IP Library › Granted Patent US 12,475,615
Granted Patent B2
US 12,475,615 · App. 17/390,523 · Granted Nov 18, 2025

Systems and methods for trending patterns within time-series data

Inventors: Dustin Garvey (Exeter, NH); Sampanna Shahaji Salunke (Dublin, CA); Uri Shaft (Fremont, CA)
Assignee: Oracle International Corporation
G06T11/206G06F11/3452G06F17/18G06F18/2431G06F21/55G06N20/00G06Q10/04G06Q10/06G06Q10/0631G06Q10/1093G06Q30/0202G06T11/001G06F9/505G06F2218/12G06Q10/06315
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 12,475,615
App. No.
17/390,523
Granted
Nov 18, 2025
Kind
B2
Abstract

Systems and methods for trending patterns within a set of time-series data are described. In one or more embodiments, a set of one or more groups of data points that are associated with a particular seasonal pattern are generated within volatile and/or non-volatile storage. A set of pairwise slopes is determined for data point pairs within the set of one or more groups of data points. Based, at least in part on the plurality of pairwise slopes, a representative trend rate for the particular seasonal pattern is determined. A set of forecasted values is then generated within volatile or non-volatile storage based, at least in part, on the representative trend rate for the particular seasonal pattern.

Claims (71)

1 . A method comprising:

receiving a time-series dataset comprising a plurality of data points from a plurality of seasons, a sample rate, and a time horizon, the time-series data set comprising:

a first seasonal pattern corresponding to a first set of data points in a first season corresponding to a first period of time and a second set of data points in a second season, corresponding to a second period of time, wherein an exhibited behavior of the first set of data points recurs in the second set of data points and wherein the first period of time does not overlap with the second period of time and wherein the first period of time and the second period of time have the same duration, and

a second seasonal pattern corresponding to a third set of data points in the first season and a fourth set of data points in the second season, wherein an exhibited behavior of the third set of data points recurs in the fourth set of data points;

for the time-series data set:

determining, by a computer, a first representative trend rate for the first seasonal pattern based at least in part on a first weighted median slope associated with a first set of pairwise slopes for each pairing of data points within and among the first set of data points and the second set of data points, and a second representative trend rate for the second seasonal pattern based at least in part on a second weighted median slope associated with a second set of pairwise slopes for each pairing of data points within and among the third set of data points and the fourth set of data points, wherein the first representative trend rate is different from the second representative trend rate;

training, by the computer, a forecasting model to trend samples using the first representative trend rate for the first seasonal pattern and the second representative trend rate for the second seasonal pattern;

mapping the first seasonal pattern to a first set of forecasting components of the forecasting model including the first representative trend rate and a first anchor point for the first set of data points and the second set of data points;

mapping the second seasonal pattern to a second set of forecasting components of the forecasting model, including the second representative trend rate and a second anchor point for the third set of data points and the fourth set of data points, wherein the first anchor point is different than the second anchor point;

applying, by the computer, the forecasting model to the time-series dataset to project metrics for one or more hardware or software resources for a future time period comprising time from an end of the time-series dataset to the time horizon at least by:

identifying a sequence of sub-periods within the future time period based on the sample rate;

identifying, for a first sub-period, that the first sub-period is associated with the first seasonal pattern;

generating a first metric for the first sub-period, based on the first representative trend rate associated with the first seasonal pattern, as a function of at least the first representative trend rate and the first anchor point for the first seasonal pattern;

identifying, for a second sub-period, that the second sub-period is associated with the second seasonal pattern; and

generating a second metric for the second sub-period, based on the second representative trend rate associated with the second seasonal pattern, as a function of at least the second representative trend rate and the second anchor point for the second seasonal pattern; and

deploying or consolidating at least one computing resource responsive to the metrics projected by applying the forecasting model.

2 . The method of claim 1 , wherein the first set of data points and the second set of data points are seasonal highs and the third set of data points and the fourth set of data points are seasonal lows; wherein the first weighted median slope is computed based on pairwise slopes in the first and second sets of data points; wherein the second weighted median slope is computed based on pairwise slopes in the third and fourth sets of data points.

3 . The method of claim 1 , wherein the first set of data points and the second set of data points are sparse seasonal highs and the third set of data points and the fourth set of data points are dense seasonal highs.

4 . The method of claim 1 , further comprising:

grouping data points in the time-series dataset by seasonal pattern classification and a component of a season; and

computing, for each individual group of data points, pairwise slopes for each pairing of data points within each individual group, wherein a first set of groups is associated with the first seasonal pattern and a second set of groups is associated with the second seasonal pattern;

wherein the first representative trend rate is determined based on the pairwise slopes for the first set of groups associated with the first seasonal pattern and the second representative trend rate is determined based on the pairwise slopes for the second set of groups associated with the second seasonal pattern.

5 . The method of claim 4 , wherein the first weighted median slope is determined based on a first cumulative weight for sorted slopes in the first set of groups associated with the first seasonal pattern, wherein the second median slope is determined based on a second cumulative weight for sorted slopes in the second set of groups associated with the second seasonal pattern.

6 . The method of claim 1 , wherein the first weighted median slope is determined based at least in part on weights assigned to data points in the time-series dataset; wherein a weight for a data point is computed by dividing a first number representing a seasonal cycle where the data point falls by a second number representing the total number of seasonal cycles used to train the forecasting model.

7 . The method of claim 1 , wherein applying the forecasting model further comprises determining a first tolerance interval for the first seasonal pattern and a second tolerance interval for the second seasonal pattern.

8 . The method of claim 1 , further comprising: performing, by one or more hardware or software resources, one or more operations to satisfy anticipated demand based on the metrics projected by applying the forecasting model.

9 . One or more non-transitory computer-readable media storing instructions, which when executed by one or more hardware processors, cause the one or more processors to:

receiving a time-series dataset comprising a plurality of data points from a plurality of seasons, a sample rate, and a time horizon, the time-series data set comprising:

a first seasonal pattern corresponding to a first set of data points in a first season corresponding to a first time period and a second set of data points in a second season corresponding to a second time period, wherein an exhibited behavior of the first set of data points recurs in the second set of data points and wherein the first time period does not overlap with the second time period and wherein the first period of time and the second period of time have the same duration, and

a second seasonal pattern corresponding to a third set of data points in the first season and a fourth set of data points in the second season, wherein an exhibited behavior of the third set of data points recurs in the fourth set of data points;

for the time-series data set:

determine a first representative trend rate for the first seasonal pattern based at least in part on a first weighted median slope associated with a first set of pairwise slopes for each pairing of data points within and among the first set of data points and the second set of data points in a time-series dataset, and a second representative trend rate for the second seasonal pattern based at least in part on a second weighted median slope associated with a second set of pairwise slopes for each pairing of data points within and among the third set of data points and the fourth set of data points in the time-series dataset, wherein the first representative trend rate is different from the second representative trend rate;

train a forecasting model to trend samples using the first representative trend rate for the first seasonal pattern and the second representative trend rate for the second seasonal pattern;

mapping the first seasonal pattern to a first set of forecasting components of the forecasting model including the first representative trend rate and a first anchor point for the first set of data points and the second set of data points;

mapping the second seasonal pattern to a second set of forecasting components of the forecasting model, including the second representative trend rate and a second anchor point for the third set of data points and the fourth set of data points, wherein the first anchor point is different than the second anchor point;

apply the forecasting model to the time-series dataset to project metrics for one or more hardware or software resources for a future time period comprising time from an end of the time-series dataset to the time horizon at least by:

identifying a sequence of sub-periods within the future time period based on the sample rate;

identifying, for a first sub-period, that the first sub-period is associated with the first seasonal pattern;

generating a first metric for the first sub-period, based on the first representative trend rate associated with the first seasonal pattern, as a function of at least the first representative trend rate and the first anchor point for the first seasonal pattern;

identifying, for a second sub-period, that the second sub-period is associated with the second seasonal pattern; and

generating a second metric for the second sub-period, based on the second representative trend rate associated with the second seasonal pattern, as a function of at least the second representative trend rate and the second anchor point for the second seasonal pattern; and

deploy or consolidate at least one computing resource responsive to the metrics projected by applying the forecasting model.

10 . The one or more non-transitory computer-readable media of claim 9 , wherein the first set of data points and the second set of data points are seasonal highs and the third set of data points and the fourth set of data points are seasonal lows; wherein the first weighted median slope is computed based on pairwise slopes in the first and second sets of data points; wherein the second weighted median slope is computed based on pairwise slopes in the third and fourth sets of data points.

11 . The one or more non-transitory computer-readable media of claim 9 , wherein the first set of data points and the second set of data points are sparse seasonal highs and the third set of data points and the fourth set of data points are dense seasonal highs.

12 . The one or more non-transitory computer-readable media of claim 9 , wherein the instructions further cause:

grouping data points in the time-series dataset by seasonal pattern classification and a component of a season; and

computing, for each individual group of data points, pairwise slopes for each pairing of data points within each individual group, wherein a first set of groups is associated with the first seasonal pattern and a second set of groups is associated with the second seasonal pattern;

wherein the first representative trend rate is determined based on the pairwise slopes for the first set of groups associated with the first seasonal pattern and the second representative trend rate is determined based on the pairwise slopes for the second set of groups associated with the second seasonal pattern.

13 . The one or more non-transitory computer-readable media of claim 12 , wherein the first weighted median slope is determined based on a first cumulative weight for sorted slopes in the first set of groups associated with the first seasonal pattern, wherein the first second median slope is determined based on a second cumulative weight for sorted slopes in the second set of groups associated with the second seasonal pattern.

14 . The one or more non-transitory computer-readable media of claim 9 , wherein the first weighted median slope is determined based at least in part on weights assigned to data points in the time-series dataset; wherein a weight for a data point is computed by dividing a first number representing a seasonal cycle where the data point falls by a second number representing the total number of seasonal cycles used to train the forecasting model.

15 . The one or more non-transitory computer-readable media of claim 9 , wherein applying the forecasting model further comprises determining a first tolerance interval for the first seasonal pattern and a second tolerance interval for the second seasonal pattern.

16 . The one or more non-transitory computer-readable media of claim 9 , wherein the instructions further cause: performing, by one or more hardware or software resources, one or more operations to satisfy anticipated demand based on the metrics projected by applying the forecasting model.

17 . A system comprising:

one or more hardware processors;

one or more non-transitory computer-readable media storing instructions which, when executed by the one or more hardware processors, cause operations comprising:

receiving a time-series dataset comprising a plurality of data points from a plurality of seasons, a sample rate, and a time horizon, the time-series data set comprising:

a first seasonal pattern corresponding to a first set of data points in a first season corresponding to a first time period and a second set of data points in a second season corresponding to a second time period, wherein an exhibited behavior of the first set of data points recurs in the second set of data points and wherein the first time period does not overlap with the second time period and wherein the first period of time and the second period of time have the same duration, and

a second seasonal pattern corresponding to a third set of data points in the first season and a fourth set of data points in the second season, wherein an exhibited behavior of the third set of data points recurs in the fourth set of data points;

for the time-series data set:

determining a first representative trend rate for the first seasonal pattern based at least in part on a first weighted median slope associated with a first set of pairwise slopes for each pairing of data points within and among the first set of data points and the second set of data points, and a second representative trend rate for the second seasonal pattern based at least in part on a second weighted median slope associated with a second set of pairwise slopes for each pairing of data points within and among the third set of data points and the fourth set of data points in the time-series dataset, wherein the first representative trend rate is different from the second representative trend rate;

training a forecasting model to trend samples using the first representative trend rate for the first seasonal pattern and the second representative trend rate for the second seasonal pattern;

mapping the first seasonal pattern to a first set of forecasting components of the forecasting model including the first representative trend rate and a first anchor point for the first set of data points and the second set of data points;

mapping the second seasonal pattern to a second set of forecasting components of the forecasting model, including the second representative trend rate and a second anchor point for the third set of data points and the fourth set of data points, wherein the first anchor point is different than the second anchor point;

applying the forecasting model to the time-series dataset to project metrics for one or more hardware or software resources for a future time period comprising time from an end of the time-series dataset to the time horizon at least by:

identifying a sequence of sub-periods within the future time period based on the sample rate;

identifying, for a first sub-period, that the first sub-period is associated with the first seasonal pattern;

generating a first metric for the first sub-period, based on the first representative trend rate associated with the first seasonal pattern, as a function of at least the first representative trend rate and the first anchor point for the first seasonal pattern;

identifying, for a second sub-period, that the second sub-period is associated with the second seasonal pattern; and

generating a second metric for the second sub-period, based on the second representative trend rate associated with the second seasonal pattern, as a function of at least the second representative trend rate and the second anchor point for the second seasonal pattern; and

deploying or consolidating at least one computing resource responsive to the metrics projected by applying the forecasting model.

18 . The system of claim 17 , wherein the first set of data points and the second set of data points are seasonal highs and the third set of data points and the fourth set of data points are seasonal lows; wherein the first weighted median slope is computed based on pairwise slopes in the first and second sets of data points; wherein the second weighted median slope is computed based on pairwise slopes in the third and fourth sets of data points.

Assignments (2)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Nov 15, 2025
From: CHEN, GUANNAN
To: HONGKONG YI ZHAN E-COMMERCE LIMITED
Reel/Frame 072917/0457 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Aug 2, 2021
From: GARVEY, DUSTIN; SALUNKE, SAMPANNA SHAHAJI; SHAFT, URI
To: ORACLE INTERNATIONAL CORPORATION
Reel/Frame 057052/0105 →
Continuity (4)
Continuation 15266987 · Sep 15, 2016
Provisional Application 62301585 · Feb 29, 2016
Provisional Application 62301590 · Feb 29, 2016
Related Publication 20220020188A1 · Jan 20, 2022
References Cited (290)
US 5448476A · Kurokawa et al. · 1995 [cited by applicant]
US 6298063B1 · Coile et al. · 2001 [cited by applicant]
US 6438592B1 · Killian · 2002 [cited by applicant]
US 6597777B1 · Ho · 2003 [cited by applicant]
US 6643613B2 · McGee et al. · 2003 [cited by applicant]
US 6928398B1 · Fang et al. · 2005 [cited by applicant]
US 6996599B1 · Anders et al. · 2006 [cited by applicant]
US 7343375B1 · Dulac · 2008 [cited by applicant]
US 7529991B2 · Ide et al. · 2009 [cited by applicant]
US 7672814B1 · Raanan et al. · 2010 [cited by applicant]
US 7739143B1 · Dwarakanath et al. · 2010 [cited by applicant]
US 7739284B2 · Aggarwal et al. · 2010 [cited by applicant]
US 7783510B1 · Gilgur et al. · 2010 [cited by applicant]
US 7987106B1 · Aykin · 2011 [cited by applicant]
US 8014983B2 · Crowe et al. · 2011 [cited by applicant]
US 8200454B2 · Dorneich et al. · 2012 [cited by applicant]
US 8229876B2 · Roychowdhury · 2012 [cited by applicant]
US 8234236B2 · Beaty et al. · 2012 [cited by applicant]
US 8363961B1 · Avidan et al. · 2013 [cited by applicant]
US 8576964B2 · Taniguchi et al. · 2013 [cited by applicant]
US 8583649B2 · Ailon et al. · 2013 [cited by applicant]
US 8635328B2 · Corley et al. · 2014 [cited by applicant]
US 8650299B1 · Huang et al. · 2014 [cited by applicant]
US 8676964B2 · Gopalan et al. · 2014 [cited by applicant]
US 8694969B2 · Bernardini et al. · 2014 [cited by applicant]
US 8776066B2 · Krishnamurthy et al. · 2014 [cited by applicant]
US 8880525B2 · Galle et al. · 2014 [cited by applicant]
US 8893086B2 · Bassin et al. · 2014 [cited by applicant]
US 8930757B2 · Nakagawa · 2015 [cited by applicant]
US 8949677B1 · Brundage et al. · 2015 [cited by applicant]
US 9002774B2 · Karlsson · 2015 [cited by applicant]
US 9053171B2 · Ailon et al. · 2015 [cited by applicant]
US 9081857B1 · Huet et al. · 2015 [cited by applicant]
US 9141914B2 · Viswanathan et al. · 2015 [cited by applicant]
US 9147167B2 · Urmanov et al. · 2015 [cited by applicant]
US 9195563B2 · Scarpelli · 2015 [cited by applicant]
US 9218232B2 · Khalastchi et al. · 2015 [cited by applicant]
US 9292408B2 · Bernstein et al. · 2016 [cited by applicant]
US 9323599B1 · Iyer et al. · 2016 [cited by applicant]
US 9323837B2 · Zhao et al. · 2016 [cited by applicant]
US 9330119B2 · Chan et al. · 2016 [cited by applicant]
US 9355357B2 · Hao et al. · 2016 [cited by applicant]
US 9367382B2 · Yabuki · 2016 [cited by applicant]
US 9389946B2 · Higuchi · 2016 [cited by applicant]
US 9471778B1 · Seo et al. · 2016 [cited by applicant]
US 9495220B2 · Talyansky · 2016 [cited by applicant]
US 9495395B2 · Chan et al. · 2016 [cited by applicant]
US 9507718B2 · Rash et al. · 2016 [cited by applicant]
US 9514213B2 · Wood et al. · 2016 [cited by applicant]
US 9529630B1 · Fakhouri et al. · 2016 [cited by applicant]
US 9658910B2 · Poola et al. · 2017 [cited by applicant]
US 9658916B2 · Yoshinaga et al. · 2017 [cited by applicant]
US 9692662B2 · Chan et al. · 2017 [cited by applicant]
US 9710493B2 · Wang et al. · 2017 [cited by applicant]
US 9727533B2 · Thibaux · 2017 [cited by applicant]
US 9740402B2 · Manoharan et al. · 2017 [cited by applicant]
US 9779361B2 · Jones et al. · 2017 [cited by applicant]
US 9811394B1 · Kogias et al. · 2017 [cited by applicant]
US 9961571B2 · Yang et al. · 2018 [cited by applicant]
US 10073906B2 · Lu et al. · 2018 [cited by applicant]
US 10210036B2 · Iyer et al. · 2019 [cited by applicant]
US 10331802B2 · Garvey et al. · 2019 [cited by applicant]
US 10692255B2 · Garvey et al. · 2020 [cited by applicant]
US 10699211B2 · Garvey et al. · 2020 [cited by applicant]
US 10885461B2 · Garvey et al. · 2021 [cited by applicant]
US 10915830B2 · Garvey et al. · 2021 [cited by applicant]
US 11146463B2 · Tedaldi et al. · 2021 [cited by applicant]
US 11295217B2 · Herzog · 2022 [cited by applicant]
US 11404145B2 · Saripalli et al. · 2022 [cited by applicant]
US 20020019860A1 · Lee et al. · 2002 [cited by applicant]
US 20020092004A1 · Lee et al. · 2002 [cited by applicant]
US 20020183972A1 · Enck et al. · 2002 [cited by applicant]
US 20020188650A1 · Sun et al. · 2002 [cited by applicant]
US 20030149603A1 · Ferguson et al. · 2003 [cited by applicant]
US 20030154044A1 · Lundstedt et al. · 2003 [cited by applicant]
US 20030224344A1 · Shamir et al. · 2003 [cited by applicant]
US 20040138936A1 · Johnson et al. · 2004 [cited by applicant]
US 20050119982A1 · Ito et al. · 2005 [cited by applicant]
US 20050132030A1 · Hopen et al. · 2005 [cited by applicant]
US 20050159927A1 · Cruz et al. · 2005 [cited by applicant]
US 20050193281A1 · Ide et al. · 2005 [cited by applicant]
US 20060065717A1 · Hurwitz et al. · 2006 [cited by applicant]
US 20060087962A1 · Golia et al. · 2006 [cited by applicant]
US 20060106743A1 · Horvitz · 2006 [cited by applicant]
US 20060106797A1 · Srinivasa et al. · 2006 [cited by applicant]
US 20060161485A1 · Meldahl · 2006 [cited by applicant]
US 20060212593A1 · Patrick et al. · 2006 [cited by applicant]
US 20060287848A1 · Li et al. · 2006 [cited by applicant]
US 20070011281A1 · Jhoney et al. · 2007 [cited by applicant]
US 20070150329A1 · Brook et al. · 2007 [cited by applicant]
US 20070168494A1 · Liu et al. · 2007 [cited by applicant]
US 20070179836A1 · Juang et al. · 2007 [cited by applicant]
US 20080221974A1 · Gilgur et al. · 2008 [cited by applicant]
US 20080288089A1 · Pettus et al. · 2008 [cited by applicant]
US 20090024427A1 · Shan · 2009 [cited by applicant]
US 20090030752A1 · Senturk-Doganaksoy et al. · 2009 [cited by applicant]
US 20090198559A1 · Wang et al. · 2009 [cited by applicant]
US 20100027552A1 · Hill · 2010 [cited by applicant]
US 20100036857A1 · Marvasti et al. · 2010 [cited by applicant]
US 20100050023A1 · Scarpelli et al. · 2010 [cited by applicant]
US 20100082132A1 · Marruchella et al. · 2010 [cited by applicant]
US 20100082697A1 · Gupta et al. · 2010 [cited by applicant]
US 20100185499A1 · Dwarakanath et al. · 2010 [cited by applicant]
US 20100257026A1 · Brocklebank · 2010 [cited by applicant]
US 20100324869A1 · Cherkasova et al. · 2010 [cited by applicant]
US 20110022879A1 · Chavda et al. · 2011 [cited by applicant]
US 20110040575A1 · Wright et al. · 2011 [cited by applicant]
US 20110125894A1 · Anderson et al. · 2011 [cited by applicant]
US 20110126197A1 · Larsen et al. · 2011 [cited by applicant]
US 20110126275A1 · Anderson et al. · 2011 [cited by applicant]
US 20110213788A1 · Zhao et al. · 2011 [cited by applicant]
US 20110265164A1 · Lucovsky et al. · 2011 [cited by applicant]
US 20120005359A1 · Seago et al. · 2012 [cited by applicant]
US 20120051369A1 · Bryan et al. · 2012 [cited by applicant]
US 20120066389A1 · Hegde et al. · 2012 [cited by applicant]
US 20120110462A1 · Eswaran et al. · 2012 [cited by applicant]
US 20120110583A1 · Balko et al. · 2012 [cited by applicant]
US 20120203823A1 · Manglik et al. · 2012 [cited by applicant]
US 20120240072A1 · Altamura et al. · 2012 [cited by applicant]
US 20120265881A1 · Chen et al. · 2012 [cited by applicant]
US 20120278477A1 · Terrell et al. · 2012 [cited by applicant]
US 20120278663A1 · Hasegawa · 2012 [cited by applicant]
US 20120296696A1 · Cantor et al. · 2012 [cited by applicant]
US 20120323988A1 · Barzel et al. · 2012 [cited by applicant]
US 20130013535A1 · Punera et al. · 2013 [cited by applicant]
US 20130024173A1 · Brzezicki et al. · 2013 [cited by applicant]
US 20130103616A1 · Hao et al. · 2013 [cited by applicant]
US 20130151179A1 · Gray · 2013 [cited by applicant]
US 20130226320A1 · Berg-Sonne et al. · 2013 [cited by applicant]
US 20130282891A1 · Davis et al. · 2013 [cited by applicant]
US 20130326202A1 · Rosenthal et al. · 2013 [cited by applicant]
US 20130329981A1 · Hiroike · 2013 [cited by applicant]
US 20140058572A1 · Stein et al. · 2014 [cited by applicant]
US 20140095422A1 · Solomon et al. · 2014 [cited by applicant]
US 20140101119A1 · Li et al. · 2014 [cited by applicant]
US 20140101300A1 · Rosensweig et al. · 2014 [cited by applicant]
US 20140143401A1 · Carlen et al. · 2014 [cited by applicant]
US 20140156557A1 · Zeng et al. · 2014 [cited by applicant]
US 20140215470A1 · Iniguez · 2014 [cited by applicant]
US 20140310235A1 · Chan et al. · 2014 [cited by applicant]
US 20140325649A1 · Zhang · 2014 [cited by applicant]
US 20140379717A1 · Urmanov et al. · 2014 [cited by applicant]
US 20150032775A1 · Yang et al. · 2015 [cited by applicant]
US 20150033084A1 · Sasturkar et al. · 2015 [cited by applicant]
US 20150040142A1 · Cheetancheri et al. · 2015 [cited by applicant]
US 20150046123A1 · Kato · 2015 [cited by applicant]
US 20150046920A1 · Allen · 2015 [cited by applicant]
US 20150065121A1 · Gupta et al. · 2015 [cited by applicant]
US 20150081877A1 · Sethi et al. · 2015 [cited by applicant]
US 20150180734A1 · Maes et al. · 2015 [cited by applicant]
US 20150205691A1 · Seto · 2015 [cited by applicant]
US 20150234869A1 · Chan et al. · 2015 [cited by applicant]
US 20150242243A1 · Balakrishnan et al. · 2015 [cited by applicant]
US 20150244597A1 · Maes et al. · 2015 [cited by applicant]
US 20150248446A1 · Nordstrom et al. · 2015 [cited by applicant]
US 20150251074A1 · Ahmed et al. · 2015 [cited by applicant]
US 20150254330A1 · Chan et al. · 2015 [cited by applicant]
US 20150296030A1 · Maes et al. · 2015 [cited by applicant]
US 20150302318A1 · Chen et al. · 2015 [cited by applicant]
US 20150309840A1 · Ding et al. · 2015 [cited by applicant]
US 20150312274A1 · Bishop et al. · 2015 [cited by applicant]
US 20150317589A1 · Anderson et al. · 2015 [cited by applicant]
US 20150371144A1 · Engle · 2015 [cited by applicant]
US 20150377938A1 · Bansal et al. · 2015 [cited by applicant]
US 20160042289A1 · Poola et al. · 2016 [cited by applicant]
US 20160062950A1 · Brodersen et al. · 2016 [cited by applicant]
US 20160071517A1 · Beaver et al. · 2016 [cited by applicant]
US 20160092516A1 · Poola et al. · 2016 [cited by applicant]
US 20160105327A9 · Cremonesi et al. · 2016 [cited by applicant]
US 20160139964A1 · Chen et al. · 2016 [cited by applicant]
US 20160171037A1 · Mathur et al. · 2016 [cited by applicant]
US 20160253381A1 · Kim et al. · 2016 [cited by applicant]
US 20160283533A1 · Urmanov et al. · 2016 [cited by applicant]
US 20160292611A1 · Boe et al. · 2016 [cited by applicant]
US 20160294773A1 · Yu et al. · 2016 [cited by applicant]
US 20160299938A1 · Malhotra et al. · 2016 [cited by applicant]
US 20160299961A1 · Olsen · 2016 [cited by applicant]
US 20160321588A1 · Das · 2016 [cited by examiner]
US 20160342909A1 · Chu · 2016 [cited by examiner]
US 20160357674A1 · Waldspurger et al. · 2016 [cited by applicant]
US 20160378809A1 · Chen et al. · 2016 [cited by applicant]
US 20170061297A1 · Joshi et al. · 2017 [cited by applicant]
US 20170061321A1 · Maiya et al. · 2017 [cited by applicant]
US 20170249563A1 · Garvey et al. · 2017 [cited by applicant]
US 20170249564A1 · Garvey et al. · 2017 [cited by applicant]
US 20170249648A1 · Garvey et al. · 2017 [cited by applicant]
US 20170249649A1 · Garvey et al. · 2017 [cited by applicant]
US 20170249763A1 · Garvey et al. · 2017 [cited by applicant]
US 20170262223A1 · Dalmatov et al. · 2017 [cited by applicant]
US 20170284903A1 · Anderson et al. · 2017 [cited by applicant]
US 20170329660A1 · Salunke et al. · 2017 [cited by applicant]
US 20170351563A1 · Miki et al. · 2017 [cited by applicant]
US 20170364851A1 · Maheshwari et al. · 2017 [cited by applicant]
US 20180026907A1 · Miller et al. · 2018 [cited by applicant]
US 20180039555A1 · Salunke et al. · 2018 [cited by applicant]
US 20180052804A1 · Mikami et al. · 2018 [cited by applicant]
US 20180053207A1 · Modani et al. · 2018 [cited by applicant]
US 20180059628A1 · Yoshida · 2018 [cited by applicant]
US 20180060744A1 · Achin et al. · 2018 [cited by applicant]
US 20180081629A1 · Kuhhirte et al. · 2018 [cited by applicant]
US 20180219889A1 · Oliner et al. · 2018 [cited by applicant]
US 20180268152A1 · Cuomo et al. · 2018 [cited by applicant]
US 20180321989A1 · Shetty et al. · 2018 [cited by applicant]
US 20180324199A1 · Crotinger et al. · 2018 [cited by applicant]
US 20180330433A1 · Frenzel et al. · 2018 [cited by applicant]
US 20180349797A1 · Garvey et al. · 2018 [cited by applicant]
US 20180351786A1 · Pope et al. · 2018 [cited by applicant]
US 20190042982A1 · Qu et al. · 2019 [cited by applicant]
US 20190065275A1 · Wong et al. · 2019 [cited by applicant]
US 20190121808A1 · Chadha et al. · 2019 [cited by applicant]
US 20190163806A1 · Bauer et al. · 2019 [cited by applicant]
US 20190305876A1 · Sundaresan et al. · 2019 [cited by applicant]
US 20190379589A1 · Ryan et al. · 2019 [cited by applicant]
US 20190392098A1 · Mehta et al. · 2019 [cited by applicant]
US 20200027024A1 · Aggarwal et al. · 2020 [cited by applicant]
US 20200034745A1 · Nagpal et al. · 2020 [cited by applicant]
US 20200074323A1 · Martin et al. · 2020 [cited by applicant]
US 20200125471A1 · Garvey et al. · 2020 [cited by applicant]
US 20200125988A1 · Garvey et al. · 2020 [cited by applicant]
US 20200337648A1 · Saripalli et al. · 2020 [cited by applicant]
US 20200387797A1 · Ryan et al. · 2020 [cited by applicant]
US 20210028973A1 · Ct et al. · 2021 [cited by applicant]
US 20210073680A1 · Garvey et al. · 2021 [cited by applicant]
US 20210257060A1 · Curtis et al. · 2021 [cited by applicant]
US 20220138624A1 · Mizoguchi · 2022 [cited by applicant]
CN 1097829A · 1995 [cited by applicant]
CN 101482944A · 2009 [cited by applicant]
CN 103984938A · 2014 [cited by applicant]
CN 105144112A · 2015 [cited by applicant]
CN 105426411A · 2016 [cited by applicant]
CN 109359763A · 2019 [cited by applicant]
EP 2984568A1 · 2016 [cited by applicant]
JP 2006129446A · 2006 [cited by applicant]
WO 2011071624A2 · 2011 [cited by applicant]
WO 2013016584A1 · 2013 [cited by applicant]
WO 2014168981A1 · 2014 [cited by applicant]
WO 2014169056A1 · 2014 [cited by applicant]
Suntinger, “Trend-based similarity search in time-series data,” 2010, Second International Conference on Advances in Databases, Knowledge, and Data Applications, IEEE, pp. 97-106 (Year: 2010). [cited by examiner]
Ghosh, “Biting off safely more than you can chew: Predictive analytics for resource over-commit in iaas cloud,” 2012, In 2012 IEEE Fifth International Conference on Cloud Computing, pp. 25-32 (Year: 2012). [cited by examiner]
Herbst, “Self-adaptive workload classification and forecasting for proactive resource provisioning”, 2014, ICPE'13, pp. 187-198 (Year: 2014). [cited by examiner]
Guajardo, et al., “A model updating strategy for predicting time series with seasonal patterns” Applied Soft Computing, vol. 10 No. 1, 2010, pp. 276-283. [cited by applicant]
Kuhn, Markus, A summary of the international standard date and time notation (https://www.cl.cam.ac.uk/˜mgk25/iso-time.html), date retrieved from web.archive.org Oct. 13, 2018, 5 pages (Year: 2018). [cited by applicant]
Morgan, Derek P., Chapter 4: ISO 8601 Dates, Times, Datetimes, Durations, and Functions, The Essential Guide to SAS Dates and Times, Second Edition, Dec. 2014, 40 pages (Year: 2014). [cited by applicant]
“OpenStack Compute Administration Manual”, Mar. 1, 2011 (Mar. 1, 2011), XP055207492, Retrieved from the Internet: URL:http://web.archive.org/web/20110708071910/http://docs.openstack.org/bexar/openstack-compute/admin/os-… [cited by applicant]
“OpenStack Object Storage Administrator Manual”, Jun. 2, 2011 (Jun. 2, 2011), XP055207490, Retrieved from the Internet: URL:http://web.archive.org/web/20110727190919/http://docs.openstack.org/cactus/openstack-object-sto… [cited by applicant]
“Time Series Pattern Search: A tool to extract events from time series data”, available online at <https://www.ceadar.ie/pages/time-series-pattern-search/>, retrieved on Apr. 24, 2020, 4 pages. [cited by applicant]
Ahmed, Reservoir-based network traffic stream summarization for anomaly detection, Article in Pattern Analysis and Applications, Oct. 2017. [cited by applicant]
Alberto Zuin: “OpenNebula Setting up High Availability in OpenNebula with LVM”, May 2, 2011 (May 2, 2011), XP055207701, Retrieved from the Internet: URL:http://opennebula.org/setting-up-highavailability-in-opennebula-wi… [cited by applicant]
Andrew Beekhof: “Clusters from Scratch—Apache, DRBD and GFS2 Creating Active/Passive and Active/Active Clusters on Fedora 12”, Mar. 11, 2010 (Mar. 11, 2010), XP055207651, Retrieved from the Internet: URL:http://clusterl… [cited by applicant]
Anonymous: “High Availability for the Ubuntu Enterprise Cloud (UEC)—Cloud Controller (CLC)”, Feb. 19, 2011 (Feb. 19, 2011), XP055207708, Retrieved from the Internet: URL:http://blog.csdn.net/superxgl/article/details/619… [cited by applicant]
Charapko, Gorilla—Facebook's Cache for Time Series Data, http://charap.co/gorilla-facebooks-cache-for-monitoring-data/, Jan. 11, 2017. [cited by applicant]
Chris Bunch et al: “AppScale: Open-Source Platform-As-A-Service”, Jan. 1, 2011 (Jan. 1, 2011), XP055207440, Retrieved from the Internet: URL:http://128.111.41.26/research/tech reports/reports/2011-01 .pdf [retrieved on … [cited by applicant]
Davies, David L., et al., “A Cluster Separation measure”, IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. PAMI-1, No. 2, Apr. 1979, pp. 224-227. [cited by applicant]
Dunning et al., Computing Extremely Accurate Quantiles Using t-Digests. [cited by applicant]
Faraz Rasheed, “A Framework for Periodic Outlier Pattern Detection in Time-Series Sequences,” May 2014, IEEE. [cited by applicant]
Greenwald et al. “Space-efficient online computation of quantile summaries.” ACM Proceedings of the 2001 SIGMOD international conference on Management of data pp. 58-66. [cited by applicant]
Greunen, “Forecasting Methods for Cloud Hosted Resources, a comparison,” 2015, 11th International Conference on Network and Service Management (CNSM), pp. 29-35 (Year: 2015). [cited by applicant]
Gueyoung Jung et al: “Performance and availability aware regeneration for cloud based multitier applications”, Dependable Systems and Networks (DSN), 2010 IEEE/IFIP International Conference On, IEEE, Piscataway, NJ, USA… [cited by applicant]
Gunter et al., Log Summarization and Anomaly Detection for Troubleshooting Distributed Systems, Conference: 8th IEEE/ACM International Conference on Grid Computing (GRID 2007), Sep. 19-21, 2007, Austin, Texas, USA, Proc… [cited by applicant]
Hao et al., Visual Analytics of Anomaly Detection in Large Data Streams, Proc. SPIE 7243, Visualization and Data Analysis 2009, 10 pages. [cited by applicant]
Haugen et al., “Extracting Common Time Trends from Concurrent Time Series: Maximum Autocorrelation Factors with Applications”, Stanford University, Oct. 20, 2015, pp. 1-38. [cited by applicant]
Jain and Chlamtac, P-Square Algorithm for Dynamic Calculation of Quantiles and Histograms Without Storing Observations, ACM, Oct. 1985 (10 pages). [cited by applicant]
Jarvis, R. A., et al., “Clustering Using a Similarity Measure Based on Shared Neighbors”, IEEE Transactions on Computers, vol. C-22, No. 11, Nov. 1973, pp. 1025-1034. [cited by applicant]
Lehmann, “Variability of Atmospheric Circulation Patterns Associated With Large Volume Changes of the Baltic Sea”, Adv. Sci. Res., 12, 219-225, 2015, www.adv-sci-res.net/12/219/2015/DOI: 10.5.194/ASR-12-219-2015 (Year: … [cited by applicant]
Li et al., “Forecasting Web Page Views: Methods and Observations,” in 9 J. Machine Learning Res. 2217-50 (2008). (Year: 2008). [cited by applicant]
Lin, Xuemin, et al. “Continuously maintaining quantile summaries of the most recent n elements over a data stream,” IEEE, 2004. [cited by applicant]
Niino, Junichi, “Open Source Cloud infrastructure ‘OpenStack’, its History and Scheme”, available online at <http://www.publickey1.jp/blog/11/openstack_1.html>, Jun. 13, 2011, 8 pages. [cited by applicant]
Nurmi D et al: “The Eucalyptus Open-Source Cloud-Computing System”, Cluster Computing and the Grid, 2009. CCGRID '09. 9th IEEE/ACM International Symposium On, IEEE, Piscataway, NJ, USA, May 18, 2009 (May 18, 2009), pp. … [cited by applicant]
Qiu, Hai, et al. “Anomaly detection using data clustering and neural networks.” Neural Networks, 2008. IJCNN 2008.(IEEE World Congress on Computational Intelligence). IEEE International Joint Conference on. IEEE, 2008. [cited by applicant]
Slipetskyy, Rostyslav, “Security Issues in OpenStack”, Maste s Thesis, Technical University of Denmark, Jun. 2011, p. 7 (entire document especially abstract). [cited by applicant]
Somlo, Gabriel, et al., “Incremental Clustering for Profile Maintenance in Information Gathering Web Agents”, Agents '01, Montreal, Quebec, Canada, May 28-Jun. 1, 2001, pp. 262-269. [cited by applicant]
Szmit et al., “Usage of Modified Holt-Winters Method in the Anomaly Detection of Network Traffic: Case Studies”, Journal of Computer Networks and Communications, vol. 2012, Article ID 192913, Mar. 29, 2012, pp. 1-5. [cited by applicant]
Taylor J W et al: “Forecasting intraday time series with multiple seasonal cycles using parsimonious seasonal exponential smoothing”, Omega, vol. 40, No. 6, Dec. 2012 (Dec. 2012), pp. 748-757. [cited by applicant]
Time Series Pattern Search: A tool to extract events from time series data, available online at <https://www.ceadar.ie/pages/time-series-pattem-search/>, retrieved on Apr. 24, 2020, 4 pages. [cited by applicant]
Toreti, “A Novel Approach for the Detection of Inhomogeneities Affecting Climate Time Series”, Journal of Applied Meteorology and Climatology, vol. 51, Feb. 2012, DOI: 10.1175/JAMC-D-10-05033.1 (Year: 2012). [cited by applicant]
Voras et al., “Criteria for evaluation of Open Source Cloud Computing Solutions”, Information Technology Interfaces (ITI), Proceedings of the ITI2011 33rd International Conference on Information Technology Interfaces, U… [cited by applicant]
Voras I et al: “Evaluating open-source cloud computing solutions”, MIPRO, 2011 Proceedings of the 34th International Convention, IEEE, May 23, 2011 (May 23, 2011), pp. 209-214. [cited by applicant]
Wilks, Samuel S. “Determination of sample sizes for setting tolerance limits,” The Annals of Mathematical Statistics 12.1 (1941): 91-96. [cited by applicant]
Willy Tarreau: “HAProxy Architecture Guide”, May 25, 2008 (May 25, 2008), XP055207566, Retrieved from the Internet: URL:http://www.haproxy.org/download/1.2/doc/architecture.txt [retrieved on Aug. 13, 2015]. [cited by applicant]
Yin, “System resource utilization analysis and prediction for cloud based applications under bursty workloads,” 2014, Information Sciences, vol. 279, pp. 338-357 (Year: 2014). [cited by applicant]
Yokoyama, Tetsuya, “Windows Server 2008, Certification Test, Part 5: Reliability”, Apr. 15, 2008, pp. 124-125 along with 4 pages of English Translation. [cited by applicant]
Zhai, “Spatial Variation and Trends in PDSI and SPI Indices and Their Relation to Streamflow in 10 Large Regions of China”, 2010, Journal of Climate, vol. 23, 2010 American Meteorological Society, DOI: 10.1175/2009JCLI2… [cited by applicant]
Chu, “A Piecewise Linear Approach to Modeling and Forecasting Demand for Macau Tourism,” in 32 Tourism Mgmt. 1414-20 (2011). (Year: 2011). [cited by applicant]
Esling et al., “Time-Series Data Mining,” in 45.1 ACM Computing Surveys 1-34 (2012). (Year: 2012). [cited by applicant]
Wang, “Online Monitoring and Prediction of Complex Time Series Events from Nonstationary Time Series Data,” doctoral dissertation, Rutgers U. (2012). (Year: 2012). [cited by applicant]
Laptev, “Generic and scalable framework for automated time-series anomaly detection,” 2015, In Proceedings of the 21th ACM SIGKDD international conference on knowledge discovery and data mining, pp. 1939-1947 (Year: 201… [cited by applicant]
Carvalho et al., “Long-term SLOs for reclaimed cloud computing resources,” 2014, In Proceedings of the ACM Symposium on Cloud Computing (SOCC '14). Association for Computing Machinery, New York, NY, USA, 1-13 (Year: 201… [cited by applicant]
Cortez, et al., Internet Traffic Forecasting using Neural Networks, 2006 International Joint Conference on Neural Networks, Jul. 21, 2006, pp. 4942-4949 (Year: 2006). [cited by applicant]
Dettling, Applied Time Series Analysis, SS 2020, Zurich University of Applied Sciences, Mar. 1, 2020, pp. 1-83 (Year: 2020). [cited by applicant]
Farahani, Anomaly Detection on Gas Turbine Time-series' Data Using Deep LSTM-Autoencoder, Master's Thesis, Umea University, Autumn 2020, pp. 1-48 (Year: 2020). [cited by applicant]