results show that the performance of the PCP algorithm is very promising.

This article proposes a new hybrid methodology, together with an associated series of experiments employing this methodology, for an evolutionary gait generator that uses trigonometric truncated Fourier series formulations with coefficients optimized by a Genetic Algorithm. The Fourier series is used to model joint angle trajectories of a simulated humanoid robot with 25 degrees of freedom. The humanoid robot in this study learns to imitate the human walking behavior on flat terrains in a dynamically simulated environment. The simulation result shows the robustness of the developed walking behaviors even in extremely high and low speeds providing appropriate frequency. Number of range limitations were applied to the genetic algorithm used in this research to improve the learning period to less than 48 hours. The research seeks to improve upon the previous works on evolutionary gait generation, in robots with lower degrees of freedom. In addition, the proposed solution adapts a hybrid approach, thereby avoiding the long learning curves and unstable and slow gaits associated with evolutionary approaches.

Various forms of swarm intelligence are inspired by social behavior of insects that live collectively. AntNet is a form of such social algorithms, but it has a scalability problem with growing network size. If every node sends only one ant to each destination node and there are N nodes in the network, the total number of ants that are sent is N(N-1). In addition with increasing overhead for large networks, most of the ants are often lost for distant destinations. Furthermore, due to long travel times, ants that do arrive may carry outdated information. In this paper, a novel hierarchical algorithm is proposed to resolve this scalability problem of AntNet. The proposed Super-AntNet divides a large scale network into several small networks that are chosen based their internal traffic patterns. A separate ant colony is then assigned to each of these networks. A Super-Ant Colony is then responsible to coordinate data routing among the colonies. Performance of Super-AntNet is compared with those of standard AntNet as well as two other conventional routing algorithms such as Distance Vector (DV) and Link State (LS) in terms of end-to-end delay, throughput, packet loss ratio, increased overhead, as well as jitter. Application to a 16-node network indicates the superiority of the proposed algorithm.

In this paper we have carefully examined two variants of the Round Data Mailer protocol. It is shown that the version, which is designed to be implemented for the MAC layer, has better performance in comparison with the one which is implemented as multi layer protocol.

Many scheduling algorithms have been studied to guarantee the time constraints of real-time processes. Scheduling decision of these algorithms is usually based on parameters which are assumed to be crisp. However, in many circumstances the values of these parameters are vague. The vagueness of parameters suggests that we make use of fuzzy logic to decide in what order the requests should be executed to better utilize the system and as a result reduce the chance of a request being missed. We have proposed a new fuzzy algorithm called highest fuzzy priority first. The performance of this algorithm is compared with the well-known earliest deadline first algorithm through simulation. For both algorithms, tasks are considered to be non-preemptable. Simulation results show that this fuzzy approach outperforms the earliest deadline first has algorithm in that it decreases the number of missed deadlines and serves more important tasks better

Processor allocation is done using space-sharing or time-sharing techniques. In timesharing techniques, processes are allocated to processors by dividing the time into separate slots, with each slot allocated to a different task. In space-sharing techniques processors are divided into physical partitions and once allocated, processes do not leave the system until they are completed and finished. Early processor allocation techniques were contiguous, in which the processors are constrained to be physically adjacent. These strategies suffered significantly from internal and external fragmentation. Non-contiguous processor allocation strategies have solved the fragmentation problem but have introduced a new problem called message-passing contention. In this article, we propose ESS, which is a new non-contiguous processor allocation strategy on mesh-connected parallel computers. ESS is noncontiguous, and gives a very compact allocation, and thus performs a very successful allocation with minimum contention. Furthermore, ESS is inherently parallelizable.

A recovery program is a software component of a fault-tolerant computer system which is responsible for establishing an operational hardware configuration and resurrecting the computation interrupted due to component failures. Development of an effective recovery program is made difficult by the unusual input to the program, i.e., a faulty machine whose behavior is undefined. In this paper we present several program design techniques and system recovery strategies that have been found useful in obtaining an easily understandable recovery program. The strategies are first presented in abstract forms and then illustrated with a model and a recovery program for the Fault-Tolerant Spaceborne Computer (FTSC). Because of the difficulty of obtaining a single perfect recovery procedure, the FTSC recovery program is equipped with both an alternate recovery procedure that is used when the primary procedure is not effective, and an acceptance test that determines the need for invoking the alternate.