Data-Driven Resiliency Solutions for Boards and Systems. Jin, S. & Chakrabarty, K. In 2018 31st International Conference on VLSI Design and 2018 17th International Conference on Embedded Systems (VLSID), pages 244–249, January, 2018. doi abstract bibtex Data analytics and real-time monitoring can be used to ensure that boards and systems operate as intended. This paper first describes how machine learning, statistical techniques, and information-theoretic analysis can be used to close the gap between working silicon and a working system. Next, it describes how time-series analysis can be used to analyze health status and detect anomalies in complex core router systems. Traditional techniques fail to identify abnormal or suspect patterns when the monitored data involves temporal measurements and exhibits significantly different statistical characteristics for its constituent features. This paper thus not only describes a feature-categorization-based hybrid method and a changepoint-based method to detect anomalies in time-varying features with different statistical characteristics, but also proposes a symbol-based health analyzer to obtain a full picture of the health status of monitored core routers. A comprehensive set of experimental results is presented for data collected during 30 days of field operation from over 20 core routers deployed by customers of a major telecom company.
@inproceedings{jin_data-driven_2018,
title = {Data-{Driven} {Resiliency} {Solutions} for {Boards} and {Systems}},
doi = {10.1109/VLSID.2018.70},
abstract = {Data analytics and real-time monitoring can be used to ensure that boards and systems operate as intended. This paper first describes how machine learning, statistical techniques, and information-theoretic analysis can be used to close the gap between working silicon and a working system. Next, it describes how time-series analysis can be used to analyze health status and detect anomalies in complex core router systems. Traditional techniques fail to identify abnormal or suspect patterns when the monitored data involves temporal measurements and exhibits significantly different statistical characteristics for its constituent features. This paper thus not only describes a feature-categorization-based hybrid method and a changepoint-based method to detect anomalies in time-varying features with different statistical characteristics, but also proposes a symbol-based health analyzer to obtain a full picture of the health status of monitored core routers. A comprehensive set of experimental results is presented for data collected during 30 days of field operation from over 20 core routers deployed by customers of a major telecom company.},
booktitle = {2018 31st {International} {Conference} on {VLSI} {Design} and 2018 17th {International} {Conference} on {Embedded} {Systems} ({VLSID})},
author = {Jin, S. and Chakrabarty, K.},
month = jan,
year = {2018},
keywords = {Anomaly detection, Correlation, Fault diagnosis, Feature extraction, Internet, Maintenance engineering, Monitoring, Real-time systems, boards, complex core router systems, condition monitoring, constituent features, data analysis, data analytics, data-driven resiliency solutions, feature-categorization, field operation, health status, hybrid method, information-theoretic analysis, learning (artificial intelligence), machine learning, monitored core routers, monitored data, real-time monitoring, statistical analysis, statistical characteristics, statistical techniques, symbol-based health analyzer, telecom company, telecommunication computing, telecommunication network routing, temporal measurements, time 30.0 d, time series, time-series analysis, time-varying features, working system},
pages = {244--249},
}
Downloads: 0
{"_id":"xiRZH9nWvk73mY9ad","bibbaseid":"jin-chakrabarty-datadrivenresiliencysolutionsforboardsandsystems-2018","author_short":["Jin, S.","Chakrabarty, K."],"bibdata":{"bibtype":"inproceedings","type":"inproceedings","title":"Data-Driven Resiliency Solutions for Boards and Systems","doi":"10.1109/VLSID.2018.70","abstract":"Data analytics and real-time monitoring can be used to ensure that boards and systems operate as intended. This paper first describes how machine learning, statistical techniques, and information-theoretic analysis can be used to close the gap between working silicon and a working system. Next, it describes how time-series analysis can be used to analyze health status and detect anomalies in complex core router systems. Traditional techniques fail to identify abnormal or suspect patterns when the monitored data involves temporal measurements and exhibits significantly different statistical characteristics for its constituent features. This paper thus not only describes a feature-categorization-based hybrid method and a changepoint-based method to detect anomalies in time-varying features with different statistical characteristics, but also proposes a symbol-based health analyzer to obtain a full picture of the health status of monitored core routers. A comprehensive set of experimental results is presented for data collected during 30 days of field operation from over 20 core routers deployed by customers of a major telecom company.","booktitle":"2018 31st International Conference on VLSI Design and 2018 17th International Conference on Embedded Systems (VLSID)","author":[{"propositions":[],"lastnames":["Jin"],"firstnames":["S."],"suffixes":[]},{"propositions":[],"lastnames":["Chakrabarty"],"firstnames":["K."],"suffixes":[]}],"month":"January","year":"2018","keywords":"Anomaly detection, Correlation, Fault diagnosis, Feature extraction, Internet, Maintenance engineering, Monitoring, Real-time systems, boards, complex core router systems, condition monitoring, constituent features, data analysis, data analytics, data-driven resiliency solutions, feature-categorization, field operation, health status, hybrid method, information-theoretic analysis, learning (artificial intelligence), machine learning, monitored core routers, monitored data, real-time monitoring, statistical analysis, statistical characteristics, statistical techniques, symbol-based health analyzer, telecom company, telecommunication computing, telecommunication network routing, temporal measurements, time 30.0 d, time series, time-series analysis, time-varying features, working system","pages":"244–249","bibtex":"@inproceedings{jin_data-driven_2018,\n\ttitle = {Data-{Driven} {Resiliency} {Solutions} for {Boards} and {Systems}},\n\tdoi = {10.1109/VLSID.2018.70},\n\tabstract = {Data analytics and real-time monitoring can be used to ensure that boards and systems operate as intended. This paper first describes how machine learning, statistical techniques, and information-theoretic analysis can be used to close the gap between working silicon and a working system. Next, it describes how time-series analysis can be used to analyze health status and detect anomalies in complex core router systems. Traditional techniques fail to identify abnormal or suspect patterns when the monitored data involves temporal measurements and exhibits significantly different statistical characteristics for its constituent features. This paper thus not only describes a feature-categorization-based hybrid method and a changepoint-based method to detect anomalies in time-varying features with different statistical characteristics, but also proposes a symbol-based health analyzer to obtain a full picture of the health status of monitored core routers. A comprehensive set of experimental results is presented for data collected during 30 days of field operation from over 20 core routers deployed by customers of a major telecom company.},\n\tbooktitle = {2018 31st {International} {Conference} on {VLSI} {Design} and 2018 17th {International} {Conference} on {Embedded} {Systems} ({VLSID})},\n\tauthor = {Jin, S. and Chakrabarty, K.},\n\tmonth = jan,\n\tyear = {2018},\n\tkeywords = {Anomaly detection, Correlation, Fault diagnosis, Feature extraction, Internet, Maintenance engineering, Monitoring, Real-time systems, boards, complex core router systems, condition monitoring, constituent features, data analysis, data analytics, data-driven resiliency solutions, feature-categorization, field operation, health status, hybrid method, information-theoretic analysis, learning (artificial intelligence), machine learning, monitored core routers, monitored data, real-time monitoring, statistical analysis, statistical characteristics, statistical techniques, symbol-based health analyzer, telecom company, telecommunication computing, telecommunication network routing, temporal measurements, time 30.0 d, time series, time-series analysis, time-varying features, working system},\n\tpages = {244--249},\n}\n\n","author_short":["Jin, S.","Chakrabarty, K."],"key":"jin_data-driven_2018","id":"jin_data-driven_2018","bibbaseid":"jin-chakrabarty-datadrivenresiliencysolutionsforboardsandsystems-2018","role":"author","urls":{},"keyword":["Anomaly detection","Correlation","Fault diagnosis","Feature extraction","Internet","Maintenance engineering","Monitoring","Real-time systems","boards","complex core router systems","condition monitoring","constituent features","data analysis","data analytics","data-driven resiliency solutions","feature-categorization","field operation","health status","hybrid method","information-theoretic analysis","learning (artificial intelligence)","machine learning","monitored core routers","monitored data","real-time monitoring","statistical analysis","statistical characteristics","statistical techniques","symbol-based health analyzer","telecom company","telecommunication computing","telecommunication network routing","temporal measurements","time 30.0 d","time series","time-series analysis","time-varying features","working system"],"metadata":{"authorlinks":{}},"downloads":0,"html":""},"bibtype":"inproceedings","biburl":"https://bibbase.org/zotero/bxt101","dataSources":["Wsv2bQ4jPuc7qme8R"],"keywords":["anomaly detection","correlation","fault diagnosis","feature extraction","internet","maintenance engineering","monitoring","real-time systems","boards","complex core router systems","condition monitoring","constituent features","data analysis","data analytics","data-driven resiliency solutions","feature-categorization","field operation","health status","hybrid method","information-theoretic analysis","learning (artificial intelligence)","machine learning","monitored core routers","monitored data","real-time monitoring","statistical analysis","statistical characteristics","statistical techniques","symbol-based health analyzer","telecom company","telecommunication computing","telecommunication network routing","temporal measurements","time 30.0 d","time series","time-series analysis","time-varying features","working system"],"search_terms":["data","driven","resiliency","solutions","boards","systems","jin","chakrabarty"],"title":"Data-Driven Resiliency Solutions for Boards and Systems","year":2018}