Design and Evaluation of a Joint Optimization Algorithm for High-Precision RFID-IoT-Based Cargo Tracking Systems

Abstract

In the context of the booming modern logistics and supply chain management, cargo tracking technology has emerged as a pivotal means to enhance logistics efficiency and transparency. High-precision cargo tracking systems are particularly crucial in complex warehousing and transportation scenarios, as they can effectively address issues like positioning errors and signal attenuation. This research puts forward a high-precision cargo tracking approach grounded in a joint optimization algorithm. By integrating multiple positioning technologies, namely Received Signal Strength Indicator (RSSI), Time Difference of Arrival (TDOA), and Angle of Arrival (AOA), accurate positioning across diverse environmental conditions is attained. The experimental design encompasses a battery of evaluations, including accuracy tests, real-time performance tests, and system stability analyses, to validate the practical application efficacy of the algorithm. In the accuracy tests, compared with the traditional positioning algorithm, the joint optimization algorithm demonstrated remarkable improvements. In high signal strength areas, the positioning error was slashed by 20%, dropping from an average of 0.8 meters in traditional algorithms to 0.64 meters. In low signal strength areas, the error was reduced by 30%, from 1.5 meters to 1.05 meters. And in high-density obstacle areas, the error was cut by 35%, decreasing from 2.2 meters to 1.43 meters. During real-time tests in high-concurrency environments, the joint optimization algorithm outperformed traditional algorithms significantly. The response time was shortened by 55%, from an average of 0.8 seconds in traditional algorithms to 0.36 seconds, and the throughput increased by 30%, rising from 100 requests per second to 130 requests per second. System stability and fault tolerance tests indicated that the joint optimization algorithm exhibited minimal error accumulation during long - term operation. After continuous operation for 48 hours, the error accumulation of the traditional algorithm reached 3 meters, while that of the joint optimization algorithm was merely 1.2 meters. Additionally, in abnormal situations such as sensor failure and network interruption, the joint optimization algorithm could swiftly restore positioning accuracy within 5 minutes on average, ensuring seamless operation. Based on these experimental results, the joint optimization algorithm proposed in this paper showcases substantial advantages in high-precision cargo tracking and holds great promise for practical applications.