Apis Training

eSIM for IoT

linda — Mon, 01 Jun 2026 16:28:03 +0000

eSIM for IoT

eLearning

€ 195*

*Prices exclude VAT

Course Contents

This course presents the eSIM technology for the Internet of Things and the GSMA Remote SIM Provisioning standards that enable it.

The course starts with the fundamentals and history of the SIM, USIM and UICC and the evolution to the eSIM/eUICC. It then explains the foundational M2M standard (SGP.02) and the consumer standard (SGP.22), before focusing in detail on the new IoT standards SGP.31 and SGP.32, including the eIM and IPA entities. The last part covers the benefits, commercial opportunities and real-world use cases of eSIM for IoT.

Course outline

Fundamentals and History

• SIM, USIM, UICC and ISIM: the basics
• Mobile Equipment, UICC and the air interface
• SIM form factors and the evolution to eSIM/eUICC
• The GSMA eSIM standards family: SGP.02, SGP.22, SGP.31 and SGP.32
• Why IoT needs a new Remote SIM Provisioning standard

SGP.02 and SGP.22: Foundations and Consumer Standard

• M2M eSIM architecture and roles (SGP.02): SM-DP, SM-SR and EUM
• Consumer eSIM architecture and roles (SGP.22): SM-DP+, SM-DS and the LPA
• M2M versus consumer eSIM: key differences
• SGP.02 profile lifecycle, interfaces (ES1–ES8) and profile structure
• SGP.22 interfaces (ES2+ to ES12) and the LPA architecture
• eUICC security domains and profile download signalling flows

SGP.31 and SGP.32: eSIM for IoT

• SGP.31 and SGP.32: overview, design goals and new entities
• IoT system architecture: the eIM, the IPA and the IoT eUICC
• The eIM (eSIM IoT Manager) and its interfaces (EIM1–EIM6)
• The IPA (IoT Profile Assistant): IPA-ME and IPA-eUICC variants
• SGP.32 profile download flow (Option A and Option B)
• SGP.32 profile lifecycle and state model
• Protocol stack for constrained devices: CoAP, DTLS and HTTPS

Benefits, Opportunities and Use Cases

• Operational benefits: zero-touch provisioning, remote operator switching and fleet management
• Business opportunities for MNOs, device makers and enterprise deployers
• Use case: smart metering and utilities
• Use case: connected vehicles and logistics
• Use case: industrial IoT and critical infrastructure
• Use case: healthcare and agriculture

Prerequisites

Basic technical knowledge of mobile networks (GSM/UMTS/LTE/5G) and IoT connectivity is recommended.

Public course application form

linda — Thu, 21 May 2026 16:42:15 +0000

AI in Telecom_260616

linda — Thu, 21 May 2026 13:03:58 +0000

How to Apply

1. Fill Out the Form: Complete the form with your details.
2. Get Contacted: Our team will reach out to you with more information and next steps.

AI in Telecom : 16-17 June 2026

Every public session has a limited number of seats and our larger key account clients are informed about dates before everyone else. If you haven’t taken courses with us before and your company does not have a frame agreement, we would love for you to join but please share as much info as possible in the message box (role, company, upskilling needs, number of participants etc.)

AI in Telecom

linda — Wed, 20 May 2026 18:47:26 +0000

AI in Telecom

Virtual Classroom

€ 1020*

Classroom Training

€ 1020*

*Prices exclude VAT

Course Contents

This course gives engineers and architects a technically rigorous grounding in how Artificial Intelligence and Machine Learning are deployed across modern telecom networks. It moves beyond vendor marketing to examine the real data pipelines, model architectures, API interfaces, and operational constraints that determine whether an AI system succeeds or fails in a production network environment.

The modules are ordered to build understanding progressively: from the industry context and programmable-network foundations, through domain-specific use cases in RAN, Core, and BSS, to Generative AI and the governance disciplines required for safe deployment. Lab exercises are integrated into each module.

The course covers both classical ML models (anomaly detection, churn prediction, reinforcement learning) and Large Language Model applications (NOC copilots, agentic operations, configuration generation). Hands-on lab exercises are included throughout.

Target Audience

The target group is engineers, architects, and technical managers who need to understand, design, or evaluate AI systems operating on live telecom networks including network operations engineers, RAN and Core architects, BSS developers, and data scientists working in the telecom domain.

Note: Lab exercises require a Python 3.11+ environment.

Course outline

Introduction

• The four macro-trends converging in telecom AI: margin pressure, software-defined networks, democratised ML tooling, and Generative AI
• Market investment signals and deployment maturity: Customer Experience AI, Revenue Assurance, AIOps, RAN Optimisation, Generative AI
• The Autonomous Network vision: TM Forum ANL maturity scale (L0-L5) and where operators stand today
• Hype vs. reality: NOC engineer replacement, zero-touch networks, federated learning at scale, LLM configuration push
• The API foundation: 3GPP SBA, O-RAN interfaces (A1/E2/O1/O2), CAMARA/GSMA Open Gateway, TM Forum Open APIs

Network Anomaly Detection & AIOps

• The problem with threshold-based operations: alert storms, blind spots, slow MTTR, excessive false positives
• Data sources and ingestion: SNMP traps, 3GPP PM counters, Syslogs, NetFlow/IPFIX, TM Forum TMF642 alarm feeds, signalling traces
• ML techniques for anomaly detection: Isolation Forest, Autoencoders, LSTM-based forecasting
• Supervised methods: Gradient Boosted Trees (XGBoost/LightGBM), Graph Neural Networks for root cause analysis
• Alarm correlation and Root Cause Analysis (RCA) topology-aware graph scoring
• Closed-loop remediation: low-risk automated actions, medium-risk configuration within safe bounds, high-risk human approval gate

AI-Driven RAN Optimisation

• Why the RAN is the hardest optimisation problem: rule-based SON limitations and multi-objective trade-offs
• O-RAN architecture and AI integration points: Non-RT RIC, Near-RT RIC, xApps and rApps
• O-RAN A1/E2 control loops timescales and primary use cases
• Handover optimisation with Reinforcement Learning: state, action, reward formulation; PPO agents
• AI-driven energy saving: traffic prediction, sleep candidate identification, coverage verification, O1 NETCONF/YANG command issuance
• Beam management in 5G NR mmWave: CNN/LSTM on CSI feedback, position-assisted beam prediction, federated learning across gNBs

Intelligent Core: Traffic Steering & Network Slicing

• The 5G Core as a programmable system: Service Based Architecture, NRF service discovery, key NFs relevant to AI (PCF, NWDAF, SMF, UDM, AMF)
• NWDAF – the native AI node of the 5G Core: analytics types, Nnwdaf_AnalyticsInfo and Nnwdaf_DataManagement services (3GPP TS 23.288 / TS 29.520)
• AI-powered network slicing: demand forecasting per slice, admission control models for URLLC, resource reallocation via NSSMF
• Intent-Based Networking: intent parsing (NLP/LLM), intent fulfilment engine, actuator layer (NETCONF/YANG, 5GC SBI, SDN controller APIs)

AI in BSS: Churn, Revenue Assurance & Customer Experience

• Why BSS data is uniquely valuable for AI: CDRs, CRM data, billing and payment data, customer care interaction transcripts
• Churn prediction: feature engineering with ARPU trend, data usage delta, care contacts, network quality signals; LightGBM/XGBoost model; SHAP explanations
• Revenue assurance with AI: anomaly detection on CDR streams, Wangiri fraud detection, graph-based fraud ring detection via GNN
• AI-powered customer experience: intelligent care routing and next-best-action (NBA), network experience indexing (QoE index), proactive care

Generative AI & LLMs in Telecom Operations

• Where Generative AI fits and where it does not: NOC copilots, configuration drafting, customer care chatbots vs. real-time closed-loop control
• NOC Copilot architecture: Retrieval-Augmented Generation (RAG) with runbook vector store, alarm context, and topology data
• Network configuration generation from natural-language intent: LLM drafting + deterministic validation agent + human approval gate
• Agentic AI in network operations: ReAct framework, tool-equipped agents for multi-step diagnostic workflows
• Telecom domain adaptation of LLMs: RAG over 3GPP/O-RAN specs, domain fine-tuning, structured output with schema validation

Architecture Patterns, Governance & Deployment

• Reference architecture: AI/ML Platform layer, AI Orchestration & Application layer, Network Exposure & API layer, Physical/Virtual Network
• MLOps for telecom: data drift monitoring, model versioning and staged rollout, shadow mode testing, feedback loop monitoring
• Explainability and auditability: SHAP values for tabular models, attention visualisation for neural networks, full audit trails for configuration changes
• Privacy and data governance: GDPR requirements, telecom-specific regulation, federated learning, differential privacy, data minimisation in feature pipelines
• Standards references: 3GPP TS 23.501/23.502/23.288/29.520/32.500, O-RAN WG1/WG2/WG3 specs, TM Forum IG1230/IG1251, ETSI GR ENI 001, ETSI GS ZSM 002

Practical Exercises During the Course

• Anomaly detection with Isolation Forest (Python / scikit-learn) on synthetic PM counter dataset
• Reinforcement learning for handover optimisation (PPO agent, Stable-Baselines3) using E2 telemetry dataset
• NWDAF slice load monitoring and proactive resource reallocation via mock NSSMF API (Python / Flask)
• Churn prediction with LightGBM and SHAP feature attribution on synthetic CDR + CRM dataset
• NOC Copilot with Anthropic API: incident summary, root cause, and ranked remediation steps from alarm context

Prerequisites

• Familiarity with RESTful / gRPC APIs
• Basic understanding of telecom network architecture (RAN, Core, OSS/BSS)
• Exposure to ML concepts (helpful but not required)

Webinar | 5G Standalone

linda — Tue, 31 Mar 2026 15:04:29 +0000

The deployment of 5G Standalone (5G SA) represents a major evolution in mobile network architecture.

Designed to support modern applications requiring higher throughput, ultra-low latency and improved reliability, 5G Standalone introduces new capabilities across both the access network and the core network.

This webinar explores the key technologies and architectural concepts behind 5G SA deployments.

Webinar Topics

5G Standalone system domains: access network and core network
5G access network options
New Radio characteristics and frequency bands (FR1 and FR2)
Network slicing and edge computing
Private network deployments

HTTP/2 in 5G

linda — Fri, 27 Mar 2026 13:08:33 +0000

HTTP/2 in 5G

Virtual Classroom

€ 595*

Classroom Training

€ 595*

eLearning

€ 195*

*Prices exclude VAT

Course Contents

This course presents features and usage of HTTP/2 protocol used for communication within 5G Core Network.

The course starts with an introduction of the basic HTTP features, methods, history. This is followed by description of various new features in HTTP/2 version of the protocol. The last part contains several topics describing use of the protocol in communication between Network Functions in the 5G Core Network.

Course outline

Introduction and Evolution

• HTTP introduction
• HTTP history and transport
• HTTP methods and responses

HTTP/2 Features

• HTTP/2 streams
• Server push in HTTP/2
• Binary framing
• Frame types and formats
• Header flags and protocol settings
• Use of the connection preface
• Overview of HPACK header compression

HTTP/2 in 5G

• 5G network architecture
• Rationale behind selection of HTTP/2 for 5G
• RESTful APIs
• 5G Service Based Architecture communication principles
• Examples of NF services, operations, procedures
• Mapping of service operations to HTTP/2 methods and responses
• Example OpenAPI specifications
• Overview of registration, discovery, authorisation procedures
• Lists of mandatory request and response standard and custom headers
• Security of HTTP/2 communication in 5G
• Sample trace file snapshots

Prerequisites

Basic technical knowledge of 5G networks and data communication is recommended.

IMS Architecture_260908

linda — Wed, 04 Mar 2026 13:09:03 +0000

How to Apply

1. Fill Out the Form: Complete the form with your details.
2. Get Contacted: Our team will reach out to you with more information and next steps.

IMS Architecture: 8 September 2026

5G System Overview_260615

linda — Fri, 27 Feb 2026 17:13:21 +0000

How to Apply

1. Fill Out the Form: Complete the form with your details.
2. Get Contacted: Our team will reach out to you with more information and next steps.

5G System Overview: 15-18 June 2026

5G NSA Signalling

linda — Fri, 27 Feb 2026 16:06:04 +0000

5G NSA Signalling

Virtual Classroom

€ 2600*

Classroom Training

€ 2600*

*Prices exclude VAT

Course Contents

The 5G network architecture is a significant evolution from the 4G LTE EPC. Multi-Access Edge Computing (MEC) and Network Slicing are new abilities that enable the operator to improve the network to meet specific applications’ requirements.

During this course you will go through key operations such as power up and system acquisition, RRC connection setup, bearer setup with 5G NR, and DL and UL operations on 5G NR. This course covers key operations through call flows with details of major messages and their key parameters.

This course offers an insight into the signalling protocols applied in the 5G RAN. You will focus on the details of the NR interface signalling exchanged between the UE and the network, but the most important aspects of other NG-RAN interfaces are also covered. Most important network procedures, such as signalling connection establishment, registration, service request and handover are discussed and presented on signalling diagrams.

Target Audience

Network engineers, people involved in network design or systems performance, and operations related job functions who need to get an in-depth understanding of signalling procedures and Function.

Course outline

5G NSA Overview

• 5G NSA architecture
• 5G NSA gNB functional blocks and interfaces
• 5G core (5GC)
• MIMO TM1-10 and massive MIMO introduction
• 5G NSA LTE & NR measurements
• EN_DC (option 3x) description
• EN_DC split bearer setup, maintain, release

5G NSA L3 Signalling

• 3GPP LTE/5G NAS signalling for (option 3x) EN_DC architecture
• 3GPP LTE/5G RRC signalling procedures and services
• 3GPP 5G RRC signalling messages
• 3GPP 5G RRC Information Elements (IE) and parameters
• BCCH SIB messages indicating EN_DC cell support
• SIB parameters description for 5G cell support
• 3GPP EN_DC service setup, split bearer setup, release signalling flow
• Practical Exercises: RRC signalling log files analysis

5G NSA L2 Signalling

• 3GPP PDCP protocol procedures and services
• 3GPP RLC protocol procedures and services
• 3GPP MAC protocol procedures and services
• 3GPP MAC scheduler
• LTE Random Access analysis
• EN_DC Random Access analysis
• 5G NR HARQ procedures
• 5G NR LDPC and polar coding
• 5G NSA NR MIMO-OFDM mapping
• 5G NSA & SA NR mMIMO-OFDM mapping (analog and digital beamforming)
• Practical Exercises: L2 MAC signalling log files analysis

5G NSA Mobility

• 5G NSA EN_DC Mobility overview
• 5G NSA re-establishment (EN_DC splitting bearer to LTE MCG bearer)
• 3GPP re-establishment Parameters – related discussion for vendor specific parameters
• Practical Exercises: EN_DC split bearer setup and EN_DC split bearer to LTE MCG bearer signalling log files analysis

5G NSA Optimization

• 5G NSA EN_DC split bearer failure
• Failure analysis and related parameters
• Practical Exercises: split bearer failure signalling log files analysis
• Parameter configuration and Optimization discussion

Prerequisites

LTE Signalling – strongly recommended!
5G System Overview – strongly recommended!

5G mMIMO RAN Design Principles

linda — Wed, 25 Feb 2026 10:16:00 +0000

5G mMIMO RAN Design Principles

Virtual Classroom

€ 1870*

Classroom Training

€ 1870*

*Prices exclude VAT

Course Contents

This 5G training course explains in detail the MIMO radio channel modeling as well as capacity and coverage impairments. The configuration of CSI-RS logical ports is discussed vs. channel estimation, SMUX and beamforming. Coverage Analysis and Throughput performance are evaluated and good planning hints are discussed and explained based on the requested achievable targets.

Target Audience

• 5G RAN Engineers
• Radio Network Optimization Engineers
• Radio Network (RAN) Planners
• 5G RAN Performance Analysis Engineers

Course Outcomes

• Ability to analytically interpret 5G mMIMO KPIs
• Clear understanding of CSI, SINR, and throughput coupling
• Improved system-level optimization decisions
• Capability to bridge theory with real network behavior

Course outline

5G Radio Channel, OFDM and Performance Foundations

• 5G NR radio channel fundamentals
• Large-scale vs small-scale fading
• Time, frequency, and spatial coherence
• OFDM waveform principles and guard intervals
• Physical Resource Block (PRB) structure
• Numerology and subcarrier spacing impact
• OFDM simulation models and channel assumptions
• Noise, interference, and SINR formulation
• Relationship between SINR, BLER, and throughput
• Introduction to system-level KPIs

Channel Estimation and CSI Fundamentals

• MIMO technology overview
• MIMO SMUX vs. Beamforming
• MIMO beamwidths and gains
• Beamforming Reference signals in 5G NR
• CSI-RS design and reporting framework
• Channel estimation accuracy limits
• Impact of mobility and Doppler
• Interpolation in time and frequency
• Effective SINR mapping concepts
• CSI feedback errors and performance loss

mMIMO and Beamforming Performance

• mMIMO channel matrix modeling
• Spatial correlation and rank
• Beamforming principles (digital, hybrid)
• CSI-based beam selection
• Impact of antenna count and array geometry
• Beamforming gain vs beam width
• Pilot contamination and reciprocity

Throughput, Capacity and Optimization

• Downlink and uplink throughput modeling
• Scheduler behavior and resource allocation
• Multi-layer transmission limits
• CSI quality vs achievable rank
• Load impact on mMIMO performance
• Energy efficiency considerations
• Realistic KPI interpretation and troubleshooting

Prerequisites

Understanding on 5G Physical Layer procedures, 5G RAN technology, 5G RAN Planning and Optimization principles.