Abstract: Embodiments relate to analyzing network packets in a telecommunication networks using machine learning models. The network packets are correlated and then labeled to indicate successes or failures in a subtask of communication flow. Features are extracted based on the labels and correlated network packets. The extracted features are applied to a machine learning model to predict or infer success or failure of the entire communication flow. The result from the machine learning model may again be applied to subsequent machine learning models to predict root cause of a failure or to predict or infer the type of success. In this way, more accurate diagnosis of network issues in the telecommunication networks may be made in a more expedient manner.

Abstract: A processor is responsive to a thermistor temperature (Tth) adjacent a FET and to a drain-to-source voltage (VDS) of the FET. The processor stores the characteristics of the PET and a thermal model of the system hardware and uses a first set of equations to determine the temperature (TJ) at the junction of the PET in a stable region of operation where TJ?Tth is nearly constant. The processor is further responsive to a step change in successive measurements of VDS indicative of a lag of Tth relative to TJ. In this step-change region, the processor then resolves TJ based upon a second set of equations.