WCDT: Systematic WCET Optimization for Decision Tree Implementations

2025-01-29

AI Summary

Real-time deployment of decision trees on resource-constrained embedded systems requires verifiable worst-case execution time (WCET) guarantees, yet existing implementations suffer from excessive WCET and lack provably optimal optimization mechanisms. Method: We propose the first linear execution-time surrogate model based on path length and branch count; design a WCET-driven structural remapping strategy; and develop a static-analysis-guided, path-level optimization algorithm. Contribution/Results: Our approach yields the first provably optimal WCET realization for decision trees. Under strict static analysis constraints, experimental evaluation demonstrates up to a 17% reduction in WCET—significantly enhancing real-time safety and feasibility of embedded deployment.

Technology Category

• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems
• Constraint Satisfaction and Optimization: Satisfiability Modulo Theories
• Reasoning under Uncertainty: Stochastic Optimization

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Experiences and lessons learnt from Web-based algorithms and system deployments
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Responsible Web: Human-perceived consequences of algorithmic deployment on the web

Abstract

Machine-learning models are increasingly deployed on resource-constrained embedded systems with strict timing constraints. In such scenarios, the worst-case execution time (WCET) of the models is required to ensure safe operation. Specifically, decision trees are a prominent class of machine-learning models and the main building blocks of tree-based ensemble models (e.g., random forests), which are commonly employed in resource-constrained embedded systems. In this paper, we develop a systematic approach for WCET optimization of decision tree implementations. To this end, we introduce a linear surrogate model that estimates the execution time of individual paths through a decision tree based on the path's length and the number of taken branches. We provide an optimization algorithm that constructively builds a WCET-optimal implementation of a given decision tree with respect to this surrogate model. We experimentally evaluate both the surrogate model and the WCET-optimization algorithm. The evaluation shows that the optimization algorithm improves analytically determined WCET by up to $17%$ compared to an unoptimized implementation.

Problem

• Embedded Systems
• Decision Trees
• Worst-Case Execution Time (WCET)

Innovation

• WCDT
• WCET Optimization
• Embedded Systems