Distribution planning for multi-echelon networks considering multiple sourcing and lateral transshipments

Contributors

Sampling-Based Approximation Schemes for Capacitated Stochastic Inventory Control Models

Location-allocation problem as one of the strategic decisions in supply chain management has become the focus of research attention. In this paper we design a distribution network by modelling for location-allocation in a supply chain that involves a fixed plant, distribution centres with multiple levels of capacities and retailers. The aim is to select the optimum numbers, locations, capacities of the opening warehouses, allocation retailers to the opened warehouses, therefore all multi-product stochastic customer demands are satisfied at the minimum total cost of the distribution network and the maximum average of warehouse utilisation. In addition lateral transshipment within an inventory system is considered (i.e., product movements between locations of the same echelon). The model developed as a mixed-integer nonlinear programming model and an efficient heuristic-based memetic algorithm is proposed. Furthermore, a number of test problems are solved and the associated results are compared to evaluate the performance of the proposed algorithm.

Inventory models with lateral transshipments: A review

Inventory planning and optimization are crucial components of effective supply chain management, playing a pivotal role in providing a balance between customer demand and operational efficiency. This research article investigates the current landscape of inventory optimization processes, their implementation, and their considerable impact on business performance in the context of recent global supply-chain disruptions and technological advancements. The study also proceeds to examine various characteristics of inventory management, including but not limited to demand forecasting, inventory strategy formulation, and stock replenishment methodologies. By analysis of data from multiple sources and case studies, the effectiveness of different optimization approaches, such as machine learning-based demand forecasting, multi-objective optimization, and advanced inventory models are investigated. The research also delves into the aspects of integration of artificial intelligence and machine learning in developing inventory optimization processes, especially in the face of stochastic demand and supply chain disruptions. Our findings indicate that successful inventory optimization strategies contribute significantly reducing costs, improving customer satisfaction, and increasing overall supply chain resilience. The study reveals that companies implementing data-driven inventory optimization techniques experience a 15-20% reduction in inventory holding costs and a 10-15% improvement in service levels. Additionally, the research highlights the importance technology and human handshake of real-time data analysis, cross-functional collaboration, and adaptive strategies in achieving optimal inventory levels to avoid opportunity cost. The impact of recent global disruptive events, such as the COVID-19 pandemic that was unprecedented, on supply chain management practices is also examined, providing insights into the development of more resilient and flexible inventory systems. This comprehensive examination and evaluation of inventory planning and optimization provides valuable insights for supply chain professionals and researchers, offering a foundation for future advancements in this critical area of business operations in an increasingly volatile and interconnected global market.

For complex system, often a variety of equipment with different priorities require a spare. Spares supply management constitutes a fundamental decision-making problem, especially in systems which require high support levels. Considering the priority demand classes in actual spares supply, a two-echelon and multi-location continuous review inventory model with waiting time constraints is formed. To better match supply and demand, lateral transshipments and emergency shipments occur in response to stockouts. The model is to find an optimal inventory for each stock point under target service level, against a backdrop of cost minimization objective. A genetic algorithm is applied to get the results and a numerical example is presented to demonstrate the validity of the model. Finally,the proposed model manages to incentive a dexterous spares supply based on service differentiation and successfully provide a theoretical basis for decision makers to plan and control inventory.

This paper aims to optimise healthcare resource pre-positioning, patient scheduling, and patient transferring under uncertain demands and stochastic resource consumption. We propose a two-stage stochastic programming model that formulates the patient scheduling problem as a Markov decision process. To address complexities and uncertainties, we use Artificial Intelligence (AI) techniques to improve both model formulation and algorithmic performance. To tackle the limited data challenge, we introduce a Wasserstein distance-based ambiguity set and propose a two-stage distributionally robust optimisation (DRO) model, which derives a deterministic equivalent using the Lagrangian dual of non-anticipativity constraints. The solution process is accelerated with a scenario decomposition approach and the K-means clustering method. Both theoretical and numerical results demonstrate the consistency of the two-stage DRO model with the sample average approximation (SAA) method. The potential of AI to improve the model's performance is evident through the significant reduction in computation time achieved with the K-means clustering approach without compromising solution quality. Compared to the SAA method, the DRO model exhibits a considerable reduction in the waiting penalty cost for out-of-sample cases, ranging from 43.06 % to 81.23 % . Numerical results show that the proposed algorithm outperforms SAA methods and several benchmark policies in terms of computational efficiency and solutions.

Inventory management faces increasing challenges, including data limitations and demand uncertainty. To enhance inventory forecasting and optimization in supply chain management, this study proposes a Transfer-learning Bayesian Network (TBN) framework that integrates causal inference and transfer learning. Unlike traditional inventory forecasting models that rely on historical data patterns, the proposed framework introduces a causal inference-based Bayesian network to establish explicit causal relationships between sales volume, sales revenue, and inventory levels. To address data scarcity and improve generalization, a novel transfer learning mechanism is incorporated, leveraging a balanced weight coefficient method to optimize model adaptation from a source domain to a target domain. The results indicate that the proposd approach ensures effective knowledge transfer and maintains prediction accuracy with limited training data. The TBN model consistently outperforms traditional machine learning methods and other Bayesian-based models. On the self-constructed dataset, the TBN framework achieved a mean squared error (MSE) of 4.97 and a mean absolute error (MAE) of 2.78, demonstrating superior predictive accuracy. Additionally, an analysis of the balance weight coefficient further validated its role in enhancing transfer learning efficiency and model robustness, which provides a scalable and adaptable solution for intelligent inventory management in supply chain systems.

In this paper, we combine two approaches to handling uncertainty: we use techniques for finding optimal solutions in the expected sense to solve combinatorial optimization problems in an online setting.

PurposeLogistics practitioners must continually improve inventory management processes as they daily respond to the twin drivers of customer satisfaction and cost efficiency. The purpose of this paper is to investigate the scenario of sourcing goods through lateral transshipments in a periodic-review policy setting, against a backdrop of cost optimization objectives.Design/methodology/approachThe authors develop decision rules that make cost-optimized selection between backordering and combined reactive and proactive lateral transshipment options possible. This necessarily takes account of the trade-off between purchasing, holding and backorder cost components. In addition, the authors use simulation studies to illustrate the superior performance of the proposed decision options.FindingsAccording to results of the simulation studies, the proposed two-step decision rule generates the lower inventory cost than the alternative decisions rules. The outperformance of proposed two-step decision rule is valid in different scenario.Practical implicationsThis study develops the decision rules to assist wholesaler logistics practitioners to make optimized decisions with regard to whether they should proactively lateral transshipments and if selected, the optimum size of the extra lateral transshipment.Originality/valueThis study has made a significant contribution to the existing knowledge base as it develops decision rules for a combined proactive and reactive approach using lateral transhipments to meet both urgent demand and a part of the demand expected during the supplier lead time in a cost-efficient way.

Improving the sustainability of a reverse supply chain system under demand uncertainty by using postponement strategies.

Reducing the mean supply delay of spare parts using lateral transshipments policies

In traditional enterprise management mode, there is no necessary information for the inventory optimization, it is very difficult to get the optimal solution meeting the actual requirements in the process of solving the model. On the base of analyzing the problems of the traditional inventory optimization model, this study shows that inventory optimization should be directed by the thought of supply chain management, the neural network model as a tool, using the BP neural networks to integrate a variety of effective information, improving the traditional inventory optimization model, and then a more satisfactory inventory optimization strategy. And based on the actual inventory circumstances of a company, we give the specific application case.

Inventory optimization is pivotal in mitigating economic losses and enhancing efficiency in supply chain management. This paper examines the challenges associated with traditional inventory practices, including inefficiencies, demand variability, and supply chain disruptions, which lead to substantial financial and operational setbacks. Building on theoretical foundations and insights from existing research, a comprehensive inventory optimization framework is proposed, integrating advanced technologies such as Artificial Intelligence (AI), the Internet of Things (IoT), and cloud-based systems. The framework emphasizes data-driven decision-making, real-time tracking, lean inventory management, and sustainability, offering scalable solutions for diverse industries. Practical recommendations for implementation include investments in advanced technologies, collaborative supply chain practices, and continuous performance monitoring. The proposed framework aims to reduce costs, improve operational resilience, and align inventory management with broader economic and environmental goals. By adopting this innovative approach, organizations can navigate the complexities of modern supply chains and achieve long-term success.. Keywords: Inventory Optimization, Supply Chain Management, Economic Losses, Advanced Technologies, Lean Inventory, Sustainability.

Purpose – This paper aims to give a comprehensive review, summary, and discussion on inventory models that have appeared in the literature. During these past ten decades, no seminal paper reviewing the field of inventory lot sizing has even been published. This limitation has been identified in the literature by several researchers over the years, with the sheer volume of the number of published inventory lot sizing models acting as a factor which has limited a research endeavor to review the literature on inventory lot sizing models. Design/methodology/approach – This article reviews research on inventory lot size models and provides a review of previously published literature review papers on inventory models. Based on this initial review, the literature extending current research practices on inventory modeling in supply chains and in sustainable practices is presented. Directions for expanding research in these two areas are examined in light of concerns expressed in the historical use of inventory models and in light of a new inventory research paradigm. Findings – In our paper, we have adopted a novel strategy to overcome this limitation by focusing our review on a review of inventory lot sizing review papers. Originality/value – By adopting the methodology of reviewing published inventory review papers, we can contribute a comprehensive review of the inventory lot sizing literature that serves to provide in one paper a consolidation of inventory research that can serve as a single source to keep researchers up to date with the research developments in inventory lot sizing models. We also identify gaps in the field which could stimulate new research agendas in the areas of supply chain management and sustainable inventory practices.