Optimization Methods in Power Market and Machine Learning Algorithms with Sustainable Energies Penetration
Date
2019-06
Authors
Journal Title
Journal ISSN
Volume Title
Publisher
Alfred University. Inamori School of Engineering.
Abstract
The targeted goal of the renewable energies in the recent years has received more attention due to the high volume of the world pollution, greenhouse gases and global warming. Moreover, the process of the control and monitoring of the renewable energies has always been an issue and since the climate change might not have a recognized patterns in different locations, researchers and scientists look for optimizing the better use of the sustainable energies and increase the efficiency. One of the problems with the renewable energies such as solar or wind power is that they cannot be trustworthy and in power planning context, having a forecast about the future power need for the consumers is critically essential. By mathematical modeling, researchers try to formulate these environmental impacts to be able to forecast them and plan on a long-term usage of sustainable energies. This thesis along with the published works mentioned in the following talks about control and monitoring the power market with different approaches. At first, I looked at the households with battery electric vehicles (BEVs) penetration in New York State and how the increasing number of the BEVs can affect on the power market and how a smart grid can shave the high demand picks of hours. By this look, we maintained the electricity usage of the consumer alongside with respect to the least pressure on the grid. The proposed algorithm can benefit both the consumer and the electricity provider in terms of pricing and pressure. Moreover, the next argument is about the optimized locations of wind turbines in a wind farm. By the proposed algorithm and micrositing, we can guarantee the maximum power generation of the wind farm and address the forecasting issue. In the meantime, machine learning algorithms can benefit us with the forecasting of the wind power generation for the future. Here we discuss about how the machine learning and artificial intelligence can improve our understanding of the power generation forecast for the sustainable energies.
Description
Thesis completed in partial fulfillment of the requirements for the degree of Master of Science in Mechanical Engineering at the Inamori School of Engineering, Alfred University
Type
Thesis
item.page.format
Keywords
Renewable energy sources, Energy consumption--Forecasting, Machine learning