ADAPTIVE ALGORITHMS FOR IOT TECHNOLOGY MANAGEMENT IN RESOURCE-CONSTRAINED ENVIRONMENTS
DOI:
https://doi.org/10.18372/2310-5461.63.18950Keywords:
adaptive algorithms, internet of things, IoT, resource constraints, management, efficiencyAbstract
The article is dedicated to the research and analysis of the application of adaptive algorithms in managing IoT technology under resource-constrained conditions. In the context of the rapidly growing popularity of IoT, effective management of this technology in conditions of limited computational, energy, and network resources becomes a crucial task. Article proposes adaptive management methods aimed at optimizing resource utilization and improving the performance of IoT systems.
An analysis of three adaptive IoT management algorithms, namely Q-learning, fuzzy logic algorithm, and swarm intelligence algorithm, is presented. The features, efficiency, and suitability of these algorithms for use under resource-constrained conditions, such as computational power and energy efficiency, are examined.
As a solution to the existing problem, the article proposes a new algorithm: a hybrid of fuzzy logic and swarm intelligence algorithms. This new algorithm opens up new possibilities for managing IoT devices under limited resource conditions, as it combines the best features of both algorithms while avoiding their obvious drawbacks. The proposed algorithm has the potential to increase the efficiency of IoT systems by an average of 10-25%.
However, to achieve better results, it is also important to consider various IoT use cases, as the effectiveness of the algorithms may vary depending on specific conditions. For example, devices operating in remote or hard-to-reach locations require greater autonomy and resilience to network resource limitations. Such factors play a crucial role in ensuring stable and reliable IoT system operation in real-world conditions.
The conclusions of the article aim to determine the most effective IoT management algorithm under resource-constrained conditions. The research results may be useful for developers and implementers of IoT systems focused on optimizing resource usage and improving system performance.
References
Wikipedia. Internet of things. URL: https://en.wikipedia.org/wiki/Internet_of_things (дата звернення: 29.04.2024).
IEEE Xplore. The research and implement of smart home system based on Internet of Things. URL: https://ieeexplore.ieee.org/document/6066672 (дата звернення: 29.04.2024)
Big Data Statistics 2023: How Much Data is in The World? URL: https://firstsiteguide.com/big-data-stats/ (дата звернення: 29.04.2024)
Exploding Topics. 80+ Amazing IoT Statistics. URL: https://explodingtopics.com/blog/iot-stats#iot-industry-size (дата звернення: 07.05.2024)
What’s the big data. Top Machine Learning Statistics to know. URL: https://whatsthebigdata.com/top-machine-learning-statistics/ (дата звернення: 07.05.2024)
Watkins, C.J.C.H. Learning from Delayed Rewards. PhD thesis. 1989. Pp. 220-228.
Fuzzy logic. URL: http://www.scholarpedia.org/article/Fuzzy_logic (дата звернення: 29.04.2024)
Hassanien E. Swarm Intelligence for Resource Management in Internet of Things. 2020. Pp. 1-19.
Wikipedia. Q-навчання. URL: https://uk.wikipedia.org/wiki/Q-%D0%BD%D0%B0%D0%B2%D1%87%D0%B0%D0%BD%D0%BD%D1%8F (дата звернення: 07.05.2024)
Medium. Machine Learning with Fuzzy Logic. URL: https://towardsdatascience.com/machine-learning-with-fuzzy-logic-52c85b46bfe4 (дата звернення: 07.05.2024)
Wikipedia. Колективний інтелект. URL: https://uk.wikipedia.org/wiki/%D0%9A%D0%BE%D0%BB%D0%B5%D0%BA%D1%82%D0%B8%D0%B2%D0%BD%D0%B8%D0%B9_%D1%96%D0%BD%D1%82%D0%B5%D0%BB%D0%B5%D0%BA%D1%82 (дата звернення: 09.05.2024)
LinkedIn. How does Swarm Intelligence work and what are its potential applications? URL: https://www.linkedin.com/pulse/how-does-swarm-intelligence-work-what-its-potential-giovanni-sisinna (дата звернення: 09.05.2024).
