Htm-based predictions for system behavior management

A computer program product comprising one or more computer readable storage media, and program instructions collectively stored on the one or more computer readable storage media, the program instructions executable by controller circuitry to cause the controller circuitry to perform operations comprising:

• duplicating an input dataset being input to a model predictive control (MPC) module for input to a first Hierarchical Temporal Memory (HTM) network, the input dataset being associated with a system, the input dataset including first system input data that is input to the system, the input dataset including data associated with a plurality of dimensions of the system, and the input dataset including a characteristic dataset representative of a characteristic of the system;
• generating system behavior data representative of a system behavior curve using the MPC module for the characteristic datasets;
• generating first HTM prediction data from the input dataset and the system behavior data using the first HTM network comprising a plurality of regions each having a plurality of active and inactive nodes, the first HTM prediction data comprising predictions for respective dimensions of the system based on the active nodes for respective regions of the first HTM network;
• generating second HTM prediction data from the first HTM prediction data and system output data using a second HTM network comprising a plurality of regions each having a plurality of active and inactive nodes, the second HTM prediction data comprising a distinction between the first HTM prediction and the system output data based on the active nodes for respective regions of the second HTM network;
• determining that the distinction of the second HTM prediction data indicates an anomaly;
• and
• adjusting second system input data that is input to the system based on the anomaly.

A computer system comprising a processor and one or more computer readable storage media, and program instructions collectively stored on the one or more computer readable storage media, the program instructions executable by the processor to cause the processor to perform operations comprising:

• duplicating an input dataset being input to a model predictive control (MPC) module for input to a first Hierarchical Temporal Memory (HTM) network, the input dataset being associated with a system, the input dataset including first system input data that is input to the system, the input dataset including data associated with a plurality of dimensions of the system, and the input dataset including a characteristic dataset representative of a characteristic of the system;
• generating system behavior data representative of a system behavior curve using the MPC module for the characteristic datasets;
• generating first HTM prediction data from the input dataset and the system behavior data using the first HTM network comprising a plurality of regions each having a plurality of active and inactive nodes, the first HTM prediction data comprising predictions for respective dimensions of the system based on the active nodes for respective regions of the first HTM network;
• generating second HTM prediction data from the first HTM prediction data and system output data using a second HTM network comprising a plurality of regions each having a plurality of active and inactive nodes, the second HTM prediction data comprising a distinction between the first HTM prediction and the system output data based on the active nodes for respective regions of the second HTM network;
• determining that the distinction of the second HTM prediction data indicates an anomaly;
• and
• adjusting second system input data that is input to the system based on the anomaly.