US20160021173A1 - Resource management in a big data environment - Google Patents

Resource management in a big data environment Download PDF

Info

Publication number
US20160021173A1
US20160021173A1 US14/800,648 US201514800648A US2016021173A1 US 20160021173 A1 US20160021173 A1 US 20160021173A1 US 201514800648 A US201514800648 A US 201514800648A US 2016021173 A1 US2016021173 A1 US 2016021173A1
Authority
US
United States
Prior art keywords
network
data
computer system
network element
notification
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.)
Abandoned
Application number
US14/800,648
Other languages
English (en)
Inventor
Pablo Tapia
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.)
Tupl Inc
Original Assignee
Tupl Inc
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 Tupl Inc filed Critical Tupl Inc
Priority to US14/800,648 priority Critical patent/US20160021173A1/en
Assigned to TUPL, Inc. reassignment TUPL, Inc. ASSIGNMENT OF ASSIGNORS INTEREST (SEE DOCUMENT FOR DETAILS). Assignors: TAPIA, PABLO
Priority to PCT/US2015/040809 priority patent/WO2016011295A2/fr
Priority to JP2017523189A priority patent/JP6853172B2/ja
Publication of US20160021173A1 publication Critical patent/US20160021173A1/en
Priority to US17/185,847 priority patent/US20210185117A1/en
Priority to JP2021038871A priority patent/JP7280302B2/ja
Priority to JP2022205693A priority patent/JP2023027358A/ja
Abandoned legal-status Critical Current

Links

Images

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L67/00—Network arrangements or protocols for supporting network services or applications
    • H04L67/01—Protocols
    • H04L67/10—Protocols in which an application is distributed across nodes in the network
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L47/00—Traffic control in data switching networks
    • H04L47/70—Admission control; Resource allocation
    • H04L47/82—Miscellaneous aspects
    • H04L47/822—Collecting or measuring resource availability data
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L67/00—Network arrangements or protocols for supporting network services or applications
    • H04L67/01—Protocols
    • H04L67/12—Protocols specially adapted for proprietary or special-purpose networking environments, e.g. medical networks, sensor networks, networks in vehicles or remote metering networks
    • H04L67/125—Protocols specially adapted for proprietary or special-purpose networking environments, e.g. medical networks, sensor networks, networks in vehicles or remote metering networks involving control of end-device applications over a network
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W72/00—Local resource management
    • H04W72/04—Wireless resource allocation

Definitions

  • wireless communications which have experienced constant and significant transformation, guided by the continuous development of new network technologies and services, ushered in by the smartphone revolution and its countless applications.
  • wireless, such as cellular, systems have continuously evolved to cope with the increasing traffic demands, as well as the performance requirements imposed by these applications.
  • the evolution of the wireless communication systems have typically taken place in isolated blocks, such as improving the performance at the radio level, or improving the architecture of the core network. While wireless communication has improved in the past decade, portions of the backend systems that support the networks still may include legacy architectures such as 3G and 2G networks.
  • FIG. 1 illustrates an example network architecture for implementing a radio resource management architecture.
  • FIG. 2 illustrates an example high level interface block diagram of the elements of a radio access network.
  • FIG. 3 is a block diagram showing a Radio Resource Management (RRM) module interacting with the data framework, consistent with an exemplary embodiment.
  • RRM Radio Resource Management
  • FIG. 4 is a flow diagram of an example process for a modified RRM utilizing Big Data Records.
  • FIG. 5 is a flow diagram of an example process for adjusting a connection between an eNodeB and an EU based on a notification from the measurements megastore.
  • FIG. 6 is a block diagram of a data framework, consistent with an exemplary embodiment.
  • FIG. 7 illustrates an example model for a root cause identification.
  • FIG. 8 is a flow diagram of an example process for maintaining a radio access network performance.
  • FIG. 9 is an example user interface of a terminal coupled to a measurements megastore.
  • FIG. 10 which illustrates a high level diagram of a system that includes remote health monitoring, consistent with an exemplary embodiment.
  • FIG. 11 is a block diagram of a data framework of a monitoring system, consistent with an exemplary embodiment.
  • FIG. 12 is a flow diagram of an example process for identifying a health condition using Big Data Records.
  • FIG. 13 illustrates a network or host computer.
  • FIG. 14 illustrates a computer with user interface elements.
  • a scalable network backend is provided based on an open architecture that provides simplified access to data and increases automation.
  • the operational efficiency and the overall cost of operation of the network is reduced by automation of functions and rationalization of hardware and software resources.
  • the systems described herein provide an open platform where multiple data feeds from disparate sources are combined and processed in real time.
  • the system performs continuous monitoring and transmission of the monitored data from each network node, which can be synthesized at a centralized remote server.
  • the synthesized data harvested from disparate sources is analyzed for potential problems and relevant solutions are provided.
  • data from disparate sources related to a first network element is received by a processing layer.
  • Contextual information from a measurements megastore related to the first network element and other network elements is retrieved.
  • the data from the disparate sources and the contextual information is analyzed by an intelligence layer.
  • a notification is provided to the first network element.
  • FIG. 1 illustrates an example network architecture for implementing a radio resource management architecture.
  • FIG. 1 illustrates a mobile communication network 100 as may be operated by a carrier or service provider to provide a wide range of mobile communication services and ancillary services or features to its subscriber customers and associated mobile device users.
  • the elements generally indicated by the reference numeral 100 are elements of the mobile communication network and are operated by or on behalf of the carrier.
  • the mobile communication network 100 provides communications between user equipment (UE) 102 a to 102 d , as well as communications for the UE with networks and stations outside the mobile communication network 100 .
  • UE user equipment
  • UE's appear in the drawing, to represent some examples of the devices that may receive various services via the mobile communication network 122 .
  • UE's typically take the form of portable handsets, smart-phones, tablet computers, personal digital assistants (PDAs), and smart watches, although they may be implemented in other form factors, including consumer, business, and medical electronic devices, such as a wearable personal health monitor 102 d .
  • the mobile communication network 100 allows users of the UE's (e.g., customers or subscribers) to initiate communication, and receive information from the internet 120 .
  • the mobile communication network 100 typically is implemented by a number of interconnected networks.
  • the overall network 100 may include a number of Radio Access Networks (RANs) 122 , as well as regional ground networks interconnecting a number of RANs and a wide area network (WAN) interconnecting the regional ground networks to core network elements, such as the Multimedia Messaging Service Centers (MMSCs).
  • RANs Radio Access Networks
  • WAN wide area network
  • MMSCs Multimedia Messaging Service Centers
  • a regional portion of the network 100 such as that serving UE's 102 b and 102 c may include one or more RANs (represented by wireless communication network 122 ) and a regional circuit and/or packet switched network and associated signaling network facilities.
  • Physical elements of a RAN 122 include a number of base stations represented in the example of FIG. 1 by an eNodeB 119 node.
  • Such eNodeB 119 nodes may include a base transceiver system (BTS) that communicates via an antennae system at the site of the node and over the air-link with one or more of the UE's ( 102 a to 102 d ) when the UE's are within range.
  • BTS base transceiver system
  • Each eNodeB 119 node may include a BTS coupled to several antennae mounted on a radio tower within a coverage area often referred to as a “cell.”
  • the BTS is the part of the radio network that sends and receives RF signals to/from the UE's that the eNodeB node 119 currently serves.
  • the radio access networks 122 carries the user communications for the UE's between the respective eNodeB 119 nodes and other elements with or through which the UE's communicate.
  • the radio that transmits communication signals (to one or more UE's) at each eNodeB may adjust the power output, bandwidth, etc., based on contextual information received from a measurements megastore 140 and/or alerts received from a monitoring server 130 , discussed in more detail later.
  • Individual elements such as switches and/or routers forming the radio access network 122 are omitted here for simplicity but are discussed in relevant part in the context of FIG. 2 .
  • the radio access network portion 122 of the mobile communication network 100 connects to a public packet data communication network, such as the network commonly referred to as the “Internet” shown at 120 .
  • Packet communications via the radio access network 122 and the Internet 120 may support a variety of services through the network 100 , such as providing contextual information from the measurements megastore and alerts from the monitoring server 130 to various network elements of the radio access network 122 , as well as provide communications of text and multimedia messages, e-mail, web surfing or browsing, programming and media downloading (including audio and video), etc. to the UE's.
  • the UE's 102 a to 102 d may be able to receive messages from and send messages to user terminal devices, such as personal computers, either directly (peer-to-peer) or via various servers (not separately shown).
  • the Evolved Packet Core (EPC) of the radio access network 122 uses the concept of Evolved Packet System (EPS) bearer channels to route IP traffic from a gateway 107 in the radio access network 122 to a UE.
  • a bearer channel is an IP packet flow with a defined quality of service (QoS) between the Packet Data Network (PDN) Gateway (PGW) 107 and the UE (e.g., 13 a to 13 e ).
  • QoS quality of service
  • the eNodeBs 119 are normally interconnected with each other by an interface known as “X2.”
  • the communication between each eNodeB includes Radio Resource Management (RRM), which covers all functions related to the radio bearers, such as radio bearer control, radio admission control, radio mobility control, scheduling, and dynamic allocations of resources to UEs in both uplink and downlink.
  • RRM Radio Resource Management
  • the RRM can communicate with the measurements megastore 140 and/or receive messages from the monitoring server 130 to optimize its control features.
  • network 100 includes a measurements megastore server 140 , which is coupled for communication via the internet 120 .
  • the measurements megastore server stores contextual information (which may be from various sources) that is relevant to creating a more efficient connection (e.g., power consumption and/or speed) between a UE and the radio access network 122 as well as optimizing the components of the radio access network 122 .
  • the UE and the components of the radio access network are collectively referred herein as network elements.
  • the contextual information provided by the measurements megastore server 140 may include different types of information.
  • the contextual information may include application level information that is extracted via Deep Packet Inspection (DPI) that is received from one or more radio access networks 122 .
  • DPI Deep Packet Inspection
  • the contextual information at the server 140 may include UE terminal category (e.g., smart-phone, tablet, laptop, personal health monitoring device, etc.) information.
  • the contextual information may also relate the capabilities of the network element, such as the maximum transmission bitrate and whether it is configured to be a low power device (configured for low power versus high performance).
  • the contextual information may provide the latest stored power status of the network element, which may be used to optimize the connection between the radio access network 122 and the respective UE.
  • the measurements megastore server 140 stores contextual information comprising disparate data from various sources.
  • the data stored in the server 140 comprises information that can be used by the network elements of the wireless communication network 122 to provide a tailored optimization of the resources of the each network element, respectively.
  • the monitoring server 130 can retrieve the contextual information from the measurements megastore 140 , which includes information from the entire network 100 , and analyze the contextual information together with data from disparate sources related to a network element to determine whether one or more predetermined conditions are met to trigger a message to the respective network element to optimize its performance in the context of the entire network 100 .
  • a prior art cellular communication network may only utilize locally obtained metrics from a small subset of network elements such as network elements in the core network from the same vendor, or network elements deployed to implement a specific feature in the network, to decide how to optimally assign resources to each communication link of a UE 102 to the to the Radio Access Network 122 .
  • a prior art radio scheduler may merely consider locally accessible information, such as the amount of data in the buffer of the respective UE, the identified radio quality, and the device capability, for the scheduler to determine the number of turns to assign to each link between the UE and the corresponding eNodeB.
  • locally accessible information such as the amount of data in the buffer of the respective UE, the identified radio quality, and the device capability
  • the scheduler may determine the number of turns to assign to each link between the UE and the corresponding eNodeB.
  • DPI Deep Packet Inspection
  • FTP File Transfer Protocol
  • the system described herein allows the sharing of information across multiple eNodeB's 119 by storing contextual information at a measurements megastore server 140 , which improves the capacity of the wireless communication network 122 by allocating, for example, the type of resources in a connection between a UE (e.g., 102 d ) and its corresponding eNodeB 119 .
  • the radio communication between a UE 102 and the radio access network 122 is better adjusted by making use of contextual information such as the type of customer, data plan, type of application, type of device, etc., which is provided by the measurements megastore 140 via the internet 140 .
  • the monitoring server 130 and the measurements megastore 140 may be implemented in a distributed fashion on a number of similar platforms, to distribute the processing load and/or to provide additional functionality.
  • a remote health (e.g., for humans) monitoring server 150 that is similar in configuration to the measurements megastore 140 but may be specialized in remote health monitoring.
  • the system 100 provides an open platform where multiple data feeds from various UE's, such as the personal health monitor 102 d , and disparate systems, such as other networks and servers, can be combined and processed in real time, for millions of individuals.
  • the functionality described herein with respect to each of the servers 130 , 140 , and 150 can also be provided by one or multiple different servers. The actual operation of the system 100 is described by way of example later.
  • FIG. 2 illustrates an example high level interface block diagram of the logical nodes of a radio access network 122 .
  • the System Architecture Evolution (SAE) 200 is the core network architecture of Third Generation Partnership Project's (3GPP's) Long Term Evaluation (LTE) wireless communication standard.
  • the SAE 200 has a flat, all-IP architecture with separation of control plane and user plane traffic.
  • the SAE 200 system includes eNodeB 219 , Mobility Management Entity (MME) 202 , Home Subscriber Server (HSS) 204 , and the Policy Control and Charging Rules Function (PCRF) 206 , which are part of the mobile traffic network 122 and are each network elements.
  • MME Mobility Management Entity
  • HSS Home Subscriber Server
  • PCRF Policy Control and Charging Rules Function
  • the eNodeB 219 can be viewed as an enhanced base station that acts as an interface between the UE 202 and the radio access network 122 .
  • MME 202 is a control-node for the communication access network. For example, it is used for idle mode mobile device tracking and paging procedure including retransmissions. It also provides bearer channel activation/deactivation process and selection of the serving gateway (SGW) 212 for the UE 202 e.
  • SGW serving gateway
  • the Home Subscriber Server (HSS) 204 is a central database that contains user-related and subscription-related information.
  • the HSS 204 provides features such as mobility management, call and session establishment support, user authentication and access authorization.
  • the HSS stores the Mobile Station International Subscriber Directory Number (MSISDN), the SIM-card identification information, and the like.
  • MSISDN Mobile Station International Subscriber Directory Number
  • SIM-card identification information and the like.
  • the Packet Data Network (PDN) Gateway (PGW) 107 provides connectivity from the UE 202 to external packet data networks.
  • the Policy Control and Charging Rules Function (PCRF) 206 provides for policy control decision-making, as well as for controlling the flow-based charging functionalities in the Policy Control Enforcement Function (PCEF), which resides in the PGW 107 .
  • the PCRF 206 provides the QoS authorization that decides how certain data flow is treated in the PCEF and ensures that this is in accordance with the user's subscription profile.
  • the Serving Gateway (SGW) 212 routes and forwards data packets to the mobile 202 through the MME 202 .
  • a data packet can include a notification message that an account threshold is exceeded.
  • the SGW 212 manages and stores mobile device parameters of the IP bearer channel service, including network internal routing information. Each of these network elements and others can be adjusted in performance based on the contextual data from the measurements megastore 140 and the alerts/messages of the monitoring server 130 .
  • RRM Radio Resource Management
  • FIG. 3 is a block diagram showing a Radio Resource Management (RRM) module interacting with the data framework, consistent with an exemplary embodiment.
  • the eNodeB 319 acts as a base station between one or more UE's (e.g., UE 302 ) and a wireless communication network.
  • each eNodeB 330 includes a scheduler 322 that is configured to provide priority (e.g., allocating the number of turns) for data transmission between the UE 302 and the wireless communication network.
  • the eNodeB 319 may include a link adaptation 324 unit that is configured to adjust the transmission mode to the channel conditions by, for example, adjusting modulation, coding, and selecting the appropriate time for transmission.
  • the eNodeB 319 may include a flow control 326 unit that is configured to control the flow of the operations of the eNodeB 319 .
  • the flow control 326 unit may provide admission control, coordination of the security signaling, compression, etc.
  • the eNodeB includes an antenna 330 that is configured to communicate with various UE's (e.g. UE 302 ) within its wireless communication range.
  • the various components of the eNodeB 319 together comprise an RRM module 328 , which is configured to communicate with the data framework 370 via an open Application Program Interface (API) 334 .
  • the data framework may include the measurements megastore 340 , an intelligence layer 350 and a data processing layer 352 .
  • the API 334 may facilitate communication between eNodeB 319 through the wireless communication network 122 , via the internet 120 (of FIG. 2 ) to the measurements megastore 340 .
  • the data processing layer 352 may also receive localized information from the RRM 328 .
  • the measurements megastore 340 is configured to store contextual information from various network elements, such as RRM modules of different eNodeB's, that can be shared by eNodeB 319 (and other eNodeB's configured to receive information from the measurements megastore 140 ), to better adjust the respective network element of the radio communication over the wireless communication network 122 of FIG. 1 .
  • Such optimization may include at least one of: admission control, scheduler, link adaptation, and power control procedures of the respective eNodeB.
  • data is gathered by the data processing layer 352 of system 300 .
  • the data gathered by the processing layer may be from various sources, which may include data from elements of the wireless communication network 122 , such as RRM module's coupled to the wireless communication network 122 , as well as other servers (e.g., 130 , 150 ) of the system 100 .
  • the type of information received by the data processing layer 352 may include subscriber radio trace (e.g., location) provided by a UE, operations subsystem (OSS), customer care records, billing, application performance monitoring reports, and other information, including relevant information from the internet. In one embodiment, at least some of this information is provided by the measurements megastore 340 .
  • the data includes information from Deep Packet Inspection (DPI) provided by various eNodeB's.
  • DPI Deep Packet Inspection
  • the data processing layer 352 may be performed in real time and/or in batch.
  • the data may be provided to a network element (e.g., an RRM module 328 at an eNodeB 319 ) via a query performed by the network element in real time or may be pushed to the RRM module at predetermined time intervals or in response to a notification generated by the intelligence layer 350 .
  • a network element e.g., an RRM module 328 at an eNodeB 319
  • the intelligence layer 350 may be configured to receive the information from the data processing layer 352 and determine whether predetermined one or more conditions are met. These conditions may be provided by a rule set stored in a memory of the intelligence layer. When a predetermined condition is met, the intelligence layer may generate a relevant alert. For example, the intelligence layer 350 may analyze the patterns of the data provided by the data processing layer 352 for any outliers that may indicate a problem at an RRM. In this regard, the intelligence layer 350 may trigger a notification to other RRM modules to prevent and/or mitigate the problem from spreading. The alert may simply be a notification (e.g., a suggestion to act) or an active control signal that alters the RRM method of one or more modules that are part of the system 300 .
  • a notification e.g., a suggestion to act
  • an active control signal that alters the RRM method of one or more modules that are part of the system 300 .
  • the intelligence layer 350 typically includes a probability tree that stores the probabilities that particular causes and/or events were the root cause of a network event such as a dropped call.
  • the implementation of a probability tree is described in further detail with respect to FIG. 7 . Note that that a node with an intelligence layer 350 need not have the same probability tree as other nodes. In this way, nodes may be partitioned according to scenario and/or use cases.
  • the data processing layer 352 may receive information from first RRM module that is indicative of a problem.
  • the data received from the first RRM module may, for example, indicate that the SGW is overloaded with signaling messages.
  • the intelligence layer 350 upon identifying the problem with the first SGW, may retrieve contextual information from the measurements megastore related to the network element and other network elements. Upon determining that a condition is met or a predetermined threshold is exceeded, the intelligence layer 350 may issue a notification to other RRM modules configured to receive messages from the data framework 370 .
  • the first RRM module also receives the alert from the data framework 370 , generated by the intelligence layer 350 .
  • the other eNodeB modules can buffer or discard the communication requests going to their systems, respectively, to prevent the problem that affected the first RRM module.
  • the contextual information in the measurements megastore 340 can be made available to an RRM module by the measurements megastore 340 in response to a request (e.g., query) from the RRM module, or may be provided as a notification from the data framework 370 .
  • FIG. 4 illustrates a high level flow chart of the data framework 430 and an RRM module 402 and their interaction with one another.
  • the RRM module 402 may be one of several RRM modules that are configured to receive data from a data framework 430 .
  • the data framework 430 includes contextual information that is gathered from multiple sources, which is used by the RRM module 402 for adjusting the resources of the RRM module (e.g., optimize a connection between an eNodeB and an UE).
  • relevant data is collected from various sources into a common data framework.
  • This data is collected by a data processing layer in real-time and/or in batch.
  • the data gathered may be from various sources, which may include different components of the wireless communication network 122 , including separate RRM module's configured to operate on the wireless communication network 122 .
  • each RRM module may provide the radio resources based on its local knowledge of the wireless communication network 122 and its corresponding UE(s) of the system 100 of FIG. 1 .
  • the sources of the data gathered may also include other servers of system 100 and the internet.
  • the type of information received by the data framework 430 may include subscriber radio trace (e.g., location) provided by a UE, operations subsystem (OSS), customer care records, billing, application performance monitoring reports, and other information, including relevant information from the internet.
  • subscriber radio trace e.g., location
  • OSS operations subsystem
  • customer care records billing, application performance monitoring reports, and other information, including relevant information from the internet.
  • the data harvested by the data processing layer ultimately becomes the contextual data that is stored at the measurements megastore server 340 , which may be used retrieved by other network elements or the data processing layer.
  • the data gathered from the various sources by the data framework 430 is provided to the RRM module 402 to adjust its resources allocated to a connection between its eNodeB and a corresponding UE.
  • the information may include data that has not been processed by the intelligence layer, such as general information on subscribers and network nodes.
  • the data gathered by the data framework is further processed by an intelligence layer, which is operative to analyze the data and extract patterns and/or trends therefrom.
  • the intelligence layer may determine whether one or more thresholds are exceeded or one or more criteria are met. For example, the RRM module is OFF or the number of dropped calls exceeds 0.1%.
  • the considerations by the intelligence layer may include user/subscriber predetermined preferences, subscriber limitations (e.g., exceeding a threshold data usage), the type of plan (e.g., higher grade plans may be given priority), type of UE (e.g., devices that are intended to work under low power conditions are provided connections that demand less power), etc.
  • the data framework 430 may provide one or more messages to the appropriate RRM module(s) in a form of special alerts, which may include instructions on how to adjust the local resources for a connection between the eNodeB and its corresponding UE, on an individual basis.
  • the appropriate RRM module(s) where the alert from the data framework 430 to the RRM module(s) are sent may be based on sector and/or time (e.g., the RRMs covering a sports stadium at the time of a game).
  • the RRM module 402 calculates the radio resources based on local knowledge.
  • the local knowledge may include the type of device (UE) it is establishing a connection with, the number of UE's the local eNodeB is connected with, traffic, power consumption, modulation quality, temperature of the eNodeB, etc. In one embodiment (not shown) this information is provided to the data framework 430 via the data processing layer 352 .
  • the RRM module 402 adjusts the resource allocation between its eNodeB and each UE on an individual basis, based on the general information data received from the data framework 430 in step 420 .
  • the RRM module 402 may receive one or more messages from the data framework 430 in the form of one or more special alerts (i.e., notifications).
  • the RRM module 402 assigns the resources of eNodeB based on the special alerts on subscribers and network nodes received from the data framework. While steps 408 and 408 have been illustrated by way of example to be separate steps, in one embodiment, the adjustment of resources and the assignment of resources may be performed by the same step (e.g., 408 ).
  • the eNodeB of the RRM module 402 may adjust the connection based on the power (e.g., consumption limitation) requirements for each UE individually.
  • an eNodeB may gradually reduce the number of UE's that are allowed to connect to a respective eNodeB in order to balance the radio access network 122 resources and/or prevent failure.
  • the scheduler 322 upon receiving a warning from the measurements megastore 340 , may stop sending new session requests to the radio access network 122 .
  • remedial actions may include reducing the bandwidth or preventing communication with specific UE's that have exceeded predetermined thresholds or have not met one or more criteria.
  • the restriction(s) may be lifted after a threshold time or upon receiving a message from the measurements megastore 140 that the UE is within predetermined thresholds.
  • the restrictions may be lifted when a criterion is met (e.g., sporting event at an arena, which is serviced by eNodeB 319 , has completed), which reduces the risk of overloading the eNodeB of the RRM module 402 .
  • FIG. 5 is a flow diagram of an example process for adjusting a connection between an eNodeB and an EU based on a notification from the measurements megastore 140 .
  • the flow diagram of FIG. 5 is a particular example that considers the type of the network element and the stored criteria for such a type of element.
  • the RRM module determines the radio signal quality between an UE the eNodeB based on local knowledge.
  • the RRM module determines the appropriate coding format based on the determined radio signal quality based on local knowledge.
  • the RRM module communicates with the measurements megastore 140 to receive contextual information therefrom. This step may be performed as a query from the RRM module to the measurements megastore 140 , or a push notification from the measurements megastore 140 to the RRM module based on predetermined criteria stored at the measurements megastore 140 .
  • the RRM module may perform a query (e.g., over the internet 120 ) to the measurements megastore 140 in support of various network operations.
  • the network operation is to initiate and establish a communications for a UE.
  • the RRM may send the UE device identifier and/or other indicators of radio signal quality based on local knowledge to the measurements megastore 140 .
  • the measurements megastore 140 may indicate that the type of UE that the RRM module is in the process of establishing a connection with, is intended to work at low power, and the connection between the eNodeB and the UE should be optimized for low power operation.
  • the connection may be serving an M2M customer that may benefit from a connection that uses the least amount of power.
  • This scenario may be of importance for medical devices that are implanted or are wearable personal health monitoring devices.
  • the contextual information provided by the measurements megastore 140 may be in the form of a notification (e.g., warning) or an instruction to the RRM module to adjust the connection such that the UE consumes a more optimized (e.g., least) amount of power.
  • the indicators of radio quality that were determined based on local knowledge, that were provided to the measurements megastore 140 may include the battery status (e.g., running low).
  • the measurements megastore 140 in cooperation with the intelligence layer may identify from previously stored user preferences that the UE (that is now running low on power) should be operated in low power mode to extend its duration as long as possible.
  • the intelligence layer may issue a notification (in step 520 ) to the RRM module that the connection between the eNodeB and the UE should be of low power.
  • the RRM module would not have determined that the user preferences include a low power operation when a predetermined condition is met (i.e., running at low power).
  • the RRM modifies the coding scheme to provide a connection with the UE that provides the most power savings, which may include a lower bandwidth operation, thereby freeing up radio access network 122 resources for other purposes.
  • the warning received from the intelligence layer triggers an “event handler” at the eNodeB to perform some the power saving functions.
  • a problem can be identified (and sometimes prevented) even before the customer becomes aware of the problem, which greatly improves customer relations.
  • This advantage may be better understood in view of existing approaches to address network problems and related customer complaints. For example, when a subscriber (e.g., customer) experiences a network problem, there is typically a lengthy and sometimes frustrating process involved, which is typically highly manual, requiring the frequent intervention of skilled engineers to identify and resolve the issues.
  • a customer first must call and explain the symptoms to a customer care representative, who classifies the matter based on predetermined criteria.
  • An internal record may be generated to be analyzed by an appropriately skilled engineer.
  • An engineer may create a Call Reliability Report that includes the traffic volume, number of dropped calls, reasons for the dropped calls, and an overall calculated drop call rate for the node(s) of concern.
  • there is an intermediate engineering triaging group that may address some of the complaints, while in other cases, the case is sent to a field engineer to investigate the root of the problem. Due to the complexity of the radio access network, the field engineer may investigate multiple systems to determine what the cause of the problem may be based on the limited analysis that s/he could perform from the local knowledge of the network.
  • the bulk (if not all) of the analysis of the state of the network automatically performed by a data framework that includes a measurements megastore 140 .
  • the root cause of the problem may be determined (if not prevented) even before the customer becomes aware of the problem.
  • a measurements megastore 140 that, together with a data processing layer and an intelligence layer, is configured to detect problems at a subscriber level by not only relying on local knowledge of the network element, but also using data related to the entire network and by automatically curing the problem and/or providing a notification (e.g., reporting it) to the appropriate representative and/or field engineer.
  • the measurements megastore 140 uses a massive parallel processing technology such as Hadoop, Storm, or Spark.
  • machine learning components are used to identify patterns and trends based on pre-determined training sets.
  • previously unknown problems are detected by different clustering models. For example, data is grouped in such a way wherein objects in the same group (i.e., cluster) are more similar to each other than to those in other groups (i.e., clusters).
  • FIG. 6 is a block diagram a data framework, consistent with an exemplary embodiment.
  • the data framework of FIG. 6 is similar to that of FIG. 3 discussed above, but has been redrawn for clarity to facilitate the discussion of automatic troubleshooting of radio access networks.
  • the data framework of FIG. 6 includes a data processing layer 682 , an intelligence layer 684 that may include programmable pattern detection rules 688 , an automation layer 686 that is configured to store programmable set of actions based on the problem type 690 , and a measurements megastore 680 .
  • the type of information received by the data processing layer 682 may include, among other elements: data from a customer care trouble ticket database; network element counters and KPIs; network element (UE) location; alarm and fault information; subscriber information, including subscriber plans, utilization (e.g., minutes/data), billing address, etc.; handset information, including handset type, OS, apps, battery status, etc.; subscriber detailed information records, including Geolocation, radio, core network and IP level traces; Wi-Fi records and metrics, etc.
  • the data processing layer 682 may be performed in real time and/or in batch. The monitoring may be performed continuously, 24 hours a day, 7 days a week, at predetermined intervals, or in response to a trigger from the intelligence layer 384 of the monitoring system.
  • the data processing layer 682 monitors detailed subscriber traces, and records fault situations, such as a dropped call, an access failure, or a problem with Internet connectivity. This data is stored in the measurements megastore 680 together with data from other network elements as contextual information that may be used by various network elements.
  • the intelligence layer 684 is configured to receive the information from the data processing layer 684 and pattern detection rules 688 that may be preprogrammed in the intelligence layer 684 .
  • the intelligence layer 684 may include different intelligence models for different types of failures.
  • the intelligence layer 684 is configured to identify a probable cause of a problem as well as an estimation of accuracy (error) for the error detection. In one embodiment, the accuracy of the detection is based on the frequency of the occurrence of the error.
  • the estimation of accuracy may be high when a customer may be experiencing degraded performance (drops, access failures, etc.) in an area that has been identified by the intelligence layer to be undergoing maintenance or where there is a known lack of coverage.
  • the intelligence layer may further improve the accuracy by reviewing the customer trace, network health indicators, and the UE reports, etc. From the disparate sources of data, the intelligence layer 684 can identify whether the drop is due to (1) coverage, (2) interference, (3) hardware failure, (4) software failure, etc.
  • the automation layer 686 may trigger an automatic response to an identified network error without having to rely on prior human processing of the raw data harvested by the data processing layer 682 .
  • the appropriate action for an identified problem is pre-programmed by a system administrator at the intelligence layer or at the network element node.
  • the action may be a resetting of a node or sending a note to the field engineer with the identified problem and potential solution.
  • the automated action may be to send a message to the subscriber, notifying them of the cause of the problem (e.g., there is ongoing maintenance work in the area), or providing an automatic credit to compensate for the degraded performance and notifying the subscriber of the same.
  • the automation layer 686 may automatically send a message to all subscribers in that area to prophylactically cure the problem before the subscribers are affected by the problem.
  • a notification is automatically sent to all network elements in that group.
  • network errors that are identified with an accuracy below a first threshold are treated differently from those with an accuracy of above a second threshold.
  • the first and second threshold have the same value.
  • an automatic action may not be performed until additional data is received to improve the accuracy and/or the subscriber calls about the problem.
  • the error is identified with a high accuracy, automatic immediate remedial measures are undertaken.
  • the automation layer 686 in cooperation with the intelligence layer 684 may propose a palliating action upon determining that a particular subscriber is not receiving the expected quality of service.
  • the intelligence layer may determine whether there is an option to use Wi-Fi calling.
  • the automation layer 686 may send a notification to the subscriber and care representative to facilitate the activation of Wi-Fi calling.
  • FIG. 7 illustrates an example model for an automatic root cause identification. Specifically, FIG. 7 illustrates a probability tree that stores information as to the probable root cause for a dropped call. Based on a large corpus of data, a machine learning algorithm can determine the probabilities that an event, such as a dropped call, was correlated to a particular cause. In turn, a particular cause, may have different potential causes of its own, each with their own probabilities. Eventually, the probability of a root cause, may be discerned.
  • the probability tree may then be traversed to determine the most likely root causes. To do so, the probability tree is traversed to the nodes representing potential immediate causes for the dropped call event 702 . These may include radio interference 704 , poor coverage 706 , hardware failure 708 , software failure 710 , or other failures 712 . As with the dropped call event, each cause is associated with a probability. Because, these causes are potential causes, the probabilities are expressed as conditional probabilities P(Condition
  • DC) 0.2. Similarly, the probability that a dropped call was caused by a software failure 710 is shown as P(SW
  • DC) 0.3.
  • Cause nodes may in turn have their own respective causes.
  • radio interference 704 and poor coverage 706 may have the same cause 714 .
  • Hardware failure 708 may have different possible causes, here shown as a physical error 716 and misconfiguration of user equipment 718 .
  • the each node is associated with a respective probability, and as potential causes, each probability is expressed as a conditional probability.
  • HW) 0.1.
  • HW) 0.6.
  • a software failure 710 may also be caused by misconfiguration 718 . Even though the probability tree traverses to a node also traversable from hardware failure 708 , the misconfiguration node 718 has its own probability as the cause of a software failure 710 as shown as P(MCG
  • SW) 0.3. A software failure 710 may also be caused by having a wrong version of software installed 720 , with a causal conditional probability of P(WVER
  • SW) 0.5.
  • a probability tree is generally populated via receiving a statistically significant corpus of data. The data is then applied to the probability tree to compute the probabilities in the probability tree.
  • the probability tree starts with the causes and/or KPI leaf nodes 724 , 726 , 728 , 730 , 732 .
  • the probabilities of the causes and/or KPI leaf nodes 724 , 726 , 728 , 730 , 732 are updated. For example, if a misconfiguration is actually observed, the probability of the misconfiguration 728 is changed to 100%. If a cause 724 is not observed, that probability is changed to 0%. Probabilities need not be binary, i.e. solely 100% or 0%. Intermediate (non 0% non 100%) probabilities may be computed based on a sampling or running average of data.
  • the parent node probabilities are updated according to Bayes Algorithm.
  • the conditional probabilities of the parent nodes 714 , 716 , 718 , 720 and 722 are updated using the child node as a determination as to whether a condition was satisfied.
  • the probabilities of the parent nodes 714 , 716 , 718 , 720 and 722 are then updated. This process is repeated for the level of parent nodes above, until the root node 702 is reached. At this point, all the probabilities in the probability tree have been updated in light of the observed causes and/or KPIs 724 , 726 , 728 , 730 , 732 .
  • the dropped call, 702 will be surfaced to a user by selecting all child nodes with updated probabilities exceeding a predetermined threshold.
  • the probability tree is returned to its original state and original probabilities.
  • the historical data may be collected and upon agreement by an administrator, at least a subset of the historical data may be applied to the probability tree to permanently update the probabilities in the probability tree. Subsequent analyses will then use the updated probability tree. In this way, the probability tree learns from historical data.
  • FIG. 8 is a flow diagram of an example process for assisting an engineer in maintaining a radio access network performance.
  • step 802 data is automatically collected from various sources into a common data framework that is stored in the measurements megastore.
  • step 804 a pattern recognition is performed on the data by one or more clustering algorithms.
  • the key metrics to be analyzed are preprogrammed in the measurements megastore or are interactively provided to the measurements megastore via a user interface 900 (see FIG. 9 ) by an operator.
  • the user interface 900 may be via a software application on a terminal or a handheld device that is communicatively coupled either directly or wirelessly to the measurements megastore 140 of FIG. 1 .
  • the engineer can select (e.g., 904 ) the type of analysis to be performed and the level of detail to be reported, both at the network element (e.g., geographical/node level) and at the KPI level.
  • an area with a high churn rate may show that most of the subscribers are concentrated in a small geographical area.
  • a sector experiencing degraded performance may indicate a high number of resets in a specific time period.
  • a large number of customers who call customer care may show the number of calls that are being routed directly to voice mail to be exceeding a predetermined threshold limit.
  • An area indicating a drop call rate that is within a predetermined threshold may indicate a number of instances in which customers had to re-dial within a predetermined time, to exceed a threshold limit (which may indicate a poor call quality).
  • a sector may indicate congestion despite carrying traffic that is below a threshold limit.
  • a threshold number of customers may experience their coverage shrink after a network upgrade. Of course, countless other scenarios are supported.
  • step 808 relevant patterns, as they are learned, are persisted, for example in a memory of the measurements megastore 140 .
  • the measurements megastore 140 displays the analysis results, comprising the most relevant patterns, to the engineer on the user interface 900 .
  • patterns that are associated with automated fixes may trigger the execution of those automated fixes.
  • the engineer may rate the analysis results of the measurements megastore.
  • FIG. 900 illustrates by way of example an interface that may be used by an engineer to rate the relevance of the analysis (e.g., discovery) of the measurements megastore by a selection of 1 to 5 stars 906 .
  • the selection may be performed after the engineer has confirmed and cured the network issue, or upon initial display on the user interface 900 .
  • the engineer may request an automatic KPI and/or a notification to be issued based on the analysis.
  • the KPI may be stored in the measurements megastore and used as a reference.
  • the KPIs and notifications may can be used to predict events, such as when an area will likely increase its churn level.
  • step 812 the system described above can be trained, where it automatically repeats prior analysis based on prior similar circumstances and generates similar KPI's and/or alarms continuously, at predetermined intervals, or when a specific error is identified.
  • intelligence layer of the system described herein may be combined with a self-organizing network (SON), to perform automatic planning, configuration, management, optimization, and healing of the radio access network.
  • SON self-organizing network
  • the system described herein provides an open platform where multiple data feeds from disparate sources can be combined and processed in real time.
  • Much of the preceding discussion has been towards application in network management.
  • the techniques described herein provide a learning and feedback loop that may be applied to any field where there is a stream of event data, where the event data may be classified into categories that may be correlated with causes. Where a probability tree can be constructed, the preceding techniques may be applied.
  • One example alternative field where this capability is particularly useful is in the medical field, which increasingly uses health monitors, such as UE 102 d , which may be worn by both the healthy and ill to monitor the medical well-being of the wearer.
  • health monitors such as UE 102 d
  • each health monitor can come in a variety of forms, such as implanted, worn on the wrist, worn around the neck as a necklace, strapped around the chest, etc., These monitors can monitor a variety of health functions, such as heart rate, heart rhythm, blood pressure, motion, oxygen saturation, temperature, glucose level, etc.
  • each health monitor operates in isolation.
  • the health monitor that measures the heart rate is mutually exclusive from the health monitor that measures the glucose level or motion.
  • the data points that are acquired are then provided either directly to the patient on a user display or stored in a memory of the health monitor, respectively, to be later read by one or more caregivers.
  • the acquired data is sent periodically, or upon trigger from the user, to disparate receivers at one or more caregivers.
  • Each health monitor is typically applied in response to a health ailment suspected by the caregiver. Accordingly, in traditional systems, a continuous monitoring that provided a synthesis of the information from the health monitors to identify unsuspected health conditions is not available.
  • the system described herein is capable of performing continuous monitoring and/or continuous transmission of the monitored data from each health monitor, which can be synthesized at a centralized remote health monitoring system 150 .
  • the synthesized information harvested from the disparate sources is configured to analyze the data for potential ailments and provide relevant notifications.
  • FIG. 10 illustrates a high level diagram of a system that includes remote health monitoring, consistent with an exemplary embodiment.
  • system 1000 one or more health monitors, represented by UEs 1002 ( 1 ) to 1002 (N), are operative to monitor various aspects of the health of user 1004 .
  • the health monitors 1002 ( 1 ) to 1002 (N) can provide the health information to one or more disparate monitoring systems, represented in system 1000 by application servers 1 , 2 ( 1030 , 1032 ), and UE collection systems 1 to N ( 1034 ( 1 ) to 1034 (N)).
  • application servers 1 , 2 ( 1030 , 1032 ), and UE collection systems 1 to N ( 1034 ( 1 ) to 1034 (N)) may be regarded as third party systems that provide health related recordings of measurements from corresponding health monitors, which may be in the form of a Samsung Gear Watch or Apple iWatch.
  • the health information may be provided by various networks. For example, some health monitors may communicate with their monitoring system over one radio access network 1022 ( a ) while other health monitor may communicate over another radio access network 1022 ( b ). In one embodiment, a health monitor may communicate with their respective (e.g., subscribed) monitoring system over a radio access network 1022 ( a ) by using a device that is configured to communicate over the network 1022 ( a ), such as a smart phone, tablet, etc. In one embodiment, the health monitors 1002 ( 1 ) to 1002 (N) provide the health information directly to the health monitoring server 150 .
  • the example system 1000 is compliant with the Health Insurance Portability and Accountability Act (HIPPA) in that physical and technical safeguards are included to limit the access to the remote health monitoring server to only authorized individuals and account holders.
  • HPPA Health Insurance Portability and Accountability Act
  • unique user IDs, automatic log off procedures, encryption, and decryption are required to access the system 1000 .
  • the remote health monitoring server 150 acts as a measurements megastore and provides an open platform where the multiple data feeds from the disparate servers 1030 , 1032 and collection systems 1034 ( 1 ) to 1034 (N) are combined.
  • the health data is processed in real time, for many (e.g., millions) of individuals like user 1004 by a data processing layer, which may be part of the health monitoring server 150 or in communication therewith.
  • the remote health monitoring server 150 may gather data, such as patient records from hospitals 1040 and care providers 1050 . Such data may include medical history, prior treatments, recorded blood-work, etc.
  • the remote health monitoring server may gather data from the radio access network (e.g., 1022 ( a ), 1022 ( b )) to determine the location information of the user 1004 , identify network issues that may prevent data transmission, and other variables affecting network connectivity and the customer endpoints.
  • the location of the user 1004 may be determined by various techniques, such as triangulation, multilateration, and/or the GPS coordinates that may be provided by the health monitor (e.g., 1002 ( 1 ) to 1002 (N)), or its corresponding UE (e.g., 1006 ).
  • the remote health monitoring server 150 may send a notification to the user 1004 via a notification to a user interface of the corresponding health monitor (e.g., UE 1002 ( 1 )) or corresponding UE network capable device 1006 .
  • the health monitor server 150 may send a notification to a relevant care provider 1050 and/or hospital, based on the type of condition.
  • FIG. 11 is a block diagram of a data framework of a monitoring system, consistent with an exemplary embodiment.
  • the data framework in system 1100 uses massive parallel processing methods to gather health data from one or more health monitors (UE's) in real time.
  • UE health monitors
  • the automation layer 1108 , the intelligence layer 11104 , and the data processing layer 1102 is illustrated as being separate from the measurements megastore 1110 , while it will be understood, that in various embodiments, these the functions may be combined on a single platform (i.e., a single measurements megastore that performs the features of the data processing layer, intelligence layer, and automation layer.)
  • the data framework includes a data processing layer 1102 , an intelligence layer 1104 , which may include pattern detection rules 1106 , an automation layer 1108 and a measurements megastore 1110 .
  • the type of information received by the data processing layer 352 may include subscriber radio trace (e.g., location) provided by a UE and/or the radio access network, healthcare records from one or more sources, customer care records, billing, application performance monitoring reports, and other information, including relevant information from the WEB.
  • the data processing layer 1102 may be performed in real time and/or in batch. The monitoring may be performed continuously, 24 hours a day, 7 days a week, at predetermined intervals, or in response to a trigger from the intelligence layer 1104 of the monitoring system.
  • the intelligence layer 1104 is configured to receive the information from the data processing layer 1102 and pattern detection rules 1106 that may be preprogrammed in the intelligence layer.
  • the detections may be originally programmed by expert professionals, based on prior knowledge.
  • a self-learning feature of the intelligence layer is operative to detect abnormal conditions without previous knowledge of that particular problem. Specifically, causes and/or KPIs may be detected as present when undesirable events, such as dropped calls occur. As described with respect to FIG. 7 , a probability tree may be populated and/or updated to store the probabilities that those causes and/or KPIs are correlated with the undesirable event.
  • the pattern detection rules 1106 are different depending on the type of patient (e.g., leukemia vs. diabetes).
  • the health monitoring system upon identifying patterns that are consistent with a medical condition, may update its rule set to focus on that condition by performing more analysis of the health data related to that medical condition.
  • the pattern detection rules 1106 may be different from one subscribed user to the next.
  • multiple data sources that were processed at the data processing layer 1102 may be analyzed and cross-correlated to determine whether one or more conditions are met. Specifically, first detected causes and/or KPIs are checked against a probability tree (see the discussion with respect to FIG. 7 ) whether they could possibly be a root cause for detected undesirable network events, such as dropped calls. Then the probability tree is traversed starting with the detected causes and/or KPIs. Since the probability tree stores probabilities, that the detected causes and/or KPIs caused an event, the probability tree can be traversed according to the most probable paths. In this way, conditions for undesirable network conditions may be evaluated as to the likelihood that particular causes and/or KPIs (and other events/causes along the path in the probability tree) in fact caused those undesirable network conditions.
  • the intelligence layer 1104 constantly sifts through the data to identify patterns within the disparate data sources.
  • the intelligence layer may generate a relevant alert to at least one of the user 604 , the care provider 650 , a contact person previously stored in the database of the measurements megastore 1110 , and/or an emergency service.
  • the intelligence layer 1104 may analyze the patterns of the data for individual types of measurements (blood pressure), or cross-correlate with different types of measurements or data (e.g., glucose level, weight, age, white blood cells, etc.,) provided by the data processing layer 352 and family history from the measurements megastore 1110 , to identify any outliers (e.g., meeting a predetermined condition or exceeding a predetermined threshold) that may indicate a health concern with the patient.
  • blood pressure blood pressure
  • data e.g., glucose level, weight, age, white blood cells, etc.
  • the automation layer 1108 may trigger an automatic response to the identified condition of the patient 604 without having to rely on prior human processing of the raw data harvested by the data processing layer.
  • the intelligence layer coupled with the automation layer 1108 can detect health problems at a subscriber (i.e., patient) level and provide a notification without the subscriber or the health care provider having even suspected a health problem with the subscriber.
  • An authorized care giver, medical practitioner, family and friends, or emergency response may be automatically contacted based on the preferences stored in a user profile stored in the measurements megastore 1110 .
  • the medical practitioner 211 a may provide immediate medical advice.
  • the appropriate entity may be contacted automatically via the application server automation layer 1108 of the measurements megastore 1110 .
  • the appropriate entity may be contacted through the radio access network 122 , through a public switched telephone network (PSTN) (not shown), or through an internet connection ( 120 in FIG. 1 ).
  • PSTN public switched telephone network
  • different information is sent depending on the receiving entity. For example, when family/friends are contacted, the location information and the type of emergency may be sent. In contrast, when a medical practitioner is contacted, the location information, type of emergency, vital signs, medical history, etc., are sent. Thus, while different entities may be contacted for help, only specifically authorized entities receive the location information.
  • the location information is used to send a prescription information to the closest pharmacy to the health monitor (e.g., 102 d in FIG. 1 ).
  • FIG. 12 is a flow diagram of an example process for identifying a health condition using contextual information received from a measurements megastore.
  • the health monitors may be an electronic fitness bracelet, an electronic necklace that can measure temperature/humidity, and a smart phone that is placed on the bed where the subscriber is resting. Further, the subscriber indicates on an app of the smartphone that the phone is placed on his bed, thereby allowing it to monitor his or her sleeping pattern.
  • the measurements megastore may receive continuous information from all three sensors.
  • the smart phone may provide the location information from its global positioning system (GPS) and movement information from its accelerometer;
  • the electronic fitness bracelet may provide the heart rate and movement information from its accelerometer;
  • the electronic necklace may provide a measurement of the temperature of the subscriber.
  • the health information may be received by the measurements megastore over different radio access networks and collection systems, as discussed in the context of FIG. 6 above.
  • the health information may be received by the data processing layer of the data framework that includes a measurements megastore.
  • the intelligence layer of the measurements megastore analyzes the health information to determine whether there is a high level of movement. For example, it may correlate the movement information from the fitness bracelet with the information from the smartphone. If both sources indicate that there is no high level of movement, the intelligence layer concludes that there are no health issues in connection with sleep apnea (i.e., step 1210 ). However, if one of the sources indicates a high level of movement which is not confirmed by the second source, the intelligence layer may consult the WEB to determine whether the smartphone or the fitness bracelet has a more accurate accelerometer, and base its analysis regarding movement on the more accurate fitness monitor for this measurement.
  • the intelligence layer of the measurements megastore determines whether there is a high heart rate. To that end, in step 1208 , the intelligence layer analyzes the health information obtained from the fitness bracelet. In one embodiment, the intelligence layer may consult the WEB (or a lookup table) and/or other previously stored data to determine what is considered a high heart rate for this subscriber. For example, the stored information may indicate the weight, height, and age of the subscriber and previous medical conditions that may affect the heart rate (e.g., pace-maker). If the heart rate is not considered high for this subscriber, the intelligence layer concludes that there are no health issues in connection with sleep apnea (i.e., step 1210 ).
  • the intelligence layer concludes that there are no health issues in connection with sleep apnea (i.e., step 1210 ).
  • the intelligence layer interacts with the automation layer to provide a notification to one or more recipients (e.g., the smartphone, the fitness bracelet, authorized care giver, medical practitioner, family and friends, and/or emergency response), depending on the severity of the condition or predetermined personal preferences of the subscriber. For example, the subscriber may receive a notification on their smart phone indicating that they may be suffering from sleep apnea.
  • the automation layer may also recommend one or more additional health monitors to better analyze the medical condition, which may be used in subsequent measurements (i.e., step 1214 ).
  • functions for storing contextual information, monitoring network elements, remote monitoring of subscribers' health, identifying a network status based on local knowledge, providing a connection between network elements, and other functions can be implemented on computers connected for data communication via the network elements of the radio access network 122 , operating as the monitoring server 130 , measurements megastore 140 , eNode B 119 , and components of the radio access network 122 , as shown in FIGS. 1 and 2 .
  • FIGS. 13 and 14 provide functional block diagram illustrations of general purpose computer hardware platforms.
  • FIG. 13 illustrates a network or host computer platform, as may typically be used to implement a server.
  • FIG. 14 depicts a device with user interface elements, as may be used to implement a personal computer, such as computer 102 c of FIG. 1 or a workstation, or to implement a computing device, such as a portable handset, a smart-phone, tablet computer, a personal digital assistant or other type of mobile station or mobile terminal device (e.g., devices 102 a to 102 d of FIG. 1 ), although the device of FIG. 14 may also act as a server if appropriately programmed. It is believed that the general structure and general operation of such equipment as shown in FIGS. 13 and 14 should be self-explanatory from the high-level illustrations.
  • a general purpose computer configured as a server includes a data communication interface for packet data communication.
  • the server computer also includes a central processing unit (CPU), in the form of one or more processors, for executing program instructions.
  • the server platform typically includes an internal communication bus, program storage and data storage for various data files to be processed and/or communicated by the server, although the server often receives programming and data via network communications.
  • the hardware elements, operating systems and programming languages of such servers are conventional in nature.
  • the computer system of FIG. 14 uses a massive parallel processing technology such as Hadoop, Storm, or Spark.
  • the server functions may be implemented in a distributed fashion on a number of similar platforms, to distribute the processing load.
  • the functionality of the monitoring server 130 , measurements megastore 140 , and the remote health monitoring system may be combined in one or more server platforms.
  • the software functionalities involve programming, including executable code as well as associated stored data, e.g., files used for applications on the computing device to receive data from disparate sources by the processing layer, retrieving contextual information from the measurements megastore, analyzing the data from disparate sources and the contextual information, and providing notifications.
  • the software code is executable by the computing device. In operation, the code is stored within the computing device. At other times, however, the software may be stored at other locations and/or transported for loading into the appropriate computing device system. Execution of such code by a processor of the computing device enables the computing device to perform functions of retrieving information, analyzing the information, providing notifications, etc., in essentially the manner performed in the implementations discussed and illustrated herein.
  • aspects of the methods of receiving and processing SUs as outlined above may be embodied in programming.
  • Program aspects of the technology may be thought of as “products” or “articles of manufacture” typically in the form of executable code and/or associated data that is carried on or embodied in a type of non-transitory machine readable medium.

Landscapes

  • Engineering & Computer Science (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Signal Processing (AREA)
  • Health & Medical Sciences (AREA)
  • Computing Systems (AREA)
  • General Health & Medical Sciences (AREA)
  • Medical Informatics (AREA)
  • Mobile Radio Communication Systems (AREA)
  • Data Exchanges In Wide-Area Networks (AREA)
  • Test And Diagnosis Of Digital Computers (AREA)
  • Computer And Data Communications (AREA)
US14/800,648 2014-07-16 2015-07-15 Resource management in a big data environment Abandoned US20160021173A1 (en)

Priority Applications (6)

Application Number Priority Date Filing Date Title
US14/800,648 US20160021173A1 (en) 2014-07-16 2015-07-15 Resource management in a big data environment
PCT/US2015/040809 WO2016011295A2 (fr) 2014-07-16 2015-07-16 Gestion de ressources dans un environnement de données volumineuses
JP2017523189A JP6853172B2 (ja) 2014-07-16 2015-07-16 ビッグデータ環境におけるリソース管理
US17/185,847 US20210185117A1 (en) 2014-07-16 2021-02-25 Resource management in a big data environment
JP2021038871A JP7280302B2 (ja) 2014-07-16 2021-03-11 ビッグデータ環境におけるリソース管理
JP2022205693A JP2023027358A (ja) 2014-07-16 2022-12-22 ビッグデータ環境におけるリソース管理

Applications Claiming Priority (6)

Application Number Priority Date Filing Date Title
US201462025441P 2014-07-16 2014-07-16
US201462025453P 2014-07-16 2014-07-16
US201462025958P 2014-07-17 2014-07-17
US201462025961P 2014-07-17 2014-07-17
US201562193002P 2015-07-15 2015-07-15
US14/800,648 US20160021173A1 (en) 2014-07-16 2015-07-15 Resource management in a big data environment

Related Child Applications (1)

Application Number Title Priority Date Filing Date
US17/185,847 Continuation US20210185117A1 (en) 2014-07-16 2021-02-25 Resource management in a big data environment

Publications (1)

Publication Number Publication Date
US20160021173A1 true US20160021173A1 (en) 2016-01-21

Family

ID=55075585

Family Applications (2)

Application Number Title Priority Date Filing Date
US14/800,648 Abandoned US20160021173A1 (en) 2014-07-16 2015-07-15 Resource management in a big data environment
US17/185,847 Pending US20210185117A1 (en) 2014-07-16 2021-02-25 Resource management in a big data environment

Family Applications After (1)

Application Number Title Priority Date Filing Date
US17/185,847 Pending US20210185117A1 (en) 2014-07-16 2021-02-25 Resource management in a big data environment

Country Status (3)

Country Link
US (2) US20160021173A1 (fr)
JP (3) JP6853172B2 (fr)
WO (1) WO2016011295A2 (fr)

Cited By (26)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20170142189A1 (en) * 2015-11-18 2017-05-18 International Business Machines Corporation Attachment of cloud services to big data services
US20170207951A1 (en) * 2016-01-20 2017-07-20 Level 3 Communications, Llc System and method for automatically repairing a network element
CN106982253A (zh) * 2017-03-27 2017-07-25 中国联合网络通信集团有限公司 一种用户画像解析方法及装置、网络系统
US20170262360A1 (en) * 2016-03-08 2017-09-14 International Business Machines Corporation Analyzing software test failures using natural language processing and machine learning
WO2017172639A1 (fr) * 2016-03-28 2017-10-05 TUPL, Inc. Système de configuration intelligent d'alerte et de surveillance de performance
WO2017214271A1 (fr) * 2016-06-07 2017-12-14 TUPL, Inc. Conseiller de réseau basé sur l'intelligence artificielle
WO2017218686A3 (fr) * 2016-06-14 2018-03-15 TUPL, Inc. Gestion de ressources de ligne fixe
US10437839B2 (en) 2016-04-28 2019-10-08 Entit Software Llc Bulk sets for executing database queries
US20200120214A1 (en) * 2018-10-12 2020-04-16 Verizon Patent And Licensing Inc. Methods and devices for time-based conditional presence reporting
WO2020174262A1 (fr) * 2019-02-27 2020-09-03 Telefonaktiebolaget Lm Ericsson (Publ) Apprentissage par transfert pour gestion de ressources radio
US20200402670A1 (en) * 2015-12-16 2020-12-24 Alegeus Technologies, Llc Systems and methods for reducing resource consumption via information technology infrastructure
WO2021063474A1 (fr) * 2019-09-30 2021-04-08 Telefonaktiebolaget Lm Ericsson (Publ) Commande de trafic et d'interférence dans un réseau de communication
US10992331B2 (en) * 2019-05-15 2021-04-27 Huawei Technologies Co., Ltd. Systems and methods for signaling for AI use by mobile stations in wireless networks
US11070429B2 (en) 2015-06-22 2021-07-20 Arista Networks, Inc. Tracking state of components within a network element
WO2021188821A1 (fr) * 2020-03-20 2021-09-23 Hewlett-Packard Development Company, L.P. Recommandation de modifications dans des dispositifs informatiques
US11138163B2 (en) 2019-07-11 2021-10-05 EXFO Solutions SAS Automatic root cause diagnosis in networks based on hypothesis testing
US20220006704A1 (en) * 2018-07-12 2022-01-06 Ribbon Communications Operating Company, Inc. Predictive scoring based on key performance indicators in telecomminucations system
US11249876B2 (en) 2017-08-24 2022-02-15 Tata Consultancy Services Limited System and method for predicting application performance for large data size on big data cluster
US11290912B2 (en) 2011-12-14 2022-03-29 Seven Networks, Llc Mobile device configured for operating in a power save mode and a traffic optimization mode and related method
US20220131924A1 (en) * 2016-08-12 2022-04-28 Pinterest, Inc. Generating collections of sets based on user provided annotations
US11388040B2 (en) 2018-10-31 2022-07-12 EXFO Solutions SAS Automatic root cause diagnosis in networks
US11429986B2 (en) * 2016-11-04 2022-08-30 Google Llc Realtime busyness for places
US11522766B2 (en) 2020-02-12 2022-12-06 EXFO Solutions SAS Method and system for determining root-cause diagnosis of events occurring during the operation of a communication network
US11645293B2 (en) 2018-12-11 2023-05-09 EXFO Solutions SAS Anomaly detection in big data time series analysis
US20230155907A1 (en) * 2020-04-07 2023-05-18 Nokia Solutions And Networks Oy Communicaton system
US12052134B2 (en) 2021-02-02 2024-07-30 Exfo Inc. Identification of clusters of elements causing network performance degradation or outage

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2020519079A (ja) * 2017-04-28 2020-06-25 オッポ広東移動通信有限公司Ｇｕａｎｇｄｏｎｇ Ｏｐｐｏ Ｍｏｂｉｌｅ Ｔｅｌｅｃｏｍｍｕｎｉｃａｔｉｏｎｓ Ｃｏｒｐ．， Ｌｔｄ． コンテキスト設定情報の取得方法、端末装置及びアクセスネットワーク機器
JP7246560B1 (ja) 2022-12-12 2023-03-27 株式会社インターネットイニシアティブ 通信制御方法および通信制御装置

Citations (19)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20010019960A1 (en) * 2000-03-02 2001-09-06 Kuniharu Takayama Area-dependent service system and method for mobile stations
US20060129850A1 (en) * 2004-12-15 2006-06-15 Microsoft Corporation Ultra wide band power save
US20070076728A1 (en) * 2005-10-04 2007-04-05 Remi Rieger Self-monitoring and optimizing network apparatus and methods
US20100317395A1 (en) * 2008-02-05 2010-12-16 Telefonaktiebolaget Lm Ericsson (Publ) Power Control in a Radio Base Station with Sustained Cell Radius
US20110136533A1 (en) * 2009-12-08 2011-06-09 Futurewei Technologies System and Method for Power Control
US20120072267A1 (en) * 2010-09-22 2012-03-22 Carrier Iq, Inc. Quality of Service Performance Scoring and Rating Display and Navigation System
US20120092154A1 (en) * 1998-06-22 2012-04-19 Sipco, Llc Systems and methods for monitoring conditions
US8249606B1 (en) * 2008-07-30 2012-08-21 Optimi Corporation Frequency planning optimization for mobile communications
US20120281594A1 (en) * 2011-05-04 2012-11-08 Motorola Mobility, Inc. Method and apparatus for providing user equipment access to tv white space resources by a broadband cellular network
US20130003591A1 (en) * 2010-09-23 2013-01-03 Research In Motion Limited System and Method for Dynamic Coordination of Radio Resources Usage in a Wireless Network Environment
US20130159395A1 (en) * 2011-12-14 2013-06-20 Seven Networks, Inc. Mobile network reporting and usage analytics system and method aggregated using a distributed traffic optimization system
US20130225183A1 (en) * 2012-02-24 2013-08-29 Qualcomm Incorporated Methods and apparatus for turning off macro carriers to deploy femtocells
US20140128123A1 (en) * 2002-12-24 2014-05-08 Nec Corporation Radio-resource management system and method thereof, and management apparatus, base station and terminal to be employed for it
US20140254452A1 (en) * 2011-11-18 2014-09-11 Panasonic Corporation Active bandwidth indicator for power-saving ues
US20140370830A1 (en) * 2013-06-13 2014-12-18 Research In Motion Limited Device dynamic total rf power compensation
US20150081890A1 (en) * 2013-09-13 2015-03-19 Network Kinetix, LLC System and method for real-time analysis of network traffic
US20150333994A1 (en) * 2013-09-26 2015-11-19 Wi-Lan Labs, Inc. File block placement in a distributed network
US20150350174A1 (en) * 2014-05-30 2015-12-03 Ca, Inc. Controlling application programming interface transactions based on content of earlier transactions
US20160127451A1 (en) * 2014-11-04 2016-05-05 Calay Venture S.à r.l. Triggering of notifications in a communications network

Family Cites Families (12)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPS6118011A (ja) * 1984-07-04 1986-01-25 Hitachi Ltd 機器故障診断方法
JPH07206297A (ja) * 1994-01-25 1995-08-08 Hitachi Building Syst Eng & Service Co Ltd エレベータの故障診断装置
JP5193533B2 (ja) * 2007-09-04 2013-05-08 株式会社東芝 遠隔監視システム及び遠隔監視方法
US8966055B2 (en) * 2008-11-14 2015-02-24 Qualcomm Incorporated System and method for facilitating capacity monitoring and recommending action for wireless networks
US20130145024A1 (en) * 2010-08-16 2013-06-06 Nokia Corporation Method and apparatus for transfer of radio resource allocation
US9191444B2 (en) 2011-06-09 2015-11-17 Alcatel Lucent Intelligent network management of network-related events
US8553580B2 (en) * 2011-09-30 2013-10-08 Intel Corporation Multi-radio medium-agnostic access architecture
US8942673B2 (en) * 2011-10-03 2015-01-27 At&T Intellectual Property I, L.P. Method and apparatus for providing cellphone service from any device
US9326189B2 (en) * 2012-02-03 2016-04-26 Seven Networks, Llc User as an end point for profiling and optimizing the delivery of content and data in a wireless network
JP6141889B2 (ja) * 2012-03-12 2017-06-07 ノキア ソリューションズ アンド ネットワークス オサケユキチュア 通信ネットワークにおけるサービスアクセス経験品質問題の予想及び根本原因の推奨
WO2013136813A1 (fr) * 2012-03-15 2013-09-19 日本電気株式会社 Système de communication sans fil, station sans fil, dispositif de gestion de fonctionnement de réseau et procédé de réparation de réseau
US9633041B2 (en) * 2013-09-26 2017-04-25 Taiwan Semiconductor Manufacturing Co., Ltd. File block placement in a distributed file system network

Patent Citations (19)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20120092154A1 (en) * 1998-06-22 2012-04-19 Sipco, Llc Systems and methods for monitoring conditions
US20010019960A1 (en) * 2000-03-02 2001-09-06 Kuniharu Takayama Area-dependent service system and method for mobile stations
US20140128123A1 (en) * 2002-12-24 2014-05-08 Nec Corporation Radio-resource management system and method thereof, and management apparatus, base station and terminal to be employed for it
US20060129850A1 (en) * 2004-12-15 2006-06-15 Microsoft Corporation Ultra wide band power save
US20070076728A1 (en) * 2005-10-04 2007-04-05 Remi Rieger Self-monitoring and optimizing network apparatus and methods
US20100317395A1 (en) * 2008-02-05 2010-12-16 Telefonaktiebolaget Lm Ericsson (Publ) Power Control in a Radio Base Station with Sustained Cell Radius
US8249606B1 (en) * 2008-07-30 2012-08-21 Optimi Corporation Frequency planning optimization for mobile communications
US20110136533A1 (en) * 2009-12-08 2011-06-09 Futurewei Technologies System and Method for Power Control
US20120072267A1 (en) * 2010-09-22 2012-03-22 Carrier Iq, Inc. Quality of Service Performance Scoring and Rating Display and Navigation System
US20130003591A1 (en) * 2010-09-23 2013-01-03 Research In Motion Limited System and Method for Dynamic Coordination of Radio Resources Usage in a Wireless Network Environment
US20120281594A1 (en) * 2011-05-04 2012-11-08 Motorola Mobility, Inc. Method and apparatus for providing user equipment access to tv white space resources by a broadband cellular network
US20140254452A1 (en) * 2011-11-18 2014-09-11 Panasonic Corporation Active bandwidth indicator for power-saving ues
US20130159395A1 (en) * 2011-12-14 2013-06-20 Seven Networks, Inc. Mobile network reporting and usage analytics system and method aggregated using a distributed traffic optimization system
US20130225183A1 (en) * 2012-02-24 2013-08-29 Qualcomm Incorporated Methods and apparatus for turning off macro carriers to deploy femtocells
US20140370830A1 (en) * 2013-06-13 2014-12-18 Research In Motion Limited Device dynamic total rf power compensation
US20150081890A1 (en) * 2013-09-13 2015-03-19 Network Kinetix, LLC System and method for real-time analysis of network traffic
US20150333994A1 (en) * 2013-09-26 2015-11-19 Wi-Lan Labs, Inc. File block placement in a distributed network
US20150350174A1 (en) * 2014-05-30 2015-12-03 Ca, Inc. Controlling application programming interface transactions based on content of earlier transactions
US20160127451A1 (en) * 2014-11-04 2016-05-05 Calay Venture S.à r.l. Triggering of notifications in a communications network

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
Youping Zhao, Joseph Gaeddert, Kyung K. Bae, and Jeffery H. Reed. "Radio Environment Map Enabled Situation-Aware Cognitive Radio Learning Algorithms". November 2006. Mobile and Portable Radio Research Group, Virginia Polytechnic Institute and State University. Pages 1-6. *

Cited By (49)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US11290912B2 (en) 2011-12-14 2022-03-29 Seven Networks, Llc Mobile device configured for operating in a power save mode and a traffic optimization mode and related method
US11729056B2 (en) 2015-06-22 2023-08-15 Arista Networks, Inc. Data analytics on internal state
US11070429B2 (en) 2015-06-22 2021-07-20 Arista Networks, Inc. Tracking state of components within a network element
US11489728B2 (en) 2015-06-22 2022-11-01 Arista Networks, Inc. Tracking state of components within a network element
US11388055B2 (en) 2015-06-22 2022-07-12 Arista Networks, Inc. Data analytics on internal state
US11115281B2 (en) * 2015-06-22 2021-09-07 Arista Networks, Inc. Data analytics on internal state
US10129330B2 (en) * 2015-11-18 2018-11-13 International Business Machines Corporation Attachment of cloud services to big data services
US20170142189A1 (en) * 2015-11-18 2017-05-18 International Business Machines Corporation Attachment of cloud services to big data services
US20200402670A1 (en) * 2015-12-16 2020-12-24 Alegeus Technologies, Llc Systems and methods for reducing resource consumption via information technology infrastructure
US20170207951A1 (en) * 2016-01-20 2017-07-20 Level 3 Communications, Llc System and method for automatically repairing a network element
US10999128B2 (en) 2016-01-20 2021-05-04 Level 3 Communications, Llc System and method for automatically repairing a faultily connected network element
US10355918B2 (en) * 2016-01-20 2019-07-16 Level 3 Communications, Llc System and method for automatically repairing a network element
US11226892B2 (en) 2016-03-08 2022-01-18 International Business Machines Corporation Analyzing software test failures using natural language processing and machine learning
US20170262360A1 (en) * 2016-03-08 2017-09-14 International Business Machines Corporation Analyzing software test failures using natural language processing and machine learning
US10838849B2 (en) * 2016-03-08 2020-11-17 International Business Machines Corporation Analyzing software test failures using natural language processing and machine learning
US10505789B2 (en) 2016-03-28 2019-12-10 TUPL, Inc. Intelligent configuration system for alert and performance monitoring
WO2017172639A1 (fr) * 2016-03-28 2017-10-05 TUPL, Inc. Système de configuration intelligent d'alerte et de surveillance de performance
US10437839B2 (en) 2016-04-28 2019-10-08 Entit Software Llc Bulk sets for executing database queries
RU2753962C2 (ru) * 2016-06-07 2021-08-24 Тупл, Инк. Сетевой помощник на основе искусственного интеллекта
EP3465459A4 (fr) * 2016-06-07 2020-01-01 Tupl Inc. Conseiller de réseau basé sur l'intelligence artificielle
WO2017214271A1 (fr) * 2016-06-07 2017-12-14 TUPL, Inc. Conseiller de réseau basé sur l'intelligence artificielle
US10708795B2 (en) 2016-06-07 2020-07-07 TUPL, Inc. Artificial intelligence-based network advisor
US10855514B2 (en) 2016-06-14 2020-12-01 Tupl Inc. Fixed line resource management
WO2017218686A3 (fr) * 2016-06-14 2018-03-15 TUPL, Inc. Gestion de ressources de ligne fixe
US10411946B2 (en) 2016-06-14 2019-09-10 TUPL, Inc. Fixed line resource management
US11652866B2 (en) * 2016-08-12 2023-05-16 Pinterest, Inc. Generating collections of sets based on user provided annotations
US20220131924A1 (en) * 2016-08-12 2022-04-28 Pinterest, Inc. Generating collections of sets based on user provided annotations
US11727419B2 (en) 2016-11-04 2023-08-15 Google Llc Realtime busyness for places
US11429986B2 (en) * 2016-11-04 2022-08-30 Google Llc Realtime busyness for places
CN106982253A (zh) * 2017-03-27 2017-07-25 中国联合网络通信集团有限公司 一种用户画像解析方法及装置、网络系统
US11249876B2 (en) 2017-08-24 2022-02-15 Tata Consultancy Services Limited System and method for predicting application performance for large data size on big data cluster
US12088474B2 (en) * 2018-07-12 2024-09-10 Ribbon Communications Operating Company, Inc. Predictive scoring based on key performance indicators in telecommunications system
US20220006704A1 (en) * 2018-07-12 2022-01-06 Ribbon Communications Operating Company, Inc. Predictive scoring based on key performance indicators in telecomminucations system
US11165912B2 (en) 2018-10-12 2021-11-02 Verizon Patent And Licensing Inc. Methods and devices for time-based conditional presence reporting
US10701216B2 (en) * 2018-10-12 2020-06-30 Verizon Patent And Licensing Inc. Methods and devices for time-based conditional presence reporting
US20200120214A1 (en) * 2018-10-12 2020-04-16 Verizon Patent And Licensing Inc. Methods and devices for time-based conditional presence reporting
US11388040B2 (en) 2018-10-31 2022-07-12 EXFO Solutions SAS Automatic root cause diagnosis in networks
US11736339B2 (en) 2018-10-31 2023-08-22 EXFO Solutions SAS Automatic root cause diagnosis in networks
US11645293B2 (en) 2018-12-11 2023-05-09 EXFO Solutions SAS Anomaly detection in big data time series analysis
US11658880B2 (en) 2019-02-27 2023-05-23 Telefonaktiebolaget Lm Ericsson (Publ) Transfer learning for radio resource management
WO2020174262A1 (fr) * 2019-02-27 2020-09-03 Telefonaktiebolaget Lm Ericsson (Publ) Apprentissage par transfert pour gestion de ressources radio
US10992331B2 (en) * 2019-05-15 2021-04-27 Huawei Technologies Co., Ltd. Systems and methods for signaling for AI use by mobile stations in wireless networks
US11138163B2 (en) 2019-07-11 2021-10-05 EXFO Solutions SAS Automatic root cause diagnosis in networks based on hypothesis testing
WO2021063474A1 (fr) * 2019-09-30 2021-04-08 Telefonaktiebolaget Lm Ericsson (Publ) Commande de trafic et d'interférence dans un réseau de communication
US11522766B2 (en) 2020-02-12 2022-12-06 EXFO Solutions SAS Method and system for determining root-cause diagnosis of events occurring during the operation of a communication network
WO2021188821A1 (fr) * 2020-03-20 2021-09-23 Hewlett-Packard Development Company, L.P. Recommandation de modifications dans des dispositifs informatiques
US20230155907A1 (en) * 2020-04-07 2023-05-18 Nokia Solutions And Networks Oy Communicaton system
US12068935B2 (en) * 2020-04-07 2024-08-20 Nokia Solutions And Networks Oy Communication system
US12052134B2 (en) 2021-02-02 2024-07-30 Exfo Inc. Identification of clusters of elements causing network performance degradation or outage

Also Published As

Publication number Publication date
WO2016011295A2 (fr) 2016-01-21
US20210185117A1 (en) 2021-06-17
JP6853172B2 (ja) 2021-03-31
WO2016011295A3 (fr) 2016-09-29
JP2023027358A (ja) 2023-03-01
JP2017529811A (ja) 2017-10-05
JP7280302B2 (ja) 2023-05-23
JP2021106388A (ja) 2021-07-26

Similar Documents

Publication Publication Date Title
US20210185117A1 (en) Resource management in a big data environment
US11018958B2 (en) Communication network quality of experience extrapolation and diagnosis
US12120012B2 (en) Dynamic quality of service in edge cloud architectures
US11438770B2 (en) Method and apparatus for monitoring and predicting channel availability and preemptively reconfiguring the network in a spectrum controlled network
US11399290B2 (en) Method and apparatus for monitoring and predicting capacity utilization and preemptively reconfiguring the network in a spectrum controlled network
US11811588B2 (en) Configuration management and analytics in cellular networks
KR20220003513A (ko) 머신 러닝을 이용한 근본 원인 분석 및 자동화
JP7159347B2 (ja) モデル更新方法および装置、ならびにシステム
US20170078171A1 (en) Wireless communication data analysis and reporting
US11012864B2 (en) Machine-learning framework for spectrum allocation
US11937100B2 (en) Method and apparatus for generating policies for improving network system performance
WO2019109338A1 (fr) Procédés et systèmes de génération et d'adaptation de lignes de base de réseau
US9800662B2 (en) Generic network trace with distributed parallel processing and smart caching
WO2022098713A1 (fr) Demande de rapport mda, extraction et création de rapports
US11805022B2 (en) Method and device for providing network analytics information in wireless communication network
US10887777B2 (en) Method and device for data transmission in wireless communication network
US10798019B2 (en) Context information processor, profile distribution unit and method for a communication network
US20230079052A1 (en) Mechanism for enabling custom analytics
US20230308901A1 (en) Mitigating mobile monitoring device excess network utilization
EP4038972B1 (fr) Vérification de disponibilité de ressources
US20230069767A1 (en) Method, apparatus and computer program
US20220248214A1 (en) System and Method for Network Traffic Analysis
US20240129761A1 (en) Network device inventory analytics
US20220232368A1 (en) Clustering of user entities in a cellular network
WO2022185325A1 (fr) Premier nœud, deuxième nœud, système de communication et procédés ainsi réalisés pour gérer une prédiction d'un événement

Legal Events

Date Code Title Description
AS Assignment

Owner name: TUPL, INC., WASHINGTON

Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNOR:TAPIA, PABLO;REEL/FRAME:036104/0121

Effective date: 20150715

STPP Information on status: patent application and granting procedure in general

Free format text: RESPONSE TO NON-FINAL OFFICE ACTION ENTERED AND FORWARDED TO EXAMINER

STPP Information on status: patent application and granting procedure in general

Free format text: FINAL REJECTION MAILED

STPP Information on status: patent application and granting procedure in general

Free format text: DOCKETED NEW CASE - READY FOR EXAMINATION

STPP Information on status: patent application and granting procedure in general

Free format text: NON FINAL ACTION MAILED

STPP Information on status: patent application and granting procedure in general

Free format text: RESPONSE TO NON-FINAL OFFICE ACTION ENTERED AND FORWARDED TO EXAMINER

STPP Information on status: patent application and granting procedure in general

Free format text: NON FINAL ACTION MAILED

STPP Information on status: patent application and granting procedure in general

Free format text: ADVISORY ACTION MAILED

STCB Information on status: application discontinuation

Free format text: ABANDONED -- FAILURE TO RESPOND TO AN OFFICE ACTION