Parallel power load abnormalities detection using fast density peak clustering with a hybrid canopy-K-means algorithm
Parallel power loads anomalies are processed by a fast-density peak clustering technique that capitalizes on the hybrid strengths of Canopy and K-means algorithms all within Apache Mahout's distributed machine-learning environment. The study taps into Apache Hadoop's robust tools for data...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Other Authors: | |
| Format: | Article |
| Published: |
IOS Press BV
2025
|
| Subjects: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1833413665617870848 |
|---|---|
| author | Al-Jumaili A.H.A. Muniyandi R.C. Hasan M.K. Singh M.J. Paw J.K.S. Al-Jumaily A. |
| author2 | 57212194331 |
| author_facet | 57212194331 Al-Jumaili A.H.A. Muniyandi R.C. Hasan M.K. Singh M.J. Paw J.K.S. Al-Jumaily A. |
| author_sort | Al-Jumaili A.H.A. |
| building | UNITEN Library |
| collection | Institutional Repository |
| content_provider | Universiti Tenaga Nasional |
| content_source | UNITEN Institutional Repository |
| continent | Asia |
| country | Malaysia |
| description | Parallel power loads anomalies are processed by a fast-density peak clustering technique that capitalizes on the hybrid strengths of Canopy and K-means algorithms all within Apache Mahout's distributed machine-learning environment. The study taps into Apache Hadoop's robust tools for data storage and processing, including HDFS and MapReduce, to effectively manage and analyze big data challenges. The preprocessing phase utilizes Canopy clustering to expedite the initial partitioning of data points, which are subsequently refined by K-means to enhance clustering performance. Experimental results confirm that incorporating the Canopy as an initial step markedly reduces the computational effort to process the vast quantity of parallel power load abnormalities. The Canopy clustering approach, enabled by distributed machine learning through Apache Mahout, is utilized as a preprocessing step within the K-means clustering technique. The hybrid algorithm was implemented to minimise the length of time needed to address the massive scale of the detected parallel power load abnormalities. Data vectors are generated based on the time needed, sequential and parallel candidate feature data are obtained, and the data rate is combined. After classifying the time set using the canopy with the K-means algorithm and the vector representation weighted by factors, the clustering impact is assessed using purity, precision, recall, and F value. The results showed that using canopy as a preprocessing step cut the time it proceeds to deal with the significant number of power load abnormalities found in parallel using a fast density peak dataset and the time it proceeds for the k-means algorithm to run. Additionally, tests demonstrate that combining canopy and the K-means algorithm to analyze data performs consistently and dependably on the Hadoop platform and has a clustering result that offers a scalable and effective solution for power system monitoring. ? 2024 - IOS Press. All rights reserved. |
| format | Article |
| id | my.uniten.dspace-36943 |
| institution | Universiti Tenaga Nasional |
| publishDate | 2025 |
| publisher | IOS Press BV |
| record_format | dspace |
| spelling | my.uniten.dspace-369432025-03-03T15:45:59Z Parallel power load abnormalities detection using fast density peak clustering with a hybrid canopy-K-means algorithm Al-Jumaili A.H.A. Muniyandi R.C. Hasan M.K. Singh M.J. Paw J.K.S. Al-Jumaily A. 57212194331 14030355800 55057479600 58765817900 58168727000 57208087596 Anomaly detection Cluster analysis Abnormality detection Abnormality detection and adjustment Apache mahout Canopy algorithm Hybrid (CKMA) K-mean algorithm K-mean algorithms Load data Power load Power load data K-means clustering Parallel power loads anomalies are processed by a fast-density peak clustering technique that capitalizes on the hybrid strengths of Canopy and K-means algorithms all within Apache Mahout's distributed machine-learning environment. The study taps into Apache Hadoop's robust tools for data storage and processing, including HDFS and MapReduce, to effectively manage and analyze big data challenges. The preprocessing phase utilizes Canopy clustering to expedite the initial partitioning of data points, which are subsequently refined by K-means to enhance clustering performance. Experimental results confirm that incorporating the Canopy as an initial step markedly reduces the computational effort to process the vast quantity of parallel power load abnormalities. The Canopy clustering approach, enabled by distributed machine learning through Apache Mahout, is utilized as a preprocessing step within the K-means clustering technique. The hybrid algorithm was implemented to minimise the length of time needed to address the massive scale of the detected parallel power load abnormalities. Data vectors are generated based on the time needed, sequential and parallel candidate feature data are obtained, and the data rate is combined. After classifying the time set using the canopy with the K-means algorithm and the vector representation weighted by factors, the clustering impact is assessed using purity, precision, recall, and F value. The results showed that using canopy as a preprocessing step cut the time it proceeds to deal with the significant number of power load abnormalities found in parallel using a fast density peak dataset and the time it proceeds for the k-means algorithm to run. Additionally, tests demonstrate that combining canopy and the K-means algorithm to analyze data performs consistently and dependably on the Hadoop platform and has a clustering result that offers a scalable and effective solution for power system monitoring. ? 2024 - IOS Press. All rights reserved. Final 2025-03-03T07:45:58Z 2025-03-03T07:45:58Z 2024 Article 10.3233/IDA-230573 2-s2.0-85215378155 https://www.scopus.com/inward/record.uri?eid=2-s2.0-85215378155&doi=10.3233%2fIDA-230573&partnerID=40&md5=16f6c6c7217638414360d4fe7b424d1a https://irepository.uniten.edu.my/handle/123456789/36943 28 5 1321 1346 IOS Press BV Scopus |
| spellingShingle | Anomaly detection Cluster analysis Abnormality detection Abnormality detection and adjustment Apache mahout Canopy algorithm Hybrid (CKMA) K-mean algorithm K-mean algorithms Load data Power load Power load data K-means clustering Al-Jumaili A.H.A. Muniyandi R.C. Hasan M.K. Singh M.J. Paw J.K.S. Al-Jumaily A. Parallel power load abnormalities detection using fast density peak clustering with a hybrid canopy-K-means algorithm |
| title | Parallel power load abnormalities detection using fast density peak clustering with a hybrid canopy-K-means algorithm |
| title_full | Parallel power load abnormalities detection using fast density peak clustering with a hybrid canopy-K-means algorithm |
| title_fullStr | Parallel power load abnormalities detection using fast density peak clustering with a hybrid canopy-K-means algorithm |
| title_full_unstemmed | Parallel power load abnormalities detection using fast density peak clustering with a hybrid canopy-K-means algorithm |
| title_short | Parallel power load abnormalities detection using fast density peak clustering with a hybrid canopy-K-means algorithm |
| title_sort | parallel power load abnormalities detection using fast density peak clustering with a hybrid canopy-k-means algorithm |
| topic | Anomaly detection Cluster analysis Abnormality detection Abnormality detection and adjustment Apache mahout Canopy algorithm Hybrid (CKMA) K-mean algorithm K-mean algorithms Load data Power load Power load data K-means clustering |
| url_provider | http://dspace.uniten.edu.my/ |