This article is a part of a series of articles. Links to previous parts can be found in the appendix section of the article.
Social Spider Algorithm
There are approximately 35,000+ spider species observed and described by scientists. However, only a few of them show social behavior. These social spiders, like Mallos gregalis and Oecobius civitas, reside in groups and interact with other spiders within the same group. The social spider optimization algorithm is based on the communication behavior of these spiders.
Spiders use a wide range of strategies for foraging. Most spiders detect prey by sensing vibrations and, hence, are known to be very sensitive to vibratory stimulation. Vibrations on their webs notify them of the capture of prey. If vibrations are in a frequency range, spiders attack the vibration source. Social spiders can also distinguish vibrations their prey generates from those caused by other spiders.
Social spiders also receive vibrations generated by other spiders on the same web without actively seeking these vibrations to develop a clear picture of the web. This characteristic distinguishes social spiders from other organisms as other organisms exchange information actively. Active communication reduces information loss to some degree but increases the energy used per communication action.
Researchers have found that when it comes to swarm foraging behavior, there are two broad types of foraging models:
- Information sharing (IS) model
- Producer–scrounger (PS) model .
In the IS model, individual entities perform searching and seek opportunities to join other individuals simultaneously. In the PS model, the individuals are divided into leaders and followers. For example, the Grey wolf algorithm we discussed in this series’s previous article was the PS model. Since there is no leader in social spiders, the IS model is more suitable for formulating the foraging behavior of social spiders. That model is used to control the searching pattern of the social spider algorithm.
Applications
Though not a direct application in supply chains, I could not help but share applications of social spider algorithms in social networks (see the pun there? ).
Toward text psychology analysis using social spider optimization algorithm
Sentiment Analysis in Social Networks Using Social Spider Optimization Algorithm
Social Spider Optimization for Text Classification Enhancement
Maximizing influence in social networks using social spider optimization
Sentiment Analysis in Social Networks Using Social Spider Optimization Algorithm
Though I can force-fit applications of sentiment analysis and text analysis in the supply chain (for example, in augmented analytics to enhance supply chain analytics applications), standalone applications might not be worth it at this point.
But another category is our sound old power distribution systems, which we have seen emerge consistently in most swarm algorithms covered in this series. Here are some excellent examples of research papers in this category. In previous parts of this article series, we have already discussed how this application can be extrapolated to supply chains.
Social Spider Optimization Algorithm-Based Optimized Power Management Schemes
Nature-inspired solutions for energy sustainability using novel optimization methods
Nature-inspired solutions for energy sustainability using novel optimization methods
Scheduling obviously was interesting due to its omnipresent usage in the supply chain, specifically manufacturing. Interestingly, I did find quite a few research papers that suggested leveraging this algorithm for manufacturing job scheduling. However, it might not be worth it to leverage these algorithms sometimes. Some examples of scheduling-related research papers are below.
Job scheduling problem in fog-cloud-based environment using reinforced social spider optimization
An Efficient Social Spider Optimization for Flexible Job Shop Scheduling Problem
A Social Spider Optimization Algorithm for Hybrid Flow Shop Scheduling with Multiprocessor Task
All the scheduling-related work about swarm intelligence algorithms can be easily extrapolated to the supply chain world. The key is obviously to match the right problem with the right algorithm and to understand that only an optimization-based approach may not be practical when generating these schedules in real-time.
This article concludes our swarm intelligence series that covered 15 key swarm intelligence algorithms.
Appendix
This article is part of a series of articles. Previous parts of this article series can be found here:
Cuckoo and Crow Search Algorithms
Designed Analytics Blog 