Auctioning Future Services in Edge Networks with Moving Vehicles: N-Step Look-Ahead Contracts for Sustainable Resource Provision

TL;DR

This work proposes a look-ahead contract-based auction framework that establishes N-step service contracts between edge servers (ESs) using demand forecasts and modified double auctions and improves time efficiency, energy use, and social welfare compared with existing baselines.

Abstract

Timely resource allocation in edge-assisted vehicular networks is essential for compute-intensive services such as autonomous driving and navigation. However, vehicle mobility leads to spatio-temporal unpredictability of resource demands, while real-time double auctions incur significant latency. To address these challenges, we propose a look-ahead contract-based auction framework that shifts decision-making from runtime to planning time. Our approach establishes N-step service contracts between edge servers (ESs) using demand forecasts and modified double auctions. The system operates in two stages: first, an LSTM-based prediction module forecasts multi-slot resource needs and determines ES roles (buyer or seller), after which a pre-double auction generates contracts specifying resource quantities, prices, and penalties. Second, these contracts are enforced in real time without rerunning auctions. The framework incorporates energy costs, transmission overhead, and contract breach risks into utility models, ensuring truthful, rational, and energy-efficient trading. Experiments on real-world (UTD19) and synthetic traces demonstrate that our method improves time efficiency, energy use, and social welfare compared with existing baselines.

Figures (8)

• Figure 1: Framework of our consideration (the upper box), the diagram of service trading via $N$-step ahead for green contracts (the middle box), where the numbers 3, 5, 7, and 12 indicate the abstract distances between ESs, and an example timeline (the bottom box).
• Figure 2: Example of role switching between two ESs over different time frames, where the label $\text{In}$ denotes the inherent resource, $\text{Est}$ denotes the estimated resource usage, and $\text{S,{Est-}}$ and $\text{B,{Est-}}$ denote the demand and the valuable resource, respectively (this symbol will be explained in following subsection).
• Figure 3: Schematic diagram of LSTM-based resource usage prediction and role determination (the gray box), the pre-double auction process (the green box), and contract implementation (the blue box).
• Figure 4: Location and cluster of the detectors.
• Figure 5: Predicted resource usage vs. actual data.

Theorems & Definitions (32)

• Definition 1: Individual Rationality in Our Market
• Remark 1
• Definition 2: Budget Balance
• Definition 3: Truthfulness or Incentive Compatibility
• Theorem 1
• Lemma 1.1
• Lemma 1.2
• Lemma 1.3
• Theorem 2
• Lemma 2.1