O-RAN Advance Course  /  Chapter 8 — RIC · E2 · A1 · R1 & the AI/ML Loop
O-RAN R005 train · 2026
CHAPTER 8 · MODULE M8 · NARRATED VIDEO + LAB

Now the RAN
gets a brain.

Intelligence is what makes Open RAN more than a cheaper radio. Here software steers the network: the two RICs by timescale, the E2 interface with its five verbs (report · insert · control · policy · query), E2SM-KPM to measure and E2SM-RC to act, A1 policies and R1 services, the AI/ML lifecycle — and one energy-saving use case threaded from an overnight model down to a Section Type 4 on the fronthaul. From O-RAN WG3 E2SM-KPM/RC, WG2 A1/R1, and the AI/ML workflow.

2RICs≥1s · 10ms–1s
5verbsE2 services
KPM·RCmeasure · act
A1·R1policy · rApps
AI/MLloop→ ST4
ENkaraoke subs
O-RAN.WG3 E2SM-KPM v08 · E2SM-RC v10 (Annex A.2 mobility) · WG2 A1TD v12 · R1GAP v14 · Non-RT-RIC-ARCH v07 · AIML v01.03 · CUS.0 §16 (energy)
▶ VIDEO · CHAPTER 8 · NARRATED

The intelligent RAN — RICs, E2, A1, and the AI/ML loop

The player screen is a live animation stage — the two RICs assemble on their timescales, the five E2 verbs light up, a KPM subscription builds, an RC mobility loop runs measure→decide→act, and an energy-saving use case threads down to a Section Type 4, exactly as the narration reaches each idea. Karaoke EN + Persian, fullscreen.

Chapter 2 · Open RAN Masterclass · functional splits & 7-2x
Open the pink line — down to the last bit
0:00 / 0:00
LAB · NEAR-RT CONTROL-LOOP STEPPER
Run the E2 loop yourself →
Step KPM report → policy check → RC control → KPI shift, and watch the hot cell's load drop as the xApp steers users.
LAB · NEAR-RT CONTROL-LOOP STEPPER · E2SM-KPM + RC

Run one near-RT control loop

A hot cell is at 92% load. Step the loop: the xApp measures (KPM), checks its A1 policy, acts (RC control), and the KPI shifts — all in tens of milliseconds.

idle
Press “Step the loop”.
hot cell load
interface
actor
timescale10 ms–1 s
REFERENCE · THE FIVE E2 SERVICE VERBS · E2SM-RC

E2 is verbs, not fixed messages

E2 carries service models; on top of them, five service types define what the RIC can do.

VerbWhat it doesRound trip?
REPORTstream information up on a trigger you defineno (RAN → RIC)
INSERTpause a RAN procedure and inject a decision mid-flightyes
CONTROLcommand the RAN to act now (e.g. a handover)yes (RIC → RAN)
POLICYset guardrails the RAN follows on its ownno round trip
QUERYfetch information on demandyes
TWO SERVICE MODELS
E2SM-KPM measures (counters, KPIs); E2SM-RC acts (control). RC organises abilities into control stylesStyle 3 = Connected-Mode Mobility (HO / CHO / DAPS handover for a selected UE to a target cell).
REFERENCE · KPM SUBSCRIPTION · E2SM-KPM

How the RIC measures the RAN

PartAnswersExample
Event triggerhow often / on what condition to reportevery 1000 ms
Report stylethe shape of measurementE2-node level / per-UE
Measurement listexactly which countersPRB usage, active UEs, throughput
RC MOBILITY FLOW · Annex A.2
① xApp subscribes with an INSERT trigger for handover measurement reports → ② gNB gathers a UE measurement report → ③ RAN sends a RIC Indication (INSERT) with its preliminary HO decision → ④ xApp confirms / downselects retained bearers & cells → ⑤ xApp sends a CONTROL message that initiates the handover. Measure, decide, act — in tens of milliseconds.
REFERENCE · A1 · R1 · AI/ML · WG2 + AIML

Strategy, apps, and the learning loop

Interface / thingBetweenCarries
A1Non-RT RIC ↔ Near-RT RICpolicies + enrichment info (A1TD policy types)
R1rApps ↔ Non-RT RIC frameworkservice-based framework services
E2 / Y1xApps ↔ E2 nodes / consumersKPM measurements, RC control, analytics
AI/ML workflowNon-RT RIC (train) → rApp/xApp (infer)collect → train → deploy → infer → monitor
THE ENERGY-SAVING THREAD · CUS §16 + ST4
Overnight an rApp (trained via AI/ML) decides to sleep cells → expresses it as an A1 policy → an xApp watches live KPM → issues an E2 RC control → the O-DU sends a Section Type 4 slot-config command (Chapter 3) → the O-RU powers down the carrier. One thread from an AI model to a bit on the wire.

🛠 Engineer detail block — what you'll actually meet in the field

  • Timescale decides the RIC. If a use case must react in < 1 s, it is an xApp on E2. If it optimises over minutes/hours, it is an rApp with an A1 policy. Putting a fast loop in the Non-RT RIC is the classic design error.
  • E2 nodes expose less than the spec dreams. The KPM/RC RAN-function list a real E2 node advertises is often narrower than the standard — always check what measurements and control actions the node actually supports before designing an xApp.
  • INSERT is the powerful, dangerous one. It pauses a live RAN procedure waiting for the RIC. A slow or dead xApp on an INSERT loop stalls real users — budget its latency like the near-RT loop it is.
  • A1 sets guardrails, not commands. Do not expect A1 to trigger a handover; it sets the policy the Near-RT RIC then enforces itself. Strategy downhill (A1), tactics on the ground (E2).
  • The AI/ML loop never ends. A deployed model drifts as traffic changes. Without the monitor→retrain arm, your "AI" silently rots — the closed loop is the product, not the one-off model.
✓ QUIZ · 8 QUESTIONS · SHUFFLED EVERY LOAD

Chapter 8 quiz