Abstract: Technologies for implementing edge intelligence for utility communication networks are provided. For example, a system includes a mesh network and a utility fog configured to manage the mesh network. The utility fog includes a secure utility system configured for executing a private utility application and a first edge intelligence device configured for executing a first subset of software applications. Each software application is configured to manage endpoints in the mesh network or process data collected by the mesh network. The mesh network includes the endpoints and an edge intelligence device configured for executing a second subset of the software applications that is different from the first subset of software applications.

Abstract: A system for detecting the topology and phase information of an electrical power distribution system is provided. For example, the system includes a group of meters connected to an electrical power distribution system and can communicate with each other through local network connections such as a mesh network. Each of the meters is configured to generate and transmit voltage data to a correlator of the group of meters. The correlator calculates the correlations between each pair of meters in the group based on the voltage data received and further transmits the calculated correlations to a mapper through the mesh network. The mapper determines the topological or phase relationship between at least the group of meters based on the received correlations.

Abstract: Systems and methods are disclosed for detecting node outages in a mesh network. A tracking node in the mesh network detects a set of signals originating from a tracked node in the mesh network. The set of signals includes beacons or communication messages transmitted by the tracked node. The tracking node determines that a threshold number of the beacon intervals have passed since receiving the most recent signal from the tracked node. The tracking node performs outage validation based on data received from another node in the mesh network and updates the status of the tracked node. Based on the updated status, the tracking node outputs a ping to the tracked node requesting a response to the ping. When the response to the ping is not received from the tracked node, the tracking node transmits an outage alarm message to a next topologically higher layer of the mesh network.

Abstract: Systems and methods are disclosed for detecting node outages in a mesh network. A tracking node in the mesh network detects a set of signals originating from a tracked node in the mesh network. The set of signals includes beacons and communication messages transmitted by the tracked node. The tracking node determines that a threshold number of the alive beacon intervals have passed since receiving a most recent signal from the tracked node. The tracking node then outputs a ping to the tracked node requesting a response to the ping. When the response to the ping is not received from the tracked node, the tracking node transmits an outage alarm message to a next topologically higher layer of the mesh network, the outage alarm message comprising an identification of the tracked node.

Abstract: Technologies for implementing edge intelligence for utility communication networks are provided. For example, a system includes a mesh network and a utility fog configured to manage the mesh network. The utility fog includes a secure utility system configured for executing a private utility application and a first edge intelligence device configured for executing a first subset of software applications. Each software application is configured to manage endpoints in the mesh network or process data collected by the mesh network. The mesh network includes the endpoints and an edge intelligence device configured for executing a second subset of the software applications that is different from the first subset of software applications.

Abstract: Detecting an outage by a first node in layer N of a multi-layer mesh network that is in communication with a root node via the mesh network. After waiting for a sustained outage period that expires, the first node waits for a layer-specific time interval that is based on a topology of the second layer. The first node receives a last gasp from a second node in layer N+1 of the multi-layer mesh network. The last gasp includes an identifier for the second node and an indication of layer N+1. After the layer-specific time interval expires, the first node transmits a consolidated last gasp that includes an identifier for the first node, an indication of layer N, the identifier for the second node, and the indication of layer N+1.

Abstract: An implementation of a utility meter is connected to a resource and to a customer premises. The utility meter includes a sensor, a converter, and a radio. The sensor is configured to detect a characteristic of resource usage by the customer premises. The converter is configured to convert the characteristic to raw consumption data describing the resource usage. The radio is configured to transmit the raw consumption data output by the converter to a remote processing system. The remote processing system includes one or both of a fog and a cloud. The fog is associated with a geographic region of the utility meter and performs data processing on the raw consumption data and on regional raw consumption data received from other endpoints in the geographic region. The cloud performs data processing on the raw consumption data as well as on data received from other endpoints across various geographic regions.

Abstract: Technologies for implementing edge intelligence for utility communication networks are provided. For example, a system includes a mesh network and a utility fog configured to manage the mesh network. The utility fog includes a secure utility system configured for executing a private utility application and a first edge intelligence device configured for executing a first subset of software applications. Each software application is configured to manage endpoints in the mesh network or process data collected by the mesh network. The mesh network includes the endpoints and an edge intelligence device configured for executing a second subset of the software applications that is different from the first subset of software applications.

Abstract: A method for responding to a voice activated request includes receiving a speech input request from a smart speaker requesting energy management data associated with energy consumption at a premises of the smart speaker. The method also includes generating a voice service request including a first query for a first data source. The first query includes a request for the energy management data. Additionally, the method includes communicating the first query to the first data source and receiving a first response to the first query from the first data source. Further, the method includes generating an audible speech output in response to the speech input request based on the first response to the first query and transmitting the audible speech output to the smart speaker. The smart speaker audibly transmits the audible speech output.

Abstract: Systems and methods are disclosed for detecting node outages in a mesh network. A tracking node in the mesh network detects a set of signals originating from a tracked node in the mesh network. The set of signals includes beacons or communication messages transmitted by the tracked node. The tracking node determines that a threshold number of the beacon intervals have passed since receiving the most recent signal from the tracked node. The tracking node performs outage validation based on data received from another node in the mesh network and updates the status of the tracked node. Based on the updated status, the tracking node outputs a ping to the tracked node requesting a response to the ping. When the response to the ping is not received from the tracked node, the tracking node transmits an outage alarm message to a next topologically higher layer of the mesh network.

Abstract: Systems and methods are disclosed for detecting and reporting node power outages in a connected network. A node in the network detects that a power outage has occurred at the node and the node generates a last gasp packet using a packet format containing fewer data units than a regular packet format used by the network for communication. The node broadcasts the last gasp packet to its neighboring nodes. After receiving the last gasp packet, a neighboring node estimates the time of the power outage and converts the last gasp packet into an outage alarm message using the regular packet format. The neighboring node transmits the outage alarm message to a headend system to report the power outage at the node.

Abstract: Systems and methods are disclosed for detecting node outages in a mesh network. A tracking node in the mesh network detects a set of signals originating from a tracked node in the mesh network. The set of signals includes beacons and communication messages transmitted by the tracked node. The tracking node determines that a threshold number of the alive beacon intervals have passed since receiving a most recent signal from the tracked node. The tracking node then outputs a ping to the tracked node requesting a response to the ping. When the response to the ping is not received from the tracked node, the tracking node transmits an outage alarm message to a next topologically higher layer of the mesh network, the outage alarm message comprising an identification of the tracked node.

Abstract: A system for detecting the topology and phase information of an electrical power distribution system is provided. For example, the system includes a group of meters connected to an electrical power distribution system and can communicate with each other through local network connections such as a mesh network. Each of the meters is configured to generate and transmit voltage data to a correlator of the group of meters. The correlator calculates the correlations between each pair of meters in the group based on the voltage data received and further transmits the calculated correlations to a mapper through the mesh network. The mapper determines the topological or phase relationship between at least the group of meters based on the received correlations.

Abstract: Systems and methods are disclosed for detecting node outages in a mesh network. A tracking node in the mesh network detects a set of signals originating from a tracked node in the mesh network. The set of signals includes beacons or communication messages transmitted by the tracked node. The tracking node determines that a threshold number of the beacon intervals have passed since receiving the most recent signal from the tracked node. The tracking node performs outage validation based on data received from another node in the mesh network and updates the status of the tracked node. Based on the updated status, the tracking node outputs a ping to the tracked node requesting a response to the ping. When the response to the ping is not received from the tracked node, the tracking node transmits an outage alarm message to a next topologically higher layer of the mesh network.

Abstract: Systems and methods are disclosed for detecting node outages in a mesh network. A tracking node in the mesh network detects a set of signals originating from a tracked node in the mesh network. The set of signals includes beacons and communication messages transmitted by the tracked node. The tracking node determines that a threshold number of the alive beacon intervals have passed since receiving a most recent signal from the tracked node. The tracking node then outputs a ping to the tracked node requesting a response to the ping. When the response to the ping is not received from the tracked node, the tracking node transmits an outage alarm message to a next topologically higher layer of the mesh network, the outage alarm message comprising an identification of the tracked node.

Abstract: Systems and methods are disclosed for detecting and reporting node power outages in a connected network. A node in the network detects that a power outage has occurred at the node and the node generates a last gasp packet using a packet format containing fewer data units than a regular packet format used by the network for communication. The node broadcasts the last gasp packet to its neighboring nodes. After receiving the last gasp packet, a neighboring node estimates the time of the power outage and converts the last gasp packet into an outage alarm message using the regular packet format. The neighboring node transmits the outage alarm message to a headend system to report the power outage at the node.

Abstract: Systems and methods are disclosed for detecting node outages in a mesh network. A tracking node in the mesh network detects a set of signals originating from a tracked node in the mesh network. The set of signals includes beacons or communication messages transmitted by the tracked node. The tracking node determines that a threshold number of the beacon intervals have passed since receiving the most recent signal from the tracked node. The tracking node performs outage validation based on data received from another node in the mesh network and updates the status of the tracked node. Based on the updated status, the tracking node outputs a ping to the tracked node requesting a response to the ping. When the response to the ping is not received from the tracked node, the tracking node transmits an outage alarm message to a next topologically higher layer of the mesh network.

Abstract: Systems and methods are disclosed for detecting node outages in a mesh network. A tracking node in the mesh network detects a set of signals originating from a tracked node in the mesh network. The set of signals includes beacons and communication messages transmitted by the tracked node. The tracking node determines that a threshold number of the alive beacon intervals have passed since receiving a most recent signal from the tracked node. The tracking node then outputs a ping to the tracked node requesting a response to the ping. When the response to the ping is not received from the tracked node, the tracking node transmits an outage alarm message to a next topologically higher layer of the mesh network, the outage alarm message comprising an identification of the tracked node.

Abstract: A method for responding to a voice activated request includes receiving a speech input request from a smart speaker requesting energy management data associated with energy consumption at a premises of the smart speaker. The method also includes generating a voice service request including a first query for a first data source. The first query includes a request for the energy management data. Additionally, the method includes communicating the first query to the first data source and receiving a first response to the first query from the first data source. Further, the method includes generating an audible speech output in response to the speech input request based on the first response to the first query and transmitting the audible speech output to the smart speaker. The smart speaker audibly transmits the audible speech output.

Abstract: A method for responding to a voice activated request includes receiving a speech input request from a smart speaker requesting energy management data associated with energy consumption at a premises of the smart speaker. The method also includes generating a voice service request including a first query for a first data source. The first query includes a request for the energy management data. Additionally, the method includes communicating the first query to the first data source and receiving a first response to the first query from the first data source. Further, the method includes generating an audible speech output in response to the speech input request based on the first response to the first query and transmitting the audible speech output to the smart speaker. The smart speaker audibly transmits the audible speech output.