The paper introduces a set of TinyML algorithms designed to enhance Big Data management in large-scale IoT systems. These algorithms, including TinyCleanEDF, EdgeClusterML, CompressEdgeML, CacheEdgeML, and TinyHybridSenseQ, aim to improve data processing, storage, and quality control in IoT networks by leveraging Edge AI capabilities. Each algorithm addresses specific challenges in IoT systems, such as data cleaning, anomaly detection, adaptive data compression, smart caching, and data quality assessment. The experimental evaluation, conducted using Raspberry Pi devices ranging from one to ten, demonstrates the effectiveness of these algorithms across various performance metrics, including accuracy, compression efficiency, data processing time, training time, overall efficiency, and scalability. The results show significant improvements in anomaly detection accuracy, data processing speed, communication efficiency, and system scalability, highlighting the potential of TinyML in managing the complexities of IoT, Big Data, and Edge AI.The paper introduces a set of TinyML algorithms designed to enhance Big Data management in large-scale IoT systems. These algorithms, including TinyCleanEDF, EdgeClusterML, CompressEdgeML, CacheEdgeML, and TinyHybridSenseQ, aim to improve data processing, storage, and quality control in IoT networks by leveraging Edge AI capabilities. Each algorithm addresses specific challenges in IoT systems, such as data cleaning, anomaly detection, adaptive data compression, smart caching, and data quality assessment. The experimental evaluation, conducted using Raspberry Pi devices ranging from one to ten, demonstrates the effectiveness of these algorithms across various performance metrics, including accuracy, compression efficiency, data processing time, training time, overall efficiency, and scalability. The results show significant improvements in anomaly detection accuracy, data processing speed, communication efficiency, and system scalability, highlighting the potential of TinyML in managing the complexities of IoT, Big Data, and Edge AI.