Explore the vast range of titles available.

Large scale Wireless Sensor Networks (WSNs) often utilize multiple mobile sink nodes to improve the network lifetime and scalability. However, most of the studies conducted in this context, consider unlimited buffer capacity for the sink nodes. But, this model cannot truly describe the behavior of WSNs and causes congestion in the sink nodes. To solve this problem, in this paper, we use limited buffer capacity for each mobile sink node in WSNs and present a two-level Fuzzy Logic Controller (FLC)-based dynamic clustering scheme and congestion prevention. In this scheme, sink nodes try to predict current load based on their loads in previous rounds by using ARIMA method and based on it, the first FLC selects the nearest uncongested sink node from multiple available mobile sink nodes. Then, the second FLC applies the output of the first FLC to select appropriate nodes as cluster heads to mitigate the energy consumption in the network. Extensive simulation results indicate the effectiveness of the proposed fuzzy logic-based solution in reducing congestion in the mobile sink nodes and improving load balancing in them which these result in the network lifetime improvement and decreasing the number of retransmissions.

Efficient VM management is very crucial for energy saving, increasing profit, and preventing SLA violations. VM placement schemes can be classified into reactive and proactive/predictive schemes which try to improve the VM placement results, by forecasting future workloads or resource demands using various prediction techniques. This paper puts forward an extensive survey of the proactive VM placement approaches and categorizes them according to their applied forecasting methods. It describes how each scheme has applied the prediction algorithms to conduct more effective and low overhead VM placement. Moreover, in each category, factors such as evaluation parameters, simulation software, workload data, power management method, and prediction factors are compared to illuminate more details about the investigated VM placement approaches. At last, the concluding issues and open future studies trends and area are highlighted.

A multi-objective optimization approach is suggested here for scientific workflow task-scheduling problems in cloud computing. More frequently, scientific workflow involves a large number of tasks. It requires more resources to perform all these tasks. Such a large amount of computing power can be supported only by cloud infrastructure. To implement complex science applications, more computing energy is expended, so the use of cloud virtual machines in an energy-saving way is essential. However, even today, it is a difficult challenge to conduct a scientific workflow in an energy-aware cloud platform. The hardness of this problem increases even more with several contradictory goals. Most of the existing research does not consider the essential characteristic of cloud and significant issues, such as energy variation and throughput besides makespan and cost. Therefore, a hybridization of the Antlion Optimization (ALO) algorithm with the Grasshopper Optimization Algorithm (GOA) was proposed and used multi-objectively to solve the scheduling problems. The novelty of the proposed algorithm was enhancing the search performance by making algorithms greedy and using random numbers according to Chaos Theory on the green cloud environment. The purpose was to minimize the makespan, cost of performing tasks, energy consumption, and increase throughput. WorkflowSim simulator was used for implementation, and the results were compared with the SPEA2 algorithm. Experimental results indicate that based on these metrics, a proposed multi-objective optimization algorithm is better than other similar methods.

In recent years, cloud computing paradigm has emerged as an internet-based technology to realize the utility model of computing for serving compute-intensive applications. In the cloud computing paradigm, the IT and business resources, such as servers, storage, network, and applications, can be dynamically provisioned to cloud workloads submitted by end-users. Since the cloud workloads submitted to cloud providers are heterogeneous in terms of quality attributes, management and analysis of cloud workloads to satisfy Quality of Service (QoS) requirements can play an important role in cloud resource management. Therefore, it is necessary for the provisioning of proper resources to cloud workloads using clustering of them according to QoS metrics. In this paper, we present a hybrid solution to handle the resource provisioning issue using workload analysis in a cloud environment. Our solution utilized the Imperialist Competition Algorithm (ICA) and K-means for clustering the workload submitted by end-users. Also, we use a decision tree algorithm to determine scaling decisions for efficient resource provisioning. The effectiveness of the proposed approach under two real workloads traces is evaluated. The simulation results demonstrate that the proposed solution reduces the total cost by up to 6.2%, and the response time by up to 6.4%, and increases the CPU utilization by up to 13.7%, and the elasticity by up to 30.8% compared with the other approaches.

Cloud computing provides effective mechanisms for distributing the computing tasks to the virtual resources. To provide cost-effective executions and achieve objectives such as load balancing, availability and reliability in the cloud environment, appropriate task and workflow scheduling solutions are needed. Various metaheuristic algorithms are applied to deal with the problem of scheduling, which is an NP-hard problem. This paper presents an in-depth analysis of the Particle Swarm Optimization (PSO)-based task and workflow scheduling schemes proposed for the cloud environment in the literature. Moreover, it provides a classification of the proposed scheduling schemes based on the type of the PSO algorithms which have been applied in these schemes and illuminates their objectives, properties and limitations. Finally, the critical future research directions are outlined.

Fast growth of produced data from deferent smart devices such as smart mobiles, IoT/IIoT networks, and vehicular networks running different specific applications such as Augmented Reality (AR), Virtual Reality (VR), and positioning systems, demand more and more processing and storage resources. Offloading is a promising technique to cope with the inherent limitations of such devices by which the resource-intensive code or at least a part of it will be transferred to the nearby resource-rich servers. Different approaches have been proposed to help make better decisions in respect of whether, where, when, and how much to offload and to improve the efficiency of the offloading process in the literature. On the other hand, the dynamic behavior of mobile devices running on-demand applications faces the offloading to the new challenges, which could be described as stochastic behaviors. Therefore, various stochastic offloading models have been proposed in the literature. However, to the best of the author’s knowledge, despite the existence of plenty of related offloading studies in the literature, there is not any systematic, comprehensive, and detailed survey paper focusing on stochastic-based offloading mechanisms. In this paper, we propose a survey paper concerning the stochastic-based offloading approaches in various computation environments such as Mobile Cloud Computing (MCC), Mobile Edge Computing (MEC), and Fog Computing (FC) in which to identify new mechanisms, a classical taxonomy is presented. The proposed taxonomy is classified into three main fields: Markov chain, Markov process, and Hidden Markov Models. Then, open issues and future unexplored or inadequately explored research challenges are discussed, and the survey is finally concluded.

In the data security context, anomaly detection is a branch of intrusion detection that can detect emerging intrusions and security attacks. A number of anomaly detection systems (ADSs) have been proposed in the literature that using various algorithms and techniques try to detect the intrusions and anomalies. This paper focuses on the ADS schemes which have applied fuzzy logic in combination with other machine learning and data mining techniques to deal with the inherent uncertainty in the intrusion detection process. For this purpose, it first presents the key knowledge about intrusion detection systems and then classifies the fuzzy ADS approaches regarding their utilized fuzzy algorithm. Afterward, it summarizes their major contributions and illuminates their advantages and limitations. Finally, concluding issues and directions for future researches in the fuzzy ADS context are highlighted.

Detecting and handling faulty nodes is one of the main challenges in wireless sensor networks (WSNs). Most of the existing fault detection schemes rely on the data sensed by neighboring nodes, however, these schemes do not usually consider the nature of the events and the coverage issues. In this paper, we present a novel distributed fuzzy logic-based faulty node detection algorithm for heterogeneous WSNs. To weight of the values sensed by the neighboring nodes, the proposed algorithm applies factors such as distance, coverage and the difference of the sensed values. By using the proposed distributed algorithm, each sensor node can correctly recognize its status at the presence of the events such as fire and transient faults. Extensive simulations results indicate the effectiveness of the proposed algorithm in reducing the false positive problems and improving detection accuracy in the fault detection process.

Feature selection plays a key role in data mining and machine learning algorithms to reduce the processing time and increase the accuracy of classification of high dimensional datasets. One of the most common feature selection methods is the wrapper method that works on the feature set to reduce the number of features while improving the accuracy of the classification. In this paper, two different wrapper feature selection approaches are proposed based on Farmland Fertility Algorithm (FFA). Two binary versions of the FFA algorithm are proposed, denoted as BFFAS and BFFAG. The first version is based on the sigmoid function. In the second version, new operators called Binary Global Memory Update (BGMU) and Binary Local Memory Update (BLMU) and a dynamic mutation (DM) operator are used for binarization. Furthermore, the new approach (BFFAG) reduces the three parameters of the base algorithm (FFA) that are dynamically adjusted to maintain exploration and efficiency. Two proposed approaches have been compared with the basic meta-heuristic algorithms used in feature selection on 18 standard datasets. The results show better performance of the proposed approaches compared with the competing methods in terms of objective function value, the average number of selected features, and the classification accuracy. Also, the experiments on the emotion analysis dataset demonstrate the satisfactory results.

The increasing demand for new mobile applications puts a heavy demand for more processing power and resources in smart mobile devices (SMD). Offloading is a promising solution for these issues which tries to move data, code, or computation from the SMDs to the remote or nearby resourceful servers. To increase the effectiveness of the offloading process and make better decisions, various stochastic offloading schemes are proposed in the literature which has adapted different stochastic models. Although offloading issues are vastly studied in the literature, there is a lack of comprehensive paper to focus on stochastic offloading solutions. This paper presents a meticulous review and classification of the stochastic offloading frameworks designed for different environments such as mobile cloud computing, mobile edge computing), and Fog computing. Following this, it first presents the required background concepts and key issues regarding the offloading problem and stochastic models. It then puts forward a taxonomy of the stochastic offloading approaches according to their applied stochastic models and highlights their architectures and contributions. In addition, in each category, a comparison of the stochastic offloading schemes is provided to illuminate their features. Finally, the concluding remarks and open research areas.