Practical Equations and Applications of Artificial Intelligence in the IT and Technological Areas of the CTE Model (CIET 2026, June 11-12, 2026, Split, Croatia)

 

Brief Scientific Summary and Key Findings

1. Introduction and Research Context

The telecommunications industry is entering a new phase of transformation in which Artificial Intelligence (AI) is becoming the central driver of network management, optimization and service orchestration. Unlike previous technological shifts focused primarily on infrastructure upgrades, AI introduces autonomous decision-making, predictive capabilities and adaptive optimization into telecom systems.

This scientific article extends the Comprehensive Techno-Economic (CTE) Model by introducing practical AI-oriented equations and methodologies specifically for the Technical Level (TL) of the model. The work focuses on two critical technical areas:

·         T.1 Coverage and Accessibility to Users

·         T.2 Technological and IT Development

The article provides a mathematical and operational framework for measuring how AI affects technical performance, resilience, governance, automation and network intelligence.

The central thesis of the paper is that by the period 2030–2040, AI will become the primary determinant of technical competitiveness in telecommunications. Future operators will compete not only through infrastructure ownership, but through their capability to deploy, govern and continuously improve intelligent systems.

---

2. Main Scientific Contribution of the Article

The article fills an important research gap between conceptual AI frameworks and practical implementation methodologies.

The most important scientific contributions include:

a) Development of AI-Augmented Telecom Equations

The paper introduces practical mathematical equations that integrate AI maturity into traditional telecom performance indicators.

b) AI Maturity Measurement

A new AI Maturity Index (AMI) is proposed to evaluate how advanced an organization is in AI deployment and operational capability.

c) AI Dependency and Resilience Assessment

The article recognizes that AI introduces not only opportunities but also risks. Therefore, additional indices are introduced:

·         Dependency Index (DI)

·         Resilience Score (RS)

·         Governance Score (GS)

d) Practical Implementation Framework

The work provides concrete methodologies for:

·         data collection,

·         KPI measurement,

·         AI monitoring,

·         operational validation,

·         telecom benchmarking.

e) Real Telecom Application

The article demonstrates practical implementation through telecom case studies involving:

·         5G/6G optimization,

·         predictive maintenance,

·         energy optimization,

·         autonomous network management,

·         AI-driven orchestration.

---

3. AI Maturity Index (AMI)

One of the central elements of the paper is the AI Maturity Index (AMI).

AMI represents a normalized score from 0 to 1 that measures the overall AI capability of a telecom operator.

The index consists of four dimensions:

Dimension	Description
Technical Capability	Computational infrastructure and AI algorithms
Data Quality	Accuracy and availability of training data
Automation Level	Degree of autonomous operation
Adaptation Speed	Speed of AI learning and improvement

The proposed equation is:

AMI = w₁·TechCap + w₂·DataQual + w₃·AutoLevel + w₄·AdaptSpeed

The article emphasizes that AI maturity is no longer optional. Operators with low AI maturity will struggle to remain competitive because modern telecom networks increasingly require:

·         real-time optimization,

·         predictive analytics,

·         intelligent orchestration,

·         autonomous decision-making.

---

4. AI-Augmented Technical Metrics

The article develops several new AI-augmented telecom metrics.

4.1 AI-Enhanced Mobile Data Quality

Traditional mobile quality metrics are extended using AI capabilities.

The new model combines:

·         network quality,

·         AI maturity,

·         predictive optimization accuracy.

This means telecom performance is no longer measured only through static indicators such as download speed or latency, but also through the network’s capability to:

·         predict congestion,

·         optimize traffic dynamically,

·         adapt in real time.

The paper demonstrates that AI-enhanced optimization can increase effective network quality far beyond traditional optimization methods.

---

4.2 AI-Driven Spectrum Optimization

Spectrum management becomes increasingly complex in 5G and future 6G systems.

The article introduces a new equation for AI-driven spectrum optimization that measures:

·         spectrum utilization efficiency,

·         interference reduction,

·         dynamic allocation speed.

AI enables:

·         real-time spectrum coordination,

·         autonomous resource allocation,

·         faster response to network load changes.

The paper highlights that spectrum optimization is becoming almost entirely dependent on AI capabilities.

---

4.3 Predictive Maintenance

Predictive maintenance is identified as one of the highest-value AI applications in telecommunications.

The proposed model evaluates:

·         prediction accuracy,

·         early fault detection,

·         downtime reduction,

·         false positive rate.

Instead of reacting to failures after they occur, AI systems continuously analyze network data and predict equipment problems before service interruptions happen.

Key benefits include:

·         lower operational costs,

·         reduced downtime,

·         improved reliability,

·         optimized maintenance scheduling.

The article shows that highly mature AI systems can achieve predictive maintenance scores close to theoretical maximum performance.

---

4.4 Autonomous Network Optimization

The paper identifies autonomous networks as the future direction of telecom infrastructure.

A new metric called QoAutoNet measures:

·         percentage of autonomous decisions,

·         optimization response time,

·         parameter optimization effectiveness,

·         self-healing capability.

The article explains that future telecom systems will increasingly operate as self-optimizing networks capable of:

·         detecting anomalies,

·         correcting failures automatically,

·         adapting parameters in real time,

·         minimizing human intervention.

This represents a transition toward fully autonomous “zero-touch” network management.

---

4.5 AI-Based Energy Optimization

The article also focuses on sustainability and energy efficiency.

AI systems are used to optimize:

·         energy consumption,

·         power management,

·         traffic prediction,

·         dynamic infrastructure activation.

The proposed energy efficiency model measures:

·         improvement in energy per transmitted bit,

·         effectiveness of dynamic power management,

·         load prediction accuracy.

The paper demonstrates that AI orchestration can significantly reduce:

·         electricity usage,

·         operational expenses (OPEX),

·         environmental impact.

---

5. AI Dependency, Governance and Resilience

An important contribution of the article is that it does not present AI only as an opportunity, but also analyzes strategic risks.

Dependency Index (DI)

The Dependency Index measures how dependent an operator is on external AI platforms and vendors.

High dependency may create:

·         vendor lock-in,

·         strategic vulnerability,

·         reduced digital sovereignty,

·         operational risk.

The article recommends developing internal AI capabilities whenever possible.

---

Resilience Score (RS)

The Resilience Score measures how robust AI systems are against:

·         cyberattacks,

·         adversarial manipulation,

·         system failures,

·         data drift.

The paper stresses that AI systems must be secure, stable and fault tolerant because telecom infrastructure is critical national infrastructure.

---

Governance Score (GS)

Governance includes:

·         transparency,

·         accountability,

·         explainability,

·         regulatory compliance.

The article references:

·         ITU standards,

·         OECD frameworks,

·         IEEE recommendations,

·         EU AI Act principles.

The paper emphasizes that future telecom competitiveness will depend not only on technical capability, but also on trustworthy and ethical AI governance.

---

6. Practical Telecom Case Study

The article presents a case study involving a European telecom operator with approximately 8 million subscribers.

The operator deployed:

·         AI-based traffic prediction,

·         autonomous network optimization,

·         intelligent spectrum allocation,

·         edge AI for QoS management.

After 12 months, the operator achieved:

Result	Improvement
Coverage quality	+65% effective improvement
Network capacity	+24%
Customer complaints	−31%
OPEX reduction	−18%
Energy efficiency	Major improvement
AI investment payback	14 months

The case study demonstrates that AI can generate measurable technical and financial benefits when integrated systematically.

---

7. Main Challenges Identified in the Article

The paper identifies several major challenges for telecom operators.

Data Quality Problems

AI systems depend heavily on:

·         accurate data,

·         continuous telemetry,

·         standardized infrastructure.

Legacy telecom systems often lack sufficient monitoring capabilities.

High Implementation Complexity

Successful AI deployment requires:

·         advanced infrastructure,

·         skilled personnel,

·         data science expertise,

·         long-term investment.

Lack of Industry Standards

The article notes that:

·         AI benchmarking methodologies are still immature,

·         industry-wide validation frameworks are limited,

·         performance comparisons between operators remain difficult.

Cybersecurity and Governance Risks

AI systems may introduce:

·         cybersecurity vulnerabilities,

·         opaque decision-making,

·         dependency on external providers.

---

8. Future Outlook (2030–2040)

The article predicts that telecommunications will evolve into a fully AI-driven industry.

Future telecom networks will likely feature:

·         autonomous operation,

·         AI-native architectures,

·         edge intelligence,

·         self-healing systems,

·         predictive orchestration,

·         AI-powered sustainability optimization.

The paper also discusses future technologies such as:

·         6G systems,

·         quantum AI,

·         federated learning,

·         neuromorphic computing,

·         distributed intelligence.

Operators that fail to adopt AI strategically may lose competitiveness, while AI-mature operators could become technology leaders.

---

9. Conclusion

This article represents a significant contribution to the integration of Artificial Intelligence into telecom techno-economic analysis.

The work moves beyond theoretical discussion and provides:

·         practical mathematical equations,

·         operational methodologies,

·         implementation frameworks,

·         measurable AI indicators.

The proposed AI-augmented CTE framework enables telecom operators to:

·         objectively evaluate AI impact,

·         measure technical performance,

·         benchmark AI maturity,

·         improve resilience and governance,

·         optimize strategic investments.

The central conclusion of the paper is that AI will become the dominant technological factor shaping the telecommunications industry in the coming decades.

Infrastructure alone will no longer determine competitiveness. Instead, leadership will increasingly depend on:

·         intelligence,

·         adaptability,

·         automation,

·         resilience,

·         trustworthy AI governance.

The article therefore provides both a scientific framework and a practical roadmap for the future development of AI-driven telecommunications systems.