Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Structural Knowledge-Driven Meta-Learning for Task Offloading in Vehicular Networks with Integrated Communications, Sensing and Computing

Ruijin Sun, Yao Wen, Nan Cheng, Wei Wan, Rong Chai, Yilong Hui

TL;DR

This paper investigates an I-CSC-based task offloading problem to reduce the cost caused by resource consumption while guaranteeing the latency of each task, and proposes a creative structural knowledge-driven meta-learning (SKDML) method, involving both the model-based AM algorithm and neural networks.

Abstract

Task offloading is a potential solution to satisfy the strict requirements of computation-intensive and latency-sensitive vehicular applications due to the limited onboard computing resources. However, the overwhelming upload traffic may lead to unacceptable uploading time. To tackle this issue, for tasks taking environmental data as input, the data perceived by roadside units (RSU) equipped with several sensors can be directly exploited for computation, resulting in a novel task offloading paradigm with integrated communications, sensing and computing (I-CSC). With this paradigm, vehicles can select to upload their sensed data to RSUs or transmit computing instructions to RSUs during the offloading. By optimizing the computation mode and network resources, in this paper, we investigate an I-CSC-based task offloading problem to reduce the cost caused by resource consumption while guaranteeing the latency of each task. Although this non-convex problem can be handled by the alternating minimization (AM) algorithm that alternatively minimizes the divided four sub-problems, it leads to high computational complexity and local optimal solution. To tackle this challenge, we propose a creative structural knowledge-driven meta-learning (SKDML) method, involving both the model-based AM algorithm and neural networks. Specifically, borrowing the iterative structure of the AM algorithm, also referred to as structural knowledge, the proposed SKDML adopts long short-term memory (LSTM) network-based meta-learning to learn an adaptive optimizer for updating variables in each sub-problem, instead of the handcrafted counterpart in the AM algorithm.

Structural Knowledge-Driven Meta-Learning for Task Offloading in Vehicular Networks with Integrated Communications, Sensing and Computing

TL;DR

This paper investigates an I-CSC-based task offloading problem to reduce the cost caused by resource consumption while guaranteeing the latency of each task, and proposes a creative structural knowledge-driven meta-learning (SKDML) method, involving both the model-based AM algorithm and neural networks.

Abstract

Task offloading is a potential solution to satisfy the strict requirements of computation-intensive and latency-sensitive vehicular applications due to the limited onboard computing resources. However, the overwhelming upload traffic may lead to unacceptable uploading time. To tackle this issue, for tasks taking environmental data as input, the data perceived by roadside units (RSU) equipped with several sensors can be directly exploited for computation, resulting in a novel task offloading paradigm with integrated communications, sensing and computing (I-CSC). With this paradigm, vehicles can select to upload their sensed data to RSUs or transmit computing instructions to RSUs during the offloading. By optimizing the computation mode and network resources, in this paper, we investigate an I-CSC-based task offloading problem to reduce the cost caused by resource consumption while guaranteeing the latency of each task. Although this non-convex problem can be handled by the alternating minimization (AM) algorithm that alternatively minimizes the divided four sub-problems, it leads to high computational complexity and local optimal solution. To tackle this challenge, we propose a creative structural knowledge-driven meta-learning (SKDML) method, involving both the model-based AM algorithm and neural networks. Specifically, borrowing the iterative structure of the AM algorithm, also referred to as structural knowledge, the proposed SKDML adopts long short-term memory (LSTM) network-based meta-learning to learn an adaptive optimizer for updating variables in each sub-problem, instead of the handcrafted counterpart in the AM algorithm.
Paper Structure (25 sections, 46 equations, 11 figures, 2 tables, 2 algorithms)

This paper contains 25 sections, 46 equations, 11 figures, 2 tables, 2 algorithms.

Table of Contents

  1. Introduction
  2. Motivation and Contribution
  3. Related Works
  4. System Model
  5. Offloading Framework with Integrated Sensing, Computation and Communication for Vehicular Networks
  6. Local Computation Mode
  7. DataT-based MEC Mode
  8. InstrT-based MEC Mode
  9. Problem Formulation
  10. Model-based AM Algorithm for Task Offloading with I-CSC
  11. Transmission Mode Selection
  12. Task Offloading Ratio Decision
  13. Transmission Power Allocation
  14. Bandwidth and Computing Resource Allocation
  15. Overall Alternating Minimization Algorithm for Computation Offloading
  16. ...and 10 more sections

Figures (11)

  • Figure 1: Vehicle-RSU cooperation architecture.
  • Figure 2: The latency of the considered three computation modes.
  • Figure 3: The relationship of four subproblems in the AM algorithm.
  • Figure 4: The overall structure of SKDML algorithm. The algorithm architecture is divided into inner and outer loops. In the inner loop (blue box), the four LSTMs update the variables of the subproblem separately without updating the network parameters. In the outer loop (green box), the network parameters of the four LSTMs are updated using global loss.
  • Figure 5: Convergence of the three algorithms
  • ...and 6 more figures