A RankNet-Inspired Surrogate-Assisted Hybrid Metaheuristic for Expensive Coverage Optimization

2025-01-13

AI Summary

This paper addresses the expensive coverage optimization problem with high-dimensional mixed variables—e.g., sensor or camera placement—aiming to maximize target-point coverage under local demand requirements and complex constraints while minimizing cost. To tackle the fitting difficulty of conventional surrogate models in discontinuous solution spaces, we propose a RankNet-driven pairwise ranking surrogate model. Furthermore, we integrate a surrogate-assisted Estimation of Distribution Algorithm (EDA) for local probabilistic modeling with a diversity-driven dynamic population switching mechanism to achieve adaptive balance between exploration and exploitation. Evaluated on large-scale instances with up to 300 dimensions and over 1,800 targets, our method achieves an average performance improvement of 56.5% over state-of-the-art approaches, while maintaining acceptable computational overhead.

Technology Category

• Search and Optimization: Mixed Discrete/Continuous Search
• Constraint Satisfaction and Optimization: Mixed Discrete/Continuous Optimization
• Planning, Routing, and Scheduling: Mixed Discrete/Continuous Planning

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking

Abstract

Coverage optimization generally involves deploying a set of facilities (e.g., sensors) to best satisfy the demands of specified points, with wide applications in fields such as location science and sensor networks. In practical applications, coverage optimization focuses on target coverage, which is typically formulated as Mixed-Variable Optimization Problems (MVOPs) due to complex real-world constraints. Meanwhile, high-fidelity discretization and visibility analysis may bring additional calculations, which significantly increases the computational cost. These factors pose significant challenges for fitness evaluations (FEs) in canonical Evolutionary Algorithms (EAs), and evolve the coverage problem into an Expensive Mixed-Variable Optimization Problem (EMVOP). To address these issues, we propose the RankNet-Inspired Surrogate-assisted Hybrid Metaheuristic (RI-SHM), an extension of our previous work. RI-SHM integrates three key components: (1) a RankNet-based pairwise global surrogate that innovatively predicts rankings between pairs of individuals, bypassing the challenges of fitness estimation in discontinuous solution space; (2) a surrogate-assisted local Estimation of Distribution Algorithm (EDA) that enhances local exploitation and helps escape from local optima; and (3) a fitness diversity-driven switching strategy that dynamically balances exploration and exploitation. Experiments demonstrate that our algorithm can effectively handle large-scale coverage optimization tasks of up to 300 dimensions and more than 1,800 targets within desirable runtime. Compared to state-of-the-art algorithms for EMVOPs, RI-SHM consistently outperforms them by up to 56.5$%$ across all tested instances.

Problem

• Optimization
• Sensor Networks
• Mixed-Variable Problems

Innovation

• RankNet-inspired Algorithm
• Heuristic-assisted Optimization
• Dynamic Strategy Adjustment