Network Intent Decomposition and Optimization for Energy-Aware Radio Access Network

TL;DR

This work tackles the challenge of energy consumption in dense 6G RAN by automating network intent decomposition and optimization. It introduces a framework that represents intents with a 3GPP template, models the network ontology via KAOS, and decomposes intents to network objectives using a Softgoal Interdependency Graph, followed by a DQN-assisted optimizer to select energy-saving actions. The key contributions are (i) a YAML/JSON-based intent representation pipeline and KAOS-based ontology, (ii) a SIG-based decomposition method with conflict analysis to map intents to $E_i$, $R_{i,j}$ and $T_{i,j}$ and energy-saving operations, and (iii) a DQN-driven optimization scheme demonstrating performance gains in energy, throughput, and latency. The results indicate significant improvements in decomposition time and objective performance, highlighting the framework’s potential for scalable, automated energy-aware RAN management in real-world 6G deployments.

Abstract

With recent advancements in the sixth generation (6G) communication technologies, more vertical industries have encountered diverse network services. How to reduce energy consumption is critical to meet the expectation of the quality of diverse network services. In particular, the number of base stations in 6G is huge with coupled adjustable network parameters. However, the problem is complex with multiple network objectives and parameters. Network intents are difficult to map to individual network elements and require enhanced automation capabilities. In this paper, we present a network intent decomposition and optimization mechanism in an energy-aware radio access network scenario. By characterizing the intent ontology with a standard template, we present a generic network intent representation framework. Then we propose a novel intent modeling method using Knowledge Acquisition in automated Specification language, which can model the network ontology. To clarify the number and types of network objectives and energy-saving operations, we develop a Softgoal Interdependency Graph-based network intent decomposition model, and thus, a network intent decomposition algorithm is presented. Simulation results demonstrate that the proposed algorithm outperforms without conflict analysis in intent decomposition time. Moreover, we design a deep Q-network-assisted intent optimization scheme to validate the performance gain.

Figures (10)

• Figure 1: The scenario of energy-aware radio access network.
• Figure 2: Example of network intent in YAML format.
• Figure 3: Example of intent transformation from YAML to JSON format.
• Figure 4: A modeling example of network intent using Knowledge Acquisition in automated Specification language.
• Figure 5: Example of Softgoal Interdependency Graph decomposition in JSON format.