Integrating control-theoretic predictive deep learning for resource-efficient computing systems

Machidon, Alina Luminita (avtor), Pejović, Veljko (avtor)

Deep learning (DL) powers numerous applications on ubiquitous edge devices, but its high resource demands pose a challenge. Approximate computing is often proposed to alleviate this, yet such calculation usually suffers from a fixed level of accuracy loss. We propose a novel control-theoretic approach for predictive DL inference on resource constrained devices. Our system dynamically adjusts approximation levels based on a trade-off between resource utilisation and accuracy, considering future demands. Extensive experiments across diverse domains - human activity recognition, acoustic scene profiling, and computer vision - with various neural network architectures and approximation techniques, demonstrate that our approach achieves up to 50% energy savings while maintaining the desired inference accuracy and incurring minimal runtime overhead. Furthermore, we showcase our method in a real-world deployment on low-power edge devices and confirm its superiority over current state-of-the-art solutions.

• Jezik: Angleški jezik
• Ključne besede: control systems, model predictive control, deep learning, resource efficiency, context adaptivity, approximate computing
• Vrsta gradiva: Članek v reviji
• Tipologija: 1.01 - Izvirni znanstveni članek
• Organizacija: FRI - Fakulteta za računalništvo in informatiko
• Status publikacije: Objavljeno
• Različica publikacije: Objavljena publikacija
• Leto izida: 2025
• Št. strani: Str. 921–943
• Številčenje: Vol. 63, iss. 3
• PID: 20.500.12556/RUL-169426
• UDK: 004.85
• ISSN pri članku: 0925-9902
• DOI: 10.1007/s10844-025-00919-7
• COBISS.SI-ID: 228017923
• Datum objave v RUL: 28.05.2025

Gradivo je del revije

• Naslov: Journal of intelligent information systems
• Založnik: Springer Nature
• ISSN: 0925-9902
• COBISS.SI-ID: 15633157

Licence

• Licenca: CC BY 4.0, Creative Commons Priznanje avtorstva 4.0 Mednarodna
• Povezava: http://creativecommons.org/licenses/by/4.0/deed.sl
• Opis: To je standardna licenca Creative Commons, ki daje uporabnikom največ možnosti za nadaljnjo uporabo dela, pri čemer morajo navesti avtorja.

Sekundarni jezik

• Jezik: Slovenski jezik
• Ključne besede: nadzorni sistemi, napovedni nadzor modela, globoko učenje, učinkovitost virov, prilagodljivost kontekstu, približno računalništvo