Back to results
US 11,153,175 B2Granted
Latency management by edge analytics in industrial production environments
AssigneeInternational Business Machines Corporation
InventorsDattaram Bijavara Aswathanarayana Rao, Saurabh Gupta, Rakesh Sharma Mangala Nagendra Rao, Vishwanath Narayan
Life of this patent
Estimating the term…
Abstract
A method, computer program product, and computer system are disclosed. The method includes determining probability of high data flow event, memory requirements for the high data flow and time to high data flow event by using pattern recognition based on natural language Processing (NLP), machine learning and statistical algorithms. The method applies a configuration to the edge device and network system when the probability of high data flow event is above a predetermined threshold for handling the high data flow event.
Claims20
A method comprising:
- receiving, by one or more processors of an edge device, from a central server computer, a machine learning model, wherein the machine learning model is trained using historical network data and historical configuration parameters implemented by the central server computer in response to the historical network data;
- deploying, by one or more processors of the edge device, the machine learning model on the edge device by integrating the machine learning model into configuration and runtime of the edge device;
- receiving, by one or more processors of the edge device, a first set of network data;
- utilizing, by one or more processors of the edge device, the machine learning model to determine, based, at least in part, on the first set of network data:
- (i) a probability of a high data flow event, (ii) a time to the high data flow event, and (iii) a forecasted duration of the high data flow event;
- determining that the probability of the high data flow event is above a predetermined threshold;
- based, at least in part, on the probability of the high data flow event being above the predetermined threshold, updating, by one or more processors of the edge device, a configuration parameter for the edge device, where updating the configuration parameter includes performing natural language processing to infer an impact of the high data flow event and modifying the configuration parameter to handle the high data flow event;
- processing, by one or more processors of the edge device, the first set of network data according to the updated configuration parameter;
- and
- restoring, by one or more processors of the edge device, an original configuration parameter for the edge device after a period of time based, at least in part, on the forecasted duration of the high data flow event.
7 more elements
A computer program product, comprising:
- one or more computer readable storage media and program instructions stored on the one or more computer readable storage media, wherein the one or more computer readable storage media are not transitory signals per se, the stored program instructions comprising:
- program instructions to receive, from a central server computer, a machine learning model, wherein the machine learning model is trained using historical network data and historical configuration parameters implemented by the central server computer in response to the historical network data;
- program instructions to deploy the machine learning model on the edge device by integrating the machine learning model into configuration and runtime of the edge device;
- program instructions to receive a first set of network data;
- program instructions to utilize the machine learning model to determine, based, at least in part, on the first set of network data:
- (i) a probability of a high data flow event, (ii) a time to the high data flow event, and (iii) a forecasted duration of the high data flow event;
- program instructions to determine that the probability of the high data flow event is above a predetermined threshold;
- program instructions to, based, at least in part, on the probability of the high data flow event being above the predetermined threshold, update a configuration parameter for the edge device, where updating the configuration parameter includes performing natural language processing to infer an impact of the high data flow event and modifying the configuration parameter to handle the high data flow event;
- program instructions to process the first set of network data according to the updated configuration parameter;
- and
- program instructions to restore an original configuration parameter for the edge device after a period of time based, at least in part, on the forecasted duration of the high data flow event.
8 more elements
A computer system, comprising:
- one or more computer processors;
- one or more computer readable storage devices;
- program instructions stored on the one or more computer readable storage devices for execution by at least one of the one or more computer processors, the stored program instructions comprising:
- program instructions to receive, from a central server computer, a machine learning model, wherein the machine learning model is trained using historical network data and historical configuration parameters implemented by the central server computer in response to the historical network data;
- program instructions to deploy the machine learning model on the edge device by integrating the machine learning model into configuration and runtime of the edge device;
- program instructions to receive a first set of network data;
- program instructions to utilize the machine learning model to determine, based at least in part, on the first set of network data:
- (i) a probability of a high data flow event, (ii) a time to the high data flow event, and (iii) a forecasted duration of the high data flow event;
- program instructions to determine that the probability of the high data flow event is above a predetermined threshold;
- program instructions to, based, at least in part, on the probability of the high data flow event being above the predetermined threshold, update a configuration parameter for the edge device, where updating the configuration parameter includes performing natural language processing to infer an impact of the high data flow event and modifying the configuration parameter to handle the high data flow event;
- program instructions to process the first set of network data according to the updated configuration parameter;
- and
- program instructions to restore an original configuration parameter for the edge device after a period of time based, at least in part, on the forecasted duration of the high data flow event.
10 more elements
Dependencies are inferred from the claim text.