Learning Library

← Back to Library

Multi-Access Edge Computing Explained

Key Points

  • Edge computing moves compute resources nearer to where data is generated to cut latency and reduce load on central servers.
  • Multi‑access Edge Computing (MEC) extends this concept by placing compute directly on telecom infrastructure (e.g., base stations), integrating it with the network itself.
  • For data‑heavy, real‑time workloads such as HD video analysis, locating the processing service at the edge dramatically lowers round‑trip time and avoids sending massive streams to distant back‑end servers.
  • MEC adds the challenge of mobility, requiring the edge resources to be deployed wherever users may move, which is achieved by embedding compute at the radio access network or network data centers.

Full Transcript

# Multi-Access Edge Computing Explained **Source:** [https://www.youtube.com/watch?v=Do7gsyXWj4E](https://www.youtube.com/watch?v=Do7gsyXWj4E) **Duration:** 00:05:29 ## Summary - Edge computing moves compute resources nearer to where data is generated to cut latency and reduce load on central servers. - Multi‑access Edge Computing (MEC) extends this concept by placing compute directly on telecom infrastructure (e.g., base stations), integrating it with the network itself. - For data‑heavy, real‑time workloads such as HD video analysis, locating the processing service at the edge dramatically lowers round‑trip time and avoids sending massive streams to distant back‑end servers. - MEC adds the challenge of mobility, requiring the edge resources to be deployed wherever users may move, which is achieved by embedding compute at the radio access network or network data centers. ## Sections - [00:00:00](https://www.youtube.com/watch?v=Do7gsyXWj4E&t=0s) **Understanding Multi-Access Edge Computing** - Dan Kehn explains that multi-access edge computing advances traditional edge computing by locating compute resources on telco network infrastructure, dramatically lowering latency for high‑performance workloads such as real‑time video and image analysis. - [00:03:09](https://www.youtube.com/watch?v=Do7gsyXWj4E&t=189s) **Dynamic Edge Placement Benefits** - The speaker explains that in multi‑access edge computing, edge servers are installed directly on network infrastructure (such as base stations or data‑center nodes) instead of fixed sites, delivering ultra‑low latency, reducing backend load, enabling on‑site machine‑learning, maintaining service continuity during outages, and leveraging radio access network data. ## Full Transcript
0:00What is multi-access edge computing? How is  it different than regular edge computing? Hi, 0:05I'm Dan Kehn from IBM Cloud, and before I answer  those questions, please click like and subscribe. 0:11Edge computing is about bringing compute capacity  closer where data is created to reduce response 0:17time and the load on back-end servers. Multi-access  edge computing is the next logical step in edge 0:24computing for telco cloud. It brings compute  capacity directly to network's edge, literally 0:30on the same infrastructure as the network itself.  Let's go through it using an example. So we have 0:38say an image application that does image  analysis. It communicates with the core network. 0:53That in turn works with a back-end server. 1:02For sake of discussion, on that  back-end server, let's assume we have 1:06a service called "image analysis service" installed. 1:14Okay, this is a classical  application design pattern; 1:18the user makes a request, it  goes to a back-end server, 1:22it formulates a response that it returns the end  user. The round trip for that including latency 1:27might be on the order of 100 milliseconds.  That's perfectly fine for many applications. 1:32But let's assume we have a more demanding  application, for example, one that does video. 1:39And it isn't using just one user that it wants  to capture, it's capturing a crowd. Maybe it's 1:46used for security purposes, maybe it's used for  threat analysis -- those are just some examples. 1:51What really drives us towards an edge computing  solution are two things: First, there's a lot 1:58of data. Now an HD video camera, that could  stream as much as six megabits per second. 2:04The other thing is the real-time  aspect -- we need a real-time response, 2:11It would be difficult to send all that data  back to the back-end server, process it, and 2:15return it in real-time. That's why we install edge  servers closer to where the source of data is. 2:23So say, for example, we install some edge servers, 2:29and on those we install  the "video analysis service". 2:38This really helped with our latency problem. We  no longer have to send data across the network 2:43to a far away server. It also  helps with our data volume problem. 2:51We're no longer sending huge  amounts of data across the network. 2:57Where multi-access edge computing comes  into play is when we add a third element, 3:07specifically mobility. 3:13In the prior examples, we were assuming that  these edge computers were in a fixed location, 3:18for example, at a retail location providing a  shopping experience, maybe an IoT device at a 3:24factory that's doing assembly. Those are examples  where the edge computer location is known. 3:31In this case, for multi-access edge computing, it  could be anywhere. We cannot predict where the 3:37edge computers might be located, so we install  them on the network itself. So, for example, we 3:43have a radio access network and then install  it at the base station; or, we could install it 3:54at the data center for the network itself. This  really drives latency to its absolute minimum, 4:00as little as 10 milliseconds. It also reduces the  load on the back-end server for the enterprise. 4:07We could then repurpose that for something  else, for example, we could do machine learning. 4:13So, for example, say we do machine learning  training, then we take that result and we 4:18give it to the video analysis service  to improve the quality of its results. 4:24There's a couple other different benefits  that are worth noting. Because this is 4:28running on the network's infrastructure,  if there is a temporary outage between the 4:34back-end server and video analysis, it can continue  to process. Thus you have continuous operations. 4:42Finally, there is the ability to take  advantage of radio access network data. 4:51For example, the radio access network would  know where the location of the users are 4:57and it could potentially predict where additional  load would be required. This allows their network 5:03to be much more responsive to users' needs and  being able to deploy capacity where it's going to 5:07where it's going to be needed in the future. 5:10Multi-access edge computing means communication service 5:14providers can bring compute capacity directly to  your users no matter where or how they connect to 5:20the network. Thank you for watching. If you  have questions please drop us a line below. 5:25If you want to see more videos like this  in the future, please like and subscribe.