PMQ - Revision history

Matt.lin at 07:42, 23 March 2017

2017-03-23T07:42:58Z

Matt.lin at 07:34, 23 March 2017

2017-03-23T07:34:45Z

Matt.lin at 05:42, 23 March 2017

2017-03-23T05:42:40Z

Matt.lin at 05:18, 23 March 2017

2017-03-23T05:18:56Z

Matt.lin at 03:56, 23 March 2017

2017-03-23T03:56:45Z

Matt.lin at 03:06, 15 March 2017

2017-03-15T03:06:18Z

Matt.lin at 01:17, 10 March 2017

2017-03-10T01:17:45Z

Matt.lin at 06:41, 9 March 2017

2017-03-09T06:41:56Z

Matt.lin at 05:49, 9 March 2017

2017-03-09T05:49:16Z

Matt.lin at 05:46, 9 March 2017

2017-03-09T05:46:59Z

← Older revision		Revision as of 07:42, 23 March 2017
Line 1:		Line 1:
−	'''PMQ''' ('''Prediction Management Qualtity''') is a series of Mechine Learning and Big Data solutions for monitoring IPC/IOT Data in '''WISE-PaaS/RMM'''. Be diffierent with common device data monitor, it offers enhanced and multivariant function to help users reduce cost for monitoring tens of thousands IPC/IOT divices. PMQ not only aims at real-time or history data monitor, but also use these data to analysis effects for specific equipments ('''HDD Failure Analysis''') and predict device data in furture ('''Trend Forecasting Monitor''') by PMQ intelligent calculation.	+	'''PMQ''' ('''Prediction Management Qualtity''') is a series of Mechine Learning and Big Data solutions for monitoring IPC/IOT Data in '''WISE-PaaS/RMM'''. Be diffierent with common device data monitor, it offers enhanced and multivariant function to help users reduce cost for monitoring tens of thousands IPC/IOT divices. PMQ not only aims at real-time or history data monitor, but also use these data to analysis effects for specific equipments ('''HDD Failure Analysis''') and predict device data in furture ('''Trend Forecasting Monitor''') by PMQ intelligent calculation in Devices.
		+
		+	[[File:PMQ.jpg\|480x344px\|PMQ.jpg]]

	== <span style="font-size:large;">HDD F</span>ailure <span style="font-size:large;">Analysis</span> ==		== <span style="font-size:large;">HDD F</span>ailure <span style="font-size:large;">Analysis</span> ==

@@ Line 20: / Line 20: @@
 ;<span style="font-size:medium;">Predictive&nbsp;Process</span>
 :The first condiction is predictive object has at least '''the newest 48 history hourly averages''' in Database, and these samples are calculated by time-series prediction algorithm. Time-series prediction algorithm '''Trend Forecasting Monitor&nbsp;'''adopts is '''Exponential Smoothing'''. By the above Process, it can produce values of prediction(averages of current hour and next 3&nbsp;hours), and Trend Forecasting Monitor takes these values and the newest&nbsp;hourly average&nbsp;to compare with hourly averages in yesterday.&nbsp;If there are significant differences between values of prediction and hourly averages in yesterday, it will give&nbsp;alert message with potential risk. If there are significant differences between the newest&nbsp;hourly averages and&nbsp;hourly averages in yesterday, give&nbsp;alert message with doubtful&nbsp;risk. The standard of significant differences is based on '''Tukey's Range Test''', and the formula is:&nbsp;<span style="font-size:small;">'''[Q<sub>1</sub>-3(Q<sub>3</sub>-Q<sub>1</sub>),&nbsp;Q3+3(Q<sub>3</sub>-Q<sub>1</sub>)]'''.&nbsp;</span>Q<sub>1</sub>&nbsp;and Q<sub><span style="font-size: 12px;">3</span></sub>&nbsp;are the lower and upper quartile of hourly averages in yesterday. If data&nbsp;are in the above range, there are not significant differences between them, then the data&nbsp;status is&nbsp;normal.&nbsp;<br/>
-:[[File:PMQ- TFM.jpg|600x350px|PMQ- TFM.jpg]]<br/>
+:<br/>
 ;<span style="font-size:medium;">Predictive Result</span>
 :Result for each object contains 3 parts:&nbsp;result status, status information and&nbsp;event record list. First, for&nbsp;result status. except potential risk", doubtful risk&nbsp;and normal&nbsp;in the above statement, there is&nbsp;a&nbsp;situation abour data error, and it means disable predicting because of some data problem. For instance, miss some data in&nbsp;the newest 48 hours or query data from database error. Second, according to&nbsp;result status, web UI will show corresponded&nbsp;information, and major statement is explain reason for status and give some suggestions to users.Finally, event record list will show total records for significant change, then it can help&nbsp;users to trace initial time of abnormal data.&nbsp;

@@ Line 15: / Line 15: @@
 *Automatically Monitor Alteration of IPC/IOT Data
-:For sepecific device or sensor data(HDD Health, System CPU Usage and so on), WISE-PaaS/RMM&nbsp;server offers prediction function('''Trend Forecasting Monitor'''). It can help users know abnormal data status as soon as possible to prevent some damages.Predictive Type of Trend Forecasting Monitor are '''hourly averages''' of data, and they contain averages of current hour and even next 3&nbsp;hours in furtue.<br/>
+:For sepecific device or sensor data (HDD Health, System CPU Usage and so on), support&nbsp;prediction application ('''Trend Forecasting Monitor''') in device. It can help users know abnormal data status as soon as possible to prevent some damages.Predictive Type of Trend Forecasting Monitor are '''hourly averages''' of data, and they contain averages of current hour and even next 3&nbsp;hours in furtue.<br/>
-:Otherwise,&nbsp;Trend Forecasting Monitor also offer function&nbsp;of automatical&nbsp;monitoring hourly averages of IPC/IOT data. If it happens situation that hourly average change significantly, RMM&nbsp;server will save as&nbsp;events to notify users. &nbsp;
+:Otherwise,&nbsp;Trend Forecasting Monitor also offer function&nbsp;of automatical&nbsp;monitoring hourly averages of IPC/IOT data. If it happens situation that hourly averages or predictions change significantly, It&nbsp;will also&nbsp;notify users. &nbsp;
 :<br/>
 ;<span style="font-size:medium;">Predictive&nbsp;Process</span>
-:The first condiction is predictive object has at least '''the newest 48 history hourly averages''' in Database, and these samples are calculated by time-series prediction algorithm. Time-series prediction algorithm RMM adopts is '''Exponential Smoothing''', and is based on APIs in '''Weka''' machinne learning java libary. By the above Process, it can produce values of prediction(averages of current hour and next 3&nbsp;hours), and Trend Forecasting Monitor takes these values and the newest 3 history hourly averages to compare with hourly averages in yesterday.&nbsp;If there are significant differences between values of prediction and hourly averages in yesterday, the status of analytic result is "'''Potential Risk'''". If there are significant differences between the newest 3 history hourly averages and&nbsp;hourly averages in yesterday, the status is "'''Doubtful Risk'''". The standard of significant differences is based on '''Tukey's Range Test''', and the formula is:&nbsp;<span style="font-size:small;">'''[Q<sub>1</sub>-3(Q<sub>3</sub>-Q<sub>1</sub>),&nbsp;Q3+3(Q<sub>3</sub>-Q<sub>1</sub>)]'''.&nbsp;</span>Q<sub>1</sub>&nbsp;and Q<sub><span style="font-size: 12px;">3</span></sub>&nbsp;are the lower and upper quartile of hourly averages in yesterday. If objects are in the above range, there are not significant differences between them, then we can call status of Object is "'''Normal'''".&nbsp;<br/>
+:The first condiction is predictive object has at least '''the newest 48 history hourly averages''' in Database, and these samples are calculated by time-series prediction algorithm. Time-series prediction algorithm '''Trend Forecasting Monitor&nbsp;'''adopts is '''Exponential Smoothing'''. By the above Process, it can produce values of prediction(averages of current hour and next 3&nbsp;hours), and Trend Forecasting Monitor takes these values and the newest&nbsp;hourly average&nbsp;to compare with hourly averages in yesterday.&nbsp;If there are significant differences between values of prediction and hourly averages in yesterday, it will give&nbsp;alert message with potential risk. If there are significant differences between the newest&nbsp;hourly averages and&nbsp;hourly averages in yesterday, give&nbsp;alert message with doubtful&nbsp;risk. The standard of significant differences is based on '''Tukey's Range Test''', and the formula is:&nbsp;<span style="font-size:small;">'''[Q<sub>1</sub>-3(Q<sub>3</sub>-Q<sub>1</sub>),&nbsp;Q3+3(Q<sub>3</sub>-Q<sub>1</sub>)]'''.&nbsp;</span>Q<sub>1</sub>&nbsp;and Q<sub><span style="font-size: 12px;">3</span></sub>&nbsp;are the lower and upper quartile of hourly averages in yesterday. If data&nbsp;are in the above range, there are not significant differences between them, then the data&nbsp;status is&nbsp;normal.&nbsp;<br/>
 :[[File:PMQ- TFM.jpg|600x350px|PMQ- TFM.jpg]]<br/>
 ;<span style="font-size:medium;">Predictive Result</span>
-:Result for each object contains 3 parts:&nbsp;result status, status information and&nbsp;event record list. First, for&nbsp;result status. except "Potential Risk",&nbsp;"Doubtful Risk" and "Normal" in the above statement, there is&nbsp;a "'''Data Error'''" situation, and it means disable predicting because of some data problem. For instance, miss some data in&nbsp;the newest 48 hours or query data from database error. Second, according to&nbsp;result status, web UI will show corresponding information, and major statement is explain reason for status and give some suggestions to users.Finally, event record list will show total records for significant change, then it can help&nbsp;users to trace initial time of abnormal data.&nbsp;
+:Result for each object contains 3 parts:&nbsp;result status, status information and&nbsp;event record list. First, for&nbsp;result status. except potential risk", doubtful risk&nbsp;and normal&nbsp;in the above statement, there is&nbsp;a&nbsp;situation abour data error, and it means disable predicting because of some data problem. For instance, miss some data in&nbsp;the newest 48 hours or query data from database error. Second, according to&nbsp;result status, web UI will show corresponded&nbsp;information, and major statement is explain reason for status and give some suggestions to users.Finally, event record list will show total records for significant change, then it can help&nbsp;users to trace initial time of abnormal data.&nbsp;

← Older revision		Revision as of 05:18, 23 March 2017
Line 1:		Line 1:
−	'''PMQ''' ('''Prediction Management Qualtity''') is a series of Mechine Learning and Big Data solutions for monitoring IPC/IOT Data in '''WISE-PaaS/RMM'''. Be diffierent with common device data monitor, it offers enhanced and multivariant function to help users reduce cost for monitoring tens of thousands IPC/IOT divices. PMQ not only aims at real-time or history data monitor, but also use these data to analysis effects for specific equipments ('''HDD ~~Health~~ Analysis''') and predict device data in furture ('''Trend Forecasting Monitor''') by PMQ intelligent calculation.	+	'''PMQ''' ('''Prediction Management Qualtity''') is a series of Mechine Learning and Big Data solutions for monitoring IPC/IOT Data in '''WISE-PaaS/RMM'''. Be diffierent with common device data monitor, it offers enhanced and multivariant function to help users reduce cost for monitoring tens of thousands IPC/IOT divices. PMQ not only aims at real-time or history data monitor, but also use these data to analysis effects for specific equipments ('''HDD Failure Analysis''') and predict device data in furture ('''Trend Forecasting Monitor''') by PMQ intelligent calculation.

	== <span style="font-size:large;">HDD F</span>ailure <span style="font-size:large;">Analysis</span> ==		== <span style="font-size:large;">HDD F</span>ailure <span style="font-size:large;">Analysis</span> ==

@@ Line 6: / Line 6: @@
 :For device with HDD failure prediction intelligent application, users can know related&nbsp;status&nbsp;information of HDD that WISE-PaaS/RMM agent deliver. Status&nbsp;information contains predictive status of HDD,&nbsp;alert message&nbsp;and&nbsp;corresponding suggestion to help user check or maintain related equipments, then reduce situations that HDD fails in real.
 ;<font size="3">Implementation</font>
-:The major function of HDD failure prediction intelligent application in device is beased on some data of Indicative factor&nbsp;(contain statistic of abnormal power off count,&nbsp;HDD write/read issue and so on) to give predictive status of HDD and alert messages. For predictive status of HDD, it uses build-in&nbsp;trained&nbsp;regression analysis model to predict for data of Indicative factor. For&nbsp;alert message, it defines&nbsp;a series of rules&nbsp;by practical test in advance, and regards them as the standard of alert determination. According to two kind of informations, WISE-PaaS/RMM&nbsp;UI designs a scan button to enable this function&nbsp;, it&nbsp;will show analysis results in current hour for each device.&nbsp;When users focus on one in&nbsp;analysis results , users can know some suggestions for&nbsp; predictive status and alert meassage, and these suggestions are related with some equipments, so UI also&nbsp;shows these status of equipments (for instance, system CPU&nbsp;temperature and memory loading)&nbsp;for users to check.
+:The major function of HDD failure prediction intelligent application in device is beased on some data of indicative factor&nbsp;(contain statistic of abnormal power off count,&nbsp;HDD write/read issue and so on) to give predictive status of HDD and alert messages. For predictive status of HDD, it uses build-in&nbsp;trained&nbsp;regression analysis model to predict for data of Indicative factor. For&nbsp;alert message, it defines&nbsp;a series of rules&nbsp;by practical test in advance, then&nbsp;these content of&nbsp;rules is given the reasonable range of indicative factors, and regards them as the standard of alert determination. According to two kind of informations, WISE-PaaS/RMM&nbsp;UI designs a scan button to enable this function&nbsp;, it&nbsp;will show analysis results in one&nbsp;hour for each device.&nbsp;When users focus on one in&nbsp;analysis results , users can know some suggestions for&nbsp; predictive status and alert meassage, and these suggestions are related with some equipments, so UI also&nbsp;shows these status of equipments (for instance, system CPU&nbsp;temperature and memory loading)&nbsp;for users to check.
 == <span style="font-size:large;">Trend Forecasting Monitor</span> ==

@@ Line 1: / Line 1: @@
 '''PMQ''' ('''Prediction Management Qualtity''') is a series of Mechine Learning and Big Data solutions for monitoring IPC/IOT Data in&nbsp;'''WISE-PaaS/RMM'''. Be diffierent with common device data monitor, it&nbsp;offers enhanced and multivariant&nbsp;function to help users reduce cost for monitoring tens of thousands IPC/IOT divices. PMQ&nbsp;not only aims at&nbsp;real-time&nbsp;or history data monitor, but also use these data to analysis effects for specific equipments ('''HDD Health Analysis''') and predict device data in furture&nbsp;('''Trend Forecasting Monitor''')&nbsp;by PMQ&nbsp;intelligent calculation. &nbsp;
-== <span style="font-size:large;">HDD Health Analysis</span> ==
+== <span style="font-size:large;">HDD F</span>ailure <span style="font-size:large;">Analysis</span> ==
 ;<font size="3">Function</font>

← Older revision		Revision as of 06:41, 9 March 2017
Line 1:		Line 1:
−	PMQ(Prediction Management Qualtity)	+	'''PMQ''' ('''Prediction Management Qualtity''') is a series of Mechine Learning and Big Data solutions for monitoring IPC/IOT Data in '''WISE-PaaS/RMM'''. Be diffierent with common device data monitor, if offers enhanced and multivariant function to help users reduce cost for monitoring tens of thousands IPC/IOT divices. PMQ not only aims at real-time or history data monitor, but also use these data to analysis effects for specific equipments ('''HDD Health Analysis''') and predict device data in furture ('''Trend Forecasting Monitor''') by PMQ intelligent calculation.

	== <span style="font-size:large;">HDD Health Analysis</span> ==		== <span style="font-size:large;">HDD Health Analysis</span> ==