Design Of Hybrid Energy Storage System For Wind Power Suppression Based On The Integrated Prediction Of Source And Joad

With the goal of carbon neutralization and peaking proposed,the large-scale grid connection technology of renewable energy has gradually attracted the attention of all countries.Due to the randomness and volatility of wind resources,wind power generation cannot be directly connected to the grid.Random and fluctuating wind power integration will inevitably disrupt the stable operation of the power grid.Because of unique energy storage and release capacity,energy storage has become a bridge for energy transition in the power system.Therefore,energy storage media can play a role in absorbing wind power fluctuations in the process of wind power grid connection,thus improving the wind power grid connection capacity.Unreasonable capacity allocation in energy storage systems is bound to cause problems such as increased cost and reduced service life,so reasonable capacity allocation of energy storage systems in wind farms has become a problem that cannot be ignored.Wind power and load power prediction can provide data reference in solving the problem of capacity configuration in energy storage systems,and higher precision power prediction model has better guidance ability for capacity configuration and help for accurate configuration of energy storage systems.Therefore,combining source and load prediction models to optimize the design of hybrid energy storage systems(HESS)has become a worthwhile research direction.Utilizing the source/load duality of energy storage media to construct the topology and control model of the source network load/storage combining power system.Aiming at the problem of wind power fluctuation and energy storage system cost,a dual control strategy of wind power grid connection based on power prediction is proposed.First,the advantages of the prediction model are explored,and a high-precision prediction model is established by combining convolutional neural network and short-term memory neural network to provide data for further design of HESS control strategy;Smooth the grid connected data using the sliding average method,and obtain the target grid connected power that meets the national wind power grid connection standard.Second,the empirical mode decomposition method is used to decompose the reference power of the HESS and reconstruct it into high and low frequency signals.An upper level control strategy based on the dual channel adaptive sliding average method was designed,the lower part of the high frequency power and the higher part of the low frequency power are extracted by setting the step size of the Moving-average model sampling window as the intermediate frequency power signal,at this point,the reference power of HESS is responded by supercapacitor,battery and flywheel energy storage array.Design a lower level control strategy based on a stepped power allocation strategy,using the state of charge and the number of charges and discharges of the flywheel energy storage unit as policy variables to further optimize the internal power allocation of the flywheel energy storage array.Finally,the improved particle swarm algorithm is used to establish an optimization model with the cost of HESS as the objective functionUsing the actual load data of a wind farm with an installed capacity of 30 MW and an industrial park,the output of each part of a typical daily power system is extracted and verified by simulation results,therefore,the grid-connected capacity of wind power is improved,and the energy storage medium can respond accurately by eliminating the energy mixing,so as to optimize the storage medium capacity configuration The response times of typical day-and-middle-season flywheel energy storage unit decreased by 44.69%,49.83%,34.62% and 44.69% respectively,which effectively extended the service life of the energy storage unit The cost of the HESS was reduced by 33.23%,50.27%,61.40% and 24.65%,respectively.It is verified that the strategy can optimize the cost of the energy storage system while suppressing the fluctuation of wind power,and provide reference for the configuration of the energy storage system of the wind farm.