Machine Learning Meets Computation and Communication Control in Evolving Edge and Cloud: Challenges and Future Perspective

In current world, processing the data by the users, researchers, organizations, etc. through online source (ie. cloud) is increasing tremendously, where it offers various services like storing the data, allocating the resources, retrieval of data, security, etc. Since the data is stored in cloud, processing it leads to increase in latency, due to its long-distance communication. As distance increases, data transmission produces a delay between source and destination which is called as latency. To get over this problem, MEC (Mobile Edge Computing) system can be positioned between the cloud infrastructure and the user equipment(UE) in the IoT environment. Instead of sending data to the cloud directly which is collected by IoT sensors, edge computing processes those data within the network. The study of this review focuses on the various techniques such as deep learning algorithms, deep reinforcement learning approaches for offloading decisions and optimization techniques in 5G networks for minimizing the latency in the MEC systems, for producing higher processing capability to the clients. For increasing the MEC system performance, efficient offloading strategies can be used to minimize latency for various tasks.

Mobile edge computing (MEC) brings a breakthrough for Internet of Things (IoT) for its ability of offloading tasks from user equipments (UEs) to nearby servers which have rich computation resource. 5G network brings a huge breakthrough on transmission rate. Together with MEC and 5G, both execution delay of tasks and time delay from downloading would be shorter and the quality of experience (QoE) of UEs can be improved. Considering practical conditions, the computation resource of an MEC server is finite to some extent. Therefore, how to prevent the abuse of MEC resource and further allocate the resource reasonably becomes a key point for an MEC system. In this paper, an MEC system with multi-user is considered where a base station (BS) with an MEC server, which can not only provide computation offloading service but also data cache service. Especially, we take the charge for both data transmission and task computation as one part of total cost of UEs, and then explore a joint optimization for downlink resource allocation, offloading decision and computation resource allocation to minimize the total cost in terms of the time delay and the charge to UEs. The proposed problem is formulated as a mixed integer programming (MIP) one which is NP-hard. Therefore, we decouple the original problem into two subproblems which are downlink resource allocation problem and joint offloading decision and computation resource allocation problem. Then we address these two subproblems by using convex and nonconvex optimization techniques, respectively. An iterative algorithm is proposed to obtain a suboptimal solution in polynomial time. Simulation results show that our proposed algorithm performs better than benchmark algorithms.

In recent years, the need for computation-intensive applications in mobile networks requiring more storage, powerful processors, and real-time responses has risen substantially. Vehicular networks play an important role in this ecosystem, as they must support multiple services, such as traffic monitoring or sharing of data involving different aspects of the vehicular traffic. Moreover, new resource-hungry applications have been envisaged, such as autonomous driving or in-cruise entertainment, hence making the demand for computation and storage resources one of the most important challenges in vehicular networks. In this context, Mobile Edge Computing (MEC) has become the key technology to handle these problems by providing cloud-like capabilities at the edge of mobile networks to support delay-sensitive and computation-intensive tasks. In the meantime, researchers have envisaged use of onboard vehicle resources to extend the computing capabilities of MEC systems. This paper presents a comprehensive review of the most recent works related to MEC-assisted vehicular networks, as well as vehicle-assisted MEC systems. We illustrate the MEC system architecture and discuss its deployment in vehicular environments, as well as the key technologies to realize this integration. After that, we review the recent literature by identifying three different areas, i.e.: (i) MEC providing additional resources to vehicles (e.g., for task offloading); (ii) MEC enabling innovative vehicular applications (e.g., platooning), and (iii) vehicular networks providing additional resources to MEC systems. Finally, we discuss open challenges and future research directions, addressing the possible interplays between MEC systems and vehicular networks.

To cope with the low latency requirements and security issues of the emerging applications such as Internet of Vehicles (IoV) and Industrial Internet of Things (IIoT), the blockchain-enabled Mobile Edge Computing (MEC) system has received extensive attention. However, blockchain is a computing and communication intensive technology due to the complex consensus mechanisms. To facilitate the implementation of blockchain in the MEC system, this paper adopts the committee-based Practical Byzantine Fault Tolerance (PBFT) consensus algorithm and focuses on the committee selection problem. Vehicles and IIoT devices generate the transactions which are records of the application tasks. Base Stations (BSs) with MEC servers, which serve the transactions according to the wireless channel quality and the available computing resources, are blockchain nodes and candidates for committee members. The income of transaction service fees, the penalty of service delay, the decentralization of the blockchain and the communication complexity of the consensus process constitute the performance index. The committee selection problem is modeled as a Markov decision process, and the Proximal Policy Optimization (PPO) algorithm is adopted in the solution. Simulation results show that the proposed PPO-based committee selection algorithm can adapt to the system design requirements with different emphases and outperforms other comparison methods.

UAV-mounted IRS assisted wireless powered mobile edge computing systems: Joint beamforming design, resource allocation and position optimization

In the scenario of Industry 4.0, mobile smart devices (SDs) on production lines have to process massive amounts of data. These computing tasks sometimes far exceed the computing capability of SDs and require lots of energy and time to process. How to effectively reduce energy consumption and latency is necessary to be solved. To this end, we first propose an SDN (Software Defined Network)-based MEC (Mobile Edge Computing) system. In the MEC system, SDs can offload computation tasks to edge servers to decrease the processing latency and avoid the waste of energy. At the same time, taking advantage of SDNs programmability, scalability, and isolation of the control plane and the data plane, an SDN controller can manage edge devices within the MEC system. Secondly, based on a stochastic game, we study the computation offloading and resource allocation problems in the MEC system and establish a stochastic game-based computation offloading model. Furthermore, we prove that the multi-user stochastic game in this system can achieve Nash Equilibrium. We further consider each SD as an independent agent and design a stochastic game-based resource allocation algorithm with prioritized experience replays (SGRA-PER) to minimize energy consumption and processing latency with Multi-Agent Reinforcement Learning. Experiment results demonstrate that the proposed SGRA-PER is superior to MADDPG, Q-Mix, and MAPPO algorithms, which can significantly reduce the processing delay and energy consumption with dynamic resource allocation. Moreover, SGRA-PER can still keep a higher performance under the increase of SDs, which can be applied in a large-scale MEC system.

Driven by the visions of Internet of Things and 5G communications, recent years have seen a paradigm shift in mobile computing, from the centralized mobile cloud computing toward mobile edge computing (MEC). The main feature of MEC is to push mobile computing, network control and storage to the network edges (e.g., base stations and access points) so as to enable computation-intensive and latency-critical applications at the resource-limited mobile devices. MEC promises dramatic reduction in latency and mobile energy consumption, tackling the key challenges for materializing 5G vision. The promised gains of MEC have motivated extensive efforts in both academia and industry on developing the technology. A main thrust of MEC research is to seamlessly merge the two disciplines of wireless communications and mobile computing, resulting in a wide-range of new designs ranging from techniques for computation offloading to network architectures. This paper provides a comprehensive survey of the state-of-the-art MEC research with a focus on joint radio-and-computational resource management. We also discuss a set of issues, challenges, and future research directions for MEC research, including MEC system deployment, cache-enabled MEC, mobility management for MEC, green MEC, as well as privacy-aware MEC. Advancements in these directions will facilitate the transformation of MEC from theory to practice. Finally, we introduce recent standardization efforts on MEC as well as some typical MEC application scenarios.

Mobile edge computing (MEC) systems provide mobile devices (MDs) with low-latency cloud services by deploying edge servers (ESs) in the vicinity. In fact, various mobile applications may generate cotasks, each of which is completed only if all its constituent tasks are finished. Existing works have been devoted to the design of MEC offloading and scheduling, but none of them exploits the cotask feature to better utilize the networked computing resources. In this paper, we investigate the problem of joint cotask-aware offloading and scheduling in MEC systems (Cool-Edge), and we formulate it as a mixed integer non-linear program (MINLP), the objective of which is to minimize average cotask completion time (ACCT). To cope with the Cool-Edge problem, we propose two low-complexity algorithms to offload cotasks based on an LP rounding technique and schedule them according to an earliest-cotask-arrival-first rule, respectively, and we further prove the approximation factor jointly achieved by the two algorithms. Finally, we conduct testbed experiments and simulations to demonstrate the effectiveness of our proposed solution, and we also show how ACCT varies with the network environment.

Mobile edge computing (MEC) within 5G networks brings the power of cloud computing, storage, and analysis closer to the end user. The increased speeds and reduced delay enable novel applications such as connected vehicles, large-scale IoT, video streaming, and industry robotics. Machine Learning (ML) is leveraged within mobile edge computing to predict changes in demand based on cultural events, natural disasters, or daily commute patterns, and it prepares the network by automatically scaling up network resources as needed. Together, mobile edge computing and ML enable seamless automation of network management to reduce operational costs and enhance user experience. In this paper, we discuss the state of the art for ML within mobile edge computing and the advances needed in automating adaptive resource allocation, mobility modeling, security, and energy efficiency for 5G networks.

Mobile edge computing (MEC) has emerged as an appealing paradigm to accommodate demands for computation intensive applications. By investing in resources in MEC, departments (DPs) of the operator (OP) can move services closer to network edge, which receive profits from their respective investment in different resources. The trading of resources and services between DPs is usually modeled as a long-time contract. In this paper, we study the relationship between the ownership allocation and invest policy of DP, and then we investigate the problem that how to choose the optimal investments in an MEC scenario. In specific, we first develop a general investment system model with multiple DPs of the OP to participate in MEC. Then, we formulate the optimal investments of the utility maximization problem. Furthermore, we focus on a special ownership allocations with two DPs and two resources. An analysis of the ownership allocation and invest efficiency is given. Finally, simulation results demonstrate that DPs are motivated to make more investments and receive more utilities under its own integration.

As a key technology in the 5G era, mobile edge computing (MEC) has developed rapidly in recent years. MEC aims to reduce the service delay of mobile users, while alleviating the processing pressure on the core network. MEC can be regarded as an extension of cloud computing on the user side, which can deploy edge servers and bring computing resources closer to mobile users, and provide more efficient interactions. However, due to the user's dynamic mobility, the distance between the user and the edge server will change dynamically, which may cause fluctuations in Quality of Service. Therefore, when a mobile user moves in the MEC environment, certain approaches are needed to schedule services deployed on the edge server to ensure the user experience. In this article, we model service scheduling in MEC scenarios and propose a delay‐aware and mobility‐aware service management approach based on concise probabilistic methods. This approach has low computational complexity and can effectively reduce service delay and migration costs. Furthermore, we conduct experiments by utilizing multiple realistic datasets and use iFogSim to evaluate the performance of the algorithm. The results show that our proposed approach can optimize the performance on service delay, with 8%–20% improvement and reduce the migration cost by more than 75% compared with baselines during the rush hours.

The aging and multimorbid population and health personnel shortages pose a substantial burden on primary health care. While predictive machine learning (ML) algorithms have the potential to address these challenges, concerns include transparency and insufficient reporting of model validation and effectiveness of the implementation in the clinical workflow. To systematically identify predictive ML algorithms implemented in primary care from peer-reviewed literature and US Food and Drug Administration (FDA) and Conformité Européene (CE) registration databases and to ascertain the public availability of evidence, including peer-reviewed literature, gray literature, and technical reports across the artificial intelligence (AI) life cycle. PubMed, Embase, Web of Science, Cochrane Library, Emcare, Academic Search Premier, IEEE Xplore, ACM Digital Library, MathSciNet, AAAI.org (Association for the Advancement of Artificial Intelligence), arXiv, Epistemonikos, PsycINFO, and Google Scholar were searched for studies published between January 2000 and July 2023, with search terms that were related to AI, primary care, and implementation. The search extended to CE-marked or FDA-approved predictive ML algorithms obtained from relevant registration databases. Three reviewers gathered subsequent evidence involving strategies such as product searches, exploration of references, manufacturer website visits, and direct inquiries to authors and product owners. The extent to which the evidence for each predictive ML algorithm aligned with the Dutch AI predictive algorithm (AIPA) guideline requirements was assessed per AI life cycle phase, producing evidence availability scores. The systematic search identified 43 predictive ML algorithms, of which 25 were commercially available and CE-marked or FDA-approved. The predictive ML algorithms spanned multiple clinical domains, but most (27 [63%]) focused on cardiovascular diseases and diabetes. Most (35 [81%]) were published within the past 5 years. The availability of evidence varied across different phases of the predictive ML algorithm life cycle, with evidence being reported the least for phase 1 (preparation) and phase 5 (impact assessment) (19% and 30%, respectively). Twelve (28%) predictive ML algorithms achieved approximately half of their maximum individual evidence availability score. Overall, predictive ML algorithms from peer-reviewed literature showed higher evidence availability compared with those from FDA-approved or CE-marked databases (45% vs 29%). The findings indicate an urgent need to improve the availability of evidence regarding the predictive ML algorithms' quality criteria. Adopting the Dutch AIPA guideline could facilitate transparent and consistent reporting of the quality criteria that could foster trust among end users and facilitating large-scale implementation.

Driven by the emergence of new compute-intensive applications and the vision of the Internet of Things (IoT), it is foreseen that the emerging 5G network will face an unprecedented increase in traffic volume and computation demands. However, end users mostly have limited storage capacities and finite processing capabilities, thus how to run compute-intensive applications on resource-constrained users has recently become a natural concern. Mobile edge computing (MEC), a key technology in the emerging fifth generation (5G) network, can optimize mobile resources by hosting compute-intensive applications, process large data before sending to the cloud, provide the cloud-computing capabilities within the radio access network (RAN) in close proximity to mobile users, and offer context-aware services with the help of RAN information. Therefore, MEC enables a wide variety of applications, where the real-time response is strictly required, e.g., driverless vehicles, augmented reality, robotics, and immerse media. Indeed, the paradigm shift from 4G to 5G could become a reality with the advent of new technological concepts. The successful realization of MEC in the 5G network is still in its infancy and demands for constant efforts from both academic and industry communities. In this survey, we first provide a holistic overview of MEC technology and its potential use cases and applications. Then, we outline up-to-date researches on the integration of MEC with the new technologies that will be deployed in 5G and beyond. We also summarize testbeds and experimental evaluations, and open source activities, for edge computing. We further summarize lessons learned from state-of-the-art research works as well as discuss challenges and potential future directions for MEC research.

In order to improve the quality of service for users and reduce the energy consumption of the cloud computing environment, Mobile Edge Computing (MEC) is a promising paradigm by providing computing resources which is close to the end device in physical distance. Nevertheless, the computation offloading policy to satisfy the requirements of the service provider and consumer at the same time within a MEC system still remains challenging. In this paper, we propose an offloading decision policy with three-level structure for MEC system different from the traditional two-level architecture to formulate the offloading decision optimization problem by minimizing the total cost of energy consumption and delay time. Because the traditional optimization methods could not solve this dynamic system problem efficiently, Reinforcement Learning (RL) has been used in complex control systems in recent years. We design a deep reinforcement learning (DRL) approach to minimize the total cost by applying deep Q-learning algorithm to address the issues of too large system state dimension. The simulation results show that the proposed algorithm has nearly optimal performance than traditional methods.

This paper jointly studies the fairness and efficient trajectory design problem for facilitating ultra-reliable and low latency communications (URLLC) in unmanned aerial vehicle (UAV)-enabled mobile edge computing (MEC) systems, in the context of sixth-generation (6G) networks. In this regard, a fixed-wing UAV is equipped with an aerial server, and it is programmed to collect critical task allocation data from Internet of things (IoT) devices deployed on the ground. To prolong the operational time of the ground IoT devices, we aim to minimize the maximum energy consumption among the ground IoT devices. Furthermore, due to the non-convexity of the original problem, we use successive convex approximations (SCA) to divide the original problem into two convex sub-problems. To this end, we propose an iterative sub-optimal joint fairness and trajectory design algorithm (JFTDA), which is numerically shown to yield fair data allocation for task offloading and comparable energy consumption among all the ground IoT devices to that of different deployment scenarios. Lastly, the proposed JFTDA also yields a decoding error probability of less than $$10^{-5}$$ ensuring URLLC for the UAV-enabled MEC systems.