The Internet of Things (IoT) has transpired as a fascinating technology for smart cities, smart homes, and smart grids by using a vast amount of IoT data. A smart grid is one of the core components where transport, generation, delivery, and electricity consumption are enhanced in terms of protection and reliability. The existing power grid is suffering from many problems such as outages and unpredictable power disturbances, inflexible energy rates, unnoticeable customer fraud, and many other disadvantages. These problems lead to the ever-rising demand for fossil fuel and service costs. For example, the peak hour demand needs to be overestimated and more energy generated to minimize the risk of an outage. The main problem of the smart grid is the tremendous amount of data needs to be collected from the IoT devices, and processing the data is a challenge. Using and predicting a large amount of data in smart Grid and IoT is still in its infancy. To remedy this problem, we propose a hybrid solution by using the Cloud and Edge Computing to process the data. Processing and predicting at the edge that is close to the embedded devices and homes to save in latency and storage compared to putting all the processing in the Cloud. In this paper, we define a hybrid solution where we use the edge computing for the smart grid information processing where the microgrids are located on the edge of the IoT network, and on the Cloud to use for the power grid that distributes power to the microgrids. We proposed a machine learning engine that used the decision tree to establish the communication between the edge layer, failover between edges, and the Cloud layer.
Software And Hardware
• Hardware: Processor: i3 ,i5 RAM: 4GB Hard disk: 16 GB • Software: operating System : Windws2000/XP/7/8/10 Anaconda,jupyter,spyder,flask Frontend :-python Backend:- MYSQL