Efficient processing of system scenarios in statistical and machine learning studies for power system operational and investment planning

Role of Statistical and Machine Learning Methods in Special Protection Scheme Logic Design and Failure Assessment

“…Therefore, an efficient sampling process as described earlier will be highly advantageous to form better SPS operating rules. This efficient sampling can be realized using importance sampling method, a Monte Carlo variance reduction technique; the framework was properly demonstrated in [16,26]. The importance sampling procedure is a statistical method that will help to bias the sampling process toward the stability boundary and therefore generate operating conditions close to stability boundary region of the operational parameter state space.…”

“…Such intelligence is usually lacking in traditional sampling approaches. This concept of identifying the most important operating conditions and a highly intelligent dataset for efficient knowledge discovery is dealt with in detail in [16,26].…”

“…ASSESS and TROPIC software [25,26], which can perform the traditional power flow and time domain simulations, are used. The unique feature of ASSESS is that it has an outer layer that allows the user to perform a Monte Carlo simulation study considering a myriad of uncertainties in power system conditions.…”