Machine learning enabled self-detection for truck rolls on end-user satellite terminals
A system and method for collecting, at a terminal, statistical data regarding performance of a transport between the terminal and a satellite; analyzing, at the terminal with an ML model, the statistical data to determine a failure state of the terminal and notifying a user of the failure state, wherein the ML model is trained on a training dataset collected from a terminal population, and the statistical data comprises a terminal state and transport metrics for the terminal.
1 . A method for determining a failure state of a satellite terminal using a Machine Learning (ML) system comprising a computer processor, the method comprising:
collecting, at a terminal, statistical data regarding performance of a transport between the terminal and a satellite;
analyzing, at the terminal with an ML model, the statistical data to determine a failure state of the terminal;
notifying a user of the failure state; and
pre-processing the statistical data to homogenize and to normalize the statistical data prior to the analyzing,
wherein the ML model is trained on a training dataset collected from a terminal population, and the statistical data comprises a terminal state and transport metrics for the terminal.
2 . The method of claim 1 , wherein the failure state comprises one or more of a normal state, a dispatch state, or a failure prediction.
3 . The method of claim 1 , wherein the failure state comprises a likely cause of an operational failure.
4 . The method of claim 1 , wherein the failure state comprises a predicted failure duration.
5 . The method of claim 1 , wherein the terminal performs a self-healing based on the failure state.
6 . The method of claim 1 , wherein the notifying comprises displaying the failure state.
7 . The method of claim 1 , wherein the notifying comprises sending a message to a customer care center prior to the failure state necessitating a truck roll.
8 . The method of claim 1 , further comprising setting up the ML model in the terminal over the transport for execution at the terminal.
9 . The method of claim 1 , wherein the transport metrics comprise one or more of a frequency band, a satellite constellation, an antenna, a carrier frequency, a gateway identification, an outdoor unit, a Packet Loss Rate (PLR), a Modulation and Coding (MODCOD) symbol rate, a MODCOD modulation, a transport layer queue depth, a transport layer queue latency, a link type, a congestion level, an interface cost, a latency, a jitter, bytes sent and received, a terminal restart count or a combination thereof.
10 . A satellite communication system to determine a failure state of a satellite terminal using a Machine Learning (ML) system comprising a computer processor, the satellite communication system comprising:
a terminal to collect statistical data regarding performance of a transport between the terminal and a satellite, and to notify a user of a failure state; and
an ML model, at the terminal, to analyze the statistical data to determine the failure state of the terminal,
wherein the ML model is trained on a training dataset collected from a terminal population, and the statistical data comprises a terminal state and transport metrics for the terminal, and
wherein the ML model pre-processes the statistical data to homogenize and to normalize the statistical data prior to the analyzing.
11 . The satellite communication system of claim 10 , wherein the failure state comprises one or more of a normal state, a dispatch state, or a failure prediction.
12 . The satellite communication system of claim 10 , wherein the failure state comprises a likely cause of an operational failure.
13 . The satellite communication system of claim 10 , wherein the failure state comprises a predicted failure duration.
14 . The satellite communication system of claim 10 , wherein the terminal performs a self-healing based on the failure state.
15 . The satellite communication system of claim 10 , wherein the terminal displays the failure state.
16 . The satellite communication system of claim 10 , wherein the terminal sends a message to a customer care center prior to the failure state necessitating a truck roll.
17 . The satellite communication system of claim 10 , wherein the terminal receives the ML model over the transport to execute at the terminal.
18 . The satellite communication system of claim 10 , wherein the transport metrics comprise one or more of a frequency band, a satellite constellation, an antenna, a carrier frequency, a gateway identification, an outdoor unit, a Packet Loss Rate (PLR), a Modulation and Coding (MODCOD) symbol rate, a MODCOD modulation, a transport layer queue depth, a transport layer queue latency, a link type, a congestion level, an interface cost, a latency, a jitter, bytes sent and received, a terminal restart count or a combination thereof.