Spot market electricity seller quotation method based on reinforcement learning
The invention discloses a spot market electricity seller quotation method based on reinforcement learning, and the method comprises the steps: setting a spot market transaction rule, carrying out the market transaction through employing a bilateral centralized bidding mode of electricity purchasing...
Saved in:
Main Authors | , , |
---|---|
Format | Patent |
Language | Chinese English |
Published |
12.08.2022
|
Subjects | |
Online Access | Get full text |
Cover
Loading…
Summary: | The invention discloses a spot market electricity seller quotation method based on reinforcement learning, and the method comprises the steps: setting a spot market transaction rule, carrying out the market transaction through employing a bilateral centralized bidding mode of electricity purchasing and selling parties, and carrying out the clearing settlement through a time-phased stepped quotation mode and employing a unified marginal clearing mode; establishing an electricity seller income model, giving a target model of different types of electricity seller quotation strategies, and performing assumption condition and initial value setting on the model; a reinforcement learning algorithm is introduced, state spaces, action spaces and reward functions of all the electricity sellers in the model are defined according to the reinforcement learning algorithm, and a spot market electricity seller quotation model based on reinforcement learning is established; and solving by adopting an epsilon-greedy algorithm |
---|---|
Bibliography: | Application Number: CN202210274106 |