Automation Control for Energy Optimization in High Rack Storage Systems

A Conceptual Framework for Predictive Warehouse Design Processes

Authors

  • Zafer ÖZDEMİR Department of Industrial Engineering, Faculty of Architecture and Engineering, İstanbul Nişantaşı University, Istanbul, Turkey
  • Furkan İlker AKIN Department of Business Administration, Faculty of Economic, Administrative and Social Sciences, Istanbul Nişantaşı University, Turkey https://orcid.org/0000-0002-6655-0297

Keywords:

High-Bay Storage, Energy Optimization, Logistics Automation Control, Machine Learning, Warehouse Design Processes

Abstract

In today's rapidly evolving logistics and storage sector, constantly changing market conditions and consumer demands exert a significant pressure on the efficiency and sustainability of storage systems. High-rack storage systems have become a widely used strategy in warehouse design, but the integration of factors such as energy optimization and automation of logistics processes is crucial to the success of these systems.

In this context, this study aims to present a conceptual framework that combines machine learning-based prediction methods with logistics automation controls to increase the energy efficiency of high-rack storage systems and optimize logistics processes. This innovative approach in the warehouse design process aims to enhance storage system performance by optimizing energy consumption.

By filling a gap in the existing literature, this study seeks to provide a general strategy to overcome the challenges that high-rack storage systems will face in the future. This strategy aims to meet the need for sustainable storage solutions by increasing the efficiency of logistics operations and standing out in the competitive business environment of the future.

The modern logistics industry has rapidly changed in the impact of constant technological improvements; thus, one can speak about AI and ML technologies’ growing importance for warehousing activities. Drawing on the concentration noted in review of existing literature works, this paper will outline ways AI and ML technologies like artificial neural networks, fuzzy logic deep learning reinforcement can be used industry logistics fields certain purposes applied logistics management.

These include supplier evaluation processes, operational planning; big data solution logic methods, social media data analytics and supply chain management & logistics. Unlike earlier studies, this article goes beyond the idea of simple traceability targets and presents warehouse management systems where such monitoring data is used, as well as machine learning approaches that allow for training classifiers capable predicting various aspects of any Warehouse design.

Furthermore, it validates this machine learning approach to support the strategic planning of warehouse design using verified and generalizable case studies with real company data. This provides important insights into how monitoring data in warehouse management systems can be effectively used for design and operational management.

Finally, the purpose of this article is to use machine learning for warehouse management to predict and measure the performance of future warehouse operations. Essentially, this article addresses the identification of warehouse operations, determination of performance criteria, creation and evaluation of machine learning models, and prediction of future warehouse operations. The approach aims to inform warehouse managers' decision-making processes and provide comprehensive guidance to optimize operational efficiency.

Downloads

Download data is not yet available.

Downloads

Published

02-07-2024

Issue

Section

Articles

How to Cite

ÖZDEMİR, Z., & AKIN, F. İlker. (2024). Automation Control for Energy Optimization in High Rack Storage Systems: A Conceptual Framework for Predictive Warehouse Design Processes. TWIST, 19(3), 44-52. https://twistjournal.net/twist/article/view/324

Share

Most read articles by the same author(s)

Similar Articles

1-10 of 144

You may also start an advanced similarity search for this article.