Oranits: Mission Assignment and Task Offloading in Open RAN-based ITS using Metaheuristic and Deep Reinforcement Learning

2025-07-25

AI Summary

In Open RAN-enabled intelligent transportation systems, existing task offloading and mission allocation approaches neglect intricate inter-task dependencies and edge offloading costs, leading to suboptimal decisions under dynamic conditions. To address this, we propose a deep reinforcement learning framework integrating multi-agent coordination with a multi-action selection mechanism. Our method innovatively combines Chaotic Gaussian Global Adaptive Resource Optimization (CGG-ARO) with Multi-Agent Double Deep Q-Networks (MA-DDQN) to jointly optimize both single-slot and sequential decision-making. It explicitly models task dependencies and offloading overhead, thereby enhancing real-time responsiveness and system adaptability. Experimental results demonstrate that CGG-ARO improves task completion rate by 7.1% and overall utility by 7.7% over baseline methods; integrating MA-DDQN further boosts these gains to 11.0% and 12.5%, respectively—validating the proposed framework’s significant advantages in efficiency and reward maximization.

Technology Category

• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems
• Multiagent Systems: Multiagent Learning
• Intelligent Robots: Learning & Optimization for ROB

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

In this paper, we explore mission assignment and task offloading in an Open Radio Access Network (Open RAN)-based intelligent transportation system (ITS), where autonomous vehicles leverage mobile edge computing for efficient processing. Existing studies often overlook the intricate interdependencies between missions and the costs associated with offloading tasks to edge servers, leading to suboptimal decision-making. To bridge this gap, we introduce Oranits, a novel system model that explicitly accounts for mission dependencies and offloading costs while optimizing performance through vehicle cooperation. To achieve this, we propose a twofold optimization approach. First, we develop a metaheuristic-based evolutionary computing algorithm, namely the Chaotic Gaussian-based Global ARO (CGG-ARO), serving as a baseline for one-slot optimization. Second, we design an enhanced reward-based deep reinforcement learning (DRL) framework, referred to as the Multi-agent Double Deep Q-Network (MA-DDQN), that integrates both multi-agent coordination and multi-action selection mechanisms, significantly reducing mission assignment time and improving adaptability over baseline methods. Extensive simulations reveal that CGG-ARO improves the number of completed missions and overall benefit by approximately 7.1% and 7.7%, respectively. Meanwhile, MA-DDQN achieves even greater improvements of 11.0% in terms of mission completions and 12.5% in terms of the overall benefit. These results highlight the effectiveness of Oranits in enabling faster, more adaptive, and more efficient task processing in dynamic ITS environments.

Problem

• Optimizing mission assignment in Open RAN-based ITS
• Reducing task offloading costs to edge servers
• Improving decision-making with mission dependencies

Innovation

• Chaotic Gaussian-based Global ARO algorithm
• Multi-agent Double Deep Q-Network framework
• Mission dependencies and offloading costs optimization