Graduate Research Papers

Availability

Open Access Graduate Research Paper

Abstract

Prediction of electricity peak demand is an integral part in any electrical utility. Many models were previously proposed for prediction, ranging from short-term, intermediate to long-term prediction. Prediction of electricity peak demand is crucial in avoiding unneeded expenses to upgrade the electrical power supply. It is a continuous process that is still in need of study and improvement. University of Northern Iowa is an educational institution with 10,380 undergraduate students, 66% of whom reside in university housing and 59% of the total electricity demand is purchased from Cedar Falls utilities. The university utilizes a model based on computerized live reading of previous demand that undergoes continuous short-term, intermediate and long-term prediction. The model has succeeded in reducing peak demand. The purpose of the present research is to review the currently used modeling system at UNI, and to test the impact of temperature, humidity, and time variables on peak demand prediction through a Multiple Linear Regression (MLR) short-term model. The MLR model was tested three times, including in each different number of variables, ranging from two to four, with most significant results occurring when four weather and time variables were used.

Year of Submission

2015

Department

Department of Technology

First Advisor

Jin Zhu

Comments

If you are the rightful copyright holder of this graduate research paper and wish to have it removed from the Open Access Collection, please submit an email request to scholarworks@uni.edu. Include your name and clearly identify the thesis by full title and author as shown on the work.

Date Original

8-4-2015

Object Description

1 PDF file (53 pages)

Download

Comments?

Share

COinS