The In-Network Computing (COIN) paradigm is a promising solution that leverages unused network resources to perform some tasks to meet up with computation-demanding applications, such as metaverse. In this vein, we consider the metaverse partial computation offloading problem for multiple subtasks in a COIN environment to minimise energy consumption and delay while dynamically adjusting the offloading policy based on the changing computation resources status. We prove that the problem is NP and thus transformed it into two subproblems: task splitting problem (TSP) on the user side and task offloading problem (TOP) on the COIN side. We modelled the TSP as an ordinal potential game (OPG) and proposed a decentralised algorithm to obtain its Nash Equilibrium (NE). Then, we model the TOP as Markov Decision Process (MDP) proposed double deep Q-network (DDQN) to solve for the optimal offloading policy. Unlike the conventional DDQN algorithm, where intelligent agents sample offloading decisions randomly within a certain probability, our COIN agent explores the NE of the TSP and the deep neural network. Finally, simulation results show that our proposed model approach allows the COIN agent to update its policies and make more informed decisions, leading to improved performance over time compared to the traditional baseline.

翻译：网络内计算（COIN）范式作为一种极具前景的解决方案，通过利用闲置网络资源执行部分任务，以满足元宇宙等高计算需求应用。针对此背景，我们研究了COIN环境中多子任务的元宇宙部分计算卸载问题，目标是在动态调整计算资源状态的基础上，最小化能耗与延迟。我们证明该问题为NP难问题，并将其转化为两个子问题：用户侧的任务分割问题（TSP）和COIN侧的任务卸载问题（TOP）。将TSP建模为序数势博弈（OPG），并提出一种去中心化算法求解其纳什均衡（NE）。随后，将TOP建模为马尔可夫决策过程（MDP），采用双深度Q网络（DDQN）求解最优卸载策略。与智能体以固定概率随机采样卸载决策的传统DDQN算法不同，我们的COIN智能体协同探索TSP的NE与深度神经网络。仿真结果表明，所提模型方法使COIN智能体能够动态更新策略并做出更优决策，相较于传统基线模型，系统性能随时间推移持续提升。