Logistic Analytics Management in the Service Supply Chain Market Using Swarm Intelligence Modelling

Logistic Analytics Management in the Service Supply Chain Market Using Swarm Intelligence Modelling

Congcong Wang
DOI: 10.4018/IJISSCM.305851
Article PDF Download
Open access articles are freely available for download


The industry sustainability in today's globalization relies on cost-effective supply chain management of diverse markets and logistics. Supply chain risks typically limit profits over the overall expense of the supply chain. In the supply chain design practices, the volatility of demand and limitations of levels are essential concerns. In this paper, a swarm intelligence-assisted supply chain management framework (SISCMF) has been proposed to increase profit and improve logistics performance. Due to the simplicity of design and rapid convergence, swarm intelligence (SI) algorithms are widely used in most supply network design fields and efficiently solve large-dimensional problems. A significant increase in resolving these problems has been seen in particle swarm optimization and ant colony algorithm. The simulation result suggested the operational cost (92.7%), demand prediction ratio (95.2%), order delivery ratio (96.9%), customer feedback ratio (98.2%), and product quality ratio (97.2%).
Article Preview


The Supply Chain is a present organization to buy products from other companies instead of domestically produced (Li, at al., 2017). Logistics can be well-defined as a Subsidiary of a Supply chain, focusing on inventory control, marketing strategy, management and inspection of production and consumption points regarding maintaining a flexible and cost-efficient storage system and delivering products (or order) time (Manogaran, et al., 2020). The algorithm for scheduling is then needed to determine which items are sent to consumers (Arntzen, et al., 1995). One approach to accomplish this aim is to delegate orders to individual agents and allow the agent population to identify an optimal schedule solution interactively (Kumar, et al., 2020). The exchange of quantity, starting, and arrival information between management will contribute to managers' interaction (Kadadevaramath, et al., 2012). These logistical challenges are complicated, and effective processes of optimization are required (Das, et al., 2020). Natural processes operate very well with self coordinating structures to overcome complicated problems (Guide Jr, et al., 2000). The idea is to imitate these processes of the ant colony algorithm (Pham, et al., 2020).

Ant algorithms are multi-agents that simulate individual ants' actions and their interaction with each other through each agent's action (Aladwan, et al., 2020). If the ants go to a nutrition source from the nest and vice versa, they leave a compound pheromone along the way (Gao, et al., 2020). Other ants are headed and pursued, leaving the pheromones behind (Singh, et al., 2016). The shorter direction from nest to food supply is the dominant course of the oldest pheromones as it evaporates over time Al-Turjman, et al., 2009). To solve many NP-hard classes, including dynamic scheduling, Dorigo introduced the ACO (Al-Turjman, etal., 2020). Ant Colony Optimization (ACO) is a system for optimizing pheromone paths to convey food's shortest routes (Tayal, et al., 2021). The core elements in ACO include artificial ants, basic computing agents that construct solutions to the problem individually and on an iterative process (Kumar, et al., 2021). Ants explore a visiting graph of nodes linked by boundaries (Li, et al., 2020). An ordered node sequence is a solution to the problem (Meade, et al., 1998, Boveiri, et al., 2019). The search is performed on multiple constructive computational threads in parallel (Karthikeyan, et al., 2020). The first ACO algorithm proposed is the Ant system (AS) (El‐Shorbagy, et al. 2019). ⠀

This paper first explains the necessary improvements to the SISCMF and the impact on the ACO. These modifications are described in detail step-by-step to enable the Ant Colony Algorithm to combine the material demands on routes and send them to their paths. ACO based method to solve SISCMF problems more effectively in a short time to identify effective solutions and analyses the efficiency of heuristic approaches in detail.

The main contribution of this paper is,

  • Design swarm intelligence assisted supply chain management frameworkhas been proposedtoincrease profit and improve logistics performance.

  • Determine the Ant Colony Algorithm (ACA) simulation analysis to find the shortest path to deliver the products.

  • The numerical outcomes show that the suggested SISCMF improves the operational cost, demand prediction ratio, order delivery ratio, customer feedback ratio, and product quality ratio compared to other existing models.

Complete Article List

Search this Journal:
Volume 17: 1 Issue (2024)
Volume 16: 1 Issue (2023)
Volume 15: 7 Issues (2022): 6 Released, 1 Forthcoming
Volume 14: 4 Issues (2021)
Volume 13: 4 Issues (2020)
Volume 12: 4 Issues (2019)
Volume 11: 4 Issues (2018)
Volume 10: 4 Issues (2017)
Volume 9: 4 Issues (2016)
Volume 8: 4 Issues (2015)
Volume 7: 4 Issues (2014)
Volume 6: 4 Issues (2013)
Volume 5: 4 Issues (2012)
Volume 4: 4 Issues (2011)
Volume 3: 4 Issues (2010)
Volume 2: 4 Issues (2009)
Volume 1: 4 Issues (2008)
View Complete Journal Contents Listing