OmniPlan: An Adaptive Framework for Timely and Near-Optimal Network Planning Optimization

2026-06-16

AI Summary

This work addresses the challenge of network planning optimization under complex constraints, where existing approaches struggle to simultaneously achieve computational efficiency, high solution quality, and alignment with user intent. To bridge this gap, we propose OmniPlan, a novel framework that leverages large language models (LLMs) to translate natural language expressions of user intent into unified preference vectors. OmniPlan integrates a mixture-of-experts architecture that dynamically orchestrates mixed-integer programming (MIP) solvers, heuristic algorithms, and deep reinforcement learning models to generate efficient, near-optimal, and intent-aware planning decisions. Evaluated in the context of distributed machine learning task offloading, our method reduces end-to-end latency by up to 97.8% and decreases device resource consumption by 11.5%, while maintaining near-optimal solution quality.

Abstract

Network planning optimization is a fundamental problem across diverse domains, including transportation systems, communication networks, and power grids. It requires simultaneous optimization of multiple competing objectives under complex constraints. Existing network planning optimization frameworks rely on mixed integer programming (MIP) solvers, heuristics, and deep reinforcement learning (DRL) models to compute planning decisions. However, they lack effective adaptability to diverse and dynamic user intents, thus leading to the trade-off between execution time and optimality. In this paper, we propose OmniPlan, an adaptive framework that achieves both timeliness and near-optimality in network planning optimization. To achieve the adaptability lacking in existing solutions, OmniPlan employs a large language model (LLM)-based interpreter to convert heterogeneous natural-language intents into a unified and quantifiable user-preference vector. Then it employs a mixture-of-experts architecture that integrates MIP solvers, heuristics, and DRL models as specialized experts, where OmniPlan adapts to diverse intents by dynamically selecting timely and near-optimal experts. Finally, it incorporates a DRL-based expert configuration module that fine-tunes optimization objective weights to align planning decisions with user-specific preferences. We evaluate OmniPlan with a representative real-world workload, i.e., distributed machine learning (ML), where we leverage OmniPlan to offload a wide spectrum of ML inference tasks, e.g., decision trees, SVM, naive Bayes, XGBoost, and random forests, onto a network of hardware devices. Our experiments on a real-world testbed indicate that OmniPlan achieves near-optimal and low-execution-time offloading for real-world ML inference tasks, reducing latency by up to 97.8\% and network device resource consumption by up to 11.5\%.

Problem

• network planning optimization
• user intent adaptability
• execution time vs optimality trade-off
• heterogeneous intents
• near-optimality

Innovation

• Large Language Model (LLM)
• Mixture-of-Experts
• Network Planning Optimization
• Deep Reinforcement Learning (DRL)
• Adaptive Framework