18272896. METHOD AND SYSTEM TO PREDICT NETWORK PERFORMANCE USING A HYBRID MODEL INCORPORATING MULTIPLE SUB-MODELS simplified abstract (Telefonaktiebolaget LM Ericsson (publ))
Contents
- 1 METHOD AND SYSTEM TO PREDICT NETWORK PERFORMANCE USING A HYBRID MODEL INCORPORATING MULTIPLE SUB-MODELS
- 1.1 Organization Name
- 1.2 Inventor(s)
- 1.3 METHOD AND SYSTEM TO PREDICT NETWORK PERFORMANCE USING A HYBRID MODEL INCORPORATING MULTIPLE SUB-MODELS - A simplified explanation of the abstract
- 1.4 Simplified Explanation
- 1.5 Potential Applications
- 1.6 Problems Solved
- 1.7 Benefits
- 1.8 Potential Commercial Applications
- 1.9 Possible Prior Art
- 1.10 Unanswered Questions
- 1.11 Original Abstract Submitted
METHOD AND SYSTEM TO PREDICT NETWORK PERFORMANCE USING A HYBRID MODEL INCORPORATING MULTIPLE SUB-MODELS
Organization Name
Telefonaktiebolaget LM Ericsson (publ)
Inventor(s)
Jenny Yang of Sunnyvale CA (US)
Simone Vincenzi of Santa Cruz CA (US)
Prasad Jogalekar of San Jose CA (US)
METHOD AND SYSTEM TO PREDICT NETWORK PERFORMANCE USING A HYBRID MODEL INCORPORATING MULTIPLE SUB-MODELS - A simplified explanation of the abstract
This abstract first appeared for US patent application 18272896 titled 'METHOD AND SYSTEM TO PREDICT NETWORK PERFORMANCE USING A HYBRID MODEL INCORPORATING MULTIPLE SUB-MODELS
Simplified Explanation
The patent application describes methods and systems to predict network performance using a hybrid model incorporating a generalized additive model and an autoregressive integrated moving average model.
- The method involves training a first sub-model using a subset of time series data values and determining parameters within univariate functions of the first sub-model.
- A second sub-model is trained using the same subset of data values, and a weight distribution between the first and second sub-models is determined using additional data values to generate the hybrid model.
- The hybrid model is then used to predict the performance indicator of the network at a later date.
Potential Applications
This technology could be applied in various industries where predicting network performance is crucial, such as telecommunications, internet service providers, and data centers.
Problems Solved
This technology helps in predicting network performance accurately, allowing for proactive maintenance and optimization of network resources.
Benefits
The benefits of this technology include improved network performance, reduced downtime, optimized resource allocation, and enhanced user experience.
Potential Commercial Applications
Potential commercial applications of this technology include network monitoring and management software, predictive maintenance solutions, and network optimization tools.
Possible Prior Art
One possible prior art could be existing network performance prediction models that may not incorporate a hybrid approach like the one described in this patent application.
Unanswered Questions
How does the hybrid model compare to traditional network performance prediction models in terms of accuracy and efficiency?
The article does not provide a direct comparison between the hybrid model and traditional models in terms of accuracy and efficiency.
What are the specific parameters and functions used in the first and second sub-models to predict network performance?
The article does not delve into the specific parameters and functions used in the first and second sub-models for predicting network performance.
Original Abstract Submitted
Methods and systems to predict network performance of a network are disclosed. In one embodiment, a method comprises: training a first sub-model using a subset of a plurality of time series of data values, where the first sub-model comprises a type of generalized additive model, and where training the first sub-model comprises determining parameters within a plurality of univariate functions of the first sub-model; and training a second sub-model using the subset of the time series of data values, wherein the second sub-model comprises a type of autoregressive integrated moving average (ARIMA) model. The method further comprises determining a weight distribution between the first and second sub-models using additional data values from the time series of data values to generate a hybrid model incorporating the first and second sub-models, and predicting a data value of the performance indicator of the network at a later day using the hybrid model.
