epcAware: A Game-Based, Energy, Performance and Cost-Efficient Resource Management Technique for Multi-Access Edge Computing

Abstract

The Internet of Things (IoT) is producing an extraordinary volume of data daily, and it is possible that the data may become useless while on its way to the cloud for analysis, due to longer distances and delays. Fog/edge computing is a new model for analyzing and acting on time-sensitive data (real-time applications) at the network edge, adjacent to where it is produced. The model sends only selected data to the cloud for analysis and long-term storage. Furthermore, cloud services provided by large companies such as Google, can also be localized to minimize the response time and increase service agility. This could be accomplished through deploying small-scale datacenters (reffered to by name as cloudlets) where essential, closer to customers (IoT devices) and connected to a centrealised cloud through networks-which form a multi-access edge cloud (MEC). The MEC setup involves three different parties, i.e. service providers (IaaS), application providers (SaaS), network providers (NaaS); which might have different goals, therefore, making resource management a defficult job. In the literature, various resource management techniques have been suggested in the context of what kind of services should they host and how the available resources should be allocated to customers' applications, particularly, if mobility is involved. However, the existing literature considers the resource management problem with respect to a single party. In this paper, we assume resource management with respect to all three parties i.e. IaaS, SaaS, NaaS; and suggest a game theoritic resource management technique that minimises infrastructure energy consumption and costs while ensuring applications performance. Our empirical evaluation, using real workload traces from Google's cluster, suggests that our approach could reduce up to 11.95% energy consumption, and approximately 17.86% user costs with negligible loss in performance. Moreover, IaaS can reduce up to 20.27% energy bills and NaaS can increase their costs savings up to 18.52% as compared to other methods.

Survey on Placement Methods in the Edge and Beyond

“…2) Resource allocation in edge and fog computing systems: This section is devoted to the research works addressing services consisting of multiple components, such as VMs, containers or tasks, but there is no relation among the constituent elements taken into account. Following our Platform components dimension, the underlying infrastructure, where the service components are mapped to, can be multi-edge [80], [95], [129], [131]- [133], [135], [137], [140], [169], [180], [182], cloud-edge [59], [64], [68], [70], [75], [127], [161], [170], [174], [176], [178] or multi-cloud [51] but the core problem to be tackled, i.e., component placement, is similar.…”

“…The authors define a link-path formalization along with a heuristic approach for the placement of virtualization infrastructure resources and user assignments, i.e., determining where to install cloudlet facilities among sites, and assign access points, such as base stations, to them. In a similar vein, researchers in [75] suggest game-theoretic techniques for VM placement to ensure application's performance while they aim to jointly minimize infrastructure energy consumption and cost. Dedicated telco use cases are addressed with similar objectives, where the management cost of Telecom infrastructure vendors' network [170] and the 5G infrastructure [95] is to be optimized.…”

“…Due to the edge environment, customers are generally connected via mobile networks, therefore, considering user mobility can also be essential. In several research papers [75], [131]- [133], [135], [140], [174], [180], [182], mobility patterns are incorporated in the models and the service deployment and/or resource allocation are optimized either proactively based on predictions or reactively based on measurements. For example, utilizing user mobility to meet the extreme low service latency requirements is studied in [132], where the trade-off of resource footprint versus application delay is formalized.…”

“…Therefore, in general, the addressed problems are multifaceted, and therefore they inspire researchers to apply various tool sets for mathematical formalization. In Table VII and VIII, we list the formalization approaches we have encountered [145] Graph partitioning Other heuristic solution [65]- [67], [123], [124], [162], [167] Game theory Game theory Game theory [84] Best response search [75] Auction theory n/a [49] Stackelberg [81] in the collected papers, and we assign each paper to its respective specific model type. The left-most two columns in both Tables VII and VIII depict the large categories and the specific models of problem formalization, respectively.…”

Energy-Aware Scheduling in Edge Computing Based on Energy Internet

“…Based on the prediction results, a mobile data offloading strategy based on cross-entropy is proposed to maximize the system throughput by determining which users to be offloaded to Wi-Fi systems. Z. Muhammad et al [29] suggested game-theoretic resource management techniques to minimize infrastructure energy consumption and costs while meeting QoS of users. B. Ali et al proposed [30] a Volunteer Supported Fog Computing (VSFC) that tries to explore the interplay of these two distributed computing domains and targets to reduce inherent communication delays of cloud computing, energy consumption, and network usage.…”