<![CDATA[This study aims to detect anomalies, types of anomalies, and identify attributes that contribute to the cause of anomalies in the LAPAN-A2 microsatellite power system. Anomaly detection is cumulative-based, where the first year's dataset is added to the datasets of subsequent years for eight years. Anomaly detection uses a voting-based statistical ensemble (VBSE) approach and a combination of Apriori-Close to find associations and reduce rules. The VBSE obtained an average recall value of 86.49 and an average F1-score of 70.49. The F1-score value of VBSE increased by 4.2-fold compared with IForest (16.95), by 12.6-fold compared with ECOD (5.57), and by 5.6-fold compared with LOF (12.65). VBSE showed an increase in performance as the dataset complexity increased (DS1 → DS8), whereas IForest, LOF, and ECOD tended to decrease. The combination of metrics minSupp. 0.02%, minConf. 0.9, and lift is proven to be effective in capturing rare, reliable anomalies and significant association relationships. A strong correlation was observed between batteries (VBatt1–VBatt3) and a causal relationship between U_UMPB and VBatt. The types of anomalies detected included single, contextual, and correlation anomalies.]]>
Copyrights © 2026
