Identification and feature selection of non-technical losses for industrial consumers using the software WEKA

This work has as objectives the implementation of a intelligent computational tool to identify the non-technical losses and to select its most relevant features, considering information from the database with industrial consumers profiles of a power company. The solution to this problem is not trivial and not of regional character, the minimization of non-technical loss represents the guarantee of investments in product quality and maintenance of power systems, introduced by a competitive environment after the period of privatization in the national scene. This work presents using the WEKA software to the proposed objective, comparing various classification techniques and optimization through intelligent algorithms, this way, can be possible to automate applications on Smart Grids. © 2012 IEEE.

New directions for public management

Includes bibliography

National private groups in Mexico, 1987-1993

Includes bibliography

Globalization and restructuring the energy sector in Latin America

Includes bibliography

Changes in the industrial development of Latin America

Includes bibliography

Regulating the private provision of drinking water and sanitation services

Includes bibliography

The effects of growth and economic reform on income distribution in Latin America

Includes bibliography

Structural changes and productivity in Latin American industry, 1970-1996

Includes bibliography

The potential for hub ports on the Pacific coast of South America

Includes bibliography

The adjustment strategies of Mexican ejidatarios in the face of neoliberal reform

Includes bibliography

Making infrastructure reform in Latin America work for the poor

Includes bibliography

Whither reform? Towards a new agenda for Latin America

Includes bibliography

The market and water management reform in Peru

Includes bibliography

Multilayer perceptron neural networks training through charged system search and its Application for non-technical losses detection

The non-technical loss is not a problem with trivial solution or regional character and its minimization represents the guarantee of investments in product quality and maintenance of power systems, introduced by a competitive environment after the period of privatization in the national scene. In this paper, we show how to improve the training phase of a neural network-based classifier using a recently proposed meta-heuristic technique called Charged System Search, which is based on the interactions between electrically charged particles. The experiments were carried out in the context of non-technical loss in power distribution systems in a dataset obtained from a Brazilian electrical power company, and have demonstrated the robustness of the proposed technique against with several others nature-inspired optimization techniques for training neural networks. Thus, it is possible to improve some applications on Smart Grids. © 2013 IEEE.

An overview of the British water privatisation

Includes bibliography