Interkey Intelligent DPI

Video optimization for mobile operators and ISPs

Video optimization for telecom operators: start by identifying the video

Video optimization starts with a question that is harder than it sounds: which flows on the network are video, and from which application? Interkey Intelligent DPI classifies traffic by application in real time, including encrypted traffic, without decrypting it, and supports video optimization by giving operator policy and service chains an accurate view of video traffic, per application, subscriber group or cell. What is optimised, and how, is the operator's decision.

A Saudi product, built by Interkey

For network, capacity and product teams at mobile operators and ISPs. Reviewed November 2026.

  • What it is:video optimization supported by DPI classification of video applications.
  • What it does:identifies video traffic by application and lets operator policy and service chains act on it, per application, subscriber group or cell.
  • Who it is for:network, capacity and product teams at mobile operators and ISPs.
  • Where it works:fixed and mobile networks, inline where policy acts on traffic, on your own infrastructure; it can operate entirely in the Kingdom.

How DPI classification supports video optimization

Steps of video optimization and the role of Interkey Intelligent DPI
StepWhat happensRole of Interkey Intelligent DPI
Find the videoEach flow is matched to its application, so video is separated from other traffic.Classifies flows by application in real time, including encrypted flows.
Decide the treatmentThe operator decides which video classes get which treatment, for which subscriber groups or cells.Applies operator-defined policy per application, subscriber group or cell.
Route the flowsSelected flows are directed through the functions that act on them, in a defined order.Service-chain control: the classification decides which traffic enters which chain.
See the effectCapacity, plan and product teams check what changed.Live View trends at network and application level, and policy execution feedback.

Why identifying video is harder than it was

Encryption removes the payload signal, and many applications share the same common ports, so a video flow often looks like any other web traffic when it is classified by port number or payload alone. A rule aimed at video then misses some video and catches some traffic that is not video.

Interkey Intelligent DPI classifies from flow behaviour, such as handshake structure, packet sizing and timing, and endpoint behaviour, and an AI traffic model built into the engine core retrains automatically as applications change. Measure detection and false-positive rates for the video applications that matter to you on your own traffic. See Measuring DPI classification accuracy on your traffic.

Applying video policy and service chains

  • Scope.Policies act per application, subscriber group or cell, so a video rule can apply to one cell that is congested, or one plan, and leave other traffic untouched.
  • Service chains.Classification decides which traffic enters which chain. For the design questions, see Service chaining and traffic steering for telecom operators.
  • Placement.Policy and steering act on traffic, so they need an inline deployment. Out-of-band, the platform classifies and reports, which is where to validate the video classes first.
  • Report-only first.A rule shows which traffic it would have affected before it changes anything.
  • Actions.The functions and parameters your deployment uses for video, and the connection to your policy and charging architecture, are defined with your team during scoping and documented in the integration plan.

Seeing where video matters

Live View shows traffic trends by application, so a capacity team can see when video drives load and where. That is useful before any rule exists, and it is the evidence for deciding whether a rule is needed. For the mobile case, see Mobile network congestion by application.

The reports describe classes of traffic and subscriber groups. The platform is built for network governance and regulatory compliance, not for monitoring individuals.

Governance for video rules

  1. 1. Published terms.The rule matches what subscribers were told for their plan, and applicable regulation.

  2. 2. A policy catalogue.For each rule: the video classes, the scope, the action, the basis and an owner.

  3. 3. An approval route.Who signs off the move from report-only to enforcement.

  4. 4. Change control.Rule changes and model updates enter the live network through your change-control process.

What to bring to a first scoping meeting

  • Your network points.Which parts of the network are covered in the first phase: fixed, mobile or both.
  • Your architecture.The policy and charging architecture, the enforcement points, and the reporting and security systems that results must reach.
  • Your data rules.Retention, access, and whether everything must stay in the Kingdom.
  • Your timeline.Whether you start out-of-band, and when an inline decision is due.

Test it on your network in 3 stages

  1. 1. Written acceptance criteria.Agree which classes and rules are tested, on which traffic and subscriber groups, how results are measured and what counts as a pass.

  2. 2. Out-of-band classification against verified traffic.Measure false positives as carefully as detection, for every class the rules depend on.

  3. 3. Report-only policy, then the inline decision.Each rule shows what it would have done; enforcement follows only after classification has proven itself.

Questions about video optimization

Does Interkey Intelligent DPI support video optimization?

Yes. It identifies video traffic by application and gives operator policy and service chains an accurate view of it. Which functions and parameters your deployment uses for video are defined with your team during scoping.

Does it work on encrypted video?

It classifies encrypted flows from observable characteristics without decrypting them. Results depend on your application mix and encryption share, so measure them on your own traffic.

Do we need an inline deployment?

For policy and steering that act on video, yes. Out-of-band deployment gives you classification and reporting, and is the usual first phase.

Can a rule apply to one cell or one plan only?

Yes. Policies act per application, subscriber group or cell.

Does it work when most traffic is encrypted?

It classifies encrypted and tunnelled flows from observable characteristics without decrypting them. Results depend on your subscriber mix, application mix and encryption share, so measure them on your own traffic.

How is it priced?

On a quote basis, depending on deployment, capacity, throughput, network placement and the capabilities in scope. There is no published price list.

Proof of concept in three phases

  1. Written acceptance criteria.Agree which rules are tested, on which traffic and subscriber groups, how results are measured and what counts as a pass.

  2. Out-of-band classification against verified traffic.Measure false positives as carefully as detection for every class the rules depend on.

  3. Report-only policy, then the inline decision.Each rule shows what it would have done; enforcement follows only after classification has proven itself.

Discuss a proof of concept on your network

Discuss video optimization on your network

Tell us which video applications and cells matter, what you want to change, and your timeline. Our team in Riyadh replies in Arabic or English.

  1. Our engineers read your request
  2. We agree the scope of a technical session
  3. You see the product on a use case you choose

Tell us your network type (mobile, fixed, ISP), approximate traffic volume and the use case you are evaluating.

By sending this form, you agree to our Privacy Notice.