36 results about "Heuristics" patented technology

A method using machine learned, scenario based control heuristics including: providing a simulation model for predicting a system state vector of the dynamical system in time based on a current scenario parameter vector and a control vector; using a Model Predictive Control, MPC, algorithm to provide the control vector during a simulation of the dynamical system using the simulation model for different scenario parameter vectors and initial system state vectors; calculating a scenario parameter vector and initial system state vector a resulting optimal control value by the MPC algorithm; generating machine learned control heuristics approximating the relationship between the corresponding scenario parameter vector and the initial system state vector for the resulting optimal control value using a machine learning algorithm; and using the generated machine learned control heuristics to control the complex dynamical system modelled by the simulation model.

The invention provides a sparse technology-based fast Gauss-Seidel power flow algorithm for a power system and belongs to the analyzing and computing field of the power system. According to the technical scheme of the algorithm, data only containing non-zero elements in a data file are quickly read into an array Y(n, d), so that the reading time of a storage unit and the data file is greatly reduced. Vi and the Qi of a PV node are quickly calculated based on the array Y(n, d), so that the invalid computation of a large amount of zero elements is avoided. Meanwhile, an optimal acceleration factor is quickly determined based on the improved heuristics method, so that the iterative computation speed is greatly improved. The above algorithm is completely applicable to the checking calculation process of all IEEE systems, such as an IEEE-118 system. Compared with the prior art, the time spent in reading the data file is reduced by about 85%, and the time spent on the power flow iteration process is reduced by about 90%. Moreover, the entire computation time is reduced by about 88%. In addition, the more the nodes of a system, the greater the advantages of the algorithm.