3 results about "Load forecasting" patented technology

The invention discloses a power system short-term load prediction method based on deep learning. The method comprises: firstly, obtaining historical loads, week types, holidays and festivals, meteorological information and other data; carrying out preprocessing such as normalization and coding to serve as input characteristics, learning the deep belief network formed by the stacked limited Boltzmann mechanism layer by layer by using a contrast divergence algorithm, extracting deep characteristics, and finally finely adjusting parameters of the whole deep belief network by using a back propagation algorithm, namely constructing the load prediction model by offline training; and carrying out online prediction on the load of the power system after 24 hours to obtain a predicted load. The short-term load prediction method improves the short-term load prediction precision of the power system.

The invention relates to the technical field of power grid energy prediction, in particular to an AI-based network source load prediction data management system, which comprises an information acquisition module, a prediction processing module, a data verification module, a database module and a dispatching master station end, and is characterized in that the information acquisition module comprises a weather receiving unit, an actual load unit, a date recording unit and an OSB interface unit; the input end of the OSB interface unit is connected to the output end of the dispatching master station end through a wireless network, and the weather receiving unit is used for receiving weather information sent by the dispatching master station end. According to the invention, the information acquisition module and the database module can realize data information interaction and extraction with the scheduling master station end; the scheduling master station end can synchronously obtain the prediction result, so that corresponding decisions can be made in time, meteorological information and actual load information are received in real time for prediction analysis, the predicted load data information can be verified and corrected, and the basis reliability of the predicted load data information is ensured.