Utilizing an ensemble-based machine learning model architecture for long term forecasting of data

A device, comprising:

• one or more memories;
• and
• one or more processors to:
• receive time series data from one or more Internet of things (IoT) devices;
• define a first quantity of steps into past data utilized to make future predictions associated with one or more parameters associated with the one or more IoT devices;
• define a second quantity of steps into the future predictions;
• define a third quantity of steps to skip in the future predictions;
• determine whether the second quantity is less than or equal to the third quantity;
• and
• selectively:
• process the time series data, with each of a plurality of machine learning models, to generate a plurality of future predictions that do not overlap based on the second quantity being less than or equal to the third quantity,
• merge the plurality of future predictions into a list of future predictions, and
• cause the one or more IoT devices to modify the one or more parameters based on the plurality of future predictions to prevent potential issues associated with the one or more IoT devices from occurring;
• or
• process the time series data, with each of the plurality of machine learning models, to generate another plurality of future predictions that do overlap based on the second quantity not being less than or equal to the third quantity,
• average values of the other plurality of future predictions that overlap to generate averaged future predictions,
• merge the other plurality of future predictions, based on the averaged future predictions, into another list of future predictions,
• cause the one or more IoT devices to modify the one or more parameters based on the averaged future predictions to prevent potential issues associated with the one or more IoT devices from occurring, and
• perform one or more actions based on the list or the other list.

A non-transitory computer-readable medium storing a set of instructions, the set of instructions comprising:

• one or more instructions that, when executed by one or more processors of a device, cause the device to:
• receive time series data from one or more Internet of things (IoT) devices;
• define a first quantity of steps into past data utilized to make future predictions associated with one or more parameters associated with the one or more IoT devices;
• define a second quantity of steps into the future predictions;
• define a third quantity of steps to skip in the future predictions;
• determine whether the second quantity is less than or equal to the third quantity;
• and
• selectively:
• process the time series data, with each of a plurality of machine learning models, to generate a plurality of future predictions that do not overlap based on the second quantity being less than or equal to the third quantity,
• merge the plurality of future predictions into a list of future predictions, and
• cause the one or more IoT devices to modify the one or more parameters based on the plurality of future predictions to prevent potential issues associated with the one or more IoT devices from occurring;
• or
• process the time series data, with each of the plurality of machine learning models, to generate another plurality of future predictions that do overlap based on the second quantity not being less than or equal to the third quantity,
• average values of the other plurality of future predictions that overlap to generate averaged future predictions,
• merge the other plurality of future predictions, based on the averaged future predictions, into another list of future predictions,
• cause the one or more IoT devices to modify the one or more parameters based on the averaged future predictions to prevent potential issues associated with the one or more IoT devices from occurring, and
• provide the list or the other list for display.