Integrated Sensing, Communication, and Computing: An Information-oriented Resource Transaction Mechanism

TL;DR

The paper tackles efficient management of time-space-frequency-computing ($TSFC$) resources for information acquisition in IoAV. It introduces Integrated Sensing, Communication, and Computing (ISCC) with a decoupled resource architecture (Twin Resource Pool, TRP) and a market-like Information-oriented Resource Trading Platform (IRTP) to convert resource allocation into an information-substitution problem. It further embeds the IoAV employment topology into a Graph Neural Network framework with asynchronous multi-worker reinforcement learning (A2GNN) to drive dynamic, convergent optimization of information gain and resource use. The approach delivers scalable, information-centric resource management for IoAV by jointly optimizing sensing, communication, and computing under a unified TSFC framework, with practical implications for real-time decision-making in connected autonomous vehicles.

Abstract

Information acquisition from target perception represents the key enabling technology of the Internet of Automatic Vehicles (IoAV), which is essential for the decision-making and control operation of connected automatic vehicles (CAVs). Exploring target information involves multiple operations on data, e.g., wireless sensing (for data acquisition), communication (for data transmission), and computing (for data analysis), which all rely on the consumption of time-space-frequency-computing (TSFC) multi-domain resources. Due to the coupled resource sharing of sensing, communication, and computing procedures, the resource management of information-oriented IoAV is commonly formulated as a non-convex NP-hard problem. In this article, further combining the integrated sensing and communication (ISAC) and computing, we introduce the integrated sensing, communication, and computing (ISCC), wherein the TSFC resources are decoupled from the specific processes and shared universally among sensing, communication, and computing processes. Furthermore, the information-oriented resource trading platform (IRTP) is established, which transforms the problem of ISCC resource management into a resource-information substitution model. Finally, we embed the employment topology structure in IoAV into neural network architecture, taking advantage of the graph neural network (GNN) and multi-worker reinforcement learning, and propose the dynamic resource management strategy based on the asynchronous advantage GNN (A2GNN) algorithm, which can achieve the convergence both of information gain maximization and resource consumption minimization, realizing efficient information-oriented resource management.

Figures (4)

• Figure 1: The active wireless sensing and passive wireless sensing.
• Figure 2: The information-oriented ISCC network model. CAVs with information requirements cooperatively implement wireless sensing based on large-scale MIMO, including active wireless sensing and passive wireless sensing. The original sensing data, which includes active wireless sensing data and passive wireless sensing data, can be calculated locally or unloaded to the RSUs. Finally, the CAVs pick up interested information from the mixed information.
• Figure 3: The construction of twin resource pool and the information-oriented resource trading platform. TSFC multi-domain resources are decoupled from the specific procedures in ISCC, and converted to three discrete two-dimensional resources. The employment relationship is transformed into that the employer purchases information from the employee, and the employee uses his own resources to produce information for the employer. Middlemen "distributor" and "purchaser" optimize the transaction from the perspective of information and resources respectively.
• Figure 4: The resource transaction strategy based on graph model.