A Cloud-to-Edge Approach to Support Predictive Analytics in Robotics Industry

Harmonized Integration of GWO and J-SLnO for Optimized Asset Management and Predictive Maintenance in Industry 4.0

The study encompasses the application of two different advanced optimization algorithms on asset management and predictive maintenance in Industry 4.0-Grey Wolf Optimization and Jaya-based Sea Lion Optimization (J-SLnO). Using this derivative, the authors showed how these techniques could be combined through resource scheduling techniques to demonstrate drastic improvement in the level of efficiency, cost-effectiveness, and energy consumption, as opposed to the standard MinMin, MaxMin, FCFS, and Round Robin. In this sense, GWO results in an execution time reduction between 13 and 31%, whereas, in J-SLnO, there is an execution time reduction of 16-33%. In terms of cost, GWO shows an advantage of 8.57-9.17% over MaxMin and Round Robin, based on costs, while J-SLnO delivers a better economy for the range of savings achieved, which is between 13.56 and 19.71%. Both algorithms demonstrated tremendous energy efficiency, according to the analysis, which showed 94.1-94.2% less consumption of energy than traditional methods. Moreover, J-SLnO was reported to be more accurate and stable in predictability, making it an excellent choice for accurate and more time-trusted applications. J-SLnO is being increasingly recognized as a powerful yet realistic solution for the application of Industry 4.0 because of efficacy and reliability in predictive modeling. Not only does this research validate these optimization techniques to better use in practical life, but it also extends recommendations for putting the techniques into practice in industrial settings, thus laying the foundation for smarter, more efficient asset management and maintenance processes.