Telefonaktiebolaget Lm Ericsson (publ)

Roch Glitho

Christophe Gourraud

Rachida Dssouli

Chunyan Fu

Francois Leduc

Constant Wette Tchouati

Mohammad Abu Lebdeh

Thomas Crowe

Richard Joseph Brunner

Jacques Bugnon

Bernard Pagurek

Lena Hogberg

David Sugirtharaj

Amin Ebrahimzadeh

Razieh Abbasi Ghalehtaki

Fetahi Wuhib

Patricia Funnell

Richard Holm

Mario Banville

Marc Coulombe

Benoit Coulombe

Fatna Belqasmi

Cristina Mazzi

Bo Svensson

Diala Naboulsi

Evelina Evloguieva

Jingrong Tang

Anthony P R White

Embodiments described herein relate to a method and apparatus for detecting and explaining anomalies in data obtained from an environment using an encoder-decoder machine learning model. A state of the environment is represented by a plurality of features, and the machine learning model is trained with a first set of data samples. Each data sample in the first set of data samples comprises values for each of the plurality of features. The method comprises determining a respective first threshold for each of the plurality of features based on respective maximum reconstruction errors for each feature found during training of the encoder-decoder machine learning model; obtaining an anomalous data sample; determining respective reconstruction errors for each feature in the anomalous data sample using the trained encoder-decoder machine learning model; and determining one or more features in the anomalous data sample that are responsible for the anomalous data sample being anomalous responsive to the reconstruction errors associated with the one or more features being greater than or equal to the respective first thresholds.

Method and apparatus for detecting and explaining anomalies

There is provided a network node and method for placement of virtual network functions managers (VNFMs) in a network functions virtualization (NFV) system. The method comprises determining a number of VNFMs for the NFV system, determining a type for each VNFM, determining a placement for each VNFM over distributed Network Function Virtualization Infrastructure Points of Presence (NFVI-PoPs) and determining a plurality of associations between the VNFMs and VNF instances in the system, thereby generating a VNFMs placement solution.

Method for VNF managers placement in large-scale and distributed NFV systems

The disclosure relates to an orchestrator, for a Virtual Network Platform as a Service (VNPaaS), which orchestrates the management of a Network Service (NS). The orchestrator is operative to select an orchestration zone for each of a plurality of Virtual Network Functions (VNFs) in the NS based on selected deployment locations, where each orchestration zone comprises at least one VNF. The orchestrator is operative to associate sub-services to the selected orchestration zones, the sub-services being obtained from a decomposition of the NS into a number of sub-services equal to a number of orchestration zones selected and each sub-service comprising at least one of the plurality of VNFs. The orchestrator is operative to initiate deployment of the sub-services in the selected orchestration zones.

Orchestrator for a virtual network platform as a service (VNPAAS)

Systems, methods, devices and software for negotiating and executing registry composition are described. Signaling frameworks for both of these aspects of registry composition are provided.

Signaling framework for negotiating and executing composition of registries

A cluster of terminals, and an ad-hoc network of two or more such clusters, for carrying a multi-party, cluster-based, conference, wherein each cluster includes a super member comprising a super user agent, and one or more members including a user agent. Communications sessions are established between the super member of each cluster and each member terminals of the same cluster, and between the super members of each one of the first and second clusters. The user agent comprises identity of the super member, a conference identity, cluster parameters including a split value (Sv) indicative of a maximum number of terminals that may be part of the cluster, wherein when Sv is reached during the conference the cluster is split, and a merge value (Mv) indicative of a minimum number of terminals that may be part of the cluster, wherein when Mv is reached the cluster is merged with another cluster. The super user agent comprises a cluster member list, the conference identity, a cluster neighbour list, the one or more terminals also participating to the same conference, and cluster parameters.

Cluster of terminals and ad-hoc network for cluster-based multi-party conferencing

Methods for establishing a cluster-based multi-party conference and for carrying on the conference as participants join or leave the conference are provided. First, two or more terminals participating to the conference are joined in a cluster, wherein one of them is elected as a super member of the cluster. The other terminal is updated with the identity of the super member terminal, the identification of the conference, and with cluster parameters including a split value Sv indicative of a maximum number of terminals that may be part of the cluster, wherein when the split value Sv is reached during the conference, the cluster is split; and a merge value Mv indicative of a minimum number of terminals that may be part of the cluster, wherein when the merge value Mv is reached during the conference, the cluster is merged with another cluster. A method for splitting the cluster, and a method for merging two clusters are also provided.

Methods for cluster-based multi-party conferencing in ad-hoc networks

A system and method of accessing services from end terminals disposed in an integrated telecommunications network having a packet-switched network (PSN) portion such as, for example, a network portion using the Internet Protocol (IP) and a circuit-switched network (CSN) portion such as, for example, a wireless telephony network portion. A generalized service invocation and realization architecture includes one or more call control modules modified to include service-related Detection Points (DPs), a Service Access component or instance that is created when a new DP is encountered, and one or several service proxies which invoke services on behalf of the Service Access component and mediate between the call control modules and services. A common Service Logic Environment is implemented for local services, mobile agent services, and remote services. The PSN portion is preferably realized as a Voice-over-IP (VoIP) network having a gateway connected to the CSN portion.

System and method for providing access to service nodes from entities disposed in an integrated telecommunications network

A system and method of creating subscriber services in an Internet Protocol (IP)-based telecommunications network. A service creation architecture includes a Service Component Creator (SCC) that creates service proxy objects, and posts them on a Lookup Service (LUS). The LUS is accessible through the Internet by Enterprise Service Creators (ESCs). The ESCs download the posted service proxy objects from the LUS, and customize the downloaded objects to create customized services for enterprise users. The ESCs upload the customized service proxy objects to an Enterprise LUS, and the, Enterprise LUS downloads the customized service proxy objects to a Service Management Unit (SMU) serving the end user. A gatekeeper serving the end users utilizes the service proxy code downloaded to the SMU to determine the location of a Service Implementation Repository (SIR) that stores actual service code for implementing the customized service. The gatekeeper then downloads the actual service code from the SIR, constructs a customized User Service Agent (USA) that includes the actual service code, and sends the customized USA to an agency (mobile agent platform) at the user's terminal.

System and method of creating subscriber services in an IP-based telecommunications network

A system and method of device-aware service provisioning in a hybrid/integrated telecommunications network having a packet-switched network portion (PSN) and heterogeneous circuit-switched network (CSN) portions. A user profile is provided which partitions a service in three dimensions: a user-specific service part, a device-specific service part, and a combination part which specifies service conditions when an end-user uses a particular device or terminal. A common IP telephony Value-Added Services infrastructure is included wherein device-aware service triggers are provided for triggering appropriate service partitions of the user profile. Upon encountering a device-aware service trigger in a call control process, a service switching node queries the user profile and determines the service conditions associated with the particular device-specific service part to be invoked. Responsive to determining the service conditions, the service switching node instructs a service node to execute an appropriate Service Logic Program. Upon receiving a result or an indication thereof from the service node, the service switching node takes a corresponding service action.

System and method for providing device-aware services in an integrated telecommunications network

A system and method for providing Value-Added Services (VAS) in an integrated telecommunications network having a packet-switched network portion (PSN) operable with Session Initiation Protocol (SIP). The integrated telecommunications network includes a SIPext SSP server, a trigger server, and a service node having a Service Logic Program (SLP) that is operable with Intelligent Network Application Protocol (INAP). The SIPext SSP and service nodes are provided with the capability to communicate using SIP-compliant messaging. New header fields are provided that specify operations to be performed by the service node with respect to a service. INAP service parametric data is also provided in the header fields in a sequential form. When a call is received in the SIPext SSP server for a user having a subscription for a VAS, it queries the user profile stored in the trigger server. If the user is subscribed for a service, a SIP request message is formulated based on the user profile, wherein appropriate headers are populated with relevant parametric information and call context data. The service node launches the SLP based on the information provided in the request message and sends a SIP response message to the SIPext SSP server with an instruction concerning the provisioning of the VAS. The SIPext SSP server, thereafter, takes an appropriate action based on the response message and any parametric information contained therein.

System and method for providing value-added services (VAS) in an integrated telecommunications network using session initiation protocol (SIP)

A system and method of service provisioning in an integrated telecommunications network having a packet-switched network portion (PSN) and a circuit-switched network (CSN) portion with a gateway disposed therebetween. A service node comprising a Service Control Point (SCP), a Service Data Point (SDP), or both, is provided with an interface operable with the PSN portion. A first entity (e.g., served entity) is capable of accessing the service node for the purpose of invoking a service. A return result from the service node is provided, based on the decision of what action is to be taken with respect to the service request, to the first entity which then determines how the action is to be effectuated. An indication is thereafter provided by the first entity to a second entity (e.g., re-routing entity) preferably using H.450.X messages. In response, the second entity (i.e., re-routing or switching entity) takes an appropriate service action based on the return result obtained from the service node. In a presently preferred exemplary embodiment, legacy service nodes built on the basis of WIN/IN service architecture are utilized for the provisioning of Value-Added Services (VAS) or Supplementary Services (SS) in VoIP networks operable with the H.450.X Recommendations.

System and method for providing supplementary services (SS) in an integrated telecommunications network

An operation and maintenance control point (OMCP) operates at an intermediate level in a telecommunications network between the network elements and the network management system (NMS). The OMCP reduces the processing load on the NMS, and rather than reporting symptoms, provides the NMS with suggested corrective actions to correct reported problems. The NMS executes the suggested corrective actions and compares the actual results in the network with predicted results. Feedback on the results is then provided to the OMCP to improve its analysis and provide more effective corrective actions are suggested if the problem recurs. By automatically interfacing with the NMS, which analyzes and executes the suggested corrective actions, the OMCP creates a self-engineering telecommunications network.

Operation and maintenance control point and method of managing a self-engineering telecommunications network

A customer administrative system is interfaced with one or more database network elements having unique subscriber creation or deletion policies. An agent is included within the interface to process a received generic subscriber creation or deletion command originated by a customer administrative system. Responsive thereto, the one or ones of the database network elements implicated by the command are identified and issued, in accordance with the appropriate unique policy for each identified database network element, the required individual database network element specific commands necessary to effectuate the subscriber creation or deletion activity.

Subscriber creation and deletion interface between a customer administrative system and database network elements of a communications network

A customer administrative system of a wireless communications system is interfaced with one or more system database network elements to support single command meta-service activation and management tasks. In this regard, a meta-service comprises a package of individual services. An agent is included in the interface to process single meta-service command for handling by the database network elements. The database network elements supporting the individual services implicated by the meta-service command are identified and are issued appropriately formatted, device specific commands for effectuating the meta-service activation or management task. In the event that each implicated database network element cannot successfully complete the requisite meta-service activation or management task, the service provision state of each implicated database network element is rolled-back to a service provision state prior to receipt of the meta-service command.

Meta-service activating interface between a customer administrative system and database network elements of a communications network

A mapping function and method for mapping a Signaling System 7 (SS7) telecommunication signaling message from a Signaling Connection Control Part (SCCP) protocol layer to an Internet Protocol (IP) protocol layer in order to transmit the SS7 signaling message over a data network from an origination node to a destination node. The mapping function receives the SS7 signaling message from the SCCP protocol layer by sending and receiving Message Transfer Protocol (MTP) primitives from the mapping function to the SCCP protocol layer. The mapping function then maps the received SS7 signaling message into an IP message by mapping MTP primitives into IP primitives, mapping the SS7 message address into an IP message address, and utilizing a user interface to set IP protocol parameters that cannot be transferred by the SCCP protocol layer. The mapping function then sends the mapped IP message to the IP protocol layer by sending and receiving IP primitives from the mapping function to the IP protocol layer.

Growing community of inventors

Montreal, Canada

Roch Glitho