concept

Discrete Event Simulation

Also known as: Discrete Event Simulations

Facts (25)

Sources

Leveraging Knowledge Graphs and LLM Reasoning to Identify ... arxiv.org arXiv Jul 23, 2025 25 facts

claimThe initial design of a comprehensive Knowledge Graph schema tailored to specific Discrete Event Simulation (DES) model outputs requires significant upfront domain expertise and engineering effort.

procedureThe proposed framework for warehouse planning assistance structures complex relational data generated by Discrete Event Simulation using a Knowledge Graph, allowing for the explicit capture and querying of intricate dependencies and flows within the warehouse system.

claimIn the Logistics 4.0 landscape, Discrete Event Simulation is increasingly recognized as a fundamental component of Digital Twins.

claimThe proposed pipeline using step-wise thinking demonstrates significantly higher pass rates for operational questions compared to traditional baseline methods, achieving near-perfect performance in identifying key inefficiencies in warehouse Discrete Event Simulation (DES) setups.

referenceThe proposed framework utilizes a custom Knowledge Graph (KG) schema where resources such as suppliers, workers, AGVs, forklifts, and storage are represented as nodes, while the movement of packages between these resources is represented as edges. Operational data, including timestamps, is incorporated as features of these nodes and edges, with the KG constructed from output logs generated by a Discrete Event Simulation (DES) model.

claimDiscrete Event Simulation runs produce extensive event logs, time-series data on resource states, and detailed queue statistics, which capture micro-level system behavior but are difficult to analyze due to their voluminous and granular nature.

claimDiscrete Event Simulation (DES) is a technique used for modeling systems, allowing stakeholders to evaluate performance, test design alternatives, and understand system dynamics before implementation.

claimThe framework proposed in 'Leveraging Knowledge Graphs and LLM Reasoning to Identify Operational Bottlenecks for Warehouse Planning Assistance' integrates Knowledge Graphs (KGs) and Large Language Model (LLM)-based agents to analyze Discrete Event Simulation (DES) output data for warehouse operations.

claimConventional approaches to analyzing Discrete Event Simulation data, such as manual inspection of aggregate statistics or the development of custom scripts, are time-intensive, error-prone, and often fail to uncover complex, emergent system behaviors and hidden inefficiencies.

claimThe authors propose a framework that integrates Knowledge Graphs and Large Language Models to identify bottlenecks in Discrete Event Simulation data through natural language queries, aiming to assist in intelligent warehouse planning.

referenceThe study utilizes an in-house Discrete Event Simulation (DES) model that simulates warehouse facility operations, including the unloading, internal transport, and storage of incoming packages.

claimThe fusion of Discrete Event Simulation (DES) with Generative AI (GenAI) methods creates a warehouse digital twin that enables planners to make data-driven interventions such as process redesign, resource reallocation, and supplier strategy refinement.

procedureThe proposed framework transforms raw Discrete Event Simulation (DES) output data into a semantically rich Knowledge Graph (KG) to capture relationships between simulation events and entities such as suppliers, packages, workers, and equipment.

referenceJerry Banks authored the book 'Discrete event system simulation', published by Pearson Education in 2005.

measurementThe 'Step-wise Guide' method achieved the highest average performance scores of 0.82 for P@1 and 1.00 for P@4 when analyzing operational data from a Discrete Event Simulation (DES) model, outperforming both 'Direct QA' and 'Direct QA + SR' methods.

claimThere is a noticeable gap in the application of Knowledge Graph technology specifically to structure, analyze, and interpret the output data generated from simulations, such as Discrete Event Simulation (DES).

claimThe application of Knowledge Graph-Large Language Model (KG-LLM) systems to analyze Discrete Event Simulation (DES) output data for operational insights, such as iterative bottleneck diagnosis and root cause analysis, remains largely unexplored.

claimDiscrete Event Simulation (DES) can function as a cyber twin, potentially updated with real-time operational data to mirror physical system states and behaviors, according to research by Rasheed et al. (2020), Leng et al. (2019), and Agalianos et al. (2020).

claimThe Discrete Event Simulation (DES) model used in the study replicates real-world warehouse logistics by capturing interactions between resources including trucks (suppliers), workers, automated guided vehicles (AGVs), forklifts, and storage infrastructure.

claimThe authors present the first application combining Knowledge Graphs and Large Language Model agents to analyze output data from Discrete Event Simulations of warehouse operations specifically to identify bottlenecks and inefficiencies.

claimThe proposed framework for warehouse operations integrates Knowledge Graphs with a reasoning-capable Large Language Model (LLM) agent to facilitate interaction with Discrete Event Simulation (DES) data.

procedureThe research framework aims to enable LLM-based agents to transform natural language questions about Discrete Event Simulation (DES) output into executable queries over a Knowledge Graph, iteratively refine analytical paths based on retrieved evidence, and synthesize information from disparate parts of the Knowledge Graph to diagnose operational issues.

claimThe authors of the paper propose a novel LLM-based agent that employs an iterative, self-correcting reasoning process over Knowledge Graphs derived from Discrete Event Simulation (DES) outputs to automate and enhance the identification and diagnosis of warehouse inefficiencies.

claimDiscrete Event Simulation is extensively employed in logistics and warehousing to model operational facets, providing key performance indicators such as overall system throughput, queue lengths at processing stages, waiting times for entities like orders and products, and utilization rates of critical resources.

referenceThe proposed framework for warehouse operational analysis consists of two main components: the ontological construction of a Knowledge Graph from Discrete Event Simulation output data, and an LLM-agent equipped with an iterative reasoning mechanism that features sequential sub-questioning, Cypher generation for Knowledge Graph interaction, and self-reflection.