PGU-SGP: A Pheno-Geno Unified Surrogate Genetic Programming For Real-life Container Terminal Truck Scheduling

2025-04-15

AI Summary

In dynamic and uncertain container terminal environments, truck scheduling optimization suffers from prohibitively expensive simulation-based evaluation and insufficient accuracy of surrogate models. Method: This paper proposes a surrogate genetic programming (GP) framework integrating phenotypic and genotypic features. We introduce a unified phenotypic-genotypic similarity metric and design a lightweight genotypic encoding (GC), overcoming the limitation of conventional behavior-only (phenotypic) similarity (PC). Coupled with a KNN-based surrogate model and a hybrid distance metric, our approach yields an end-to-end trainable, lightweight surrogate system. Results: Experiments demonstrate a 76% reduction in training time; under identical computational budgets, our method achieves significantly faster convergence and superior solution quality compared to standard GP and state-of-the-art (SOTA) approaches. Moreover, the surrogate model exhibits improved rank preservation and enhanced selection pressure.

Technology Category

• Search and Optimization: Sampling/Simulation-based Search
• Planning, Routing, and Scheduling: Scheduling under Uncertainty
• Reasoning under Uncertainty: Stochastic Optimization

Application Category

• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Economics, Online Markets and Human Computation: Trust and reliance of crowd workers and data experts on GenAI
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Data-driven genetic programming (GP) has proven highly effective in solving combinatorial optimization problems under dynamic and uncertain environments. A central challenge lies in fast fitness evaluations on large training datasets, especially for complex real-world problems involving time-consuming simulations. Surrogate models, like phenotypic characterization (PC)-based K-nearest neighbors (KNN), have been applied to reduce computational cost. However, the PC-based similarity measure is confined to behavioral characteristics, overlooking genotypic differences, which can limit surrogate quality and impair performance. To address these issues, this paper proposes a pheno-geno unified surrogate GP algorithm, PGU-SGP, integrating phenotypic and genotypic characterization (GC) to enhance surrogate sample selection and fitness prediction. A novel unified similarity metric combining PC and GC distances is proposed, along with an effective and efficient GC representation. Experimental results of a real-life vehicle scheduling problem demonstrate that PGU-SGP reduces training time by approximately 76% while achieving comparable performance to traditional GP. With the same training time, PGU-SGP significantly outperforms traditional GP and the state-of-the-art algorithm on most datasets. Additionally, PGU-SGP shows faster convergence and improved surrogate quality by maintaining accurate fitness rankings and appropriate selection pressure, further validating its effectiveness.

Problem

• Reducing computational cost in genetic programming for optimization
• Integrating phenotypic and genotypic data for better surrogate models
• Improving efficiency in real-life container terminal truck scheduling

Innovation

• Combines phenotypic and genotypic characterization
• Proposes unified similarity metric PC-GC
• Reduces training time by 76% effectively