Time-Dependent Path Selection and Online Learning for Efficient DAG Task Offloading in In-Network Computing

Weiwen Zhang

doi:10.1109/JIOT.2026.3662691

Time-Dependent Path Selection and Online Learning for Efficient DAG Task Offloading in In-Network Computing

2026-02-09

0

PRE

AI

DOI：10.1109/JIOT.2026.3662691

Original

Original request for help

Save

Abstract

En 中文

In this article, we present the joint optimization of computation path selection and workload allocation for directed acyclic graph (DAG) tasks in edge computing networks. Existing works primarily focus on end-to-end latency and are often restricted to simple task chains, neglecting critical factors such as server operational costs and the dynamics of the arrival of tasks. To bridge this gap, we formulate the online scheduling problem as a mixed integer program to minimize server operational costs and latency. We then decompose this problem into a minimum-latency path selection subproblem and a task scheduling subproblem formulated as a Markov decision process (MDP). Our solution consists of a latency-aware transmission scheduling (LATS) algorithm and a novel online scheduler based on proximal policy optimization (PPO). Furthermore, we leverage graph neural networks (GNNs) and long short-term memory (LSTM) networks to encode the system state, thereby significantly improving the agent’s perception of the complex environment. Finally, extensive simulation results demonstrate that the proposed algorithm shows good adaptability and outperforms the state-of-the-art algorithms.

Keywords:

Directed acyclic graph (DAG) task offloading

in-network computing

path selection

reinforcement learning

Time-Dependent Path Selection and Online Learning for Efficient DAG Task Offloading in In-Network Computing

Abstract

Journal

Organization