Energy efficient Firmware Over The Air Update for TinyML models in LoRaWAN agricultural networks

Nicolas, Chollet; Bouchemal, Naila; Amar, Ramdane-Cherif

doi:10.1109/itnac55475.2022.9998338

Cited by 7 publications

(3 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It discusses the challenges and solutions for efficient FUOTA implementation in LoRaWAN networks. Then, the study [5] focuses on energy-efficient firmware updates for TinyML models in LoRaWAN agricultural networks. This paper presents a study of the FUOTA process for LoRaWAN networks, analyzing its feasibility in the context of TinyML firmware updates and evaluating energy consumption and packet delivery ratio in various network scenarios.…”

Section: Related Workmentioning

confidence: 99%

“…FUOTA allows for efficient updates of device firmware without physical access to the devices. However, this convenience also introduces potential security issues that are of primary concern to researchers and network administrators [4] [5]. Thus, addressing these security vulnerabilities within FUOTA processes is a critical area of focus for ongoing research and development efforts in the field of IoT security [6].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

The Design of Security Framework for LoRaWAN FUOTA

Hayati

2024

JET

View full text Add to dashboard Cite

This research outlines a comprehensive security framework for LoRaWAN Firmware Updates Over-The-Air (FUOTA), which is essential for ensuring the reliability of IoT devices in critical infrastructures. It addresses multiple security threats specific to the wireless transmission of firmware updates, initiating an assessment of the vulnerabilities faced by the LoRaWAN FUOTA process. The framework incorporates several security measures, including secure transmission using lightweight encryption to maintain data confidentiality, robust authentication and authorization strategies to prevent unauthorized access, and digital signatures for integrity verification to ensure only authentic firmware updates are installed. It also includes anti-replay measures like sequence numbers and timestamps to protect against replay attacks and emphasizes efficient resource management to optimize power and computational resources for IoT devices. Additionally, secure multicast management techniques are employed to handle the challenges of simultaneously distributing updates to multiple devices. The framework provides an integrated and detailed approach to enhancing the security and operational efficiency of LoRaWAN FUOTA, making it an invaluable resource for practitioners and researchers in the field.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

The Design of Security Framework for LoRaWAN FUOTA

Hayati

2024

JET

View full text Add to dashboard Cite

show abstract

“…The impact of TinyML extends to many areas, including wearable technology [12][13][14][15][16], smart cities [17][18][19][20][21][22], smart homes [23][24][25], smart agriculture [26][27][28][29][30][31], climatic change, environment protection, green AI sustainable applications [32][33][34][35][36][37][38], and automobiles [39,40]. Overcoming TinyML's challenges, especially in hardware, is key and can be advanced through creating an open-source community.…”

Section: Introductionmentioning

confidence: 99%

TinyML Algorithms for Big Data Management in Large-Scale IoT Systems

Karras,

Giannaros,

Karras

et al. 2024

Future Internet

View full text Add to dashboard Cite

In the context of the Internet of Things (IoT), Tiny Machine Learning (TinyML) and Big Data, enhanced by Edge Artificial Intelligence, are essential for effectively managing the extensive data produced by numerous connected devices. Our study introduces a set of TinyML algorithms designed and developed to improve Big Data management in large-scale IoT systems. These algorithms, named TinyCleanEDF, EdgeClusterML, CompressEdgeML, CacheEdgeML, and TinyHybridSenseQ, operate together to enhance data processing, storage, and quality control in IoT networks, utilizing the capabilities of Edge AI. In particular, TinyCleanEDF applies federated learning for Edge-based data cleaning and anomaly detection. EdgeClusterML combines reinforcement learning with self-organizing maps for effective data clustering. CompressEdgeML uses neural networks for adaptive data compression. CacheEdgeML employs predictive analytics for smart data caching, and TinyHybridSenseQ concentrates on data quality evaluation and hybrid storage strategies. Our experimental evaluation of the proposed techniques includes executing all the algorithms in various numbers of Raspberry Pi devices ranging from one to ten. The experimental results are promising as we outperform similar methods across various evaluation metrics. Ultimately, we anticipate that the proposed algorithms offer a comprehensive and efficient approach to managing the complexities of IoT, Big Data, and Edge AI.

show abstract