Mobility-Induced Service Migration in Mobile Micro-clouds

Tactical networks are highly constrained in communication and computation resources, particularly at the edge. This limitation can be effectively addressed by the emerging technology of mobile micro-clouds (MMCs) that is aimed at providing seamless computing/data access at the edge of such networks. Deployment of MMCs can enable the delivery of critical, timely, and mission relevant situational awareness to end users in highly dynamic environments. Different from traditional clouds, an MMC is smaller and deployed closer to users, typically attached to a fixed or mobile basestation that is deployed in the field. Due to the relatively small coverage area of each basestation, a mobile user may frequently switch across areas covered by different basestations. An important issue therefore is where to place the service so that acceptable service performance can be maintained, while coping with the user and network dynamics. Existing work has considered this problem mainly from a theoretical angle. In this paper, with the aim of pushing the theoretical results one step closer to practice, we study the performance of dynamic service placement using an emulation framework, namely the Common Open Research Emulator (CORE) which embeds the Extendable Mobile Ad-hoc Network Emulator (EMANE). We first present the system architecture used in the emulation. Then, we present the message exchange and control process between different network entities, as well as methods of deciding where to place the services. Finally, we perform emulation using real-world user mobility traces of San Francisco taxis and present the results. The results show several insightful observations in a realistic network setting, such as the impact of randomness and delay on the service placement performance.

Joint edge caching and dynamic service migration in SDN based mobile edge computing

We explore the use of clock skew of a wireless local area network access point (AP) as its fingerprint to detect unauthorized APs quickly and accurately. The main goal behind using clock skews is to overcome one of the major limitations of existing solutions - the inability to effectively detect Medium Access Control (MAC) address spoofing. We calculate the clock skew of an AP from the IEEE 802.11 Time Synchronization Function (TSF) time stamps sent out in the beacon/probe response frames. We use two different methods for this purpose - one based on linear programming and the other based on least-square fit. We supplement these methods with a heuristic for differentiating original packets from those sent by the fake APs. We collect TSF time stamp data from several APs in three different residential settings. Using our measurement data as well as data obtained from a large conference setting, we find that clock skews remain consistent over time for the same AP but vary significantly across APs. Furthermore, we improve the resolution of received time stamp of the frames and show that with this enhancement, our methodology can find clock skews very quickly, using 50-100 packets in most of the cases. We also discuss and quantify the impact of various external factors including temperature variation, virtualization, clock source selection, and NTP synchronization on clock skews. Our results indicate that the use of clock skews appears to be an efficient and robust method for detecting fake APs in wireless local area networks.

In this paper, we introduce the scheme for bandwidth allocation and congestion avoidance in wireless intelligent ATM networks which is based on reinforcement learning (RL). Our solution guarantees a desired bandwidth to connections which require a fixed wide bandwidth according to QoS constraints. Any unused bandwidth is momentarily backed up (returned) to Virtual Circuits. Proposed RL method is also suitable for supporting the mapping between a single ATM switch port and a wireless access points. It can control the access points in wireless intelligent ATM networks.

A lot of access points (APs) in wireless mesh networks (WMNs) are battery powered. In order to minimize their energy consumption, the APs can adaptively adjust their transmission power and time based on various network conditions. In this paper, the problem of minimizing the AP energy consumption is formulated as an optimization problem with the constraint to satisfy the throughput requirements of associated mobile stations (MSs). Balancing the energy consumption of the APs can be important to prolong the network lifetime, particularly in a network with high and random user mobility, which can easily result in unbalanced traffic load and energy consumption among the APs. Two distributed handoff schemes are proposed for a WMN with adaptive transmission power and rate. One scheme attempts to achieve balanced energy consumption among the APs during each scheduling interval, and the other scheme balances the AP energy consumption over a longer term. Numerical results show that both schemes achieve much longer network lifetime than the traditional distance-based handoff scheme, while the long-term based handoff scheme can achieve the objective with approximately the same number of handoffs as the distance-based handoff.

Mobile Edge Computing (MEC) is a promising paradigm to support high-quality time-sensitive applications. In this paper, we investigate the service migration (i.e., whether, when, and where to migrate the services) to seamlessly serve mobile users in small-cell MEC systems. The service migration is formulated as an optimization problem to minimize the long-term system average delay that consists of queuing, communication, and migration delays. Considering the dynamic user mobility and network conditions, the formulated problem is non-convex and difficult to solve in real time. To this end, we propose a Mobility-aware Service Migration scheme, named MSM, to make real-time decisions on service migrations by utilizing reinforcement learning (RL) approaches. Specifically, we first design a user classification mechanism based on users’ mobility patterns to reduce the complexity of decision-making. We then formulate the service migration as a Markov decision process and devise an RL-based framework to make service migration decisions in real time in the dynamic MEC environment. Extensive data-driven experiments demonstrate the efficacy of MSM in reducing the system average delay.

The global positioning system (GPS) is a popular choice for accurate location sensing and is often used in navigation systems. However, GPS fails to operate inside buildings because satellite signals are blocked. Thus, GPS cannot be used for localization indoors. Moreover, it is difficult to distinguish between the different floors. Research to overcome this problem using the ultrawideband (UWB), radio frequency identification (RFID), and infrared ray (IR) has been conducted. These methods, however, have drawbacks, such as the need for an additional communication module and database. Wireless local area network (WLAN) access point (AP) is widely installed at various locations, and using these WLAN APs can be a viable alternative. The proposed system in this paper indicates the location information in the service set identifier (SSID) of virtual AP. Therefore, merely by scanning the WLAN signals, mobile users can detect their location indoors.

Envisioned low-latency services in 5G, like automated\n\t\t\t\t driving, will rely mainly on Multi-access Edge Computing\n\t\t\t\t (MEC) to reduce the distance, and hence latency, between users\n\t\t\t\t and the remote applications. MEC hosts will be deployed close to\n\t\t\t\t mobile base stations, constituting a highly distributed computing\n\t\t\t\t platform. However, user mobility may raise the need to migrate a\n\t\t\t\t MEC application among MEC hosts to ensure always connecting\n\t\t\t\t users to the optimal server, in terms of geographical proximity,\n\t\t\t\t Quality of Service (QoS), etc. However, service migration may\n\t\t\t\t introduce: (i) latency for users due to the downtime duration;\n\t\t\t\t (ii) cost for the network operator as it consumes bandwidth\n\t\t\t\t to migrate services. One solution could be the use of service\n\t\t\t\t replication, which pro-actively replicates the service to avoid service\n\t\t\t\t migration and ensure low latency access. Service replication\n\t\t\t\t induces cost in terms of storage, though, requiring a careful\n\t\t\t\t study on the number of service to replicate and distribute in\n\t\t\t\t MEC. In this paper, we propose to compare service migration\n\t\t\t\t and service replication via an analytical model. The proposed\n\t\t\t\t model captures the relation between user mobility and service\n\t\t\t\t duration on service replication as well as service migration costs.\n\t\t\t\t The obtained results allow to propose recommendations between\n\t\t\t\t using service migration or service replication according to user\n\t\t\t\t mobility and the number of replicates to use for two types of\n\t\t\t\t service.

How many small cell (SC) access points (APs) are required to guarantee a chosen quality of service in a heterogeneous network? In this chapter, we answer this question considering two different network models. The first is the downlink of a finite-area SC network where the locations of APs within the chosen area are uniformly distributed. A key step in obtaining the closed-form expressions is to generalize the well-accepted moment matching approximation for the linear combination of lognormal random variables. For the second model, we focus on a two-layer downlink heterogeneous network with frequency reuse-1 hexagonal macro cells (MCs), and SC APs that are placed at locations that do not meet a chosen quality of service from macro base stations (BSs). An important property of this model is that the SC AP locations are coupled with the MC coverage. Here, simple bounds for the average total interference within an MC makes the formulation possible for the percentage of MC area in outage, as well as the required average number of SCs (per MC) to overcome outage, assuming isolated SCs. Introduction Heterogeneous cellular networks (HCNs) are being considered as an efficient way to improve system capacity as well as effectively enhance network coverage [1, 2]. Comprising multiple layers of access points (APs), HCNs encompass a conventional macro cellular network (first layer) overlaid with a diverse set of small cells (SCs) (higher layers). Cell deployment is an important problem in heterogeneous networks, both in terms of the number and positioning of the SCs. Traditional network models are either impractically simple (such as the Wyner model [3]) or excessively complex (e.g., the general case of random user locations in a hexagonal lattice network [4]) to accurately model SC networks. A useful mathematical model that accounts for the randomness in SC locations and irregularity in the cells uses spatial point processes, such as Poisson point process (PPP), to model the location of SCs in the network [5–10]. The independent placement of SCs from the MC layer, has the advantage of analytical tractability and leads to many useful SINR and/or rate expressions. However, even assuming that wireless providers would deploy SCs to support mobile broadband services, the dominant assumption remains that SCs are deployed randomly and independent of the MC layer [11].

This paper demonstrates hosting IoT gadgets on the wireless AP(Access Point) at home. For this, the process and profile of the IoT gadgets need to be virtualized into JavaScript-based objects. Then, to execute and control the instances of the virtualized IoT objects on the wireless AP, a novel instance management method is required. The demonstration shows the IoT gadget registration, monitoring, and control on the wireless AP. In addition, generating mash-up instances by connecting multiple gadgets and controlling them together is performed.

How to perform efficient service migration in a mobile edge environment has become one of the research hotspots in the field of service computing. Most service migration approaches assume that the mobile edge network on which the migration depends is stable. However, in practice, these networks often fluctuate greatly due to the fault of edge devices, resulting in unexpected service interruptions during the migration process. Besides, most of the existing solutions do not consider the migration cost and path selection in the event of edge network fault. Aiming at the above problems, we propose a service migration approach based on network fault prediction (SMNFP) for mobile edge environment. The SMNFP method first introduces the software-defined network as a global controller, which is used to monitor and collect the changing of the edge network and schedule the migration tasks. Second, a network fault prediction model based on Wide&Deep model is proposed to predict the upcoming faults in the network according to the alarm information of network equipment. Finally, the service migration problem is constructed as a Markov decision process, and a fault penalty function is introduced to avoid faulty nodes, together with the deep Q-learning method to solve the migration strategy. Simulation experiments are conducted on the public metro network fault dataset, and results show the proposed method can effectively predict network faults and complete service migration.

Edge computing (EC) extends the ability of cloud computing to the network edge to support diverse resource-sensitive and performance-sensitive IoT applications. However, due to the limited capacity of edge servers (ESs) and the dynamic computing requirements, the system needs to dynamically update the task allocation policy according to real-time system states. Service migration is essential to ensure service continuity when implementing dynamic task allocation. Therefore, this article investigates the long-term dynamic task allocation and service migration (DTASM) problem in edge-cloud IoT systems where users’ computing requirements and mobility change over time. The DTASM problem is formulated to achieve the long-term performance of minimizing the load forwarded to the cloud while fulfilling the seamless migration constraint and the latency constraint at each time of implementing the DTASM decision. First, the DTASM problem is divided into two subproblems: 1) the user selection problem on each ES and 2) the system task allocation problem. Then, the DTASM problem is formulated as a Markov decision process (MDP) and an approach based on deep reinforcement learning (DRL) is proposed. To tackle the challenge of vast discrete action spaces for DTASM task allocation in the system with a mass of IoT users, a training architecture based on the twin-delayed deep deterministic policy gradient (DDPG) is employed. Meanwhile, each action is divided into a differentiable action for policy training and one mapped action for implementation in the IoT system. Simulation results demonstrate that the proposed DRL-based approach obtains the long-term optimal system performance compared to other benchmarks while satisfying seamless service migration.

SummaryBoth mobile computing and cloud computing have experienced rapid development in recent years. Although centralized cloud computing exhibits abundant resources for computation‐intensive tasks, the unpredictable and unstable communication latency between the mobile users and the cloud makes it challenging to handle latency‐sensitive mobile computing tasks. To address this issue, fog computing recently was proposed by pushing the cloud computing to the network edge closer to the users. To realize such vision, we can augment existing access points in wireless networks with cloudlet servers for hosting various mobile computing tasks. In this paper, we investigate how to deploy the servers in a cost‐effective manner without violating the predetermined quality of service. In particular, we practically consider that the available cloudlet servers are heterogeneous, ie, with different cost and resource capacities. The problem is formulated into an integer linear programming form, and a low‐complexity heuristic algorithm is invented to address it. Extensive simulation studies validate the efficiency of our algorithm by it performs much close to the optimal solution.

Virtual machine (VM) is an important mechanism to multiplex computer resources. The increasing popularity of network computing has renewed research interests in the adaptive and distributed virtual machines. Service migration is a vital technique to construct reconfigurable VMs. By incorporating mobile agent technology, VM systems can improve their resource utilization, load-balancing and fault-tolerance significantly. This work focuses on the decision problem of hybrid mobility for load-balancing in reconfigurable distributed VMs. We tackle this problem from three aspects: migration candidate determination, migration timing and destination server selection. The service migration timing and destination server selection are formulated as two optimization models. We derive the optimal migration policy for distributed and heterogeneous systems based on stochastic optimization theories. Renewal processes are applied to model the dynamics of migration. We solve the agent migration problem by dynamic programming and extend the optimal service migration decision by considering the interplay of the hybrid mobility. Our decision policy is complementary to the existing service and agent migration techniques. Its accuracy is verified by simulations.

Mobile edge computing (MEC) provides a promising approach to significantly reduce network operational cost and improve quality of service (QoS) of mobile users by pushing computation resources to the network edges, and enables a scalable Internet of Things (IoT) architecture for time-sensitive applications (e-healthcare, real-time monitoring, and so on.). However, the mobility of mobile users and the limited coverage of edge servers can result in significant network performance degradation, dramatic drop in QoS, and even interruption of ongoing edge services; therefore, it is difficult to ensure service continuity. Service migration has great potential to address the issues, which decides when or where these services are migrated following user mobility and the changes of demand. In this paper, two conceptions similar to service migration, i.e., live migration for data centers and handover in cellular networks, are first discussed. Next, the cutting-edge research efforts on service migration in MEC are reviewed, and a devisal of taxonomy based on various research directions for efficient service migration is presented. Subsequently, a summary of three technologies for hosting services on edge servers, i.e., virtual machine, container, and agent, is provided. At last, open research challenges in service migration are identified and discussed.