Abstract: A method for identifying missing components of a computer system may include receiving telemetry signals characterizing a current configuration of the computer system and determining a cross power spectral density signature of at least some of the telemetry signals. The method may further include comparing information about the determined cross power spectral density signature with information about a predetermined cross power spectral density signature to determine whether a component is missing within the computer system.

Abstract: A method for identifying missing components of a computer system may include receiving telemetry signals characterizing a current configuration of the computer system and determining a cross power spectral density signature of at least some of the telemetry signals. The method may further include comparing information about the determined cross power spectral density signature with information about a predetermined cross power spectral density signature to determine whether a component is missing within the computer system.

Abstract: One embodiment of the present invention provides a system that optimizes a regression model which predicts a signal as a function of a set of available signals. During operation, the system receives training data for the set of available signals from a computer system during normal fault-free operation. The system also receives an objective function which can be used to evaluate how well a regression model predicts the signal. Next, the system initializes a pool of candidate regression models which includes at least two candidate regression models, wherein each candidate regression model in the pool includes a subset of the set of available signals.

Abstract: One embodiment of the present invention provides a system that reconstructs a high-resolution signal from a set of low-resolution quantized samples. During operation, the system receives a time series containing low-resolution quantized signal values which are sampled from the high-resolution signal. Next, the system performs a spectral analysis on the time series to obtain a frequency series for the low-resolution quantized signal values. The system next selects a subset of frequency terms from the frequency series which have the largest amplitudes. The system then reconstructs the high-resolution signal by performing an inverse spectral analysis on the subset of the frequency terms.

Abstract: A method of tagging a manufactured product with a passive tag includes processing a subset of a plurality of unique combinations of at least two axis ratios, where the subset is determinable by a plurality of parameters that define a portion of a coordinate space, to determine a first particular unique combination of the at least two axis ratios. A gas having the determined particular one unique combination of at least two axis ratios is incorporated into the manufactured product. The product to be tagged may be a first product, characterized by a first particular characteristic, and a second product is characterized by a second particular characteristic different from the first particular characteristic. The unique combination of at least two axis ratios is a first unique combination.

Abstract: A system that facilitates estimating power consumption in a computer system by inferring the power consumption from instrumentation signals. During operation, the system monitors instrumentation signals within the computer system, wherein the instrumentation signals do not include corresponding current and voltage signals that can be used to directly compute power consumption. The system then estimates the power consumption for the computer system by inferring the power consumption from the instrumentation signals and from an inferential power model generated during a training phase.