IoT-based Fresh Produce Supply Chain Under Uncertainty: An Adaptive Optimization Framework

TL;DR

The paper tackles perishable fresh-produce logistics under uncertainty in travel and environmental conditions by proposing an IoT-driven adaptive optimization framework that dynamically adjusts routing and temperature control. It combines Arrhenius and Q$_{10}$ shelf-life models with five optimization paradigms (Deterministic, RO, SP, DRO, and the adaptive model) and demonstrates, via scenario-based and synthetic-data experiments, that the adaptive framework can extend shelf life and substantially reduce temperature deviations while maintaining near-optimal travel times. Key findings show the adaptive model yields up to ~18% shelf-life improvement and up to ~80% reduction in freshness deviation compared to non-adaptive baselines, validating its practicality for cold-chain logistics. The study highlights the value of real-time IoT feedback in enabling robust, data-driven decisions and outlines future extensions using reinforcement learning to further enhance policy adaptation in long-horizon, uncertain environments.

Abstract

Fruits and vegetables form a vital component of the global economy; however, their distribution poses complex logistical challenges due to high perishability, supply fluctuations, strict quality and safety standards, and environmental sensitivity. In this paper, we propose an adaptive optimization model that accounts for delays, travel time, and associated temperature changes impacting produce shelf life, and compare it against traditional approaches such as Robust Optimization, Distributionally Robust Optimization, and Stochastic Programming. Additionally, we conduct a series of computational experiments using Internet of Things (IoT) sensor data to evaluate the performance of our proposed model. Our study demonstrates that the proposed adaptive model achieves a higher shelf life, extending it by over 18\% compared to traditional optimization models, by dynamically mitigating temperature deviations through a temperature feedback mechanism. The promising results demonstrate the potential of this approach to improve both the freshness and efficiency of logistics systems an aspect often neglected in previous works.

Figures (6)

• Figure 1: Scenario-wise comparison of the adaptive optimization model's performance in terms of total trip time versus total freshness deviation.
• Figure 2: Total Travel Hours (Deterministic vs Adaptive)
• Figure 3: Total Freshness Deviation (Deterministic vs Adaptive)
• Figure 4: Left: Tive Tag affixed to a shipment for temperature monitoring. Right: Flowchart illustrating the data movement from the Tive Tag to the cloud and mobile application.
• Figure 5: Sensitivity analysis of correction strength $\beta$: (a) Total temperature deviation and (b) final shelf life.