Identifying abnormalities in resource usage

An apparatus comprising:

• a storage device storing a model representing a plurality of modes for use of a form of energy from training data comprising a first plurality of measurements of a first performance of the use of the form of energy over a period of time, wherein each of the plurality of modes is identified as one of normal and abnormal;
• a data processing system comprising a processor unit and configured to receive activity data comprising a second plurality of measurements of a second performance of the use of the form of energy and compare a portion of the activity data with the plurality of modes in the model;
• and
• a user interface configured to provide a notification of an abnormality in the second performance of the use of the form of energy and provide a request for confirmation of the abnormality, in response to an identification that the portion of the activity data matches a mode in the plurality of modes that is identified as abnormal,
• wherein the data processing system is further configured to:
• identify the plurality of modes for the activity from the training data, wherein a first mode in the plurality of modes comprises a range in measurements expected during performance of the activity;
• receive an indication of whether the first mode in the plurality of modes is one of normal and abnormal;
• and store the first mode and the indication in association with the model in a storage device.

A data processing system for identifying abnormalities in data, the data processing system comprising:

• a bus system;
• a storage device connected to the bus system, wherein the storage device includes program code;
• and
• a processor unit connected to the bus system, wherein the processor unit is configured to execute the program code to retrieve a model representing a plurality of modes for an activity generated from training data comprising a first plurality of measurements of a first performance of the activity over a period of time, wherein each of the plurality of modes is identified as one of normal and abnormal, receive activity data comprising a second plurality of measurements of a second performance of the activity, compare a portion of the activity data with the plurality of modes in the model, and generate a notification of an abnormality in the second performance of the activity and request confirmation of the abnormality via a user interface in response to identifying that the portion of the activity data matches a mode in the plurality of modes that is identified as abnormal;
• wherein the processor unit is further configured to execute the program code to identify the plurality of modes for the activity from the training data, wherein a first mode in the plurality of modes comprises a range in measurements expected during performance of the activity, receive an indication of whether the first mode in the plurality of modes is one of normal and abnormal, and store the first mode and the indication in association with the model in a storage device.