Hybrid computing framework security in dynamic offloading for IoT-enabled smart home system

Abstract

In the distributed computing era, cloud computing has completely changed organizational operations by facilitating simple access to resources. However, the rapid development of the IoT has led to collaborative computing, which raises scalability and security challenges. To fully realize the potential of the Internet of Things (IoT) in smart home technologies, there is still a need for strong data security solutions, which are essential in dynamic offloading in conjunction with edge, fog, and cloud computing. This research on smart home challenges covers in-depth examinations of data security, privacy, processing speed, storage capacity restrictions, and analytics inside networked IoT devices. We introduce the Trusted IoT Big Data Analytics (TIBDA) framework as a comprehensive solution to reshape smart living. Our primary focus is mitigating pervasive data security and privacy issues. TIBDA incorporates robust trust mechanisms, prioritizing data privacy and reliability for secure processing and user information confidentiality within the smart home environment. We achieve this by employing a hybrid cryptosystem that combines Elliptic Curve Cryptography (ECC), Post Quantum Cryptography (PQC), and Blockchain technology (BCT) to protect user privacy and confidentiality. Additionally, we comprehensively compared four prominent Artificial Intelligence anomaly detection algorithms (Isolation Forest, Local Outlier Factor, One-Class SVM, and Elliptic Envelope). We utilized machine learning classification algorithms (random forest, k-nearest neighbors, support vector machines, linear discriminant analysis, and quadratic discriminant analysis) for detecting malicious and non-malicious activities in smart home systems. Furthermore, the main part of the research is with the help of an artificial neural network (ANN) dynamic algorithm; the TIBDA framework designs a hybrid computing system that integrates edge, fog, and cloud architecture and efficiently supports numerous users while processing data from IoT devices in real-time. The analysis shows that TIBDA outperforms these systems significantly across various metrics. In terms of response time, TIBDA demonstrated a reduction of 10-20% compared to the other systems under varying user loads, device counts, and transaction volumes. Regarding security, TIBDA's AUC values were consistently higher by 5-15%, indicating superior protection against threats. Additionally, TIBDA exhibited the highest trustworthiness with an uptime percentage 10-12% greater than its competitors. TIBDA's Isolation Forest algorithm achieved an accuracy of 99.30%, and the random forest algorithm achieved an accuracy of 94.70%, outperforming other methods by 8-11%. Furthermore, our ANN-based offloading decision-making model achieved a validation accuracy of 99% and reduced loss to 0.11, demonstrating significant improvements in resource utilization and system performance.

Keywords: Artificial intelligence; Big data; Blockchain; Cryptography; Data security and privacy; Hybrid computing; Internet of Things (IoT); Machine learning; Offloading; Smart home.

Figure 1. Smart home devices connect to edge, fog, and cloud servers via a base station for data processing and analytics. Edge servers are preferred if nearby; otherwise, fog servers are used. For critical processing, requests are forwarded to cloud servers.

Image source credits: Smart home technology set icons, FreePik, https://www.freepik.com; Cloud server, Database free icons, Wifi, FlatIcon, https://www.flaticon.com; Cloud server, https://freepngimg.com/png/11351-cloud-server-png-file#google_vignette, CC BY-NC 4.0; Vector Server Icon, server icons PNG Designed By EncoderXSolutions from https://pngtree.com/freepng/vector-server-icon_4973694.html?sol=downref&id=bef; Database, https://icon-icons.com/icon/database-data/19664, CC BY-NC 4.0.

Figure 2. Smart home user process flow with proposed TIBDA methodology.

It begins with user initiation, followed by data encryption with ECC-PQC and Blockchain. Anomaly detection is conducted using Isolation Forest and Random Forest algorithms. Hash verification confirms user permissions, and servers are selected via an ANN algorithm, secured with Blockchain. Finally, the process concludes with analytics processing, ultimately directing data for further processing, analytics, or action to the exact user. Image source credits: Smart home created by Freepik - Flaticon; Cctv Camera, created by Tru3 Art - Flaticon; Smart House, created by Tru3 Art - Flaticon; Smart TV, created by Corner Pixel - Flaticon; Internet Of Things, created by Chattapat - Flaticon; Router, created by Graficon - Flaticon; Hacker, created by Andrean Prabowo - Flaticon; Csv File, created by surang - Flaticon; Machine Learning, created by Iconjam - Flaticon; Result, created by Uniconlabs - Flaticon; Profile, created by Paul J. - Flaticon; Decryption, created by Nhor Phai - Flaticon; Bandwidth, created by Flat Icons - Flaticon; Latency, created by Vectors Tank - Flaticon; Decision, created by GOWI - Flaticon; Cloud Server, created by turkkub - Flaticon; Networking, created by Konkapp - Flaticon; Cpu Tower, created by Freepik - Flaticon; Broadcast, created by Freepik - Flaticon; Cloud Server, created by Uniconlabs - Flaticon; Blockchain, created by Freepik - Flaticon; Data Analytics, created by vectorsmarket15 - Flaticon; Encryption, Data Processing, Mind development, Testing, Malware, Block user, Batteries, Fog, www.freepik.com.

Figure 3. Framework process flow diagram.

Figure 4. Average response time (ms) and numbers of users comparison.

Figure 5. Average response time (ms) and numbers of devices comparison.

Figure 6. Average response time (ms) and numbers of devices transactions comparison.

Figure 7. A comparison of the security utilizing the AUC at different user levels.

Figure 8. Approaches comparison analysis for system reliability.

Figure 9. Analysis and results of anomalies detection.

Figure 10. Comparison of anomaly detection algorithm accuracies.

Figure 11. Confusion matrix analysis for random forest algorithm.

Figure 12. Performance comparison of malicious and non-malicious classification.

Figure 13. ANN offloading model training and validation accuracy.

Figure 14. ANN offloading model training and validation loss.

Figure 15. ANN offloading confusion matrix.

Figure 16. ANN offloading strategies results presentation.