Digital twins pinpoint efficiency factors, enhance system design, and monitor degradation. They also assess soiling losses and optimize inverter performance

1.

ELECTRICITY SERVICE
CLASSIFICATION
Done:
Student of Group A31TT1
Ihar Lakidon
Minsk 2026

2.

Abstract
• Renewable systems are becoming more complex.
• Digital twins offer real-time virtual replicas.
• The review uses AI, ML, and text mining.
• Benefits and limitations are mapped across five energy sources.

3.

Introduction
Why the Transition
Matters
Climate pressure, rising demand, renewable
integration, smarter energy systems, digital
twins, variability, scale, grid complexity.

4.

The Digital Twin Idea
Physical
Virtual
Connection
Asset, sensor data,
Dynamic model,
Bidirectional flow,
operational reality.
simulation,
feedback, control.
prediction.

5.

IoT
Simulation
Evolution
Real-time connectivity
and sensors
CAD and physics-based
models
From CAD to AI
1960s–1990s: simulation and CAD
2000s: product lifecycle management
2010s: IoT and connectivity
2020s: AI integration and learning
PLM
AI
Product lifecycle
coordination
Adaptive learning and
insights
The concept moves from static models to real-time, intelligent systems.

6.

Wind Energy
• Predict unknown parameters and correct inaccurate measurements.
• Optimise blade pitch, yaw, and torque.
• Support condition-based maintenance and fault detection.
• Improve farm-level coordination and wake effects.

7.

Solar Energy
Digital twins, efficiency, system
design, degradation, soiling losses,
optimise, inverter performance.
Performance ratio
Soiling loss
Degradation tracking

8.

Geothermal + Hydroelectric
Geothermal
Hydroelectric
Drilling simulation, reservoir
System dynamics, water release,
modelling, cost reduction.
fatigue and sediment management.

9.

Biomass + Method
Biomass digital twins enhance visibility,
configuration, supply chains, and emissions
control. The study uses systematic review
and text mining.

10.

Conclusions
• Digital twins are transformative, but limitations remain.
• Key gaps: data quality, validation, computation, legacy integration.
• The roadmap points to better sensing, modelling, and collaboration.
• Future energy digitalisation depends on sustained research and adoption.