In real-world many internet-based service companies need to closely monitor large amounts of data in order to ensure stable operation of their business.However,anomaly detection for these data with various patterns an...In real-world many internet-based service companies need to closely monitor large amounts of data in order to ensure stable operation of their business.However,anomaly detection for these data with various patterns and data quality has been a great challenge,especially without labels.In this paper,we adopt an anomaly detection algorithm based on Long Short-Term Memory(LSTM)Network in terms of reconstructing KPIs and predicting KPIs.They use the reconstruction error and prediction error respectively as the criteria for judging anomalies,and we test our method with real data from a company in the insurance industry and achieved good performance.展开更多
For many Internet companies,a huge amount of KPIs(e.g.,server CPU usage,network usage,business monitoring data)will be generated every day.How to closely monitor various KPIs,and then quickly and accurately detect ano...For many Internet companies,a huge amount of KPIs(e.g.,server CPU usage,network usage,business monitoring data)will be generated every day.How to closely monitor various KPIs,and then quickly and accurately detect anomalies in such huge data for troubleshooting and recovering business is a great challenge,especially for unlabeled data.The generated KPIs can be detected by supervised learning with labeled data,but the current problem is that most KPIs are unlabeled.That is a time-consuming and laborious work to label anomaly for company engineers.Build an unsupervised model to detect unlabeled data is an urgent need at present.In this paper,unsupervised learning DBSCAN combined with feature extraction of data has been used,and for some KPIs,its best F-Score can reach about 0.9,which is quite good for solving the current problem.展开更多
Most of the isolated electrical systems throughout the world suffer from similar problems of fragility and high dependence on external resources to generate energy. Smart Grid solutions and integration of renewable en...Most of the isolated electrical systems throughout the world suffer from similar problems of fragility and high dependence on external resources to generate energy. Smart Grid solutions and integration of renewable energies in order to solve their problems have increased, although it is necessary to know their specific characteristics to select the optimal solutions for each case. Therefore, as the overall objective of INSULAE Project, the development of an Investment Planning Tool, IPT, is on the way. This paper provides a view on a characterization methodology developed for the set of Reference Islands and how it will help to exploit the IPT developed. For that, characterization vectors have been defined based on a selection of Key Performance Indicators (KPIs). And Reference Islands have been obtained from the analysis of KPIs data gathered from EU islands considering the vectors formed. The linkage of new islands to reference islands helps provide the new islands with an assessment on the possibility space of their investment plans with the aim of being a decarbonization plan considering the demonstrations already evaluated.展开更多
文摘In real-world many internet-based service companies need to closely monitor large amounts of data in order to ensure stable operation of their business.However,anomaly detection for these data with various patterns and data quality has been a great challenge,especially without labels.In this paper,we adopt an anomaly detection algorithm based on Long Short-Term Memory(LSTM)Network in terms of reconstructing KPIs and predicting KPIs.They use the reconstruction error and prediction error respectively as the criteria for judging anomalies,and we test our method with real data from a company in the insurance industry and achieved good performance.
文摘For many Internet companies,a huge amount of KPIs(e.g.,server CPU usage,network usage,business monitoring data)will be generated every day.How to closely monitor various KPIs,and then quickly and accurately detect anomalies in such huge data for troubleshooting and recovering business is a great challenge,especially for unlabeled data.The generated KPIs can be detected by supervised learning with labeled data,but the current problem is that most KPIs are unlabeled.That is a time-consuming and laborious work to label anomaly for company engineers.Build an unsupervised model to detect unlabeled data is an urgent need at present.In this paper,unsupervised learning DBSCAN combined with feature extraction of data has been used,and for some KPIs,its best F-Score can reach about 0.9,which is quite good for solving the current problem.
文摘Most of the isolated electrical systems throughout the world suffer from similar problems of fragility and high dependence on external resources to generate energy. Smart Grid solutions and integration of renewable energies in order to solve their problems have increased, although it is necessary to know their specific characteristics to select the optimal solutions for each case. Therefore, as the overall objective of INSULAE Project, the development of an Investment Planning Tool, IPT, is on the way. This paper provides a view on a characterization methodology developed for the set of Reference Islands and how it will help to exploit the IPT developed. For that, characterization vectors have been defined based on a selection of Key Performance Indicators (KPIs). And Reference Islands have been obtained from the analysis of KPIs data gathered from EU islands considering the vectors formed. The linkage of new islands to reference islands helps provide the new islands with an assessment on the possibility space of their investment plans with the aim of being a decarbonization plan considering the demonstrations already evaluated.
