Methods and apparatus for predicting impact of proposed changes and implementations in distributed networks

A system for predicting a service criterion in a distributed computer network, the system comprising:

• a what-if scenario receiving module for receiving information for a what-if scenario including selected conditions, the selected conditions including a change to a property of the distributed computer network that will impact the performance of the distributed computer network;
• a relevant feature module for receiving features associated with the distributed computer network and for determining which ones of the features are relevant to the what-if scenario based on the property of the distributed computer network;
• a dependencies module for identifying which ones of the relevant features have parent or child dependencies to other ones of the relevant features by identifying, for the property of the distributed computer network, which of the relevant features are cause variables and which are no-cause variables;
• an input distribution module for filtering data associated with the relevant features;
• a processor for managing operation of the relevant feature module, the dependencies module and the input distribution module;
• and
• memory for storing instructions and data for execution by the processor, the relevant feature module, the dependencies module and the input distribution module.

A system for predicting a service criterion in a distributed computer network, the system comprising:

• means for receiving information for a what-if scenario including selected conditions, the selected conditions including a change to a property of the distributed computer network that will impact the performance of the distributed computer network
• means for receiving features associated with the distributed computer network and for determining which ones of the features are relevant to the what-if scenario based on the property of the distributed computer network;
• means for identifying which ones of the relevant features have parent or child dependencies to other ones of the relevant features by identifying, for the property of the distributed computer network, which of the relevant features are cause variables and which are no-cause variables;
• means for filtering data associated with the relevant features;
• and
• memory for storing the filtered data.

A method for determining relevant variables of a distributed computer network, the method comprising:

• receiving selected conditions for a scenario, the selected conditions including a change to a property of the distributed computer network that will impact performance of the distributed computer network;
• identifying a first variable of a dataset of variables based on the property of the distributed computing network;
• determining whether the first variable is a categorical variable;
• and
• if the first variable is categorical, generating, with a processor, a conditional distribution for the first variable.

A method of processing data of a distributed computing network, the method comprising:

• receiving selected conditions for a what-if scenario, the selected conditions including a change to a property of the distributed computing network that will impact performance of the distributed computing network;
• obtaining a global set of data for a distributed computing network;
• filtering the global dataset to obtain an initial test dataset based on the property of the distributed computing network;
• applying, with a processor, the change the property of the distributed computing network to the initial test dataset to obtain an updated test dataset;
• and
• processing the updated test dataset to output a predicted scenario result to a user.

A system for processing data of a distributed computing network, the system comprising:

• a processor for managing operation of a plurality of modules;
• memory for storing instructions and data for execution by the at least one processor;
• a first one of the plurality of modules for obtaining a global set of data for the distributed computing network and for filtering the global dataset to obtain an initial test dataset using a use parameter associated with a what-if scenario, the what-if scenario indicating a change to a property of the distributed computing network that will impact performance of the distributed computing network;
• and
• a second one of the plurality of modules for applying the change to the property of the distributed computing network within the initial test dataset to obtain an updated test dataset and for processing the updated test dataset to output a predicted scenario result to a user.