Systems and methods for optimizing power usage for systems within quality-of-service constraints

A system comprising:

• an identification module, stored in a memory of the system, that identifies an artificial neural network that processes each input to the artificial neural network in a fixed number of operations;
• an analysis module, stored in the memory, that performs an analysis on the artificial neural network to determine an execution metric that represents the fixed number of operations performed by the artificial neural network to process each input;
• a determination module, stored in the memory, that determines a quality-of-service metric for an executing system that executes the artificial neural network;
• an optimization module, stored in the memory, that optimizes power consumption of the executing system by configuring, based on the execution metric and the quality-of-service metric, a processing throughput of at least one physical processor of the executing system, thereby causing the executing system to execute the artificial neural network at a rate that satisfies the quality-of-service metric while limiting the power consumption of the executing system;
• and
• at least one executing physical processor configured to execute the identification module, the analysis module, the determination module, and the optimization module.

A non-transitory computer-readable medium comprising one or more computer-readable instructions that, when executed by at least one processor of a computing device, cause the computing device to:

• identify an artificial neural network that processes each input to the artificial neural network in a fixed number of operations;
• perform an analysis on the artificial neural network to determine an execution metric that represents the fixed number of operations performed by the artificial neural network to process each input;
• determine a quality-of-service metric for an executing system that executes the artificial neural network;
• and
• optimize power consumption of the executing system by configuring, based on the execution metric and the quality-of-service metric, a processing throughput of at least one physical processor of the executing system, thereby causing the executing system to execute the artificial neural network at a rate that satisfies the quality-of-service metric while limiting the power consumption of the executing system.