Consumer load prediction based on NARX for electricity theft detection
A range of load prediction techniques has largely been used for energy management at various levels. However, the data used for the prediction are cumulative energy data, which reveal the activities of consumers and not individual consumer, on the distribution power network. Individual consumer...
| Main Authors: | , , |
|---|---|
| Format: | Proceeding Paper |
| Language: | English English |
| Published: |
IEEE
2016
|
| Subjects: | |
| Online Access: | http://irep.iium.edu.my/55565/ http://irep.iium.edu.my/55565/2/55565.pdf http://irep.iium.edu.my/55565/8/55556_Consumer%20load%20prediction%20based_Scopus.pdf |
| _version_ | 1848784601460244480 |
|---|---|
| author | Isqeel, Abdullateef Ayodele Salami, Momoh Jimoh Eyiomika Ismaeel, Tijani Bayo |
| author_facet | Isqeel, Abdullateef Ayodele Salami, Momoh Jimoh Eyiomika Ismaeel, Tijani Bayo |
| author_sort | Isqeel, Abdullateef Ayodele |
| building | IIUM Repository |
| collection | Online Access |
| description | A range of load prediction techniques has largely
been used for energy management at various levels.
However, the data used for the prediction are cumulative
energy data, which reveal the activities of consumers and not
individual consumer, on the distribution power network.
Individual consumer data is essential for real time
prediction, monitoring and detect of electricity theft. A new
approach of monitoring individual consumer based on
consumer load prediction using nonlinear autoregressive
with eXogenous input (NARX) network is considered in this
study. One month average energy consumption data
acquired from consumer load prototype developed was used.
Consequently, 5-minute step ahead load prediction was
achieved. The NARX architecture was based on nine hidden
neurons and two tapped delay and the network trained using
Bayesian regulation backpropagation technique. The data
set contains a total of 8928 data points representing energy
consumed at five minute interval for one month. The data
was divided into two sets at ratio 70:30 for training and
validation, respectively. The training data equals 6206 while
the validation data is 2722. MATLAB environment was used
for the processing of the data. The training and validation
MSE is 0.0225 and 0.0533 respectively, while the total time
for the training is 0.016s. |
| first_indexed | 2025-11-14T16:39:50Z |
| format | Proceeding Paper |
| id | iium-55565 |
| institution | International Islamic University Malaysia |
| institution_category | Local University |
| language | English English |
| last_indexed | 2025-11-14T16:39:50Z |
| publishDate | 2016 |
| publisher | IEEE |
| recordtype | eprints |
| repository_type | Digital Repository |
| spelling | iium-555652017-04-21T07:29:44Z http://irep.iium.edu.my/55565/ Consumer load prediction based on NARX for electricity theft detection Isqeel, Abdullateef Ayodele Salami, Momoh Jimoh Eyiomika Ismaeel, Tijani Bayo TK301 Electric meters TK4001 Applications of electric power A range of load prediction techniques has largely been used for energy management at various levels. However, the data used for the prediction are cumulative energy data, which reveal the activities of consumers and not individual consumer, on the distribution power network. Individual consumer data is essential for real time prediction, monitoring and detect of electricity theft. A new approach of monitoring individual consumer based on consumer load prediction using nonlinear autoregressive with eXogenous input (NARX) network is considered in this study. One month average energy consumption data acquired from consumer load prototype developed was used. Consequently, 5-minute step ahead load prediction was achieved. The NARX architecture was based on nine hidden neurons and two tapped delay and the network trained using Bayesian regulation backpropagation technique. The data set contains a total of 8928 data points representing energy consumed at five minute interval for one month. The data was divided into two sets at ratio 70:30 for training and validation, respectively. The training data equals 6206 while the validation data is 2722. MATLAB environment was used for the processing of the data. The training and validation MSE is 0.0225 and 0.0533 respectively, while the total time for the training is 0.016s. IEEE 2016 Proceeding Paper PeerReviewed application/pdf en http://irep.iium.edu.my/55565/2/55565.pdf application/pdf en http://irep.iium.edu.my/55565/8/55556_Consumer%20load%20prediction%20based_Scopus.pdf Isqeel, Abdullateef Ayodele and Salami, Momoh Jimoh Eyiomika and Ismaeel, Tijani Bayo (2016) Consumer load prediction based on NARX for electricity theft detection. In: 6th International Conference on Computer and Communication Engineering (ICCCE 2016), 25th-27th July 2016, Kuala Lumpur. http://ieeexplore.ieee.org/document/7808328/ 10.1109/ICCCE.2016.70 |
| spellingShingle | TK301 Electric meters TK4001 Applications of electric power Isqeel, Abdullateef Ayodele Salami, Momoh Jimoh Eyiomika Ismaeel, Tijani Bayo Consumer load prediction based on NARX for electricity theft detection |
| title | Consumer load prediction based on NARX for electricity theft detection |
| title_full | Consumer load prediction based on NARX for electricity theft detection |
| title_fullStr | Consumer load prediction based on NARX for electricity theft detection |
| title_full_unstemmed | Consumer load prediction based on NARX for electricity theft detection |
| title_short | Consumer load prediction based on NARX for electricity theft detection |
| title_sort | consumer load prediction based on narx for electricity theft detection |
| topic | TK301 Electric meters TK4001 Applications of electric power |
| url | http://irep.iium.edu.my/55565/ http://irep.iium.edu.my/55565/ http://irep.iium.edu.my/55565/ http://irep.iium.edu.my/55565/2/55565.pdf http://irep.iium.edu.my/55565/8/55556_Consumer%20load%20prediction%20based_Scopus.pdf |