Content Accuracy and Quality Aware Resource Allocation Based on LP-Guided DRL for ISAC-Driven AIGC Networks

TL;DR

This work tackles ISAC-enabled AIGC networks where sensing accuracy and AIGC generation errors jointly determine user QoE. It introduces CAQA, a content accuracy and quality aware QoE metric that multiplies sensing+generation accuracy by the delivered image quality, and formulates the CAQA-AIGC optimization to maximize AvgCAQA under sensing, computing, and communication constraints. To solve the NP-hard problem with low complexity, the authors propose LP-guided DRL-F, which decomposes into SGenRA solved by DRL-F with an action filter and ComRA solved optimally by an LP-based RCE algorithm, achieving substantial performance gains over CGQ-only and diffusion-model baselines. The results demonstrate improved AvgCAQA, faster convergence, and robust performance under varying user counts, energy budgets, and server capacities, highlighting the practical benefit of incorporating content accuracy into resource allocation for ISAC-driven AIGC services.

Abstract

Integrated sensing and communication (ISAC) can enhance artificial intelligence-generated content (AIGC) networks by providing efficient sensing and transmission. Existing AIGC services usually assume that the accuracy of the generated content can be ensured, given accurate input data and prompt, thus only the content generation quality (CGQ) is concerned. However, it is not applicable in ISAC-based AIGC networks, where content generation is based on inaccurate sensed data. Moreover, the AIGC model itself introduces generation errors, which depend on the number of generating steps (i.e., computing resources). To assess the quality of experience of ISAC-based AIGC services, we propose a content accuracy and quality aware service assessment metric (CAQA). Since allocating more resources to sensing and generating improves content accuracy but may reduce communication quality, and vice versa, this sensing-generating (computing)-communication three-dimensional resource tradeoff must be optimized to maximize the average CAQA (AvgCAQA) across all users with AIGC (CAQA-AIGC). This problem is NP-hard, with a large solution space that grows exponentially with the number of users. To solve the CAQA-AIGC problem with low complexity, a linear programming (LP) guided deep reinforcement learning (DRL) algorithm with an action filter (LPDRL-F) is proposed. Through the LP-guided approach and the action filter, LPDRL-F can transform the original three-dimensional solution space to two dimensions, reducing complexity while improving the learning performance of DRL. Simulations show that compared to existing DRL and generative diffusion model (GDM) algorithms without LP, LPDRL-F converges faster and finds better resource allocation solutions, improving AvgCAQA by more than 10%. With LPDRL-F, CAQA-AIGC can achieve an improvement in AvgCAQA of more than 50% compared to existing schemes focusing solely on CGQ.

Figures (14)

• Figure 1: An ISAC-based AIGC network.
• Figure 2: Time-frequency diagram of ISAC waveforms.
• Figure 3: Service Process of ISAC-Based AIGC.
• Figure 4: Structure of the LP-guided DRL-F Algorithm.
• Figure 5: Convergence performance.