Heterogeneous Distributed Computing-Based AI Video Generation: Real-Time Load Balancing and Intelligent Scheduling in New Media Art

Guardado en:
Bibliografiske detaljer
Udgivet i:EAI Endorsed Transactions on Scalable Information Systems vol. 12, no. 5 (Oct 2025)
Hovedforfatter: Fu, Qian
Udgivet:
European Alliance for Innovation (EAI)
Fag:
Online adgang:Citation/Abstract
Full Text - PDF
Tags: Tilføj Tag
Ingen Tags, Vær først til at tagge denne postø!

MARC

LEADER 00000nab a2200000uu 4500
001 3278345404
003 UK-CbPIL
022 |a 2032-9407 
024 7 |a 10.4108/eetsis.10614  |2 doi 
035 |a 3278345404 
045 2 |b d20251001  |b d20251031 
100 1 |a Fu, Qian 
245 1 |a Heterogeneous Distributed Computing-Based AI Video Generation: Real-Time Load Balancing and Intelligent Scheduling in New Media Art 
260 |b European Alliance for Innovation (EAI)  |c Oct 2025 
513 |a Journal Article 
520 3 |a INTRODUCTION: The rapid proliferation of Generative AI (AIGC) in new media art has intensified the need for real-time, distributed video generation with stable performance and low latency. Conventional centralized rendering and static scheduling frameworks often encounter load imbalance and communication bottlenecks in heterogeneous environments, resulting in degraded visual coherence and responsiveness. To address these challenges, this study develops a unified and adaptive distributed framework, termed H-RLSCO (Heterogeneity-aware Reinforcement Learning and Scheduling Co-Optimization), designed to enhance both computational efficiency and artistic consistency in large-scale AI video generation. The framework integrates three complementary modules: a Heterogeneity Perception Module (HPM) for node profiling and adaptive task partitioning, a Reinforcement Learning Scheduling Controller (RLSC) for dynamic task migration, and a Generation-Scheduling Co-Optimization (GSCO) mechanism that incorporates content-complexity feedback into scheduling decisions to maintain multimodal synchronization. Experiments on the ArtScene-4K and StageSyn-Real datasets demonstrate that H-RLSCO reduces average latency by 14.4% and decreases Fréchet Video Distance by approximately 12.5% compared with the RL-Scheduler baseline, while limiting performance fluctuation to within 3% under multi-noise conditions (p < 0.01). These gains remain consistent across varying bandwidths and node capabilities on a five-node heterogeneous cluster, confirming robust real-time behavior and balanced utilization. Nevertheless, the scalability of H-RLSCO remains constrained when applied to large-scale node clusters, suggesting future work should explore multi-agent reinforcement learning and lightweight diffusion-Transformer architectures to enhance efficiency and expand applicability. 
653 |a Scheduling 
653 |a Synchronism 
653 |a Multiagent systems 
653 |a Modules 
653 |a Real time 
653 |a Load balancing 
653 |a Distributed processing 
653 |a Heterogeneity 
653 |a Media art 
653 |a Optimization 
653 |a Generative artificial intelligence 
653 |a Nodes 
773 0 |t EAI Endorsed Transactions on Scalable Information Systems  |g vol. 12, no. 5 (Oct 2025) 
786 0 |d ProQuest  |t Advanced Technologies & Aerospace Database 
856 4 1 |3 Citation/Abstract  |u https://www.proquest.com/docview/3278345404/abstract/embedded/6A8EOT78XXH2IG52?source=fedsrch 
856 4 0 |3 Full Text - PDF  |u https://www.proquest.com/docview/3278345404/fulltextPDF/embedded/6A8EOT78XXH2IG52?source=fedsrch