Online scheduling method for electricity-heat comprehensive energy system based on near-end strategy optimization

Abstract

The invention discloses an online scheduling method for an electricity-heat comprehensive energy system based on near-end strategy optimization, and the method comprises the steps: constructing a real-time operation cost model of the electricity-heat comprehensive energy system for the intermittency of wind energy, the randomness of a real-time power market and the uncertainty of a user load; andthen, adopting a deep reinforcement learning method to convert a dynamic energy conversion problem into a discrete finite Markov decision process, and adopting an approximate strategy optimization algorithm to solve the decision problem, so that a system operator can adaptively determine the wind power conversion rate through online learning, the uncertainty of user load requirements, the flexibility of real-time electricity price and the uncertainty of wind power generation are also solved, and the income maximization of the electricity-heat comprehensive energy system is realized.

Description

technical field [0001] The invention belongs to the technical field of new energy power generation, and more specifically relates to an online economic dispatching method of an electric-thermal comprehensive energy system based on proximal strategy optimization. Background technique [0002] The development and utilization of wind power is a major measure for energy structure adjustment and transformation, and has entered into industrialization and large-scale development. According to the statistics of the National Energy Administration, as of the end of March 2020, the National Energy Administration announced that the cumulative installed capacity of wind power in my country reached 213 million kilowatts, of which the cumulative installed capacity of onshore wind power was 206 million kilowatts and the cumulative installed capacity of offshore wind power was 6.14 million kilowatts. Due to the time-space difference between the actual power generation curve of wind turbines ...

AI Technical Summary

Problems solved by technology

However, the introduction of integrated energy systems has increased the difficulty of optimal economic dispatch of wind power generation systems, and it is difficult to solve non-convex and nonlinear economic dispatch models in real time; facing the access of large-scale wind power sources, it is necessary to find an economic dispatch that can A real-time optimization method adapted to the characteristics of wind turbine power generation

[0005]Due to the intermittent characteristics of wind power, the operation risk of the power grid with high penetration rate wind power is high, and the emergency reserve capacity is large, which is not conducive to ensuring the stability and economy of the power grid

However, most of the existing wind power-integrated energy system optimization dispatching research is based on day-ahead optimization to dispatch wind power. Since wind power generation has unpredictable fluctuation characteristics, it is difficult for this method to ensure the real-time optimal operation of the wind power system.

Images