2 results about "Demand estimation" patented technology

In an aspect, input data can be received, including at least time series data associated with purchases of at least one product and causal influencer data associated with the purchases. The causal influencer data can include at least non-stationary data, where lost shares associated with said at least one product are unobserved. An artificial neural network can be trained based on the received input data to predict a future global demand associated with at least one product and individual market shares associated with at least one product. The artificial neural network can include at least a first temporal network to predict the global demand and a second temporal network to predict each of the individual market shares. The first temporal network and the second temporal network can be trained simultaneously.

The present invention relates to a virtual power plant to which an optimal price determination and contract renewal system based on digital twin modeling and artificial intelligence is applied. More specifically, the invention comprises: an optimal price determination system including a power generation estimation module that estimates the power generation amount of a power source per reference period, a power demand estimation module that estimates the power consumption amount of a power demander, and a price determination module that derives an optimal price by reinforcement-learned artificial intelligence based on power generation and power consumption data estimated from the power generation estimation module and the power demand estimation module, respectively; a power source management module that manages data on real-time energy transactions and history of power sources and calculates a parameter value that compensates for the difference between the price determined by the optimal price determination system and the actual transaction price, and outputs it to the power generation estimation module; a demand source management module that manages data on real-time energy transactions and history of power demanders and calculates a parameter value that compensates for the difference between the price determined by the optimal price determination system and the actual transaction price, and outputs it to the power demand estimation module; and a monitoring module that manages the optimal price determination system, monitors real-time power transactions, and manages their history. A cloud data server module that processes and manages all data regarding power trading input / output from the above monitoring module and provides it to the user;A contract renewal system comprising: a supply-side digital twin modeling module that generates multiple supply-side contract renewal digital twin modules by modeling supply-side contract renewal conditions based on supply-side power supply history data for the entire contract period and maximum / minimum range data calculated therefrom from the cloud data server module; a demand-side digital twin modeling module that generates multiple demand-side contract renewal digital twin modules by modeling demand-side contract renewal conditions based on demand-side power demand or consumption history data for the entire contract period and maximum / minimum range data calculated therefrom from the cloud data server module; and a contract renewal module that combines multiple supply-side contract renewal digital twin modules and demand-side contract renewal digital twin modules to calculate and output contract matching condition ranges by artificial intelligence for each, wherein the power generation estimation module includes multiple supply-side digital twin models that model supply quantities for price based on data regarding estimated power supply and maximum / minimum range data calculated therefrom, and the power demand estimation module includes multiple demand quantities that model demand quantities for price based on data regarding estimated power demand and maximum / minimum range data calculated therefrom The present invention relates to a virtual power plant to which a system for optimal price determination and contract renewal by digital twin modeling and artificial intelligence is applied, wherein the system includes a demand-side digital twin model, and the price determination module determines an optimal price range by artificial intelligence from multiple prices determined by matching the supply and demand quantities for each price derived from multiple supply-side digital twin models and multiple demand-side digital twin models.