Mobile Edge Computing

Mixed Reality (MR) applications are becoming very popular in different sectors such as communication, education and entertainment for its extensive application areas and also for the wide adoption of mobile and especially wearable devices. Due to weak computational efficiency and short battery life of these devices, MR applications performance can be hampered. Offloading the MR application burden to the cloud server can be a solution to this problem but this approach also creates high communication latency. Mobile Edge Computing (MEC) is an emerging technology which brings cloud close to the user proximity at the base station and utilizes radio access network for maintaining communication with the users. This paper presents a MEC based MR application for assisting blind and visually impaired people. In the proposed scheme, the computational task is offloaded to the nearest MEC server in order to prolong the battery life of the MR devices. Finally, experimental results based on laten...

In 5G and beyond telecommunication infrastructures a crucial challenge in achieving the strict Key Performance Indicators (KPIs) regarding capacity, latency, and guaranteed quality of service, is the efficient handling of the fronthaul bottleneck. This part of the next generation networks is expected to comprise the New Radio (NR) access and the Next Generation Passive Optical Network (NGPON) domains. Latest developments load the fronthaul with computing tasks as well (e.g., for AI-based processes) in the context of Mobile Edge Computing (MEC). Towards efficient management of all resource types, this paper proposes a joint allocation scheme with three optimization phases for radio, optical, and MEC resources. This scheme, which has been developed in the context of the blueSPACE 5G Infrastructure Public Private Partnership (5G PPP) project, exploits cutting-edge technologies, such as radio beamforming, spatial-spectral granularity in optical networks, and Network Function Virtualization (NFV), to provide dynamic, adaptive, and energy efficient allocation of resources. The devised model is mathematically described and the overall solution is evaluated in a realistic simulation scenario, demonstrating its effectiveness.

he  growth  of  Mobile-based  augmented  reality is  increasing tremendously,  with  the  hardware-based  MobileAR  and App-based  Mobile  AR  limitations  to  cross-platform  and  need  to  download  the  app that can  be  found  in  the  Mobile  AR. Web-primarilybasedtotallyAR(WebAR)isabrandnewimprovementinphasesofaugmentedreality.Presently  there  are  some restrictions  with  the WebAR  due  to  its  compatibility  issue,  performance  issue,  and  latency  issuesince  the WebAR  hasrecently evolved and needsenhancement to overcome weakcomputational efficiencywhich leads to slacken of WebARapplications.M-CORD  is  a  powerful platform  that  allows  to  rapidly derivingcellular  networksfor  bettercomputing  as  well  asreduction  of latency. M-CORD  determines  how  virtualization,  slicing,and  mobile  edge  computing  can permit  answers to construct out  of many disaggregated components.

Mobile edge computing (MEC) is emerging as a cornerstone technology to address the conflict between resource-constrained smart devices (SDs) and the ever-increasing computational demands of the mobile applications. MEC enables the SDs to offload computational-intensive tasks to the nearby edge nodes for providing better quality-of-services (QoS). The recently proposed offloading strategies, mainly consider a centralized approach for a limited number of SDs. However, with the growing popularity of the SDs, these offloading models may have the scalability issue and can be susceptible to single point failure. Although there are few distributed offloading models in the literature, they ignore the vast computational resources of the cloud, load sharing between the MEC servers, and other optimization parameters. Toward this end, we propose an efficient computation offloading scheme for a distributed load sharing MEC network in cooperation with cloud computing to enhance the capabilities of the SDs. We formulate a nonlinear multiobjective optimization problem by applying queuing theory to model the execution delay, energy consumption, and payment cost for using edge and cloud services. To solve the formulated problem, we propose a stochastic gradient descent (SGD) algorithm based solution approach to jointly optimize the offloading probability and transmission power of the SDs for finding an optimal trade-off between energy consumption, execution delay, and cost of the SDs. Finally, we perform extensive simulations to demonstrate the effectiveness of the proposed offloading scheme. Moreover, compared to the other solutions, the proposed scheme is scalable and outperforms the existing schemes.

The International Journal of Software Engineering & Applications (IJSEA) is a bi-monthly open access peer-reviewed journal that publishes articles which contribute new results in all areas of the Software Engineering & Applications. The goal of this journal is to bring together researchers and practitioners from academia and industry to focus on understanding Modern software engineering concepts & establishing new collaborations in these areas.

The scale of Internet-connected systems has increased considerably, and these systems are being exposed to cyber attacks more than ever. The complexity and dynamics of cyber attacks require protecting mechanisms to be responsive, adaptive, and large-scale. Machine learning, or more specifically deep reinforcement learning (DRL), methods have been proposed widely to address these issues. By incorporating deep learning into traditional RL, DRL is highly capable of solving complex, dynamic, and especially high-dimensional cyber defense problems. This paper presents a survey of DRL approaches developed for cyber security. We touch on different vital aspects , including DRL-based security methods for cyber-physical systems, autonomous intrusion detection techniques, and multi-agent DRL-based game theory simulations for defense strategies against cyber attacks. Extensive discussions and future research directions on DRL-based cyber security are also given. We expect that this comprehensive review provides the foundations for and facilitates future studies on exploring the potential of emerging DRL to cope with increasingly complex cyber security problems.

The International Journal of Computer Networks & Communications (IJCNC) is a bi monthly open access peer-reviewed journal that publishes articles which contribute new results in all areas of Computer Networks & Communications.The journal focuses on all technical and practical aspects of Computer Networks & data Communications. The goal of this journal is to bring together researchers and practitioners from academia and industry to focus on advanced networking concepts and establishing new collaborations in these areas.

Vehicular networks and the recent Internet of Vehicles (IoV) are continuously developing, aiming to solve the current and novel challenging needs in the domain of transportation systems. Edge computing offers a natural support for Internet of Vehicles, supporting fast response, context awareness, and minimization of the data transfer to the centralized data centers-all these being allowed by the edge computing availability close to mobile vehicles. Multi-access (Mobile) Edge Computing, fog computing, cloudlets, etc., are such candidates to support IoV; their architectures and technologies have overlapping characteristics but also differences in approach. A full convergence between them has not yet been achieved. Also, it is still not completely clarified which solution could be the best trade-off to be adopted in the Internet of vehicles context and for which use cases. This paper is not a complete survey, but attempts a preliminary evaluation of some of the currently proposed Mobile Edge Computing and fog computing solutions for vehicular networks.

AIRCC's International Journal of Computer Network & Communications( IJCNC) is dedicated to strengthen the field of Computer Networks and Communications and publishes only good quality papers. IJCNC is highly selective and maintains less than 5% acceptance rate. All accepted papers will be tested for plagiarism manually as well as by Docoloc. Papers published in IJCNC has received enormous citations and has been regarded as one of the best Journal in the networking research field.

In past few years, advancement in mobile applications and their integration with Cloud computing services has introduced a new computing paradigm known as Mobile Cloud Computing. Although Cloud services support a wide range of mobile applications, access to these services suffers from several
performance issues such as WAN latency, jitter, and packet
losses. Cloudlet frameworks are proposed to overcome these
performance issues. More specifically, Cloudlets aim to bring the Cloud or a specific part of the Cloud closer to the mobile device by utilizing proximate computing resources to perform compute intensive tasks. This paper presents a comprehensive survey on the state-of-the-art mobile Cloudlet architectures. We also classify the state-of-the-art Cloudlet solutions by presenting a hierarchical taxonomy. Moreover, the areas of Cloudlet applications are also identified and presented. Cloudlet discovery, resource management, data security, mobility, application offloading, and most importantly incentives to deploy a Cloudlet are areas that still needs to be investigated by the research community. The critical aspects of the current Cloudlet frameworks in Mobile Cloud Computing are analyzed to determine the strengths and weaknesses of the frameworks. The similarities and differences of the frameworks based on the important parameters, such as scalability, mobility support, Internet dependency, dynamic configuration, energy savings, and execution cost are also investigated. The requirements for deploying the Cloudlet in a Local Wireless Network are also highlighted and presented. We also discuss open research challenges that Cloudlet deployments face in Local Wireless Networks.

Based upon the context of Mobile Edge Computing (MEC) actual research and within the innovative scope of the SESAME EU-funded research project, we propose and assess a framework for security analysis applied in virtualised Small Cell Networks, with the aim of further extending MEC in the broader 5G environment. More specifically, by applying the fundamental concepts of the SESAME original architecture that aims at providing enhanced multi-tenant MEC services though Small Cells coordination and virtualization, we focus on a realistic 5G-oriented scenario enabling the provision of large multi-tenant enterprise services by using MEC. Then we evaluate several security issues by using a formal methodology, known as Secure Tropos.

As SD-WAN disrupts legacy WAN technologies and becomes the preferred WAN technology adopted by corporations, and Kubernetes becomes the de-facto container orchestration tool, the opportunities for deploying edge-computing containerized applications running over SD-WAN are vast. Service orchestration in SD-WAN has not been provided with enough attention, resulting in the lack of research focused on service discovery in these scenarios. In this article, an in-house service discovery solution that works alongside Kubernetes' master node for allowing improved traffic handling and better user experience when running micro-services is developed. The service discovery solution was conceived following a design science research approach. Our research includes the implementation of a proof-of-concept SD-WAN topology alongside a Kubernetes cluster that allows us to deploy custom services and delimit the necessary characteristics of our in-house solution. Also, the implementation's performance is tested based on the required times for updating the discovery solution according to service updates. Finally, some conclusions and modifications are pointed out based on the results, while also discussing possible enhancements.

—Recently, mobile broadband networks are focused on bringing additional capabilities to the network edge. For instance, Mobile Edge Computing (MEC) brings storage and processing capabilities closer to the mobile user i.e., at the radio access network, in order to deploy services with minimum delay. In this paper, we propose a resource constrained cloud-enabled small cell that includes a MEC server for deploying mobile edge computing functionalities. We present the architecture with special focus on realizing the proper forwarding of data packets between the mobile data path and the MEC applications, based on the principles of SDN, without requiring any changes to the functionality of existing mobile network nodes both in the access and the core network segments. The significant benefits of adopting the proposed architecture are analysed based on a proof-of-concept demonstration for content caching application use case.

The advent of new cloud-based applications such as mixed reality, online gaming, autonomous driving, and healthcare has introduced infrastructure management challenges to the underlying service network. Multi-access edge computing (MEC) extends the cloud computing paradigm and leverages servers near end-users at the network edge to provide a cloud-like environment. The optimum placement of services on edge servers plays a crucial role in the performance of such service-based applications. Dynamic service placement problem addresses the adaptive configuration of application services at edge servers to facilitate end-users and those devices that need to offload computation tasks. While reported approaches in the literature shed light on this problem from a particular perspective, a panoramic study of this problem reveals the research gaps in the big picture. This paper introduces the dynamic service placement problem and outline its relations with other problems such as task scheduling, resource management, and caching at the edge. We also present a systematic literature review of existing dynamic service placement methods for MEC environments from networking, middleware, applications, and evaluation perspectives. In the first step, we review different MEC architectures and their enabling technologies from a networking point of view. We also introduce different cache deployment solutions in network architectures and discuss their design considerations. The second step investigates dynamic service placement methods from a middleware viewpoint. We review different service packaging technologies and discuss their trade-offs. We also survey the methods and identify eight research directions that researchers follow. Our study categorises the research objectives into six main classes, proposing a taxonomy of design objectives for the dynamic service placement problem. We also investigate the reported methods and devise a solutions taxonomy comprising six criteria. In the third step, we concentrate on the application layer and introduce the applications that can take advantage of dynamic service placement. The fourth step investigates evaluation environments used to validate the solutions, including simulators and testbeds. We introduce real-world datasets such as edge server locations, mobility traces, and service requests used to evaluate the methods. We compile a list of open issues and challenges categorised by various viewpoints in the last step.

Mobile Edge Computing (MEC) and Fog are emerging computing models that extend the cloud and its services to the edge of the network. The emergence of both MEC and fog introduce new requirements, which mean their supported deployment models must be investigated. In this paper, we point out the influence and strong impact of the extended cloud (i.e., the MEC and fog) on existing communication and networking service models of the cloud. Although the relation between them is fairly evident, there are important properties, notably those of security and resilience, that we study in relation to the newly posed requirements from the MEC and fog. Although security and resilience have been already investigated in the context of the cloud - to a certain extent - existing solutions may not be applicable in the context of the extended cloud. Our approach includes the examination of models and architectures that underpin the extended cloud, and we provide a contemporary discussion on the most evident characteristics associated with them. We examine the technologies that implement these models and architectures, and analyse them with respect to security and resilience requirements. Furthermore, approaches to security and resilience-related mechanisms are examined in the cloud (specifically, anomaly detection and policy based resilience management), and we argue that these can also be applied in order to improve security and achieve resilience in the extended cloud environment.

Research on next-generation 5G wireless networks is currently attracting a lot of attention in both academia and industry. While 5G development and standardization activities are still at their early stage, it is widely acknowledged that 5G systems are going to extensively rely on dense small cell deployments, which would exploit infrastructure and network functions virtualization (NFV), and push the network intelligence towards network edges by embracing the concept of mobile edge computing (MEC). As security will be a fundamental enabling factor of small cell as a service (SCaaS) in 5G networks, we present the most prominent threats and vulnerabilities against a broad range of targets. As far as the related work is concerned, to the best of our knowledge, this paper is the rst to investigate security challenges at the intersection of SCaaS, NFV, and MEC. It is also the rst paper that proposes a set of criteria to facilitate a clear and eective taxonomy of security challenges of main elements of 5G networks. Our analysis can serve as a staring point towards the development of appropriate 5G security solutions. These will have crucial eect on legal and regulatory frameworks as well as on decisions of businesses, governments, and end-users. Keywords: Security, small cell as a service, network functions virtual-ization, mobile edge computing, 5G.

IoT (Internet of Things) devices such as sensors have been actively used in 'fogs' to provide critical data during e.g., disaster response scenarios or in-home healthcare. Since IoT devices typically operate in resource-constrained computing environments at the network-edge, data transfer performance to the cloud as well as end-to-end security have to be robust and customizable. In this paper, we present the design and implementation of a middleware featuring "intermittent" and "flexible" end-to-end security for cloud-fog communications. Intermittent security copes with unreliable network connections, and flexibility is achieved through security configurations that are tailored to application needs. Our experiment results show how our middleware that leverages static pre-shared keys forms a promising solution for delivering lightweight , fast and resource-aware security for a variety of IoT-based applications.

is paper presents an in-depth study and analysis of offloading strategies for lightweight user mobile edge computing tasks using a machine learning approach. Firstly, a scheme for multiuser frequency division multiplexing approach in mobile edge computing offloading is proposed, and a mixed-integer nonlinear optimization model for energy consumption minimization is developed. en, based on the analysis of the concave-convex properties of this optimization model, this paper uses variable relaxation and nonconvex optimization theory to transform the problem into a convex optimization problem. Subsequently, two optimization algorithms are designed: for the relaxation optimization problem, an iterative optimization algorithm based on the Lagrange dual method is designed; based on the branch-and-bound integer programming method, the iterative optimization algorithm is used as the basic algorithm for each step of the operation, and a global optimization algorithm is designed for transmitting power allocation, computational offloading strategy, dynamic adjustment of local computing power, and receiving energy channel selection strategy. Finally, the simulation results verify that the scheduling strategy of the frequency division technique proposed in this paper has good energy consumption minimization performance in mobile edge computation offloading. Our model is highly efficient and has a high degree of accuracy. e anomaly detection method based on a decision tree combined with deep learning proposed in this paper, unlike traditional IoT attack detection methods, overcomes the drawbacks of rule-based security detection methods and enables them to adapt to both established and unknown hostile environments. Experimental results show that the attack detection system based on the model achieves good detection results in the detection of multiple attacks.

World is developing at a quick pace as is data. The boom of smart phones and Internet of Things (IoT) enable more users to access data as well as computation power in real-time. The constraints of current distributed computing is a subject of more prevalent concern. In response to these rising difficulties in computing, as new requirements and challenges spring up day by day, especially in cloud computing scenario, computing paradigms that can meet these challenges are sought after. In order to expand the efficiency and to decrease the quantity of the data to be sent to the cloud for processing, numerous solutions have been proposed for the edge-centric network. In this paper, an elaborate study of computing architectures proposed for edge paradigms is carried out and application areas in the Internet of Things are ascertained. I. INTRODUCTION Computing architectures have gone through quite a few changes between centralized and decentralized models in the recent past. Cloud being the present centralized paradigm, majority of web content is served through a main data center and researchers rent their private servers from cloud for testing or experimenting. In addition Cloud offers an expedient way for both small and big businesses to obtain computing sources from a service provider instead of putting up their own data center. Usage of Cloud services like Google Cloud, AWS, Azure and VMware have become so popular in recent past. However, the new trend towards a soaring emphasis on edge devices and edge computing paradigms cannot go unnoticed. On the other side, many research organizations have given a startling prediction about the future computing scenario , that is, more than 20 billions of devices will be connected to the Internet by 2020. Thus more and more internet-enabled devices will result in generating huge amounts of data than ever. The Cisco white paper states that, IoT devices will generate 600 zettabytes of data by 2020[46]. Even though Cloud computing can be utilized in a pay-per-usage way through centrally managed resources, high latency and privacy issues are seen as solemn challenges. Hence, there is an inclination towards a decentralized solution of Cloud computing framework and the recent trend of computing paradigms lead to realization of shifting computing to the edge of the network. Since the connected devices prove to be potent in terms of computational capabilities and also battery power, they can be used for IoT applications. The requirements of low latencies and less bandwidth utilization of the data-intensive applications in the Internet of Things (IoT) are met. Most of the Cloud datacenters are centralized and located far from the nearness of the edge devices, and the latency-sensitive real-time service requests suffer due to large round-trip delays, degradation in service quality and network congestion. Such issues can be resolved efficiently by means of latest edge computing paradigms. Although the notions of edge and fog computing have been conceptualized before now, a universal understanding of these paradigms in practice is lacking. The rest of this paper is organized as follows: Section II highlights the earlier work found in literature. Section III discusses about the various edge paradigms based on their architectures. Section IV presents a comparison scenario of edge computing, fog computing and Mobile Cloud Computing (MCC) derived from an analysis of performance parameters. Section V identifies application areas for edge paradigms in the field of IoT and highlights unresolved deployment issues. Finally, Section VI concludes the paper.

The latency issue of the cloud-centric IoT management system has motivated Fog and Edge Computing (FEC) architecture, which distributes the tasks from the cloud to the edge resources such as routers, switches or the IoT devices themselves. Specifically, mobile sensors of IoT system can also carry certain tasks for FEC. Considering the need of dynamic process migration from the mobile sensors to other resources when the mobile sensors unable to continue their tasks, the IoT system needs to provide a flexible mechanism that allows the mobile sensors dynamically migrate their tasks to the other FEC resource at runtime. However, it raises a question in what is the optimal approach when the mobile sensors intend to migrate their tasks to multiple heterogeneous FEC resource? In order to address the question, the authors propose REM scheme, which is capable of optimising the process migration decision. Further, in order to realise such a system and to validate the REM scheme, the authors h...

Most of the vehicle manufacturers aim to deploy level-5 fully autonomous ground vehicles (FAGVs) on city roads in 2021 by leveraging extensive existing knowledge about sensors, actuators, telematics and Artificial Intelligence (AI) gained from the level-3 and level-4 autonomy. FAGVs by executing non-trivial sequences of events with decimetre-level accuracy live in Smart City (SC) and their integration with all the SC components and domains using real-time data analytics is urgent to establish better swarm intelligent systems and a safer and optimised harmonious smart environment enabling cooperative FAGVs-SC automation systems. The challenges of urbanisation, if unmet urgently, would entail severe economic and environmental impacts. The integration of FAGVs with SC helps improve the sustainability of a city and the functional and efficient deployment of hand over wheels on robotized city roads with behaviour coordination. SC can enable the exploitation of the full potential of FAGVs with embedded centralised systems within SC with highly distributed systems in a concept of Automation of Everything (AoE). This paper proposes a synergistic integrated FAGV-SC holistic framework - FAGVinSCF in which all the components of SC and FAGVs involving recent and impending technological advancements are moulded to make the transformation from today's driving society to future's next-generation driverless society smoother and truly make self-driving technology a harmonious part of our cities with sustainable urban development. Based on FAGVinSCF, a simulation platform is built both to model the varying penetration levels of FAGV into mixed traffic and to perform the optimal self-driving behaviours of FAGV swarms. The results show that FAGVinSCF improves the urban traffic flow significantly without huge changes to the traffic infrastructure. With this framework, the concept of Cooperative Intelligent Transportation Systems (C-ITS) is transformed into the concept of Automated ITS (A-ITS). Cities currently designed for cars can turn into cities developed for citizens using FAGVinSCF enabling more sustainable cities.

With the popularity of Massively Multiplayer Online Games (MMOGs) and Virtual Reality (VR) technologies, VR-MMOGs are looming on the surface, demanding ever faster gaming interactions and image rendering. In this paper, we identify three main challenges of VR-MMOGs: (1) stringent latency requirement for frequent local view change responses, (2) high bandwidth requirement for constant refreshing, and (3) large scale requirement for a large number of simultaneous players. Understanding that a cloud-centric gaming architecture may struggle to deliver the latency/bandwidth requirements, the community is attempting to leverage edge cloud computing. However, one problem remains unsolved: how to distribute the work among the user device, the edge clouds, and the center cloud to meet all three requirements especially when users are mobile. In this paper, we propose a hybrid gaming architecture that achieves clever work distribution. It places local view change updates on edge clouds for immediate responses, frame rendering on edge clouds for high bandwidth, and global game state updates on the center cloud for user scala-bility. In addition, we propose an efficient service placement algorithm based on a Markov decision process. This algorithm dynamically places a user's gaming service on edge clouds while the user moves through different access points. It also tries to co-place multiple users to facilitate game world sharing and reduce the overall migration overhead. We derive optimal solutions and devise efficient heuristic approaches. We also study different algorithm implementations to speed up the runtime. Through detailed simulation studies, we

This research paper investigates the running of object detection algorithms on low-end devices to detect individuals in images while leveraging cloud-based services to provide facial verification of the individuals detected. The performance of three computer vision object detection algorithms that utilize Convolutional Neural Networks (CNN) are compared: SSD MobileNet, Inception v2 and Tiny YOLO along with three cloud-based facial verification services: Kairos, AmazonWeb Service Rekognition (AWS) and Microsoft Azure
Vision API. The results contribute to the limitations of running CNN based algorithms to solve vision tasks on low-end devices and highlights the limitations of using such devices and models in an application domain such as a home-security solution.

Recently, the underwater wireless sensor networks (UWSNs)
have been proposed for exploration of the underwater resources and
to obtain information about the aquatic environment. The noise in
UWSNs challenges the successful transmission of packets from a sender
to a receiver. There are many protocols in literature that address noise
reduction/avoidance during underwater communication. However, they
require localization information of each sensor nodes that itself is a challenging issue. In this paper, the minimum channel noise is considered
and the depth and noise aware routing (DNAR) protocol is proposed
to send the packets reliably from a sender node to a surface sink. In
the DNAR protocol, more energy is assigned to the sensor nodes that
have depth level ≤150 m. Therefore, the sensor nodes that deployed are
nearby to the sink node have more capability of transmission and will
not die quickly. Also, the proposed protocol selects the forwarder candidate that have lowest depth and minimum channel noise at the receiver.
As compared to some existing schemes, the proposed scheme requires no
geographical information of the nodes for data routing. The DNAR protocol is validated by Matlab simulation and compared it with the DBR
scheme. The simulation results show that the DNAR has better results
in-terms of packet delivery ratio (PDR), total energy consumption, and
the network lifetime.

With SD-WAN being increasingly adopted by corporations, and Kubernetes becoming the de-facto container orchestration tool, the opportunities for deploying edge-computing applications running over SD-WAN are vast. Unfortunately, service orchestration in SD-WAN has not been provided with enough attention, resulting in the lack of research focused on service discovery in these scenarios. In this document, an in-house service discovery solution that works alongside Kubernetes' master node for allowing an improved traffic handling and better user experience is developed. The service discovery solution was conceived following a design science research approach. Our research includes the implementation of a proof-of-concept SD-WAN topology alongside a Kubernetes cluster that allows us to deploy custom services and delimit the necessary characteristics of our in-house solution. Also, the implementation's performance is tested based on the required times for updating the discovery solution according to service updates. Finally, some conclusions and modifications are pointed out based on the results, while also discussing possible enhancements.

We considered building high performance tools on the Raspberry Pi 4. We implemented OpenMP and OpenCoarrays Fortran in conjunction with the statistical language R. We found that the OpenCoarrays is more effective when working with vectors, while OpenMP is better in the arena with large matrices in a geostatistics application. These results can be very useful for researchers with limited access to high performance tools or limited funding.

These days, fog-cloud based healthcare application partitioning
techniques have been growing progressively. However, existing
static fog-cloud based application partitioning methods are static
and cannot adopt dynamic changes in the dynamic environment (e.
g., where network and computing nodes have resource value variation) during the execution process. This study devises a Deep
Neural Networks Energy Cost-Efficient Partitioning and Task
Scheduling (DNNECTS) algorithm framework which consists of the
following components: application partitioning, task sequencing,
and scheduling. Experimental results show the suggested methods
in terms of energy consumption and the applications' cost in the
dynamic environment.

As accessing computing resources from the remote cloud inherently incurs high end-to-end (E2E) delay for mobile users, cloudlets, which are deployed at the edge of a network, can potentially mitigate this problem. Although some research works focus on allocating workloads among cloudlets, the cloudlet placement aiming to minimize the deployment cost (i.e., consisting of both the cloudlet cost and average E2E delay cost) has not been addressed effectively so far. The locations and number of cloudlets have a crucial impact on both the cloudlet cost in the network and average E2E delay of users. Therefore, in this paper, we propose the Cost Aware cloudlet PlAcement in moBiLe Edge computing (CAPABLE) strategy, where both the cloudlet cost and average E2E delay are considered in the cloudlet placement. To solve this problem, a Lagrangian heuristic algorithm is developed to achieve the suboptimal solution. After cloudlets are placed in the network, we also design a workload allocation scheme to minimize the E2E delay between users and their cloudlets by considering the user mobility. The performance of CAPABLE has been validated by extensive simulations.

To support popular Internet of Things (IoT) applications such as virtual reality, mobile games and wearable devices, edge computing provides a front-end distributed computing archetype of centralized cloud computing with low latency. However, it's challenging for end users to offload computation due to their massive requirements on spectrum and computation resources and frequent requests on Radio Access Technology (RAT). In this paper, we investigate computation offloading mechanism with resource allocation in IoT edge computing networks by formulating it as a stochastic game. Here, each end user is a learning agent observing its local environment to learn optimal decisions on either local computing or edge computing with the goal of minimizing long term system cost by choosing its transmit power level, RAT and sub-channel without knowing any information of the other end users. Therefore, a multiagent reinforcement learning framework is developed to solve the stochastic game with a proposed independent learners based multi-agent Q-learning (IL-based MA-Q) algorithm. Simulations demonstrate that the proposed IL-based MA-Q algorithm is feasible to solve the formulated problem and is more energy efficient without extra cost on channel estimation at the centralized gateway compared to the other two benchmark algorithms.

Real-time geospatial applications are ever-increasing with modern Information and Communication Technology. Latency and Quality of Service-aware these applications are required to process at the edge of the networks, not at the central cloud servers. Edge and fog nodes of the networks are capable enough for caching the frequently accessed small volume geospatial data, processing with lightweight tools and libraries. Finally, display the image of the processed geospatial data at the edge devices according to the user's Point of Interest. Several kinds of research are going on edge and fog computing, especially in the geospatial aspects. Health monitoring, weather prediction, emergency communication, disaster management, disease expansion are examples of geospatial real-time applications. In this chapter, we have investigated the existing work in the edge and fog computing with the geospatial paradigm. We propose a taxonomy on related works. At the end of this chapter, we discuss the limitations and future direction of the geospatial edge and fog computing.

India is an agriculture based developing country. Information dissemination to the knowledge intensive agriculture sector is upgraded by mobile-enabled information services and rapid growth of mobile telephony. It bridge the gap between the availability of agricultural input and delivery of agricultural outputs and agriculture infrastructure. Mobile computing, cloud computing, machine learning and soft computing are the immerging techniques which are being used in almost all fields of research. Apart from this, they are also useful in our day-today activities such as education, medical and agriculture. This paper explores how Android Apps of agricultural services have impacted the farmers in their farming activities.