Marie Platenius Mohr ABB Corporate Research Ladenburg, Germany, marie.platenius-mohr@de.abb.com
However, in many cases, more local solutions have benefits as well, eg, in terms of end-to-end latency, or data privacy. This is why edge computing is seen as a promising technology in many areas nowadays [1,2].
In edge computing, data processing tasks are executed close to where the data is generated, in order to enable fast response times. At the edge, the data can be preprocessed, filtered, or aggregated, such that a smaller amount of data needs to be sent to the cloud.
When comparing the benefits of edge and cloud computing, there are many aspects to consider →01:
• Performance: With edge computing, it is easier to achieve low latency and high bandwidth due to the physical proximity of the computing nodes to the source of the data. This also means that higher volumes of data can be processed at faster response times.
• Scalability: Scalability and elasticity, however, are among the big advantages in favor of cloud computing.
• Integration: When connected to an edge device, legacy and very resource-constrained devices can also be integrated into an advanced OT-IT system architecture [3].
• Sustainability: There are many different opinions regarding whether edge computing contributes to a low-carbon society. Edge computing helps to reduce traffic to the cloud as well as cloud storage and cloud operations, however, the providers of the big public clouds also have strong sustainability strategies [4].
• Availability/Reliability: The edge can operate even during times of unavailability of cloud services.
• Security/Privacy: On the edge, it is usually easier to protect applications and data. Having a secured edge gateway channeling the communication to the cloud, the attack surface is smaller, compared to a system with many devices establishing their own connections.
• Costs: Depending on the application, edge resources can be less expensive than cloud resources. Often, edge computing adds to a higher CAPEX, but has a lower OPEX if used in a continuous monitoring case.
All in all, both edge computing and cloud computing have their benefits and there are always trade-offs when deciding between these deployment alternatives for a specific application. Edge computing is not to be understood as an alternative to cloud computing but as a complement. Industry investment in edge computing has grown a lot within recent years, including efforts for industrial edge computing reference architectures and standardization eg, [5,6], accordingly, edge computing is well on its way to becoming a leading digital technology.
References
[1] M. Satyanarayanan:The emergence ofedge computing,IEEE Computer, 50/1,pp. 30 – 39, 2017.[
2] “Predicts 2021:Cloud and EdgeInfrastructure CloudInfrastructure Edge,”Gartner. https://www.gartner.com/smarterwithgartner/gartner-predicts-thefuture-of-cloud-andedge-infrastructure[Accessed May 24,2022].
[3] C. Ganz, “Cloud,edge and fog computing”,ABB Review2/2019, pp. 78 – 79.
[4] “Azure Sustainability– Sustainable Technologies| Microsoft Azure,”azure.microsoft.com. https://azure.microsoft.com/en-us/global-infrastructure/sustainability [AccessedMay 24, 2022].
[5] “The Open Industry4.0 Alliance: OpenIndustry 4.0 AllianceTechnical SolutionDesign Principles. Whitepaper, version 1.0,@2019 Copyright OpenIndustry 4.0 Alliance.”Available: https://www.automation.com/getattachment/d114d4ee-d9e2-426ba788-a8f27991340a/OI4-Technical-Whitepaper.pdf?lang=en-US&ext=.pdf [Accessed:May 24, 2022]
[6] User Associationof AutomationTechnology in ProcessIndustries (NAMUR):Reference architecturefor Industrial CloudFederation -- DIN SPEC92222:2021-12, 2021.
Title photo: Michelle Kiener
