CN111095868A - Data traffic management in software defined networks - Google Patents

Data traffic management in software defined networks Download PDF

Info

Publication number
CN111095868A
CN111095868A CN201780094848.7A CN201780094848A CN111095868A CN 111095868 A CN111095868 A CN 111095868A CN 201780094848 A CN201780094848 A CN 201780094848A CN 111095868 A CN111095868 A CN 111095868A
Authority
CN
China
Prior art keywords
data traffic
sdn
model
event
events
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN201780094848.7A
Other languages
Chinese (zh)
Inventor
西蒙·乔瓦达斯
莫伊兹·杜艾夫
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Huawei Technologies Co Ltd
Original Assignee
Huawei Technologies Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Huawei Technologies Co Ltd filed Critical Huawei Technologies Co Ltd
Publication of CN111095868A publication Critical patent/CN111095868A/en
Pending legal-status Critical Current

Links

Classifications

    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04LTRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L41/00Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
    • H04L41/14Network analysis or design
    • H04L41/147Network analysis or design for predicting network behaviour
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04LTRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L41/00Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
    • H04L41/08Configuration management of networks or network elements
    • H04L41/0803Configuration setting
    • H04L41/0813Configuration setting characterised by the conditions triggering a change of settings
    • H04L41/0816Configuration setting characterised by the conditions triggering a change of settings the condition being an adaptation, e.g. in response to network events
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04LTRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L41/00Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
    • H04L41/08Configuration management of networks or network elements
    • H04L41/0895Configuration of virtualised networks or elements, e.g. virtualised network function or OpenFlow elements
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04LTRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L41/00Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
    • H04L41/14Network analysis or design
    • H04L41/145Network analysis or design involving simulating, designing, planning or modelling of a network
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04LTRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L41/00Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
    • H04L41/40Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks using virtualisation of network functions or resources, e.g. SDN or NFV entities
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04LTRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L43/00Arrangements for monitoring or testing data switching networks
    • H04L43/06Generation of reports
    • H04L43/062Generation of reports related to network traffic
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04LTRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L43/00Arrangements for monitoring or testing data switching networks
    • H04L43/20Arrangements for monitoring or testing data switching networks the monitoring system or the monitored elements being virtualised, abstracted or software-defined entities, e.g. SDN or NFV

Abstract

A data traffic management procedure in a software defined network, SDN, is provided. The process involves maintaining a plurality of models (one model characterizing events and estimated temporal relationships between data traffic to be processed within a network including the SDN) and predicting data traffic to be processed by the SDN over a period of time. The prediction is based on mapping one or more upcoming aperiodic events to one or more of the models (if information about upcoming aperiodic events is available) or data traffic reported by the SDN over a respective time period. The process also involves comparing the predicted data traffic pending by the SDN for the time period with data traffic reported by the SDN for the time period, wherein, if it is assessed that a difference between the predicted data traffic and the reported data traffic is significant, initiating a reconfiguration of the SDN and/or generating a new model or modifying an existing model, wherein the new/modified model maps one or more current events to the reported data traffic.

Description

Data traffic management in software defined networks
Technical Field
The present invention relates to Software Defined Networking (SDN), and in particular, to data traffic management in SDN.
Background
Network monitoring systems may provide information about data traffic (network traffic) in a network. To this end, the network monitoring system may include: probes embedded in network equipment or deployed as dedicated entities and performing local statistics and measurements, and a controller that collects aggregate statistics and measurements from different probes. One of the main tasks of such a network monitoring system may be to predict network traffic over a given time period.
Traffic prediction is central to several problems in network management, such as: capacity expansion, traffic engineering, load balancing, anomaly detection, and the like. In addition, accurate flow prediction helps to improve supply, planning, and thus reduce costs. However, due to the nature of the internet and events or anomalies affecting data traffic, the changes and fluctuations in data traffic can be large, resulting in accurate traffic predictions that can be extremely challenging.
Disclosure of Invention
According to a first aspect of the invention, a system for managing data traffic in an SDN is provided. The system comprises: a knowledge unit to maintain a plurality of models characterizing estimated temporal relationships between events and data traffic to be processed within a network comprising the SDN; and a prediction unit. The prediction unit is configured to predict data traffic to be processed by the SDN within a time span based on mapping one or more upcoming aperiodic events to one or more of the models (if information about upcoming aperiodic events is available) or data traffic reported by the SDN during the respective time span.
The system further comprises an activity unit for comparing the predicted data traffic pending by the SDN within the time span with data traffic reported by the SDN during the time span, wherein the activity unit is for initiating a reconfiguration of the SDN if the activity unit evaluates that a difference between the predicted data traffic and the reported data traffic is significant, and/or causing the knowledge unit to generate a new model or modify an existing model, the new/modified model mapping one or more current events to the reported data traffic.
Thus, the system allows for accurate prediction of data traffic on the links of the network by mapping context information to available models, even in the event of a large event. Furthermore, the system is able to detect unexpected events/anomalies when they occur. Further, a new model may be generated for each contingency/anomaly (for example) for future use.
In a first possible implementation of the system according to the first aspect, the activity unit is configured to initiate a reconfiguration of the SDN by causing the knowledge unit to generate the new model or modify the existing model, and providing the new/modified model to the prediction unit to predict the data traffic based on the new/modified model.
Thus, by detecting the occurrence of an incident/anomaly and adjusting the prediction based on a new/modified model appropriate for the incident/anomaly, the system is enabled to react to the incident/anomaly in real time.
In a second possible implementation of the system according to the first aspect, the reconfiguration of the SDN comprises reconfiguring one or more switches of the SDN by implementing new forwarding rules.
Thus, traffic congestion may be avoided or reduced even in the event of an accident/anomaly.
In a third possible implementation form of the system according to the first aspect, the system further comprises a database storing information of the one or more upcoming events and/or one or more current events, wherein the information comprises a start date, an end date, an estimated flow pattern comprising flow and flow shape within a time window between the start date and the end date, and at least one of an event category.
Thus, the database allows predicting the shape of the upcoming data traffic.
In a fourth possible implementation form of the system according to the first aspect, the system is configured to mine the information from the network.
Thus, the system can predict data traffic without human intervention and react in real time to information available on the network.
In a fifth possible implementation form of the system according to the first aspect, the model characterizes the estimated temporal relationship between the event and the data traffic to be processed within the network by including a parameter indicative of a time instant relative to a course of the event at which a data traffic peak is expected to occur.
Thus, the system allows coping with data traffic peaks.
In a sixth possible implementation form of the system according to the first aspect, the model indicates a data rate of the SDN link to be processed at a time when a data traffic peak is expected to occur.
This allows the SDN link to adapt to peak data rates caused by upcoming events.
According to a second aspect of the invention, a method for data traffic managed in an SDN is provided. The method comprises the following steps: maintaining a plurality of models in a knowledge base, the models characterizing estimated temporal relationships between events and data traffic to be processed within a network comprising the SDN; predicting data traffic pending by the SDN for a span of time by mapping one or more upcoming aperiodic events to one or more of the models (if information about upcoming aperiodic events is available); comparing the predicted data traffic pending by the SDN within the time span with data traffic reported by the SDN during the time span, and initiating reconfiguration of the SDN according to a result of the comparison.
Thus, the method allows for an accurate prediction of data traffic on the links of the network by mapping context information to available models, even in the event of a large event. Furthermore, the method is able to detect unexpected events/anomalies when they occur, allowing real-time reconfiguration of the SDN to avoid traffic congestion.
In a first possible implementation form of the method according to the second aspect, the method further comprises: initiate reconfiguration of the SDN by generating a new model or modifying an existing model and predicting the data traffic based on the new/modified model.
Thus, by detecting the occurrence of an incident/anomaly and adjusting the prediction based on a new/modified model appropriate to the incident/anomaly, the method allows for reacting to the incident/anomaly in real time.
In a second possible implementation of the method according to the second aspect, the reconfiguration of the SDN comprises reconfiguring one or more switches of the SDN by implementing new forwarding rules.
Thus, traffic congestion may be avoided or reduced even in the event of an accident/anomaly.
In a third possible implementation form of the method according to the second aspect, the method further comprises storing information of the one or more upcoming events, wherein the information comprises at least one of a start date, an end date, an estimated traffic pattern comprising traffic and traffic shape within a time window between the start date and the end date, and an event category.
Thus, the method allows predicting the shape of the upcoming data traffic.
In a fourth possible implementation form of the method according to the second aspect, the method further comprises mining the information from the network by analyzing at least one of a social media website and/or a blog.
Thus, the method allows for real-time reaction to information available on social media websites and/or blogs.
In a fifth possible implementation form of the method according to the second aspect, the model characterizes the estimated temporal relationship between the event and the data traffic to be processed within the network by including a parameter indicative of a time instant relative to the course of the event at which a data traffic peak is expected to occur.
Thus, the method allows coping with data traffic peaks.
In a sixth possible implementation form of the method according to the second aspect, the model indicates a data rate at which the SDN link is to be processed at a time when a data traffic peak is expected to occur.
This allows the SDN link to adapt to peak data rates caused by upcoming events.
According to a third aspect of the present invention there is provided a computer readable medium storing computer readable instructions which, if executed by a processor, cause the processor to implement the method of any one of the second aspect or implementation forms of the second aspect.
Drawings
Fig. 1 illustrates a system for managing data traffic in an SDN according to an example.
Fig. 2 schematically illustrates an exemplary dictionary of traffic shapes for two event categories.
Fig. 3 illustrates a flow diagram of a process for managing data traffic in an SDN, according to an example.
Fig. 4 illustrates an exemplary prediction/error detection process based on different models used in parallel.
Fig. 5 shows a process for detecting whether the system has recorded the flow shape.
Detailed Description
Fig. 1 illustrates an exemplary system 10 for managing data traffic in an SDN. The system 10 includes a database 12, the database 12 storing information about upcoming (actual occurrence) events and data traffic measurements from network switches of the SDN. Information about upcoming events may be collected in various ways, such as by an operator inserting contextual information (e.g., type of event, start time, duration, etc.) into the database 12, or automatically extracting (mining) contextual information from the internet (e.g., by analyzing microblogs, social media, Twitter, Facebook, etc.). For example, the context information may include information such as the category of the event, the start time/hour of the event, the approximate duration of the event, and the like.
The system 10 also includes an SDN controller 14, the SDN controller 14 may transmit the prediction parameters to a prediction unit 16. The prediction parameters may include, for example, a prediction horizon (time period), a prediction model/algorithm, and other parameters related to the prediction algorithm. The prediction unit 16 may operate in different modes. For example, in one mode, no expected events may occur within the prediction horizon, and a normal prediction model may be trained/used. In another mode, the occurrence of an event can be expected within a prediction horizon, and therefore needs to be taken into account.
The system 10 also includes a knowledge unit 18, and the knowledge unit 18 may convert the context information (which may be passed from the database 12 to the knowledge unit 18 before an expected event occurs) into a particular model that may be used, for example, for time series prediction. In particular, a general abstraction of the representation of events may be made in the knowledge unit 18, where each event may be represented by a parametric model including parameters such as "spike duration/time", "amplitude" (t, a)t) And the value of the event parameter. One possible implementation of the parametric model is based on a dictionary of event-induced traffic shapes. For example, FIG. 2 shows (t, A) for different event categoriest) Different flow shapes are shown.
Generally, events belonging to the same category or similar categories (e.g., concerts, sporting events, trade shows, etc.) are expected to produce similar traffic shapes, while events belonging to different categories are expected to produce significantly different data traffic in the respective parametric models. In view of this, the pass (t, A) may be given for different event categoriest) Different flow shapes were modeled.The database 12 may store a dictionary of such traffic shapes, which may be passed to the prediction unit 16 when a corresponding event occurs.
For example, when an event belonging to the category "event a" is expected to occur, then the knowledge unit 18 may look up the relevant entry in the traffic dictionary. The knowledge unit 18 may then send the set of entries belonging to the event to the prediction unit 16, or may identify the entry closest to the event (in terms of the context information) and transmit "duration/time of spike" and "amplitude" information for this event. Thus, the duration of an event and the traffic load during the time step in which the event will be active may be calculated based on parameters derived from previous events, assuming that the upcoming event will result in similar data traffic as the past same class event.
When the knowledge unit 18 passes event related information to the prediction unit 16, the prediction unit 16 may use this information to predict data traffic. For example, the prediction may be by To calculate, wherein, the itemCorresponding to the predicted values at time step n + i given by "conventional" time series prediction algorithms such as ARIMA, neural networks, etc. Item(s)Represents a final prediction that includes information about the event. A shape determining parameter y selected from the shape dictionary in the knowledge unit 180,...,yM-1. Furthermore, the function giMay be selected a priori or may be learned based on past observations and the context of the event finally α e 0, 1]Can be used forIf α is 0, only the information relevant to the event is considered, and if α is 1, only pure prediction is considered.
The prediction unit 16 may send the predicted data traffic values to the SDN controller 14. The SDN controller 14 may indicate to the prediction unit 16 a prediction horizon (i.e., a time period covered by the prediction) and/or other parameters (e.g., constraints on model complexity), as well as model specific parameters (order and step size of the model, etc.).
Furthermore, the system 10 may have to deal with situations where an upcoming event is not stored in the database 12 but needs to be identified and processed when the event occurs. This situation may involve the mobile unit 20. For example, if the prediction error (i.e., the absolute value of the difference between the predicted data traffic and the actual data traffic for one or more links reported by the reporting unit 22) is greater than a predefined threshold, it may be checked whether the currently occurring event corresponds to an event class known to the system 10.
To this end, the similarity of the occurring events to known event categories may be measured, and if a matching event category is identified, the database 12 may be updated by storing the events and assigning the corresponding event category to the events. Otherwise, another (novel) event category may be stored and assigned to the event that is occurring.
Fig. 3 shows a flow diagram for a data traffic management process in an SDN according to an example. The process includes eight steps (S1-S8). In step S1, the application requests the prediction unit 16 to predict the data traffic of the next time step. Time granularity, the algorithm employed (to be used to make the time series predictions), and the range may all be used as inputs. At step S2, the SDN controller 14 may send a request to the network switch and the knowledge unit 18 to start an event-aware traffic prediction counter to collect. For example, the SDN controller 14 may initiate a flow counter using the OpenFlow protocol.
At step S3, the database 12 may collect new traffic measurements and context information about upcoming events from the network switch. In step S4, the prediction unit 16 may apply the learned model or learn a new model based on the past data and predict the data flow rate in the required time range. In addition, if an upcoming event is stored in the database 12, the event may also be considered.
At step S5, the SDN controller 14 may send a new forwarding plane (TCAM) routing rule or initiate a capacity expansion/reduction command to the switch according to the prediction value. A set of predictors may be used to make the prediction at the next point/points on the timeline. That is, different models may be trained/used in parallel to estimate the predicted future data flow values. Furthermore, weights may be associated with different models, and over multiple iterations, only those models that result in low errors may be assigned larger weights, while the remaining models will be assigned weights close to zero.
In step S6, active unit 20 may be activated if the step size for which the prediction error is greater than a certain threshold exceeds a predetermined number. This may be due to the system 10 not knowing the upcoming event (i.e., the upcoming event is unexpected) or due to the upcoming event being assigned to the wrong category (or the correct event category does not yet exist). At step S7, information regarding novel events may be stored in the database 12 and passed to the knowledge unit 18 for processing. In step S8, the knowledge unit 18 may pass the event related parameters to be considered (in prediction) to the prediction unit 16.
In another example, a transition from S4 to S5 may occur regardless of whether the answer to the question in diamond is "yes" or "no". That is, if the error is less than the threshold, the active unit 20 may not be activated and normal operation may occur, i.e., network management utilization prediction point (e.g., for capacity expansion), and the process returns to S3 to process a new measurement of the data traffic. But even in the case of "yes", it is possible to switch from S4 to S5, which occurs in parallel with the transition from S4 to S6. When a transition from S6 to S4 occurs, novel events may be collected in the database 12. Otherwise, the active unit 20 may be used to improve performance.
Therefore, the range of the movable unit 20 is three-fold. The first purpose is to detect when an unreported event (before it actually starts) occurs. A second purpose is to allow the prediction (as accurately as possible) of the flow caused by the event, although the event has not been reported before. A third objective is to evaluate the novelty of the event that occurred in order to insert it into a dictionary of recorded/known flow shapes when needed.
Fig. 4 illustrates an exemplary prediction process based on different models that may be trained/used in parallel. That is, different traffic shapes may be used in parallel for data traffic prediction. In particular, several different predictions may be generated based on different flow shapes, wherein each flow shape defines a different set of parameters y0,...,yM-1. A weight (which may take values between 0 and 1) may be associated with each different traffic shape, and when the reporting unit 22 reports new measurements of data traffic, errors may be calculated and those traffic shapes that result in high prediction errors are given lower weight. The specific weight selection that results in this behavior isWherein e ist(i) Is the error using event i, β is a user defined parameter the final prediction can be given by:
computing weights may also be used to detect whether an event is novel, as shown in FIG. 5. Specifically, if there is a weight close to 1, this means that the current event is similar to the known event. Conversely, if all weights are far from 1, this means that the current event has not been previously recorded. Thus, the knowledge unit 18 may generate a new database event entry. Finally, if a new event is detected, information about the event may be collected by crowd sourcing, etc.
Thus, the presented system/process can use context information to identify future events, translate the context information into an appropriate model for data traffic prediction, and identify/ascertain in real-time whether an incident is novel.

Claims (15)

1. A system for managing data traffic in a software defined network, SDN, the system comprising:
a knowledge unit for maintaining a plurality of models, wherein one model is for characterizing an estimated temporal relationship between an event and data traffic to be processed within a network comprising the SDN;
a prediction unit to predict data traffic pending by the SDN for a period of time based on:
mapping one or more upcoming aperiodic events to one or more of the models (if information for the upcoming aperiodic events is available); or
Data traffic reported by the SDN over a respective time period;
an activity unit to compare the predicted data traffic pending by the SDN for the time period with data traffic reported by the SDN for the time period, wherein the activity unit is to, if the activity unit evaluates that a difference between the predicted data traffic and the reported data traffic is significant:
initiating a reconfiguration of the SDN; and/or
Causing the knowledge unit to generate a new model or modify an existing model, the new/modified model mapping one or more current events to the reported data traffic.
2. The system of claim 1, wherein the activity unit is configured to initiate reconfiguration of the SDN by causing the knowledge unit to generate the new model or modify the existing model, and providing the new/modified model to the prediction unit to predict the data traffic based on the new/modified model.
3. The system of claim 1 or 2, wherein the reconfiguration of the SDN comprises reconfiguring one or more switches of the SDN by implementing new forwarding rules.
4. The system of any one of claims 1 to 3, further comprising:
a database storing information of the one or more upcoming events and/or one or more current events, wherein the information comprises at least one of a start date, an end date, an estimated traffic pattern including traffic volume and traffic shape within a time window between the start date and the end date, and an event category.
5. The system of any one of claims 1 to 4, wherein said system is configured to mine said information from said network.
6. The system according to any one of claims 1 to 5, characterized in that the model characterizes the estimated temporal relationship between the event and the data traffic to be processed within the network by including a parameter indicative of a time instant relative to the course of the event at which a data traffic peak is expected to occur.
7. The system of claim 6, wherein the model indicates a data rate at which an SDN link is pending at the time at which a data traffic peak is expected to occur.
8. A method for managing data traffic in a Software Defined Network (SDN), the method comprising:
maintaining a plurality of models in a knowledge base, wherein one model is used to characterize an estimated temporal relationship between an event and data traffic to be processed within a network comprising the SDN;
predicting data traffic pending by the SDN for a period of time by mapping one or more upcoming aperiodic events to one or more of the models (if information for upcoming aperiodic events is available);
comparing the predicted data traffic pending by the SDN for the time period with data traffic reported by the SDN for the time period, and initiating reconfiguration of the SDN according to a result of the comparison.
9. The method of claim 8, further comprising:
initiate reconfiguration of the SDN by generating a new model or modifying an existing model and predicting data traffic based on the new/modified model.
10. The method of claim 8 or 9, wherein the reconfiguration of the SDN comprises reconfiguring one or more switches of the SDN by implementing new forwarding rules.
11. The method of any one of claims 8 to 10, further comprising:
storing information of the one or more upcoming events, wherein the information comprises at least one of a start date, an end date, an estimated traffic pattern including traffic volume and traffic shape within a time window between the start date and the end date, and an event category.
12. The method of any of claims 8 to 11, further comprising:
the information is mined from the network by analyzing at least one of a social media website and/or a blog.
13. The method according to any of claims 8 to 12, characterized in that the model characterizes the estimated temporal relationship between the event and the data traffic to be processed within the network by comprising a parameter indicating a time instant relative to the course of the event at which a data traffic peak is expected to occur.
14. The method of claim 13, wherein the model indicates a data rate at which an SDN link is pending at the time at which a data traffic peak is expected to occur.
15. A computer readable medium storing computer readable instructions which, if executed by a processor, cause the processor to carry out the method of any one of claims 8 to 14.
CN201780094848.7A 2017-09-12 2017-09-12 Data traffic management in software defined networks Pending CN111095868A (en)

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/EP2017/072852 WO2019052630A1 (en) 2017-09-12 2017-09-12 Data traffic management in a software defined networks

Publications (1)

Publication Number Publication Date
CN111095868A true CN111095868A (en) 2020-05-01

Family

ID=59966709

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201780094848.7A Pending CN111095868A (en) 2017-09-12 2017-09-12 Data traffic management in software defined networks

Country Status (2)

Country Link
CN (1) CN111095868A (en)
WO (1) WO2019052630A1 (en)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112838957B (en) * 2021-02-23 2022-09-09 成都卓源网络科技有限公司 Flow prediction system with intelligent scheduling function

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN1545245A (en) * 2003-11-12 2004-11-10 中国科学院计算技术研究所 Online prediction method for data network flow
CN105376105A (en) * 2014-08-27 2016-03-02 苏州大数聚信息技术有限公司 Internet traffic modeling method based on time-sliding window
CN106612289A (en) * 2017-01-18 2017-05-03 中山大学 Network collaborative abnormality detection method based on SDN
US20170230267A1 (en) * 2016-02-08 2017-08-10 Ciena Corporation Traffic-adaptive network control systems and methods

Family Cites Families (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US9588815B1 (en) * 2015-06-17 2017-03-07 EMC IP Holding Company LLC Architecture for data collection and event management supporting automation in service provider cloud environments

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN1545245A (en) * 2003-11-12 2004-11-10 中国科学院计算技术研究所 Online prediction method for data network flow
CN105376105A (en) * 2014-08-27 2016-03-02 苏州大数聚信息技术有限公司 Internet traffic modeling method based on time-sliding window
US20170230267A1 (en) * 2016-02-08 2017-08-10 Ciena Corporation Traffic-adaptive network control systems and methods
CN106612289A (en) * 2017-01-18 2017-05-03 中山大学 Network collaborative abnormality detection method based on SDN

Also Published As

Publication number Publication date
WO2019052630A1 (en) 2019-03-21

Similar Documents

Publication Publication Date Title
CN104809051B (en) Method and apparatus for predicting exception and failure in computer application
US10878327B2 (en) Detecting root cause for transaction degradation using causal bayesian networks
KR102118670B1 (en) System and method for management of ict infra
WO2014208002A1 (en) System analysis device, system analysis method and system analysis program
US10599501B2 (en) Information processing device, information processing method, and recording medium
JP6658540B2 (en) System analysis device, system analysis method and program
EP2963552B1 (en) System analysis device and system analysis method
CN105325023A (en) Method and network device for cell anomaly detection
US9530256B2 (en) Generating cumulative wear-based indicators for vehicular components
EP2963553B1 (en) System analysis device and system analysis method
US20150186617A1 (en) System and method for probabilistic evaluation of contextualized reports and personalized recommendation in travel health personal assistants
WO2020066052A1 (en) Monitoring system and monitoring method
JP5413240B2 (en) Event prediction system, event prediction method, and computer program
US11348023B2 (en) Identifying locations and causes of network faults
CN109918280B (en) Health management method and device for servo system
WO2017033443A1 (en) Traffic-congestion prediction system, traffic-congestion prediction method, and recording medium
JP2020052714A5 (en)
Gupta et al. A supervised deep learning framework for proactive anomaly detection in cloud workloads
CN111095868A (en) Data traffic management in software defined networks
JP6625839B2 (en) Load actual data determination device, load prediction device, actual load data determination method, and load prediction method
US10157113B2 (en) Information processing device, analysis method, and recording medium
US10467888B2 (en) System and method for dynamically adjusting an emergency coordination simulation system
CN112380073B (en) Fault position detection method and device and readable storage medium
CN107121943B (en) Method and device for obtaining health prediction information of intelligent instrument
Zhang et al. A novel approach for QoS prediction based on Bayesian combinational model

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
RJ01 Rejection of invention patent application after publication

Application publication date: 20200501

RJ01 Rejection of invention patent application after publication