Loading [MathJax]/extensions/MathMenu.js
FluE: A Resource Fluid Equilibrium Strategy for AIGC Within Evolving Computing Power Networks | IEEE Conference Publication | IEEE Xplore

FluE: A Resource Fluid Equilibrium Strategy for AIGC Within Evolving Computing Power Networks


Abstract:

The presence of Artificial Intelligence Generated Content (AIGC) has garnered widespread interest. AIGC enables content creation by analyzing big data, leveraging the cap...Show More

Abstract:

The presence of Artificial Intelligence Generated Content (AIGC) has garnered widespread interest. AIGC enables content creation by analyzing big data, leveraging the capabilities of extensive AI models, and substantial AI computing. Computing power networks (CPNs) represent an excellent approach for offering pervasive AI computing resources to AIGC. However, these characteristics have posed unprecedented challenges to the CPNs helped AIGC, including the uncertainty of prompts’ information value, the inability to model the continuity of computing resources, and the incapacity to represent complex multi-dimensional spaces. In this paper, we propose a computing resources equilibrium strategy based on the fluid model for AIGC helped by CPNs, namely FluE. This mechanism obtains information entropy by constructing an AIGC prompt tree to measure the information value of AIGC prompts. In addition, we model the continuity of computing resources by the fluid model. A fluid-stopping equilibrium strategy is formulated to obtain the average fluid level of computing resources based on the Laplace-Stieltjes transform. To solve the equilibrium strategy, we develop a diffusion-based algorithm for FluE to adjust the fluid policy dynamically to maximize resource rewards. Finally, the evaluations demonstrate improvements in average social welfare.
Date of Conference: 08-12 December 2024
Date Added to IEEE Xplore: 11 March 2025
ISBN Information:

ISSN Information:

Conference Location: Cape Town, South Africa

Funding Agency:


I. Introduction

Artificial intelligence-generated content (AIGC) has recently represented a groundbreaking method for generating, altering, and refining large amounts of data, marking a significant advancement in content creation and processing fields [1]. AIGC makes it feasible to create content by learning from big data, relying heavily on large-scale AI models [2]. In addition, these AI models contain billions to trillions of parameters for training, resulting in an exponential growth in AI computing resources requirements [3]. ChatGPT’s frequent downtime caused by a recent surge in user traffic reflects ChatGPT’s high reliance on computing resources.

Contact IEEE to Subscribe

References

References is not available for this document.