[Paper Review] Managing Service-Heterogeneity using Osmotic Computing

Vishal Sharma, Kathiravan Srinivasan+3 more|arXiv (Cornell University)|Apr 13, 2017

IoT and Edge/Fog Computing8 references17 citations

TL;DR

This paper proposes a fitness-based Osmosis algorithm to manage service heterogeneity in fog computing by dynamically allocating services between edge and data center resources based on energy, load, and processing time. The approach reduces allocation time and improves resource utilization through intelligent service offloading, demonstrating significant gains in efficiency via numerical simulations.

ABSTRACT

Computational resource provisioning that is closer to a user is becoming increasingly important, with a rise in the number of devices making continuous service requests and with the significant recent take up of latency-sensitive applications, such as streaming and real-time data processing. Fog computing provides a solution to such types of applications by bridging the gap between the user and public/private cloud infrastructure via the inclusion of a "fog" layer. Such approach is capable of reducing the overall processing latency, but the issues of redundancy, cost-effectiveness in utilizing such computing infrastructure and handling services on the basis of a difference in their characteristics remain. This difference in characteristics of services because of variations in the requirement of computational resources and processes is termed as service heterogeneity. A potential solution to these issues is the use of Osmotic Computing -- a recently introduced paradigm that allows division of services on the basis of their resource usage, based on parameters such as energy, load, processing time on a data center vs. a network edge resource. Service provisioning can then be divided across different layers of a computational infrastructure, from edge devices, in-transit nodes, and a data center, and supported through an Osmotic software layer. In this paper, a fitness-based Osmosis algorithm is proposed to provide support for osmotic computing by making more effective use of existing Fog server resources. The proposed approach is capable of efficiently distributing and allocating services by following the principle of osmosis. The results are presented using numerical simulations demonstrating gains in terms of lower allocation time and a higher probability of services being handled with high resource utilization.

Motivation & Objective

• Address the challenge of service heterogeneity in fog computing environments, where services vary in computational, storage, and latency requirements.
• Improve resource utilization and reduce processing latency by intelligently distributing services across edge, fog, and data center layers.
• Develop a dynamic service allocation mechanism that considers energy efficiency, load balancing, and processing time as key decision factors.
• Enable efficient service offloading using the osmotic computing paradigm to support low-latency, high-performance applications in IoT and real-time systems.

Proposed method

• Introduce a fitness function that evaluates services based on three core resource properties: energy consumption, system load, and processing time.
• Classify services into micro- and macro-components to enable fine-grained allocation across computational layers.
• Implement an Osmotic software layer that manages service migration between edge devices, in-transit nodes, and data centers.
• Use numerical simulations to evaluate the performance of the fitness-based Osmosis algorithm under varying workloads and resource conditions.
• Apply the principle of osmosis to distribute services to the most suitable execution layer based on real-time resource availability and service characteristics.
• Integrate security considerations by proposing reverse osmosis as a mechanism to detect and isolate intrusions, treating malicious entities as impurities in the system.

Experimental results

Research questions

• RQ1 How can service heterogeneity in fog computing be effectively managed using dynamic resource allocation?
• RQ2 What criteria should guide the decision to offload a service from a data center to an edge or fog resource?
• RQ3 To what extent can a fitness-based algorithm improve allocation efficiency and reduce service processing time in heterogeneous service environments?
• RQ4 How does the proposed osmotic computing model enhance resource utilization and energy efficiency in distributed computing infrastructures?
• RQ5 What role can secure containerization and reverse osmosis play in enabling trusted service migration across fog and cloud layers?

Key findings

• The fitness-based Osmosis algorithm significantly reduces service allocation time by intelligently matching services to optimal execution layers based on real-time resource metrics.
• The proposed approach increases the probability of handling services with high resource utilization, minimizing idle capacity and redundancy.
• Numerical simulations confirm that the algorithm improves system efficiency by balancing load across edge, fog, and data center resources.
• The model demonstrates improved energy efficiency by avoiding non-redundant service allocations, supporting the concept of 'Green Osmotic Computing'.
• Service migration is enhanced through dynamic reconfiguration, with the osmotic layer enabling seamless movement of services based on changing workload and proximity requirements.
• Security remains a challenge, but the concept of reverse osmosis offers a promising mechanism to detect and isolate malicious entities by treating them as system impurities.