UNIVERSIDADE FEDERAL DO RIO GRANDE DO SUL
INSTITUTO DE INFORMÁTICA
PROGRAMA DE POS-GRADUAÇÃO EM COMPUTAÇÃO
———————————————————
DEFESA DE DISSERTAÇÃO DE MESTRADO

Aluno: Alexander Javier Benavides.
Orientadora: Profa. Dra. Luciana S. Buriol.
Co-orientador: Prof. Dr. Marcus Ritt.

Titulo: Service Restoration and Switch Allocation in Power
Distribution Networks: Bounds and Algorithms.
Linha de Pesquisa: Fundamentos de Computação.

Data: 27/05/2010
Hora: 10h00
Local: Sala dos Conselhos, Sala 220 – Prédio 43412 – Instituto de Informática.

Banca Examinadora:
Prof. Dr. Paulo Morelato França (UNESP).
Prof. Dr. Marcelo de Oliveira Johann (UFRGS).
Prof. Dr. Edson Prestes e Silva Junior  (UFRGS).

Presidente da Banca: Profa. Dra. Luciana S. Buriol.

Abstract:
The improvement of reliability in electrical power distribution networks is an important issue for electricity supply industries, due to strict regulations in many countries. After a failure in the network, some switches are used to isolate the failure, while others restore the energy to some consumers. The optimal selection of the switches to open or close to restore energy is called the service restoration problem. The installation of switches in strategic places may reduce the outage time in case of blackouts, and thus improve the reliability. The optimal selection of
places to install switches is called the switch allocation problem. This two problems are closely related.
This dissertation studies the switch allocation problem, considering the service restoration problem as a sub-problem. Two methods are proposed to estimate the reliability of a distribution network with a given set of installed switches. The main focus is in heuristics to solve the joint problem. It proposes methods like tabu
search, greedy randomized adaptive search procedure, and iterated sample construction with path relinking. It also studies the benefit of greedy, semi-greedy, random, and sample construction methods, and
studies the performance of sample, first improvement and best improvement local search strategies. The different methods are compared and analyzed. The results show that sample approaches are inexpensive and lead to solutions of good quality. Iterated sample construction with path relinking is the best method to solve the joint
problem that is presented in this dissertation.

Keywords: Heuristics, switch allocation, electric power distribution networks.