Short-term Load Forecasting Using Neural Network For Future Smart Grid Application

Short-term load forecasting of power system has been a classic problem for a long time. Not merely it has been researched extensively and intensively, but also a variety of forecasting methods has been raised. This thesis outlines some aspects and functions of smart meter. It also presents different policies and current statuses as well as future projects and objectives of SG development in several countries. Then the thesis compares main aspects about latest products of smart meter from different companies. Lastly, three types of prediction models are established in MATLAB to emulate the functions of smart grid in the short-term load forecasting, and then their results are compared and analyzed in terms of accuracy. For this thesis, more variables such as dew point temperature are used in the Neural Network model to achieve more accuracy for better short-term load forecasting results.

Nutrient Load Reduction: Challenges facing the Chesapeake 2000 Agreement

The Chesapeake Bay is the largest estuary in the United States supporting a complex ecosystem that sustains many habitats and the organisms that depend on them. The bay also supports economic, recreational, and cultural activities to over 16 million people residing in the watershed. Changes within the watershed have caused excessive levels of nutrients, mainly nitrogen and phosphorous, to pollute the bay. The Chesapeake Bay Program, guided by a complex agreement, was created to address these and other issues and oversee the restoration of the bay. The most recent version of this agreement, the Chesapeake 2000, declares its continued commitment to restore the bay with over 100 goals to be met by the year 2010. Reports show that although intensive efforts have been made to promote nutrient reduction, very little reduction has actually resulted. This project described these efforts. The final results reveal obstacles affecting progress, shortcomings to current approaches and possible solutions for future implementation.