Survey on Applications, Techniques and Challenges of Machine Learning for Edge Environments

Edge computing and machine learning have changed a number of applications by extending intelligence and computation toward the data sources. A review of the present machine learning in edge applications is explained in this research focusing on areas such as IoT devices, precision agriculture, smart manufacturing, autonomous cars and healthcare monitoring. Methods like model compression and standard algorithms are used to effectively adapt and implement ML models on limited resource edge devices. The dynamic nature of edge settings, power limitations, data privacy and security, model deployment and administration and limited processing resources are some of the main challenges. This study combines detailed investigations and real-world edge machine learning implementations to address the gap between theory and practice. This study also aims to provide significant data on both the present and future advances of machine learning in edge computing by focusing on potential future applications that may benefit from expanding the fields.