Advanced Resource Allocation Optimization Techniques in IoT: A Comprehensive Review
DOI:
https://doi.org/10.22105/siot.vi.285Keywords:
IoT ,Resource Allocation ,Optimization Techniques ,Heuristic Algorithms ,Genetic Algorithms ,Particle Swarm Optimization (PSO) ,Ant Colony Optimization (ACO) ,Machine Learning ,Deep Learning ,Reinforcement Learning ,Game Theory ,Nash Equilibrium, BlockchainAbstract
As the Internet of Things (IoTs) transforms industries through instantaneous data sharing, the rapid increase in interconnected devices presents significant challenges to efficient resource allocation. The primary objectives of IoTs include achieving high performance, minimizing latency, reducing energy consumption, and ensuring security. This paper examines key techniques aimed at enhancing effective resource management within IoTs. More sophisticated optimization is crucial for the diverse array of devices with varying capabilities and power requirements in IoTs networks. The leading techniques discussed are heuristic algorithms, machine learning-based models, game-theoretic models, and hybrid approaches. Heuristic algorithms like Genetic Algorithms (GAs), Particle Swarm Optimization (PSO), and Ant Colony Optimization (ACO) provide relatively quick near-optimal solutions and are especially vital given the dynamic conditions encountered in IoTs. Additional applications include simulated annealing and Tabu Search (TS) for optimization in constrained local search. Advanced resource allocation facilitated by learning and adaptation through machine learning enables the development of models such as Convolutional Neural Networks (CNNs), Long Short-Term Memories (LSTMs), and Deep Q-Networks (DQNs). Reinforcement Learning (RL) helps IoT systems acquire accurate policies over time. Data analytics are streamlined with frameworks like Apache Spark and Hadoop, making real-time processing and resource management more efficient. In addition to crafting strategies for equitable and stable resource distribution, game-theoretic models explore the interactions among devices and networks within constructs such as Nash equilibrium. Hybrid strategies that merge heuristic methods with machine learning approaches offer an effective solution for addressing multi-objective optimization. Ongoing research will continue to evolve to enhance the adaptability of resource distribution in IoTs networks, focusing on federated learning, Blockchain, and edge computing.
References
Anbazhagan, S., & Mugelan, R. K. (2024). Next-gen resource optimization in NB-IoT networks: harnessing soft actor-critic reinforcement learning. Computer networks, 252, 110670. https://doi.org/10.1016/j.comnet.2024.110670
Sagar, A. S. M. S., Chen, Y., Rob, M. A., & Kim, H. S. (2024). Jointly optimizing resource and heterogeneity in IoT networks using a three-stage asynchronous federated reinforcement learning. Internet of things, 27, 101242. https://doi.org/10.1016/j.iot.2024.101242
Liu, J., Li, C., & Luo, Y. (2024). Efficient resource allocation for IoT applications in mobile edge computing via dynamic request scheduling optimization. Expert systems with applications, 255, 124716. https://doi.org/10.1016/j.eswa.2024.124716
Abdullah, M., Khan, H. Z., Fakhar, U., Akhtar, A. N., & Ansari, S. (2024). Satellite synergy: navigating resource allocation and energy efficiency in IoT networks. Journal of network and computer applications, 230, 103966. https://doi.org/10.1016/j.jnca.2024.103966
Raghavendar, K., Batra, I., & Malik, A. (2023). A robust resource allocation model for optimizing data skew and consumption rate in cloud-based IoT environments. Decision analytics journal, 7, 100200. https://doi.org/10.1016/j.dajour.2023.100200
Costa, W. S., dos Santos, W. G. V, Camporez, H. A. F., Faber, M. J., Silva, J. A. L., Segatto, M. E. V, & Rocha, H. R. O. (2024). Planning and resource allocation of a hybrid IoT network using artificial intelligence. Internet of things, 26, 101225. https://doi.org/10.1016/j.iot.2024.101225
Changazi, S. A., Bakhshi, A. D., Yousaf, M., Mohsin, S. M., Akber, S. M. A., Abazeed, M., & Ali, M. (2024). Optimization of network topology robustness in IoTs: A systematic review. Computer networks, 250, 110568. https://doi.org/10.1016/j.comnet.2024.110568
Ibrahim, A. M. A., Chen, Z., Eljailany, H. A., Yu, G., Ipaye, A. A., Abouda, K. A., & Idress, W. M. (2024). Advancing 6G-IoT networks: willow catkin packet transmission scheduling with AI and bayesian game-theoretic approach-based resource allocation. Internet of things, 25, 101119. https://doi.org/10.1016/j.iot.2024.101119
Sudhakar, M., & Anne, K. R. (2024). Optimizing data processing for edge-enabled IoT devices using deep learning based heterogeneous data clustering approach. Measurement: sensors, 31, 101013. https://doi.org/10.1016/j.measen.2023.101013
da Silva, L. G. F., Sadok, D. F. H., & Endo, P. T. (2023). Resource optimizing federated learning for use with IoT: A systematic review. Journal of parallel and distributed computing, 175, 92–108. https://doi.org/10.1016/j.jpdc.2023.01.006
Sun, C., Huang, G., Shu, J., Yang, Y., & Wu, B. (2024). Joint mode selection and resource allocation based on many-to-many reuse in D2D-aided IoT cellular networks. Internet of things, 25, 101104. https://doi.org/10.1016/j.iot.2024.101104
Premalatha, B., & Prakasam, P. (2024). Optimal energy-efficient resource allocation and fault tolerance scheme for task offloading in IoT-FoG computing networks. Computer networks, 238, 110080. https://doi.org/10.1016/j.comnet.2023.110080
Gelenbe, E., Nakıp, M., & Czachórski, T. (2022). Improving massive access to IoT gateways. Performance evaluation, 157, 102308. http://dx.doi.org/10.1016/j.peva.2022.102308
Sangaiah, A. K., Hosseinabadi, A. A. R., Shareh, M. B., Bozorgi Rad, S. Y., Zolfagharian, A., & Chilamkurti, N. (2020). IoT resource allocation and optimization based on heuristic algorithm. Sensors, 20(2), 539. https://doi.org/10.3390/s20020539
Metrics
