Search

Feature selection is one of the main issues in machine learning algorithms. In this paper, a new binary hyper-heuristics feature ranks algorithm is designed to solve the feature selection problem in high-dimensional classification data called the BFRA algorithm. The initial strong population generation is done by ranking the features based on the initial Laplacian Score (ILR) method. A new operator called AHWF removes the zero-importance or redundant features from the population-based solutions. Another new operator, AHBF, selects the key features in population-based solutions. These two operators are designed to increase the exploitation of the BFRA algorithm. To ensure exploration, we introduced a new operator called BOM, a binary counter-mutation that increases the exploration and escape from the BFRA algorithm’s local trap. Finally, the BFRA algorithm was evaluated on 26 high-dimensional data with different statistical criteria. The BFRA algorithm has been tested with various meta-heuristic algorithms. The experiments’ different dimensions show that the BFRA algorithm works like a robust meta-heuristic algorithm in low dimensions. Nevertheless, by increasing the dataset dimensions, the BFRA performs better than other algorithms in terms of the best fitness function value, accuracy of the classifiers, and the number of selected features compared to different algorithms. However, a case study of sentiment analysis of movie viewers using BFRA proves that BFRA algorithms demonstrate affordable performance.

Today, intelligent transportation systems (ITS) have received a lot of attention due to their significant impact on increasing the safety, efficiency, and convenience of transportation. One of the main applications of ITS is vehicular ad hoc networks (VANETs). In particular, a more flexible, reliable, real-time, and scalable routing scheme across the large urban areas is one of the most critical issues for VANETs. Past VANET routing methods have various technical issues with VANET evolutions. On the other hand, clustering improves the reliability and scalability of routing schemes in VANETs. In this paper, a cluster-based, Traffic-aware and Low-Latency Routing Schema (TaLAR) is proposed for VANETs. In the proposed scheme, the Harris hawks optimization (HHO) algorithm is used to select cluster head (CH) nodes by considering appropriate parameters such as intracluster distance, link reliability, and relative speed of vehicles. The path between source and destination CH nodes is identified by using the HHO algorithm; it chooses the appropriate route based on link reliability and intercluster distance. Also, in the interconnection area, a traffic-aware and reliable route is identified by using a digital map of the streets and the Dijkstra algorithm. The performance evaluation of the proposed scheme is analyzed in terms of packet delivery rate (PDR), average end-to-end delay, and throughput. The output of the proposed scheme is compared with the Clustering Routing Based on PSO (Particle Swarm Optimization) (CRBP) and Grey Wolf Optimization Based Clustering in Vehicular Ad Hoc Network (GWOCENT) methods. Simulation results show that the proposed scheme improves PDR (22 and 19%), throughput (25 and 21%), and average end-to-end delay (23 and 18%).

The Internet of Things (IoT) is a network of various interconnected objects capable of collecting and exchanging data without human interaction. These objects have limited processing power, storage space, memory, bandwidth and energy. Therefore, due to these limitations, data transmission and routing are challenging issues where data collection and analysis methods are essential. The Routing Protocol for Low-power and Lossy Networks (RPL) is one of the best alternatives to ensure routing in LoWPAN6 networks. However, RPL lacks scalability and basically designed for non-dynamic devices. Another drawback of the RPL protocol is the lack of load balancing support, leading to unfair distribution of traffic in the network that may decrease network efficiency. This study proposes a novel RPL-based routing protocol, QFS-RPL, using Q-learning algorithm policy and ideation from the Fisheye State Routing (FSR) protocol. The proposed QFS-RPL is as lightweight and agile as the standardized RPL and partially outperforms the mRPL protocol on mobile networks. This method supports multi-path routing, and at any given time in the network lifetime, all possible paths for sending data from any node to the sink are available. Therefore, QFS-RPL provides high resilience against errors, failures, and sudden network changes. To evaluate the performance of the proposed method, the Contiki operating system and Cooja simulator have been used in scenarios with mobile and stationary nodes and random network topologies. The results have been compared with RPL and mRPL. We have developed an algorithm for ease of data transfer in the IoT, which provides better performance than existing protocols, especially when dealing with a mobile network. The performance evaluation criteria considered for simulation are load balancing, energy consumption, number of table entries, Packet Delivery Ratio (PDR), End-to-End (E2E) latency, network throughput, convergence speed, and control packet overhead.

Optimization is necessary for solving and improving the solution of various complex problems. Every meta-heuristic algorithm can have a weak point, and multiple mechanisms and methods can be used to overcome these weaknesses. We can use hybrid meta-heuristic algorithms to arrive at an efficient algorithm. This paper presents a new and intelligent approach by hybridizing meta-heuristic algorithms and using different mechanisms simultaneously without significantly increasing the time complexity. For this purpose, two algorithms, Salp Swarm Optimization(SSO) and the African Vulture Optimization Algorithm (AVOA) have been hybridized. And to improve the optimization process of the Modified Choice Function and Learning Automata mechanisms. In addition, two other improving mechanisms, named Opposition-Based Learning (OBL) and β-hill climbing (BHC) technique, have been presented and integrated with the AVOA-SSA algorithm. Fifty-two standard benchmarks were used to test and evaluate the AVOA-SSA algorithm. Finally, an improved version of the Extreme Learning Machine(ELM) classifier has been used with real stock market data for stock market prediction. The obtained results indicate the excellent and acceptable performance of the AVOA-SSA algorithm in `solving optimization problems and has been able to achieve high-quality solutions.

As the Internet of Things networks expand globally, it is becoming increasingly important to protect against threats. one of the main reasons for the high number of false positives and low detection rates is the presence of redundant and irrelevant features. To address this problem, we propose a binary chimpanzee optimization algorithm for the feature selection process. This paper presents accurate network-based intrusion detection network, named parallel convolutional neural network long and short-term memory network branch, which has two branches. The input vector of the network is permuted in a 3-dimention space. This allows the model to extract highly discriminative features using a small number of layers. On the second branch, we used long and short-term memory network in parallel. The efficacy of the proposed deep model has been evaluated using three benchmark internet of things intrusion detection datasets, namely ToN-IoT, UNSW-NB15, and IoTID20 datasets. The experimental results demonstrated that the proposed binary chimpanzee optimization approach reduces about 60% of features, and the effectiveness of the proposed model was demonstrated by experimental results showing a high detection rate, high accuracy, and a relatively low false positive rate, which are measured as 99.54%, 99.56%, and 0.024 in the ToN-IoT and 99.79%, 99.78%, and 0.0032 in UNSW-NB15 and 100%, 100%, and zero in IoTID20 datasets, respectively.

With the increase in the number of processing cores on a chip, a highly efficient and scalable structure such as a network on a chip was proposed. Network-on-chip is a technology presented to solve the limitations of system-on-chip that includes a set of multiprocessors. In network-on-chip systems, delay in communication and reaching the ideal speed is one of the concerns of academic and industrial researchers today. Although network-on-chip offers a favorable solution to reduce the problem of the long delay of wires compared to traditional structures, communication delay is still a challenge. In this article, the various types of network router input ports architecture on the chip are reviewed and the operational comparison and evaluation of the technologies proposed in this field are mentioned.

Network on chip (NoC) is one of the communicative structures for multiple cores that has scalability. In designing the NoC micro-router architecture, the arbitration unit is very important due to its significant impact on performance, chip occupation level and NoC power consumption. In this paper, a router arbitration architecture is proposed with a combination of variable priority arbitration and Round Robin. In this architecture, arbitration examines the requests of other channels based on the Round Robin index after requesting the flit to exit the virtual channel in addition to checking the availability of the relevant virtual channel.The simulation results show that the architecture of the RR-SFVP arbitration unit compared to the standard RR method, is 13.7% smaller in area and has 5.7% less power consumption and 53.7% less critical path delay.

The Internet of Things (IoT) has rapidly grown recently, and mobile devices (MDs) have encountered widespread usage. All of these cause an increase in the demand for more powerful computing resources. Meanwhile, a new concept called mobile edge computing (MEC) was introduced as a promising technology to access powerful computing resources closer to the user side for a quick and effective response, especially for time-intensive applications. Task offloading has emerged as a solution to allocate resources among computing resources of smart devices or computational resources available in MEC. This study presents a new binary quantum approach based on an arithmetic optimization algorithm (BQAOA) for computational tasks offloading decisions on MDs with low complexity and guaranteed convergence. However, since task offloading is an NP-hard problem, there is a need to use methods that provide the optimal possible solution for various quality criteria, including response time and energy consumption. Indeed, this is where the advantages of arithmetic optimization algorithms (AOA) and quantum computing have been used to improve the performance of MDs. This paper introduces a 2-tier architecture from the user to the cloud computing server-side. Also, a Markov model is proposed to compute the average network bandwidth in the offloading problem. The proposed BQAOA is compared with the best state-of-the-art algorithms in heuristic and meta-heuristic fields in different scenarios. The simulation results showed 12.5%, 12%, and 26% improvement in energy consumption, makespan, and Energy SLA Violations (ESV) optimization parameters, respectively.

Multi-cloud is the use of multiple cloud computing in a single heterogeneous architecture. Workflow scheduling in multi-cloud computing is an NP-Hard problem for which many heuristics and meta-heuristics are introduced. This paper first presents a hybrid multi-objective optimization algorithm denoted as HGSOA-GOA, which combines the Seagull Optimization Algorithm (SOA) and Grasshopper Optimization Algorithm (GOA). The HGSOA-GOA applies chaotic maps for producing random numbers and achieves a good trade-off between exploitation and exploration, leading to an improvement in the convergence rate. Then, HGSOA-GOA is applied for scientific workflow scheduling problems in multi-cloud computing environments by considering factors such as makespan, cost, energy, and throughput. In this algorithm, a solution from the Pareto front is selected using a knee-point method and then is applied for assigning the scientific workflows’ tasks in a multi-cloud environment. Extensive comparisons are conducted using the CloudSim and WorkflowSim tools and the results are compared to the SPEA2 algorithm. The achieved results exhibited that the HGSOA-GOA can outperform other algorithms in terms of metrics such as IGD, coverage ratio, and so on.

Energy consumption is one of the main concerns in wireless sensor networks (WSNs). In this context, congestion is one of the problems which by dropping the data packets, increases the energy consumption of WSN, and reduces its lifetime. In this paper, we deal with these problems and present a distributed fuzzy clustering scheme that uses two Fuzzy Logic Controllers (FLCs) to organize WSN into some clusters. Besides, in this scheme, we consider multiple mobile sink nodes and provide another FLC for fuzzy sink selection used by cluster heads (CHs). In this scheme, CHs cooperate in multi-hop routing of data packets to minimize the energy consumption of WSN. However, in the data routing step, congestion may happen in the data forwarding nodes. In this scheme, we deal with the congestion problem by proposing a distance-based version of the Random Early Detection (RED) congestion control method to drop the data packets more intelligently. Besides, to increase the effectiveness of the proposed FLCs, we tune them using the Moth-Flame Optimization algorithm and minimize their rules. Simulation results indicate the effectiveness of the proposed clustering and distance-based RED congestion control method in improving the WSN’s lifespan, reducing the number of retransmissions, and mitigating the percentage of packet loss.

The gray wolf optimizer (GWO) and the whale optimization algorithm (WOA) are two esteemed optimization algorithms, and their various modified versions are proposed in recent years for different applications. The GWO and WOA simulate the hunting method of gray wolves and humpback whales, respectively. These algorithms have several operators for moving the search agents toward the optimum solution in the search space. But, the GWO and WOA encounter some problems such as falling in local optima and slow convergence. Various proposals have been presented so far to develop innovative and novel meta-heuristic optimization methods. Some of them are based on adding special evolutionary operators or local search steps to existing algorithms. Some others are established based on the combination of previous methods or applying the chaos theory in them. A novel hybrid method defined as chaotic GWO and WOA (CGWW) is proposed in this paper by modifying the WOA, merging it with GWO, and applying the chaotic maps. Also, the chaotic maps have been used in the CGWW algorithm to adjust the movement parameters and initialize the search agents. The combination of different operators of the mentioned algorithms and using the chaotic maps increases the exploration and exploitation power of the proposed algorithm and thus causes to obtain better results. Twenty-three mathematical benchmark functions are used to evaluate the CGWW algorithm. Besides, the proposed algorithm is applied for solving the feature selection problem in intrusion detection systems, which is intrinsically multi-objective. The proposed algorithm finds competitive results in contrast to other well-known meta-heuristic algorithms in most of the experiments. It can avoid local optima and find the global optimum in most cases using its balanced exploration and exploitation ability.

In recent years, cloud storage systems have emerged as a promising technology for storing data blocks on various cloud servers. One of the main mechanisms in cloud storage systems is data replication, for which various solutions are proposed. Data replication's main target is achieving higher performance for data-intensive applications by addressing some critical challenges of this criterion, such as availability, reliability, security, bandwidth, and response time of data access. However, to the best of the author’s knowledge, there is no systematic, comprehensive, and complete survey in the cloud data replication despite its impacts and maturity. This paper presents a comprehensive survey and classification of state-of-the-art data replication schemes among different existing cloud computing solutions in the form of a classical classification to define current schemes on the topic and present open issues. The presented classification comprises three main classes; data deduplication schemes, data auditing schemes, and data handling schemes. A complete comparative comparison of the replication schemes highlights their main properties, such as utilized classes, type of the scheme, the place of implementation, evaluation tools, and their advantages and weaknesses. Finally, open issues and future uncovered or weakly covered research challenges are discussed, and the survey will be concluded.

Software defined network (SDN) has shown significant advantages in numerous real-life aspects with separating the control plane from the data plane that provides programmable management for networks. However, with the increase in the network size, a single controller of SDN imposes considerable limitations on various features. Therefore, in networks with immense scalability, multiple controllers are essential. Specifying the optimal number of controllers and their deployment place is known as the controller placement problem (CPP), which affects the network's performance. In the present paper, a novel controller placement algorithm has been introduced using the advantages of nature-inspired optimization algorithms and network portioning. Firstly, the Manta Ray Foraging Optimization (MRFO) and Salp Swarm Algorithm (SSA) have been discretized to solve CPP. Three new operators comprising a two-point swap, random insert, and half points crossover operators were introduced to discretized the algorithms. Afterward, the resulting discrete MRFO and SSA algorithms were hybridized in a promoting manner. Next, the proposed discrete algorithm has been evaluated on six well-known software-defined networks with a different number of controllers. In addition, the networks have been chosen from various sizes to evaluate the scalability of the proposed algorithm. The proposed algorithm has been compared with several other state-of-the-art algorithms regarding network propagation delay and convergence rate in experiments. The findings indicated the effectiveness of the contributions and the superiority of the proposed algorithm over the competitor algorithms.

In recent years, social networks' growth has led to an increase in these networks' content. Therefore, text mining methods became important. As part of text mining, Sentiment analysis means finding the author's perspective on a particular topic. Social networks allow users to express their opinions and use others' opinions in other people's opinions to make decisions. Since the comments are in the form of text and reading them is time-consuming. Therefore, it is essential to provide methods that can provide us with this knowledge usefully. Black Widow Optimization (BWO) is inspired by black widow spiders' unique mating behavior. This method involves an exclusive stage, namely, cannibalism. For this reason, at this stage, species with an inappropriate evaluation function are removed from the circle, thus leading to premature convergence. In this paper, we first introduced the BWO algorithm into a binary algorithm to solving discrete problems. Then, to reach the optimal answer quickly, we base its inputs on the opposition. Finally, to use the algorithm in the property selection problem, which is a multi-objective problem, we convert the algorithm into a multi-objective algorithm. The 23 well-known functions were evaluated to evaluate the performance of the proposed method, and good results were obtained. Also, in evaluating the practical example, the proposed method was applied to several emotion datasets, and the results indicate that the proposed method works very well in the psychology of texts.

Services Oriented Architecture provides Web Services (WSs) as reusable software components that can be applied to create more complicate composite services for users according to the specified QoS limitations. However, considering many WSs that may be appropriate for each task of a user-submitted workflow, finding the optimal WSs for a composite WS to maximize the overall QoS is an NP-hard problem. As a result, numerous composition schemes have been suggested in the literature to untangle this problem by using various metaheuristic algorithms. This paper presents a comprehensive survey and taxonomy of such QoS-oriented metaheuristic WS composition schemes provided in the literature. It investigates how metaheuristic algorithms are adapted for the WS composition problem and highlight their main features, advantages, and limitations. Also, in each category of the studied composition schemes, a comparison of their applied QoS factors, evaluated metrics, exploited simulators, and properties of the applied metaheuristic algorithms are explained. Finally, the concluding remarks and future research directions are summarized to help researchers in working in this area.

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 inherent features of software-defined networking (SDN) architecture revolutionize traditional network infrastructure and provide the opportunity for integrated and centralized network monitoring. One of the shortcomings of SDNs is related to its high vulnerability to distributed denial of service attacks and other similar ones. In this paper, a novel multi-stage modular approach is proposed for detecting and mitigating security anomalies in SDN environment (SADM-SDNC). The proposed approach uses NetFlow protocol for gathering information and generating dataset and information gain ratio in order to select the effective features. Also, the C-support vector classification algorithm with radial basis function kernel, and features of Floodlight controller for developing a structure with desirable performance were used in the proposed scheme. The experimental results demonstrate that the proposed approach performs better than other methods in terms of enhancing accuracy and detection rate, and reducing classification error and false alarm rate, which were measured as 99.67%, 99.26%, 0.33%, and 0.08% respectively. Finally, thanks to utilizing REST API and Static Entry Pusher technologies in the Floodlight controller, it makes it possible to disconnect any communications with the attacking factors and remove destructive users.

Workflow is composed of some interdependent tasks and workflow scheduling in the cloud environment that refers to sorting the workflow tasks on virtual machines on the cloud platform. We will encounter many sorting modes with an increase in virtual machines and the variety in task size. Reaching an order with the least makespan is an NP-hard problem. The hardness of this problem increases even more with several contradictory goals. Hence, a meta-heuristic algorithm is what required in reaching the optimal response. Thus, the algorithm is a hybridization of the ant lion optimizer (ALO) algorithm with a Sine Cosine Algorithm (SCA) algorithm and used it multi-objectively to solve the problem of scheduling scientific workflows. The novelty of the proposed algorithm was to enhance search performance by making algorithms greedy and using random numbers according to Chaos Theory on the green cloud computing environment. The purpose was to minimize the makespan and cost of performing tasks, to reduce energy consumption to have a green cloud environment, and to increase throughput. WorkflowSim simulator was used for implementation, and the results were compared with the SPEA2 workflow scheduling algorithm. The results show a decrease in the energy consumed and makespan.

Cloud computing, with its immense potentials in low cost and on-demand services, is a promising computing platform for both commercial and non-commercial computation applications. It focuses on the sharing of information and computation in a large network that are quite likely to be owned by geographically disbursed different venders. Power efficiency in cloud data centers (DCs) has become an important topic in recent years as more and larger DCs have been established and the electricity cost has become a major expense for operating them. Server consolidation using virtualization technology has become an important technology to improve the energy efficiency of DCs. Virtual machine (VM) assignment is the key in server consolidation. In the past few years, many methods to VM assignment have been proposed, but existing VM assignment approaches to the VM assignment problem consider the energy consumption by physical machines (PM). In current paper a new approach is proposed that using a combination of the sine cosine algorithm (SCA) and ant lion optimizer (ALO) as discrete multi-objective and chaotic functions for optimal VM assignment. First objective of our proposed model is minimizing the power consumption in cloud DCs by balancing the number of active PMs. Second objective is reducing the resources wastage by using optimal VM assignment on PMs in cloud DCs. Reducing SLA levels was another purpose of this research. By using the method, the number of increase of migration of VMs to PMs is prevented. In this paper, several performance metrics such as resource wastage, power consumption, overall memory utilization, overall CPU utilization, overall storage space, and overall bandwidth, a number of active PMs, a number of shutdowns, a number of migrations, and SLA are used. Ultimately, the results obtained from the proposed algorithm were compared with those of the algorithms used in this regard, including First Fit (FF), VMPACS and MGGA.

Cloud computing, with its immense potentials in low cost and on-demand services, is a promising computing platform for both commercial and non-commercial computation applications. It focuses on the sharing of information and computation in a large network that are quite likely to be owned by geographically disbursed different venders. Energy efficiency in data centers has become a hot topic in recent years as more and larger data centers have been established and the electricity cost has become a major expense for operating them. Server consolidation using virtualization technology has become an important technology to improve the energy efficiency of data centers. Virtual machine placement is the key in server consolidation. In the past few years, many approaches to virtual machine placement have been proposed, but existing virtual machine placement approaches to the virtual machine placement problem consider the energy consumption by physical machines. In this paper, we proposed a new approach for placement based on Discrete Chaotic whale optimization Algorithm. First goal of our presented algorithm is reducing the energy consumption in datacenters by decreasing the number of active physical machines. Second goal is decreasing waste of resources and management of them using optimal placement of virtual machines on physical machines in cloud data centers. By using the method, the increase in migration of virtual machines to physical machines is prevented. Finally, our proposed algorithm is compared to some algorithms in this area like FF, ACO, MGGA, GSA, and FCFS.

Security is one of the main requirements of the current computer systems, and recently it gains much importance as the number and severity of malicious attacks increase dramatically. Anomaly detection is one of the main branches of the intrusion detection systems which enables to recognize the newer variants of the security attacks. This paper focuses on the anomaly detection schemes (ADS), which have applied support vector machine (SVM) for detecting intrusions and security attacks. For this purpose, it first presents the required concepts about the SVM classifier and intrusion detection systems. It then classifies the ADS approaches and discusses the various machine learning and artificial intelligence techniques that have been applied in combination with the SVM classifier to detect anomalies. Besides, it specifies the primary capabilities, possible limitations, or advantages of the ADS approaches. Furthermore, a comparison of the studied ADS schemes is provided to illuminate their various technical details.

Cloud computing is a new computation technology that provides services to consumers and businesses. The main idea of Cloud computing is to present software and hardware services through the Internet to the users and organizations at all levels. In Cloud computing, the users pay for the services, which means a usage-based payment system is used in this technology. Using virtualization technology in computation resources enables the appropriate utilization of resources in cloud computing. One of the most significant challenging issues in virtualization technology is the placement of optimal virtual machines on physical machines in cloud data centers. The placement of virtual machines comprises a process wherein virtual machines are mapped onto physical machines in cloud data centers. Optimal deployment leads to the reduction in power consumption, optimal use of resources, traffic reduction in data centers, costs reduction, and efficiency enhancement of the data center in the cloud. The present article proposed a new approach using a combination of the Sine–Cosine Algorithm and Salp Swarm Algorithm as discrete multi-objective and chaotic functions for optimal virtual machine placement. The first goal of the proposed algorithm was to reduce the power consumption in cloud data centers by condensing the number of active physical machines. The second goal was to reduce the waste of resources and manage it by optimally virtual machine placement on physical machines in cloud data centers. The third objective was to minimize and reduce Service Level Agreement among the active physical machines in cloud data centers. The proposed method prevent the increase in the migration of virtual machines onto physical machines. Ultimately, the results obtained from the proposed algorithm were compared with those of previous akin algorithms in the literature, including First Fit, Virtual Machine Placement Ant Colony System, and Modified Best Fit Decreasing. The proposed scheme is tested using Amazon EC2 Instances and the result indicated that the proposed algorithm performs better than the existing algorithms for various performance metrics.

Cloud computing is a computing paradigm, where a large pool of systems is connected in private or public networks to provide dynamically scalable infrastructure for application, data, and file storage. With the advent of this technology, the cost of power computation, application hosting, content storage, resource wastage, and delivery is reduced significantly. Cloud computing provides the possibility of merely concentrating on business goals instead of expanding hardware resources for users. Challenging work in virtualization technology is the placement of virtual machines under optimal conditions on physical machines in cloud data centers. Optimal placement of virtual machines over physical ones in cloud data centers can lead to the management of resources and prevention of the resources waste. Hereby, a new approach is proposed based on the combination of the hybrid discrete multi-object whale optimization algorithm, multi-verse optimizer with chaotic functions for optimal placement in the cloud data center. The first object of the proposed algorithm is to decrease power consumption, which is consumed in cloud data centers by reducing active physical machines. The second goal is to cut the resource wastage and managing resources using the optimal placement of virtual machines over physical machines in cloud data centers. With this method, the increasing rate of virtual migration to physical machines is prevented. Finally, the results obtained from the proposed algorithm were compared to some algorithms such as first fit, VMPACS, MBFD.

Software defined network (SDN) decouples the network control and data planes. Despite various advantages of SDNs, they are vulnerable to various security attacks such anomalies, intrusions, and Denial-of-Service (DoS) attacks and so on. On the other hand, any anomaly and intrusion in SDNs can affect many important domains such as banking system and national security. Therefore, the anomaly detection topic is a broad research domain, and to mitigate these security problems, a great deal of research has been conducted in the literature. In this paper, the state-of-the-art schemes applied in detecting and mitigating anomalies in SDNs are explained, categorized, and compared. This paper categorizes the SDN anomaly detection mechanisms into five categories: (1) flow counting scheme, (2) information-based scheme, (3) entropy-based scheme, (4) deep learning, and (5) hybrid scheme. The research gaps and major existing research issues regarding SDN anomaly detection are highlighted. We hope that the analyses, comparisons, and classifications might provide directions for further research.

The workflow scheduling in the cloud computing environment is a well-known NP-complete problem, and metaheuristic algorithms are successfully adapted to solve this problem more efficiently. Grey wolf optimization (GWO) is a recently proposed interesting metaheuristic algorithm to deal with continuous optimization problems. In this paper, we proposed IGWO, an improved version of the GWO algorithm which uses the hill-climbing method and chaos theory to achieve better results. The proposed algorithm can increase the convergence speed of the GWO and prevents falling into the local optimum. Afterward, a binary version of the proposed IGWO algorithm, using various S functions and V functions, is introduced to deal with the workflow scheduling problem in cloud computing data centers, aiming to minimize their executions’ cost, makespan, and the power consumption. The proposed workflow scheduling scheme is simulated using the CloudSim simulator and the results show that our scheme can outperform other scheduling approaches in terms of metrics such as power consumption, cost, and makespan.

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.

The growing number of web services (WSs) and cloud services, which can meet the users’ functional and non-functional requirements, have inspired researchers to provide more effective approaches for ranking the available services, regarding different QoS factors and selecting the best of them. In this context, several service selection frameworks using the fuzzy multicriteria decision making (MCDM) techniques are introduced in the literature. This paper focuses on such schemes, and firstly provides the required background knowledge about service selection and MCDM methods. Then, it puts forward a taxonomy of the service selection schemes, regarding their utilized fuzzy MCDM methods, and describes how the fuzzy MCDM methods are adapted to handle the fuzziness of the users’ preferences and QoS properties. Furthermore, the main features of these schemes are compared, and their contributions and possible shortcomings are discussed. Finally, the concluding remarks are provided, and directions for future studies are illuminated.

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.

The growing number of services that can meet the users’ functional requirements, inspired many researchers to provide some approaches to rank and select the best possible services regarding their quality of service (QoS) and users’ preferences. Considering various criteria which should be considered in the service selection process, multi-criteria decision making (MCDM) techniques have been vastly applied to help a decision-maker in determining the weight of each QoS factor and ranking the services provided by different service providers. This paper provides an extensive investigation of the state of the art MCDM-based service selection schemes proposed in the literature. It provides the required background knowledge and puts forward a taxonomy of the investigated service selection schemes regarding their applied MCDM methods. Also, it describes how the MCDM methods are adapted by the studied schemes, which datasets and QoS criteria are employed by each system, and which factors and environments are utilized to evaluate the service selection schemes. Finally, the concluding remarks are provided, and directions for future studies are highlighted.

Web usage data usually contain quantitative values, and this implies that fuzzy logic can be used to represent such values. The time spent by users on each web page is a part of web usage data, which can be used to analyze users’ browsing behavior. In existing research on fuzzy web mining, the time duration of web pages is shown as trapezoidal membership functions (TMFs), and the number and parameters of TMFs are already predefined. TMFs of each web page are different from those of other web pages. Therefore, instead of using predefined TMFs, in this study, we proposed a new algorithm called CALA-FOMF to find both the number of TMFs and their optimized parameters to mine fuzzy association rules in web usage data using a team of continuous action-set learning automata (CALA). CALA-FOMF contained two steps. In the first step, using a team of CALA, we introduced a new framework. The proposed framework obtained the number of TMFs as inputs and found their optimized parameters. The proposed framework was able to reduce the search space and eliminate inappropriate membership functions during the learning process. In the second step, we proposed a new algorithm using the proposed framework to find an appropriate number of TMFs and their optimized parameters. The performance of the CALA-FOMF approach was compared with that of the fuzzy web mining algorithm, which used uniform TMFs. Experiments on datasets with different sizes confirmed that the proposed CALA-FOMF increased the efficiency of mining fuzzy association rules by extracting optimized TMFs.

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.

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.

Clustering is an appealing paradigm exploited to improve the lifetime and scalability of wireless sensor networks (WSNs). Considering the NP-completeness of the clustering problem, numerous meta-heuristic algorithms are provided in the literature for the clustering of WSNs. Teaching–learning-based optimization (TLBO) is an optimization algorithm employed to tackle continuous optimization problems. In this paper, a novel discrete version of the TLBO algorithm is being presented that employs the swap and mutation operators to deal with discrete solutions. Subsequently, the new-fangled algorithm was utilized to design a hierarchical energy-aware clustering scheme for the WSNs to minimize the energy usage of the sensor nodes. In addition, an energy-aware local search algorithm was provided to enhance the network lifetime by taking factors such as energy and distance into account. Extensive simulations are conducted to indicate the effectiveness of this scheme in reducing the power usage of the sensor nodes and improving the WSN lifetime.

High cost of data centers’ energy consumption and its environmental effects such as CO2 emissions have inspired numerous researches to provide more efficient VM management approaches. VM migration is one of the critical VM management activities whose performance has a direct effect on the energy efficiency of cloud data centers (DCs). To conduct a more effective migration process and reduce the number of VM migrations, some of the VM management frameworks apply prediction algorithms to forecast various migration and VM-related factors. This paper presents an extensive survey and taxonomy of the predictive VM migration approaches adapted for the cloud DCs. For this purpose, it first provides the key issues regarding the VM migration and then classifies them based on their applied prediction algorithm. It illustrates the main contributions of each scheme and describes how prediction methods are integrated into the VM migration process, to make it more effective. Moreover, a comparison of the predictive migration schemes is provided. Finally, the concluding remarks and future research areas are specified.

Security attacks are a nightmare to many computing environments such as fog computing, and these attacks should be addressed. Fog computing environments are vulnerable to various kinds of DDoS attacks, which can keep fog resources busy. Typically in such attacks, fog environments often have less available resources, which can negatively impact the scheduling of Internet of Things (IoT) submitted workflows. However, most of the existing scheduling schemes do not consider DDoS attacks’ effect in the scheduling process, increasing the deadline missed workflows and offloaded tasks on the cloud. For dealing with these issues, a hybrid optimization algorithm is proposed, comprising both Particle Swarm Optimization (PSO) and Salp Swarm algorithm (SSA), to solve the workflow scheduling problem in multiple fog computing environments. Two discrete-time Markov chain models are proposed for each fog computing environment to address DDoS attacks’ effects on them. Our first Markov model computes the average available network bandwidth for each fog. The second Markov model finds the average number of available virtual machines (VMs) for each fog; the models address different levels of DDoS attacks. Extensive simulations show that by predicting the effects of DDoS attacks on fog environments, the proposed approach can effectively mitigate the number of offloaded tasks on cloud data centers and can reduce the number of the deadline missed workflows.

This paper employs machine learning algorithms to detect tax evasion and analyzes tax data. With the development of commercial businesses, traditional algorithms are not appropriate for solving the tax evasion detection problem. Hence, other algorithms with acceptable speed, precision, analysis, and data decisions must be used. In the case of assets and tax assessment, the integration of machine learning models with meta-heuristic algorithms increases accuracy due to optimal parameters. In this paper, intelligent machine learning algorithms are used to solve tax evasion detection. This research uses an improved particle swarm optimization (IPSO) algorithm to improve the multilayer perceptron neural network by finding the optimal weight and improving support vector machine (SVM) classifiers with optimal parameters. The IPSO-MLP and IPSO-SVM models using the IPSO algorithm are used as new models for tax evasion detection. Our proposed system applies the dataset collected from the general administration of tax affairs of West Azerbaijan province of Iran with 1500 samples for the tax evasion detection problem. The evaluations show that the IPSO-MLP model has a higher accuracy rate than the IPSO-SVM model and logistic regression. Moreover, the IPSO-MLP model has higher accuracy than SVM, Naive Bayes, k-nearest neighbor, C5.0 decision tree, and AdaBoost. The accuracy of IPSO-MLP and IPSO-SVM models is 93.68% and 92.24%, respectively.