An Intelligent Edge-centric Queries Allocation Scheme based on Ensemble Models

Abstract

The combination of Internet of Things (IoT) and Edge Computing (EC) can assist in the delivery of novel applications that will facilitate end-users' activities. Data collected by numerous devices present in the IoT infrastructure can be hosted into a set of EC nodes becoming the subject of processing tasks for the provision of analytics. Analytics are derived as the result of various queries defined by end-users or applications. Such queries can be executed in the available EC nodes to limit the latency in the provision of responses. In this article, we propose a meta-ensemble learning scheme that supports the decision making for the allocation of queries to the appropriate EC nodes. Our learning model decides over queries' and nodes' characteristics. We provide the description of a matching process between queries and nodes after concluding the contextual information for each envisioned characteristic adopted in our meta-ensemble scheme. We rely on widely known ensemble models, combine them, and offer an additional processing layer to increase the performance. The aim is to result a subset of EC nodes that will host each incoming query. Apart from the description of the proposed model, we report on its evaluation and the corresponding results. Through a large set of experiments and a numerical analysis, we aim at revealing the pros and cons of the proposed scheme. CCS Concepts: • Computing methodologies → Ensemble methods;

Queries allocation in WSNs with fuzzy control system

“…[52], the authors propose formal support for analyzing query processing strategies that are limited to WSNs and base stations (BSs). On the other hand, in paper [36], the authors only utilize computing edge (WSN). Our research, however, goes beyond that by testing and evaluating an approach that incorporates a cache server as a query processing element.…”

“…In the paper [36], the queries can be executed in the available computational edge (CE) nodes to limit the latency in providing the answers. The authors propose a meta‐set learning scheme that supports decision‐making for allocating queries to appropriate CE nodes.…”

“…In ref. [37], the authors present a model that assigns incoming requests to appropriate nodes. They provide a meta‐set learning model that is responsible for selecting the best possible node to allocate a request.…”

Intelligent tasks allocation at the edge based on machine learning and bio-inspired algorithms

“…Easily, we can conclude the complexity of each task, i.e., c t , based on the complexity of the required calculations. For that, we can rely on the algorithmic theory or other techniques like the one presented in [33]. In addition, tasks' constraints can impose a deadline representing the upper bound of time for delivering the final results, i.e., τ t .…”

“…In this paper, the proposed models can manage a high number of tasks that could be greater than the number of the available EC nodes; (ii) In this paper, we adopt a ML and an optimization technique while in [26], we are based on the solution of the known assignment problem (i.e., a minimum cost flow problem). Finally, additional efforts in the past [33], [30], [34], [35] focus on the processing/allocation of a single task while our current work deals with the management of a batch of tasks.…”