Maintaining the quality and integrity of frozen goods throughout the supply chain necessitates a robust and efficient cold chain logistics network. This research proposes a machine learning-based method for optimizing such networks, resulting in significant cost reduction and resource utilization improvement. The method employs a three-phase approach. First, K-means clustering groups sellers based on their geographical proximity, simplifying the problem and enabling more accurate demand prediction. During the second phase of the proposed method, Gaussian Process Regression models predict future sales volume for each seller cluster, leveraging historical sales data. Finally, the Capuchin Search Algorithm simultaneously optimizes distributor location and resource allocation for each cluster, minimizing both transportation and holding costs. This multi-objective approach achieved a 34.76% reduction in costs and a 15.6% reduction in resource wastage compared to the existing system. This novel method offers a valuable tool for frozen goods distribution networks, with advantages such as considering multiple goals for optimization, focusing on demand prediction, potential for reduced complexity, and focusing on managerial insights over compared methods.
Introduction
In order to achieve budgetary requirements while minimizing expenses and preventing quality loss during storage and distribution, cold chain logistics is crucial in maintaining the appropriate commodities at the right time. The cold chain is advised to maintain the proper temperature for perishable goods during the distribution process as a crucial component of the logistic system1,2,3. The perishable goods must be kept in a freezer box equipment due to the storage conditions. Frozen food is one form of perishable product with a short shelf life and limited time of sale. It is distributed by a freezer box truck, which has a greater operating cost and uses more fossil fuel than a standard vehicle. Therefore, it is thought that the effectiveness of the distribution of frozen goods has a substantial impact on both operating expenses and retail sales. The drivers must also adhere to the consumers’ and stores’ time-window requirements in order to boost service satisfaction4. A distributor that sells items with a limited shelf life, like milk, ice cream, and lunch boxes, levies a late delivery fee. Customers have higher expectations for the quality of fresh products as living standards rise5.
The quality of fresh products is significantly influenced by the temperature; specifically, high temperatures hasten product degradation6. Due to its capabilities of maintaining product quality via low temperature, cold chain logistics has emerged as the primary way of distributing fresh goods in this setting7. The quality of fresh food will decline as time goes on in addition to temperature8. Because cold chain logistics has higher standards than traditional logistics, cold chain logistics businesses face enormous hurdles in the area of customer service. Nowadays, businesses no longer have a clear price edge, so they search for new competitive advantages to boost customer satisfaction. Only by doing this will they be able to stand out from the competition in the market for cold chain logistics9. Therefore, cold chain logistics companies should thoroughly investigate ways to improve logistics services to raise client satisfaction10.
The key to evaluating the current service quality of cold chain logistics businesses is customer satisfaction measurement, which can improve communication between customers and businesses11. Additionally, measuring allows for the identification of the critical variables influencing customer satisfaction, which helps to reveal the advantages and disadvantages of the cold chain logistics firm and enhance logistical operations12.
The act of distributing products or goods from a manufacturer to a customer is known as distribution. The distributor transports the goods using a vehicle during the technical execution of the procedure. A sound plan is necessary to reduce distribution costs. Choosing the paths taken by the vehicles is part of this strategy. The vehicle routing problem (VRP) is the name given to the issue. The VRP has been addressed using a variety of techniques and is regarded as a combinatorial optimization problem13,14.
A few of the distributor’s trucks will be used in the technical execution of the product distribution to transport the goods to clients. Distributors must choose the best route for the distribution of goods given the various consumer bases. Minimizing the cost of distribution is the major goal of the solution. By reducing distribution routes and the utilization of used vehicles in the distribution process, a minimum distribution cost may be attained. Along with these, it’s important to take the vehicles’ capacity into account15. The benefits will be gained to a greater extent the higher the quality of the distribution procedure.
For frozen goods delivery, cold chain logistics network optimization is essential to preserving product integrity and quality across the supply chain. But conventional approaches to distributor location and resource allocation are frequently too simple to address intricate aspects including sellers’ geographical dispersion, shifting demand patterns, and the requirement to keep holding costs as low as possible. In order to tackle this problem, the research suggests a new, three-phase machine learning and optimization-based strategy. This strategy seeks to significantly lower costs and enhance the use of resources in frozen food cold chain logistics networks.