Optimal Design of a Distribution Transformer Using Artificial Intelligence Techniques
Zakariya Al Hamouz, مالك أحمد حبلي
كلية الهندسة-جامعة الملك فهد للبترول والمعادن · السعودية
A distribution transformer is one of the most important components in a power system network. In any distribution network, a huge number of transformers are installed. Finding a cost effective design of a distribution transformer is a challenging process, however if properly designed a large amount of savings will be achieved.The transformer design is usually a complicated and time consuming process. In this research work, a comprehensive literature survey on distribution transformer design is conducted. Different mathematical models and solution techniques are discussed and a new objective function is proposed for oil immersed distribution transformer. Results for using different techniques to achieve an optimal design for which the requirements and constraints are met have been shown. The cost of the proposed transformers for two optimization techniques, namely, Genetic Algorithm and Simulated Annealing are compared with an industry used design based on Random Walk method. Results revealed that savings in total cost of about 8% to 13% are achieved for a variation of the cost of kWh from 5 to 8 halalas