We've Moved!
Visit SDSU’s new digital collections website at https://digitalcollections.sdsu.edu
Description
Electricity plays a very important role in modern life. It is crucial for the functioning of an economy. Electricity sector is listed as critical infrastructure. All commercial, industrial, and residential operations are directly dependent on electricity. Ensuring smooth operation of the power grid is vital. Any issue in the power grid may trigger a blackout and it may disrupt the operations. Blackout in a specific region may lead to cascading failure. Potentially, a blackout in any part of the grid is a threat to the entire grid. There are many factors that may cause issues in the power grid. Significant factors are high power demand, equipment failures, equipment damage due to weather, wildlife, human intervention. High power demand triggers a blackout when many people in a specific region draw too much power from the grid simultaneously. The power drawn is more than the capacity of the grid. This scenario causes a supply and demand imbalance, which eventually results in a blackout. Our goal is to design an edge computing device that will use Machine Learning to predict power consumption with respect to the changing weather. The device will compute and display predicted power consumption values at the user end. On the backend it will relay the expected power consumption values to the utility company. If company has prior knowledge about the demand requirement, then it can arrange and supply the deficit power onto the power grid. Thereby maintaining the supply and demand balance and hence preventing a potential blackout scenario. There is a strong correlation between the changing weather and the power consumption pattern. Using this idea as the basis, we have modeled the device to perform machine learning predictions based on the changing weather. It uses the GPS to obtain location information. The device then fetches location-specific Real-Time weather data from weather servers. It uses the gathered real-time weather data to predict power consumption. The device computes dollar equivalent amount of the predicted power consumption value. It displays all the information on LCD screen, and it also sends the data to utility company server.