Resource Allocation optimization in fog Architecture Based Software-Defined Networks (original) (raw)
Related papers
Resource allocation for fog computing based on software-defined networks
International Journal of Electrical and Computer Engineering (IJECE)
With the emergence of cloud computing as a processing backbone for internet of thing (IoT), fog computing has been proposed as a solution for delay-sensitive applications. According to fog computing, this is done by placing computing servers near IoT. IoT networks are inherently very dynamic, and their topology and resources may be changed drastically in a short period. So, using the traditional networking paradigm to build their communication backbone, may lower network performance and higher network configuration convergence latency. So, it seems to be more beneficial to employ a software-defined network paradigm to implement their communication network. In software-defined networking (SDN), separating the network’s control and data forwarding plane makes it possible to manage the network in a centralized way. Managing a network using a centralized controller can make it more flexible and agile in response to any possible network topology and state changes. This paper presents a s...
SDN-based optimal task scheduling method in Fog-IoT network using combination of AO and WOA
Elsevier, 2023
The Internet of Things (IoT) is a collection of different devices that contain different software and hardware technologies to communicate with other devices using unique addressing methods [1,2]. The IoT devices collect data from their surroundings through various sensors and exchange them [2]. As a result, IoT system applied in various fields such as smart homes, smart cities, transportation, e-health care, agriculture, and industries. Cloud Computing (CC) [3] is an emerging computing technology that, due to its capabilities, can provide all the resources needed for the quality of IoT services for IoT. The CC system consists of a large number of Data Centers (DCs), each DC also consists of a large number of Virtual Machines (VMs). But due to the long geographical distance with IoT devices on the network Edge Computing (EC), the CC system is not suitable for delay-sensitive IoT devices such as emergency monitoring, and energy usage measurements from a smart grid, cause long delays that may not be acceptable for some applications in today's world [3,4]. Therefore, to solve this problem, the computing resources should be closer to the network EC devices, and the CC system is very suitable for this and can provide the resources needed to reduce the workload in cloud DC, facilitate task processing, facilitate networking, and facilitate the storage of data generated by IoT sensors, with the lowest amount of communication cost and delay [4-7]. Each server or Fog Computing (FC) node is a virtualized system equipped with a wireless communication unit, simpler processing and computing devices for data, and data storage cards. When FC nodes receive more task requests from IoT devices that exceed their capacity, they can offload some of their load to cloud layer DCs [8-10]. In other words, CC and FC are models of hosting services over the Internet for IoT devices. Fig. 8.1 shows the architecture of IoT-Fog-Cloud system, with CC in the top layer, FC in the middle layer, and IoT devices in the bottom layer. Task Scheduling (TSch) is an effective method for efficient management of virtual resources of the FC and EC environment [11] based on specific constraints and deadlines by different users, which can be used to assign the set of requested tasks by users or existing IoT devices to FC and CC resources in order to execute them [12-16]. According to Fig. 8.1, in the proposed TSch model that is considered for scheduling the task requests of IoT devices in the FC system, Fog Broker (FB) is the main part and is located in the FC layer, which includes three main parts: Task Administrator (TA), Resource Monitoring Service (RMS), and Task Scheduler (TSR). The TA receives all task requests from various IoT devices, and then forwards them to the TSR, maintaining their required resources and attributes. Also, RMS is responsible for collecting information on FC resources and monitoring the status of FC resources. TSR unit is the main core of FB unit, and TSch algorithms are executed in it. According to the characteristics of the sent task requests as well as the capabilities of the available FC resources, the TSR schedules the tasks for execution and processing by assigning the appropriate FC nodes to the task requests. Finally, the processed task requests are sent back to the FB and from there to the respective users or IoT devices [12-16]. In order to allocate FC resources based on the demand of users or IoT devices, fully flexible infrastructure virtualization that uses IoT task Handbook of Whale Optimization Algorithm.
Cost-effective resource and task scheduling in fog nodes
Indonesian Journal of Electrical Engineering and Computer Science, 2022
Cloud services are the cutting edge technology, however the growing demand for the internet of things has certain limitations which are high latency expectation and high cost of cloud resources, and this is caused by long-distance between application and cloud. Fog computing is a distributed extension of the cloud, which provide storage and computation at the network level. It consists of an internet of things (IoT) application, a fog control node, and a fog access node. This research works towards minimizing the cloud cost in scheduling. For this purpose, a cost-effective task and user scheduling algorithm are performed. The first task scheduling model is composed based on composers' roles after that task scheduling algorithm is performed to handle the various task at the fog access node in an optimized manner. Finally, the reallocation mechanism reduces the time and service delay. For the analysis purpose extensive simulation is carried out and performance statistics were compared with other existing algorithms. It was observed that the proposed algorithm provides highly cost-optimized user and task scheduling with better performance statistics and reduces the delay in the task by providing optimization in the concurrent task at the fog node.
An Optimal Task Scheduling Towards Minimized Cost and Response Time in Fog Computing Infrastructure
2019 International Conference on Information Technology (ICIT), 2019
Due to the transformation and expansion of Internet of Things(IoT), a large number of services are deployed on the edge of the network to provide the services to the end users rather than from the cloud data center since processing the data at the edge can reduce the response time and bandwidth cost while fulfilling the Quality of services(QoS). The fog-cloud computing environment offers promising solution to provision the available resources for IoT based application.Undoubtely Fog computing compliment of cloud computing helps to provide efficient solution to deal with diverse IoT application. However to provide efficient solution in such environment is challenge in different IoT based application such as health care applications, intelligent transportation system and smart cities. Task scheduling and Resource allocation are the NP-hard issues in distributed computing. Each Application consists of several modules that requires resources to execute. However, providing an optimal task scheduling policy in such a heterogeneous system is a NP class problem and has been proposed by different methods like Greedy, meta-heuristic and all nature inspired algorithm for solving an NP-complete problem. The task scheduling problem is a key challenge in the distributed computing system. In this paper, we are trying to map the independent task into the fog layer and our algorithm gives good result if we place the services in fog layer rather than cloud data center. The system resources available may be CPU, RAM, etc by assigning some priority to the task based on its deadline. Also, we have assumed that once a task assigned to a particular node will not leave that until its execution complete. In this paper, we also proposed a three-layer architecture for efficient task scheduling for application such as health care in smart homes.
International Journal of Electrical and Computer Engineering (IJECE)
In recent years, the number of end users connected to the internet of things (IoT) has increased, and we have witnessed the emergence of the cloud computing paradigm. These users utilize network resources to meet their quality of service (QoS) requirements, but traditional networks are not configured to backing maximum of scalability, real-time data transfer, and dynamism, resulting in numerous challenges. This research presents a new platform of IoT architecture that adds the benefits of two new technologies: software-defined networking and fog paradigm. Software-defined networking (SDN) refers to a centralized control layer of the network that enables sophisticated methods for traffic control and resource allocation. So, fog paradigm allows for data to be analyzed and managed at the edge of the network, making it suitable for tasks that require low and predictable delay. Thus, this research provides an in-depth view of the platform organize and performance of its base ingredients,...
Real-Time Task Scheduling Algorithm for IoT-Based Applications in the Cloud–Fog Environment
Journal of Network and Systems Management
IoT applications have become a pillar for enhancing the quality of life. However, the increasing amount of data generated by IoT devices places pressure on the resources of traditional cloud data centers. This prevents cloud data centers from fulfilling the requirements of IoT applications, particularly delay-sensitive applications. Fog computing is a relatively recent computing paradigm that extends cloud resources to the edge of the network. However, task scheduling in this computing paradigm is still a challenge. In this study, a semidynamic real-time task scheduling algorithm is proposed for bag-of-tasks applications in the cloud–fog environment. The proposed scheduling algorithm formulates task scheduling as a permutation-based optimization problem. A modified version of the genetic algorithm is used to provide different permutations for arrived tasks at each scheduling round. Then, the tasks are assigned, in the order defined by the best permutation, to a virtual machine, whic...
Scheduling Algorithms in Fog Computing: A Survey
International Journal of Networked and Distributed Computing, 2021
Nowadays, with the development of technology, the Internet of Things (IoT) applications have become parts of our daily life. Consequently, the number of devices used in these applications will increase, leading to the creation of huge amounts of data. This data will be transferred to cloud computing for processing, and because the cloud is far from these devices, there will be a delay in the response. From here, it was necessary to find a new technology closer to the Internet of Things devices and overcome the problems in the cloud. So, Cisco proposed fog computing in 2012 [1], which placed between cloud computing and the IoT devices (end users). Fog computing is an emerging computing paradigm that extends cloud computing from the core of the network to the edge of the network. It aims to bring computation, storage and networking services close to users [2]. Internet of Things applications is connecting every physical object like cameras, vehicles, sensors, wearables, and home appliances [3]. Many applications require low latency, mobility, location awareness, high response time. Although many researchers have developed algorithms to improve the performance of cloud computing about the IoT applications, there are still many challenges regarding the requirements of the IoT applications and mobile services such as low latency, high response time, cost, support for mobility and geo-distributions [4]. They can be addressed these challenges by fog computing [5]. Kazem [6] presents a comparison between fog and cloud computing according to their latency and response time. As a result of the comparison, fog computing always performs better than cloud computing to meet the demands of time-sensitive applications by reducing the delay and response time. Through the prediction of Cisco, there are more than 50 billion devices that will be connected to the internet by 2020. Also, the data produced by users, devices and their interactions will reach 500 zettabytes [7]. The general fog computing architecture can be divided into three layers, as shown in Figure 1. The first is IoT devices layer that includes different types of devices, such as smartphones, smart vehicles, tablet computers, and various smart home devices. This layer can sense the surrounding environment and collect data through sensor devices, and communicate with the fog computing layer through 3G, 4G, 5G, WiFi, and Bluetooth technologies. The second is the middle layer is the fog computing layer that includes routers, gateways, workstations, switches, access points. This layer has the capability of computing, networking, and storage. Finally, the upper layer is cloud computing that includes cloud servers with high computation power [2,8-10]. Changes like user devices in terms of bandwidth, storage, latency and computation make resource management in the fog computing environment a major issue [11]. Scheduling is the main challenge in fog computing. In a fog environment, tasks are divided into two groups: tasks requiring the computing intensity and tasks requiring the data intensity. While scheduling the tasks requiring computing intensity, the scheduler migrates the data to the high productivity resource, and hence, the task execution time is reduced. On the other hand, while scheduling
Software-Defined Fog Network Architecture for IoT
Wireless Personal Communications, 2016
Rapid increase in number and diversity of Internet-connected devices raises many challenges for the traditional network architecture, which is not designed to support a high level of scalability, real-time data delivery and mobility. To address these issues, in this paper we present a new model of Internet of Things architecture which combines benefits of two emerging technologies: software-defined networking and Fog computing. Software-defined networking implies a logically centralized network control plane, which allows implementation of sophisticated mechanisms for traffic control and resource management. On the other hand, Fog computing enables some data to be analysed and managed at the network edge, thus providing support for applications that require very low and predictable latency. In the paper, we give detailed insight into the system structure and functionality of its main components. We also discuss the benefits of the proposed architecture and its potential services.
Resource Allocation for Efficient IOT Application in Fog Computing
International Journal of Mathematical, Engineering and Management Sciences
When it comes across problems in creating Internet of Things (IOT) architecture, the major problem that arises is an automatic stipulation of resources. At the same time in today’s era, it is very important to integrate this problem with better Quality of Services (QoS) because of which the cloud computing is taking a shift. As being well acquainted that in fog computing, network’s bandwidth is limited, therefore it becomes quite important to build a joint architecture with resource allocation problem giving it a better quality of services with enhanced efficiency and low latency communication. Priority of QoS is determined by Systematic Ladder Process (SLP) and decision parameter evaluation by RECK algorithm. In this paper, there will be a design of a better framework for IOT resource allocation scheme with better efficiency and better QoS. The paper too highlights the comparison of the previous works of the resource allocation algorithms and schemes with RECK algorithm.
Maximizing the Utilization of Fog Computing in Internet of Vehicle Using SDN
IEEE Communications Letters, 2018
The IoV sensors generate huge data that are processed by cloud servers, but this leads to high latency and bandwidth occupies. This was the main motivation behind fog computing. Software Defined Network (SDN) was developed to simplify the traditional networks architecture. Sometimes, when a fog server fails to execute some tasks, it sends them to cloud servers while other fog servers are idle. This leads to inefficient utilization of fog computing resources. This paper aims to optimize the resource utilization of fog computing with meeting the deadlines of tasks via assigning them to an optimal fog server using SDN. Moreover, local and global load balance techniques are proposed. The simulation results revealed that our proposed system decreases the transference of tasks to the cloud and as a result decreases the latency and bandwidth consumption.