Auxiliary Hybrid PSO-BPNN-Based Transmission System Loss Estimation in Generation Scheduling

The conventional transmission loss estimation methods used by power system utilities in scheduling problems rely on the exactness of the network model. However, the transmission network model in the system operator database is erroneous and not updated periodically. Therefore, the transmission losse...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on industrial informatics 2017-08, Vol.13 (4), p.1692-1703
Main Authors: Ram Jethmalani, C. H., Simon, Sishaj P., Sundareswaran, Kinattingal, Nayak, P. Srinivasa Rao, Padhy, Narayana Prasad
Format: Article
Language:English
Subjects:
Ambient temperature
Artificial neural networks
B-loss coefficients
Back propagation networks
Back propagation neural network (BPNN)
Data base management systems
dynamic economic dispatch (DED)
Electric power generation
Electric utilities
Electricity distribution
Estimation
Hybrid systems
Indexes
linear programming estimator
Mathematical models
Neural networks
Parameter estimation
Particle swarm optimization
particle swarm optimization (PSO)
Power generation
Propagation losses
Reactive power
Real variables
Schedules
Scheduling
Transmission loss
transmission loss estimation
Utilities
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:The conventional transmission loss estimation methods used by power system utilities in scheduling problems rely on the exactness of the network model. However, the transmission network model in the system operator database is erroneous and not updated periodically. Therefore, the transmission losses calculated based on the erroneous network model is also erroneous. In this context, this paper proposes an auxiliary hybrid model using a back propagation neural network (BPNN) and a particle swarm optimization (PSO) technique to estimate transmission losses, while solving power system scheduling problems. Here, the historical information of the power system is processed by the BPNN and its control parameters are optimized using PSO. In the proposed PSO-BPNN loss estimator, power system variables such as real power generation levels, reactive power injection values, and ambient temperature are used as the input variables. The proposed loss estimator is validated using IEEE 30 bus system and Ontario power system.
ISSN:1551-3203
1941-0050
DOI:10.1109/TII.2016.2614659