الفهرس 
IntroductionOnly 14 pages are availabe for public view
 |  | from | 78 |  |  |
| | | from | 78 | | |
Abstract
A smart grid (SG) is an electrical network that manages electricity demand in an uninterruptible sustainable, reliable and economic manner. A smart grid uses smart net meters to overcome the weaknesses of conventional electrical grid. Demand Side Management (DSM) is a vital feature of SG to improve power efficiency, reduce the peak average load and minimize the cost.
One of the basic objectives of DSM is shifting load from peak hours to off-peak hours and reducing consumption during peak hours. Generally, a deregulated grid system is considered where the retailer purchases electricity from the electricity market to cover the end users’ energy need. In this thesis, Demand Side Management (DSM) techniques (load shifting and Peak clipping) are used to maximize the profit for Retailer Company by reducing total power demand during peak demand periods and achieve an optimal daily load schedule using linear programming technique and Genetic Algorithm. This technique is implemented on the standard IEEE 33-bus radial network. Also, a short term Artificial Neural Network technique is used to get forecasted wind speed and forecasted users load for date 25-March-2018. The neural network here uses an actual hourly load data and an actual hourly wind speed data. Then the forecasted data is used in the optimization to get optimal daily load schedule to maximize the profit for Retailer Company. Then comparison between profit using linear programing and genetic algorithm are made. The optimized DSM succeeded to increase the profits of the company by around 4.5 times its previous profit using Linear Programing and around 2.5 times using Genetic Algorithm.