Energy caching method and system in multi-source energy interaction of microgrid

Abstract

The present invention relates to the technical field of microgrid energy control, and discloses an energy caching method and system in microgrid multi-source energy interaction, comprising: renewable energy power generation is input into a microgrid energy caching system, and the energy of renewable energy input into the microgrid energy caching system in the next cycle is predicted, the energy of renewable energy input into the microgrid energy caching system and the energy of the power supply system are allocated, the interaction of multi-source energy of the microgrid is completed, the control cycle and control strategy of the microgrid energy caching system are optimized, the voltage output of the microgrid energy caching system is stabilized, and the benefits of microgrid multi-source energy interaction and the results of grid optimization and grid-connected node voltage optimization by a feedback optimization module are fed back through a feedback module; the intelligent level of microgrid multi-source energy interaction is achieved.

Description

Technical Field

[0001] The invention relates to the technical field of microgrid energy control, and discloses an energy caching method and system in microgrid multi-source energy interaction. Background Art

[0002] There are still some shortcomings in the energy caching technology in the multi-source energy interaction of microgrids. Many new energy storage technologies (such as solid-state batteries and sodium-ion batteries) are still in the research and development stage, lack of verified long-term usage data, and the commercialization process is slow.

[0003] Microgrids are usually composed of a variety of equipment and technologies. The complexity of system integration makes the design and implementation process face technical challenges and increases the risk of failure. Existing energy management systems often lack intelligence and cannot efficiently adjust the supply and demand of different energy sources in real time, resulting in inefficient resource utilization. Some regions still rely heavily on traditional energy, which affects the application and integration of renewable energy. The current lack of industry standards and specifications leads to poor compatibility between products from different manufacturers, affecting the overall performance and reliability of the system. Although the cost of energy storage technology is gradually decreasing, the initial investment is still high, which poses economic pressure on small enterprises and community microgrids in particular.

[0004] For example, a Chinese patent application with the authorization announcement number CN113690925B discloses a method and system for optimizing energy interaction based on microgrids, including: dividing the distribution network into several microgrids according to the power supply relationship between the load and the distributed energy units and energy storage devices; predicting the risk of renewable energy units; obtaining the operating costs of energy storage devices and non-renewable energy units respectively; constructing a cost objective function based on the risk prediction results and operating costs, combined with the energy interaction costs between microgrids, and determining the state constraints and power constraints of the microgrids during energy interaction; solving the cost objective function when the state constraints and power constraints are met at the same time, and adjusting the power of each microgrid during energy interaction according to the solution results. The power of buying and selling electricity from other microgrids is introduced into the cost objective function, which can reduce the power of energy interaction between microgrids and power grids during peak hours while reducing the operating costs of microgrids.

[0005] The system of the above patent only divides and controls microgrids and distributed energy units by cost without considering the actual situation. It also integrates renewable energy management, which greatly increases the cost. It does not consider the voltage fluctuations of the grid-connected nodes and the errors between the energy storage output value and the actual output value when establishing the state constraints and power constraints during energy interaction, which greatly reduces the accuracy of the cost objective function. Summary of the invention

[0006] The purpose of this section is to summarize some aspects of embodiments of the present invention and briefly introduce some preferred embodiments. Some simplifications or omissions may be made in this section and the specification abstract and the invention title of this application to avoid blurring the purpose of this section, the specification abstract and the invention title, and such simplifications or omissions cannot be used to limit the scope of the present invention.

[0007] In order to solve the above technical problems, the main purpose of the present invention is to provide an energy caching method in multi-source energy interaction of a microgrid, comprising:

[0008] S1, renewable energy power generation is input into the microgrid energy cache system, and the energy input of renewable energy into the microgrid energy cache system in the next cycle is predicted;

[0009] S2, by allocating and predicting the energy of the next cycle of renewable energy input into the microgrid energy cache system and the energy of the power supply system, the interaction of multi-source energy in the microgrid is completed;

[0010] S3, optimize the control cycle and control strategy of the microgrid energy cache system to stabilize the voltage output of the microgrid energy cache system;

[0011] S4. Feedback the benefits of multi-source energy interaction in the microgrid and the results of grid optimization and grid-connected node voltage optimization by the feedback optimization module.

[0012] As a preferred solution of the energy caching method in the multi-source energy interaction of the microgrid of the present invention, wherein:

[0013] The renewable energy sources include wind power generation and photovoltaic power generation;

[0014] The wind power generation is used to store and manage wind power generation energy;

[0015] The photovoltaic power generation is used to store and manage photovoltaic power generation energy;

[0016] The wind power output power is predicted by establishing a wind power generation model, and the establishment method includes:

[0017] S1011. Collect historical data of wind power generation, and perform data cleaning and normalization processing on the historical data;

[0018] S1012, screening out the influencing data of the output power of the wind power generation unit through correlation analysis, and establishing a wind power generation model;

[0019] S1013. Train the wind power generation model using the training set, verify the wind power output power prediction value output by the wind power generation model using the verification set, and evaluate and optimize the prediction value of the wind power generation model.

[0020] As a preferred solution of the energy caching method in the multi-source energy interaction of the microgrid of the present invention, wherein:

[0021] The correlation analysis includes establishing a data sequence, standardizing the reference sequence and the comparison sequence, and calculating the absolute value difference to complete the correlation analysis of the historical data of wind power generation;

[0022] The data sequence calculation expression is as follows:

[0023]

[0024] in, is the reference sequence matrix, is the first set of comparison sequence matrix, is the Nth group comparison sequence matrix, is the first comparison data of the first comparison sequence, is the Mth comparison data of the Nth comparison sequence, is the first reference data of the reference sequence, is the Mth reference data of the reference sequence, N is the number of sequence groups, and M is the number of data groups;

[0025] The absolute value difference calculation expression is as follows:

[0026]

[0027]

[0028] in, is the maximum difference between the comparison sequence matrix and the reference sequence matrix, The minimum difference between the comparison sequence matrix and the reference sequence matrix;

[0029] The photovoltaic power generation model predicts the correlation coefficient between meteorological factors and photovoltaic power generation output power. The calculation expression is as follows:

[0030]

[0031] Among them, Cov() is the covariance operation, γ is the correlation coefficient between meteorological factors and photovoltaic power output power, is the meteorological factor data, is the photovoltaic power output power, Ver[] is the arithmetic operator, and i is the data group number label.

[0032] As a preferred solution of the energy caching method in the multi-source energy interaction of the microgrid of the present invention, wherein:

[0033] By establishing a dynamic model of the microgrid energy cache system, the allocation of the energy of the renewable energy input microgrid energy cache system and the energy of the power supply system is realized. The calculation expression is as follows:

[0034]

[0035] in, To deploy the energy of the microgrid energy cache system, is the energy of the unallocated microgrid energy cache system, Microgrid energy cache system efficiency for renewable energy input, Energy efficiency for renewable energy output, Charging capacity for renewable energy, The amount of charge for the power supply system, Input microgrid energy cache system efficiency to the power supply system, Output energy efficiency for the power supply system, Output power to the power supply system. To maintain dynamic equilibrium time, Export electricity stored by renewable energy to the power supply system.

[0036] As a preferred solution of the energy caching method in the multi-source energy interaction of the microgrid of the present invention, wherein:

[0037] Optimizing the control cycle and control strategy of the microgrid energy cache system through the grid optimization unit;

[0038] The voltage output of the microgrid energy cache system is stabilized and the network transmission loss is reduced through the grid-connected node voltage optimization unit.

[0039] As a preferred solution of the energy caching method in the multi-source energy interaction of the microgrid of the present invention, wherein:

[0040] The grid-connected node voltage optimization unit optimization method comprises:

[0041] S301, establishing a state equation to map the global state of the microgrid energy cache system in a single cycle, wherein the state equation includes global node voltage state information of the microgrid energy cache system;

[0042] S302, establishing a voltage management model;

[0043] S303, issuing a control instruction set to the microgrid to achieve maximum voltage output of renewable energy;

[0044] S304: The reward function is used to train the voltage management model.

[0045] As a preferred solution of the energy caching method in the multi-source energy interaction of the microgrid of the present invention, wherein:

[0046] The voltage management model is used to ensure the normal operation of the microgrid energy cache system while reducing voltage fluctuations and network transmission losses. The voltage management model calculation expression is as follows:

[0047]

[0048] Among them, min() is the minimum function, is the voltage fluctuation amplitude of the ith node, is the network voltage transmission loss of the ith node, T is the current instruction cycle, m is the total number of instruction cycles, and n is the number of grid-connected nodes of the hybrid microgrid.

[0049] As a preferred solution of the energy caching method in the multi-source energy interaction of the microgrid of the present invention, wherein:

[0050] The control instruction set includes control of the maximum voltage output of the renewable energy source;

[0051] The reward function determines the importance of the control instruction corresponding to the control target by setting the reward coefficient. The reward function calculation expression is as follows:

[0052]

[0053] in, Output voltage management model optimization instructions for reward function, is the actual value of the grid-connected node voltage, is the grid-connected node voltage estimate, β is the grid-connected point voltage reward coefficient, α is the network loss reward coefficient, and L is the total number of cycles.

[0054] The energy cache system in the multi-source energy interaction of the microgrid includes:

[0055] A renewable energy module, comprising a wind power generation unit and a photovoltaic power generation unit, wherein the wind power generation unit is used to store and manage wind power generation energy, and the photovoltaic power generation unit is used to store and manage photovoltaic power generation energy;

[0056] An energy storage module, comprising an energy storage input unit, an energy storage output unit and an energy management unit, wherein the energy storage input unit is used to manage the energy stored in the renewable energy module, the energy storage output unit is used to output the stored energy, and the energy management unit is used to manage the output energy of the energy storage output unit;

[0057] Energy dispatch module, including renewable dispatch unit, load dispatch power supply unit and grid interactive dispatch unit;

[0058] An optimization module, including a power grid optimization unit and a grid-connected node voltage optimization unit, wherein the power grid optimization unit is used to optimize the control cycle and control strategy of the microgrid energy cache system, and the grid-connected node voltage optimization unit is used to stabilize the voltage output of the microgrid energy cache system and reduce network transmission loss;

[0059] The feedback module includes benefit feedback and control strategy feedback, wherein the benefit feedback is used to calculate the microgrid energy cache benefits and electricity transactions, and the control strategy feedback is used to feed back the optimization module's results of grid optimization and grid-connected node voltage optimization.

[0060] As a preferred solution of the energy cache system in the multi-source energy interaction of the microgrid of the present invention, wherein:

[0061] The energy storage module includes an energy storage management model, and the energy storage management model includes photovoltaic output power constraints, wind power output power constraints, inverter power constraints, electricity trading constraints and energy storage system constraints;

[0062] The photovoltaic output power constraint is used to control the photovoltaic power generation source to meet its own charging and discharging dynamic characteristics;

[0063] The wind power output power constraint is used to control the wind power generation source to meet its own charging and discharging dynamic characteristics;

[0064] The inverter power constraint is used to control PWM operation safety;

[0065] The electricity transaction constraint is used to control the peak value of electricity purchase and sale between the hybrid microgrid and the distribution network;

[0066] The energy storage system constraints are used to control the microgrid energy cache system to meet its own charging and discharging dynamic characteristics.

[0067] Beneficial effects of the present invention:

[0068] The present invention sets up renewable energy management to intelligently predict renewable energy output, timely adjusts the energy of renewable energy input into the microgrid, improves the input energy intelligence level of the energy caching system, improves the stability of the grid-connected node voltage by setting a reward function, reduces the loss of network transmission, and sets up a complete feedback module, which not only retains the microgrid energy caching income and electricity transaction bill, but is also used to feedback the results of grid optimization and grid-connected node voltage optimization. BRIEF DESCRIPTION OF THE DRAWINGS

[0069] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative labor. Among them:

[0070] Figure 1 It is a flow chart of the energy caching method in multi-source energy interaction of a microgrid of the present invention;

[0071] Figure 2 It is a composition diagram of the energy cache system in the multi-source energy interaction of the microgrid of the present invention;

[0072] Figure 3 It is an optimization process of a grid-connected node voltage optimization unit in an energy caching method in multi-source energy interaction of a microgrid of the present invention;

[0073] Figure 4 It is a structural topological diagram of a wind power generation unit of an energy cache system in a multi-source energy interaction of a microgrid of the present invention;

[0074] Figure 5 This is a topological diagram of the photovoltaic power generation unit structure of the energy cache system in the multi-source energy interaction of the microgrid of the present invention. DETAILED DESCRIPTION

[0075] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the accompanying drawings.

[0076] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0077] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive with other embodiments.

[0078] Embodiment 1

[0079] like Figure 1 As shown, the energy caching method in the multi-source energy interaction of the microgrid includes:

[0080] S1, renewable energy power generation is input into the microgrid energy cache system, and the energy input of renewable energy into the microgrid energy cache system in the next cycle is predicted;

[0081] Renewable energy includes wind power and photovoltaic power generation;

[0082] Among them, wind power generation is used to store and manage renewable energy wind power generation energy, and photovoltaic power generation is used to store and manage photovoltaic power generation energy.

[0083] Furthermore, the wind power output power is predicted by establishing a wind power generation model, and the steps of establishing the wind power generation model include:

[0084] S1011. Collect historical data of wind power generation, and perform data cleaning and normalization processing on the historical data; the historical data includes historical wind power output, hub height, historical wind speed, wind direction, relative humidity, rainfall and air pressure;

[0085] S1012, screening out the influencing data of the output power of the wind power generation unit through correlation analysis, and establishing a wind power generation model;

[0086] The correlation analysis includes establishing a data sequence, standardizing the reference sequence and the comparison sequence, and calculating the absolute value difference to complete the correlation analysis of the historical data of wind power generation;

[0087] Wherein, the reference sequence is standard data or correct data;

[0088] The comparison sequence is historical data or unprocessed data;

[0089] The data sequence calculation expression is as follows:

[0090]

[0091] in, is the reference sequence matrix, is the first set of comparison sequence matrix, is the Nth group comparison sequence matrix, is the first comparison data of the first comparison sequence, is the Mth comparison data of the Nth comparison sequence, is the first reference data of the reference sequence, is the Mth reference data of the reference sequence, N is the number of sequence groups, and M is the number of data groups;

[0092] Perform matrix transformation on the data series through mean normalization and range normalization;

[0093] The absolute value difference calculation expression is as follows:

[0094]

[0095]

[0096] in, is the maximum difference between the comparison sequence matrix and the reference sequence matrix, The minimum difference between the comparison sequence matrix and the reference sequence matrix;

[0097] Furthermore, The calculation method is to compare the reference data of the first row and the first column with the comparison data of the first row and the second column, and then compare the data of the first row and the first column with the comparison data of the first row and the third column, and so on. Similarly, the reference data of the second row and the first column is compared with the comparison data of the second row and the second column, and so on.

[0098] S1013, training the wind power generation model through the training set, and then verifying the wind power output power prediction value output by the wind power generation model through the verification set, and evaluating and optimizing the prediction value of the wind power generation model;

[0099] The calculation expression of the wind power generation model is as follows:

[0100]

[0101] in, is the feature map, is the convolution kernel, is the input wind power generation historical data, is the convolution operator, is the bias, is the activation function;

[0102] The predicted value of the wind power generation model is evaluated by the loss function, which is calculated by the mean square error.

[0103] The photovoltaic power generation model predicts the correlation coefficient between meteorological factors and photovoltaic power generation output power. The calculation expression is as follows:

[0104]

[0105] Among them, Cov() is the covariance operation, γ is the correlation coefficient between meteorological factors and photovoltaic power output power, is the meteorological factor data, is the photovoltaic power output power, Ver[] is the arithmetic operator, and i is the data group number label.

[0106] S2, by allocating and predicting the energy of the next cycle of renewable energy input into the microgrid energy cache system and the energy of the power supply system, the interaction of multi-source energy in the microgrid is completed;

[0107] By establishing a dynamic model of the microgrid energy cache system, the allocation of renewable energy input to the microgrid energy cache system and the energy of the power supply system is realized. The calculation expression is as follows:

[0108]

[0109] in, To deploy the energy of the microgrid energy cache system, is the energy of the unallocated microgrid energy cache system, Microgrid energy cache system efficiency for renewable energy input, Energy efficiency for renewable energy output, Charging capacity for renewable energy, The amount of charge for the power supply system, Input microgrid energy cache system efficiency to the power supply system, Output energy efficiency for the power supply system, Output power to the power supply system. To maintain dynamic equilibrium time, Export electricity stored by renewable energy to the power supply system.

[0110] Furthermore, the sum of the amount of electricity charged by the renewable energy source and the amount of electricity charged by the power supply system does not exceed the maximum storage capacity of the microgrid energy cache system;

[0111] The charging power of renewable energy shall not exceed the upper limit of power input, and charging with renewable energy shall be the main means of charging;

[0112] The energy storage of the microgrid energy cache system shall not be less than ten percent of the total capacity.

[0113] S3, optimize the control cycle and control strategy of the microgrid energy cache system to stabilize the voltage output of the microgrid energy cache system;

[0114] Optimizing the control cycle and control strategy of the microgrid energy cache system through the grid optimization unit;

[0115] Stabilize the voltage output of the microgrid energy cache system through the grid-connected node voltage optimization unit and reduce network transmission losses;

[0116] like Figure 3 As shown, the optimization steps of the grid-connected node voltage optimization unit include:

[0117] S301, establishing a state equation to map the global state of the microgrid energy cache system in a single cycle, wherein the state equation includes global node voltage state information of the microgrid energy cache system;

[0118] The global state includes the voltage magnitude and change of each global node;

[0119] S302, establishing a voltage management model;

[0120] Furthermore, the voltage management model is used to ensure the normal operation of the microgrid energy cache system while reducing voltage fluctuations and network transmission losses. The calculation expression of the voltage management model is as follows:

[0121]

[0122] Among them, min() is the minimum function, is the voltage fluctuation amplitude of the ith node, is the network voltage transmission loss of the ith node, T is the current instruction cycle, m is the total number of instruction cycles, and n is the number of grid-connected nodes of the hybrid microgrid;

[0123] The voltage management model manages voltage fluctuations and network transmission losses through constraints. Taking one day as an example, a day contains multiple control instruction cycles. T is the voltage fluctuation amplitude and network voltage transmission loss of the global node under the current instruction cycle. By calculating multiple control instruction cycles in one day, the voltage of the grid-connected node is adjusted.

[0124] S303, issuing a control instruction set to the microgrid to achieve maximum voltage output of renewable energy;

[0125] The control instruction set includes controlling the maximum voltage output of renewable energy, that is, controlling the maximum voltage output of renewable energy by controlling the flow direction of renewable energy;

[0126] If the renewable energy in the microgrid energy cache system is less than the load voltage demand, all the renewable energy will be used as system voltage output, and the power supply system will be used to supplement the microgrid energy cache system stored energy and make up for the lack of load energy. If the renewable energy in the microgrid energy cache system is equal to the load voltage demand, all the renewable energy will be used as system voltage output. If the renewable energy in the microgrid energy cache system is greater than the load voltage demand, all the renewable energy will be used as system voltage output, and the remaining energy will be input into the microgrid energy cache system.

[0127] S304, the reward function is used to train the voltage management model;

[0128] The reward function determines the importance of the control instruction to the control target by setting the reward coefficient. The reward function calculation expression is as follows:

[0129]

[0130] in, Output voltage management model optimization instructions for reward function, is the actual value of the grid-connected node voltage, is the grid-connected node voltage estimate, β is the grid-connected point voltage reward coefficient, α is the network loss reward coefficient, and L is the total number of cycles.

[0131] The reward function is not a strict mathematical operation, that is, by reducing the control instruction set to control the renewable energy output voltage strategy, resulting in grid-connected node voltage fluctuations and reducing network transmission losses, an experience action guidance mechanism is set, that is, calculation Help reduce the difference between the actual output voltage of renewable energy and the estimated output voltage, so as to facilitate timely adjustment of the grid connection point voltage and adjust it through the network loss reward coefficient α Therefore, the reward function is not a strict mathematical operation, but is expressed through the underlying logic as the reward function is the amplitude of the global node voltage fluctuation , network voltage transmission loss and the output voltage fluctuation of renewable energy.

[0132] S4. Feedback the benefits of multi-source energy interaction in the microgrid and the results of grid optimization and grid-connected node voltage optimization by the feedback optimization module.

[0133] Embodiment 2

[0134] like Figure 2 As shown, the energy cache system in the multi-source energy interaction of the microgrid includes:

[0135] A renewable energy module, comprising a wind power generation unit and a photovoltaic power generation unit, wherein the wind power generation unit is used to store and manage renewable energy wind power generation energy, and the photovoltaic power generation unit is used to store and manage photovoltaic power generation energy;

[0136] Further, such as Figure 4 As shown, the wind power generation unit includes a wind turbine, a gearbox, AC / DC, DC / AC, a step-up transformer and an AC busbar of a microgrid. The wind drives the blades to generate mechanical energy which is transmitted to the gearbox through the wind turbine. The mechanical energy is then transmitted to the induction generator after being controlled by the wind turbine gearbox. The generator converts the mechanical energy of the main shaft into electrical energy which is transmitted to the grid through the generator stator and rotor.

[0137] Furthermore, if the actual operating wind speed of the wind turbine is less than the access wind speed of the wind turbine set, the actual output power of the wind turbine set is 0. If the actual operating wind speed of the wind turbine is greater than the access wind speed of the wind turbine set and less than the safe operating rated wind speed of the wind turbine set, the actual output power of the wind turbine is the wind speed proportional coefficient multiplied by the rated output power of the wind turbine set under normal conditions. If the actual operating wind speed of the wind turbine is greater than the maximum cut-off wind speed of the wind turbine set, in order to ensure the safety of the wind turbine, the actual power output is also zero.

[0138] Further, such as Figure 5 As shown, the photovoltaic power generation unit includes a photovoltaic array, a DC / DC chopper circuit, a PWM, and a filter. Since the photovoltaic array is greatly affected by light intensity and temperature, the active power is controlled by setting a DC / DC chopper circuit. Since the photovoltaic array power generation is connected to the grid, the active power is output through maximum power point tracking, and the photovoltaic power generation power is controlled by PWM and DC / DC chopper circuits.

[0139] An energy storage module, comprising an energy storage input unit, an energy storage output unit and an energy management unit, wherein the energy storage input unit is used to manage the energy stored in the renewable energy module, the energy storage output unit is used to output the stored energy, and the energy management unit is used to manage the output energy of the energy storage output unit;

[0140] Among them, when the output power of the microgrid energy cache system is higher than the load demand, the energy cache system will store excess electric energy and release electric energy when the system power is insufficient. Through the energy storage input unit, the wind power generation unit and the photovoltaic power generation unit can work at full load to the maximum extent, thereby improving the absorption capacity of renewable energy.

[0141] Further, the energy storage output unit is used to output energy and control the microgrid energy cache system to enter a discharge mode, including a DC side and an AC side where energy flows bidirectionally;

[0142] Furthermore, the energy management unit is used to manage the control strategy of the input power and output power of the microgrid energy cache system, and the control strategy is used to constrain the strategy of the input power of the microgrid energy cache system and the strategy of the output power of the microgrid energy cache system;

[0143] Furthermore, the control strategies include power balancing strategy, demand-side response strategy, and energy storage management model;

[0144] The power balancing strategy is used to maintain the real-time dynamic power balance of the microgrid energy cache system, ensure the power balance of the AC side of the microgrid, and then achieve the balance of the microgrid energy cache system by controlling the power balance of the DC side. Furthermore, the power transmitted from the DC side to the AC side multiplied by the power conversion efficiency of the converter and the input power of renewable energy is dynamically balanced with the sum of the DC side output power and the load demand power;

[0145] The power conversion between the DC side and the AC side can be bidirectional;

[0146] Furthermore, the demand-side response strategy is used to control the load demand to be connected preferentially when the microgrid energy cache system is in surplus, and the constraints include that the load demand power increase in a single cycle is less than 50% of the original load demand power;

[0147] Furthermore, the energy storage management model includes photovoltaic output power constraints, wind power output power constraints, inverter power constraints, electricity trading constraints, and energy storage system constraints;

[0148] Photovoltaic output power constraints are used to control the photovoltaic power generation source to meet its own charging and discharging dynamic characteristics;

[0149] Wind power output power constraints are used to control wind power generation to meet its own charging and discharging dynamic characteristics;

[0150] Inverter power constraints are used to control PWM operation safety;

[0151] The power transaction constraint is used to control the peak value of power purchase and sale between the hybrid microgrid and the distribution network;

[0152] Energy storage system constraints are used to control the microgrid energy cache system to meet its own charging and discharging dynamic characteristics;

[0153] Energy dispatch module, including renewable dispatch unit, load dispatch power supply unit and grid interactive dispatch unit;

[0154] Further, the renewable deployment unit includes a wind power generation model and a photovoltaic power generation model;

[0155] The output power of photovoltaic array is predicted by photovoltaic power generation model. The wind power generation model is established based on the output data of photovoltaic power station, meteorological data, horizontal irradiance, horizontal scattered irradiance, wind speed ambient temperature, relative humidity and wind strength input. Then, data cleaning, deletion of outliers in the data set and supplementation of missing values ​​are performed. Data standardization can accelerate the convergence speed of gradient descent and improve the performance of the prediction model. Through data partitioning, the output data of photovoltaic power station, meteorological data, horizontal irradiance, horizontal scattered irradiance, wind speed ambient temperature, relative humidity, wind strength input and other data are divided into training set, test set and validation set. The photovoltaic power generation model is established through deep learning algorithm, and the output power of photovoltaic power generation unit is predicted. Finally, the optimal parameters and structure of LSTM model are found through genetic algorithm, and the photovoltaic power generation model is trained with the training set, and then the correctness of the output prediction value of photovoltaic power generation model is verified with the validation set. Finally, the prediction is evaluated and optimized by evaluation index; the evaluation index is calculated by mean square error.

[0156] Furthermore, the wind power generation model is constrained by the wind power generation unit. Through correlation analysis, the accuracy of wind power generation model prediction is improved. First, a reference data set is set, and the reference sequence and the comparison sequence are standardized. Then, the difference between the absolute values ​​of the corresponding elements in the reference data set and the comparison data set is calculated. Finally, the correlation coefficient is calculated to compare the correlation between the real-time electric power time series data of wind power generation and the historical wind power time series data, and the influencing factors of the output power of the wind power generation unit are screened out.

[0157] Based on the historical wind power output, hub height, historical wind speed, wind direction, relative humidity, rainfall and air pressure, the data was cleaned and normalized, and the influencing data of the wind power generation unit output power was screened out by correlation analysis. A wind power generation model was established, and the model was trained using the training set. The wind power output power prediction value output by the wind power generation model was then verified using the validation set, and the predicted value of the wind power generation model was evaluated using the root mean square error.

[0158] Establish a wind power generation model through neural convolutional network and predict the wind power generation output power;

[0159] The reference dataset includes historical wind power time series data;

[0160] Normalization methods include mean normalization and range normalization;

[0161] The comparison dataset includes real-time wind power time series data.

[0162] Further, the load dispatching unit is used to dispatch charging loads, such as car charging;

[0163] The grid interactive dispatching unit is used to ensure the balance of dynamic characteristics of charge and discharge, charge and discharge ratings and real-time state of charge of the microgrid energy cache system;

[0164] An optimization module, including a power grid optimization unit and a grid-connected node voltage optimization unit, wherein the power grid optimization unit is used to optimize the control cycle and control strategy of the microgrid energy cache system, and the grid-connected node voltage optimization unit is used to stabilize the voltage output of the microgrid energy cache system and improve network transmission loss;

[0165] The grid-connected node voltage optimization unit optimizes the global state of the microgrid energy cache system in a single cycle by establishing a state equation, establishing a voltage management model, and then issuing a control instruction set to the microgrid to achieve the maximum output of renewable energy. The reward function is used to train the voltage management model. By adding the reward function, the voltage management model can learn the control strategy of the microgrid energy cache system more quickly.

[0166] The feedback module includes benefit feedback and control strategy feedback, wherein the benefit feedback is used to calculate the microgrid energy cache benefits and electricity transactions, and the control strategy feedback is used to feed back the optimization module's results of grid optimization and grid-connected node voltage optimization.

[0167] Embodiment 3

[0168] A computer device includes a memory for storing instructions and a processor for executing the instructions, so that the device executes an energy caching method for realizing multi-source energy interaction in a microgrid.

[0169] Embodiment 4

[0170] A computer-readable storage medium stores a computer program, which, when executed, implements an energy caching method in multi-source energy interaction of a microgrid.

[0171] Importantly, it should be noted that the construction and arrangement of the present application shown in a plurality of different exemplary embodiments are only exemplary. Although only two embodiments are described in detail in this disclosure, it should be readily understood by those who refer to this disclosure that many modifications are possible, for example, the size, scale, structure, shape and ratio of various elements, and parameter values ​​(e.g., temperature, pressure, etc.), installation arrangement, use of materials, color, directional changes, etc., without substantially departing from the novel teachings and advantages of the subject matter described in the application. For example, the element shown as integrally formed can be composed of multiple parts or elements, the position of the element can be inverted or otherwise changed, and the nature or number or position of the discrete element can be changed or changed. Therefore, all such modifications are intended to be included in the scope of the present invention. The order or sequence of any process or method steps can be changed or reordered according to alternative embodiments. Any "device plus function" clause is intended to cover the structure of the execution function described in this article, and is not only structurally equivalent but also equivalent structure. Without departing from the scope of the present invention, other replacements, modifications, changes and omissions can be made in the design, operating conditions and arrangement of the exemplary embodiment. Therefore, the invention is not limited to a specific embodiment, but extends to numerous modifications still falling within the scope of the appended claims.

[0172] Additionally, in order to provide a concise description of exemplary embodiments, all features of an actual embodiment may not be described (ie, those features that are not relevant to the best mode presently contemplated for carrying out the invention or those features that are not relevant to implementing the invention).

[0173] It should be understood that in the development of any actual implementation, as in any engineering or design project, numerous implementation-specific decisions may be made. Such a development effort may be complex and time-consuming, but for those of ordinary skill having the benefit of this disclosure, the development effort will be a routine task of design, fabrication, and production without undue experimentation.

[0174] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. An energy caching method in multi-source energy interaction of a microgrid, characterized by: include: S1, renewable energy power generation is input into the microgrid energy cache system, and the energy input of renewable energy into the microgrid energy cache system in the next cycle is predicted; The renewable energy sources include wind power generation and photovoltaic power generation; The wind power generation is used to store and manage wind power generation energy; The photovoltaic power generation is used to store and manage photovoltaic power generation energy; The wind power output power is predicted by establishing a wind power generation model, and the establishment method includes: S1011. Collect historical data of wind power generation, and perform data cleaning and normalization processing on the historical data; S1012, screening out the influencing data of the output power of the wind power generation unit through correlation analysis, and establishing a wind power generation model; S1013, training the wind power generation model through the training set, verifying the wind power output power prediction value output by the wind power generation model through the verification set, and evaluating and optimizing the prediction value of the wind power generation model; S2, by allocating and predicting the energy of the next cycle of renewable energy input into the microgrid energy cache system and the energy of the power supply system, the interaction of multi-source energy in the microgrid is completed; S3, optimize the control cycle and control strategy of the microgrid energy cache system to stabilize the voltage output of the microgrid energy cache system; Optimizing the control cycle and control strategy of the microgrid energy cache system through the grid optimization unit; Stabilize the voltage output of the microgrid energy cache system through the grid-connected node voltage optimization unit and reduce network transmission losses; The grid-connected node voltage optimization unit optimization method comprises: S301, establishing a state equation to map the global state of the microgrid energy cache system in a single cycle, wherein the state equation includes global node voltage state information of the microgrid energy cache system; S302, establishing a voltage management model; S303, issuing a control instruction set to the microgrid to achieve maximum voltage output of renewable energy; S304, the reward function is used to train the voltage management model; The voltage management model is used to ensure the normal operation of the microgrid energy cache system while reducing voltage fluctuations and network transmission losses. The voltage management model calculation expression is as follows: ； Among them, min() is the minimum function, is the voltage fluctuation amplitude of the ith node, is the network voltage transmission loss of the ith node, T is the current instruction cycle, m is the total number of instruction cycles, and n is the number of grid-connected nodes of the hybrid microgrid; S4. Feedback the benefits of multi-source energy interaction in the microgrid and the results of grid optimization and grid-connected node voltage optimization by the feedback optimization module.

2. The energy caching method in microgrid multi-source energy interaction according to claim 1 is characterized in that: The correlation analysis includes establishing a data sequence, standardizing the reference sequence and the comparison sequence, and calculating the absolute value difference to complete the correlation analysis of the historical data of wind power generation; The data sequence calculation expression is as follows: ； in, is the reference sequence matrix, is the first set of comparison sequence matrix, is the Nth group comparison sequence matrix, is the first comparison data of the first comparison sequence, is the Mth comparison data of the Nth comparison sequence, is the first reference data of the reference sequence, is the Mth reference data of the reference sequence, N is the number of sequence groups, and M is the number of data groups; The absolute value difference calculation expression is as follows: ； ； in, is the maximum difference between the comparison sequence matrix and the reference sequence matrix, The minimum difference between the comparison sequence matrix and the reference sequence matrix; The photovoltaic power generation model predicts the correlation coefficient between meteorological factors and photovoltaic power generation output power. The calculation expression is as follows: ； Among them, Cov() is the covariance operation, γ is the correlation coefficient between meteorological factors and photovoltaic power output power, is the meteorological factor data, is the photovoltaic power output power, Ver[] is the arithmetic operator, and i is the data group number label.

3. The energy caching method in microgrid multi-source energy interaction according to claim 2 is characterized in that: By establishing a dynamic model of the microgrid energy cache system, the allocation of the energy of the renewable energy input microgrid energy cache system and the energy of the power supply system is realized. The calculation expression is as follows: ； in, To deploy the energy of the microgrid energy cache system, is the energy of the unallocated microgrid energy cache system, Microgrid energy cache system efficiency for renewable energy input, Energy efficiency for renewable energy output, Charging capacity for renewable energy, The amount of charge for the power supply system, Input microgrid energy cache system efficiency to the power supply system, Output energy efficiency for the power supply system, Output power to the power supply system. To maintain dynamic equilibrium time, Export electricity stored by renewable energy to the power supply system.

4. The energy caching method in microgrid multi-source energy interaction according to claim 3 is characterized in that: The control instruction set includes control of the maximum voltage output of the renewable energy source; The reward function determines the importance of the control instruction corresponding to the control target by setting the reward coefficient. The reward function calculation expression is as follows: ； in, Output voltage management model optimization instructions for reward function, is the actual value of the grid-connected node voltage, is the grid-connected node voltage estimate, β is the grid-connected point voltage reward coefficient, α is the network loss reward coefficient, and L is the total number of cycles.

5. An energy caching system in a microgrid multi-source energy interaction, used to implement the energy caching method in a microgrid multi-source energy interaction according to any one of claims 1 to 4, characterized in that: include: A renewable energy module, comprising a wind power generation unit and a photovoltaic power generation unit, wherein the wind power generation unit is used to store and manage wind power generation energy, and the photovoltaic power generation unit is used to store and manage photovoltaic power generation energy; An energy storage module, comprising an energy storage input unit, an energy storage output unit and an energy management unit, wherein the energy storage input unit is used to manage the energy stored in the renewable energy module, the energy storage output unit is used to output the stored energy, and the energy management unit is used to manage the output energy of the energy storage output unit; Energy dispatch module, including renewable dispatch unit, load dispatch power supply unit and grid interactive dispatch unit; An optimization module, including a power grid optimization unit and a grid-connected node voltage optimization unit, wherein the power grid optimization unit is used to optimize the control cycle and control strategy of the microgrid energy cache system, and the grid-connected node voltage optimization unit is used to stabilize the voltage output of the microgrid energy cache system and reduce network transmission loss; The feedback module includes benefit feedback and control strategy feedback, wherein the benefit feedback is used to calculate the microgrid energy cache benefits and electricity transactions, and the control strategy feedback is used to feed back the optimization module's results of grid optimization and grid-connected node voltage optimization.

6. The energy cache system in the microgrid multi-source energy interaction according to claim 5 is characterized in that: The energy storage module includes an energy storage management model, and the energy storage management model includes photovoltaic output power constraints, wind power output power constraints, inverter power constraints, electricity trading constraints and energy storage system constraints; The photovoltaic output power constraint is used to control the photovoltaic power generation source to meet its own charging and discharging dynamic characteristics; The wind power output power constraint is used to control the wind power generation source to meet its own charging and discharging dynamic characteristics; The inverter power constraint is used to control PWM operation safety; The electricity transaction constraint is used to control the peak value of electricity purchase and sale between the hybrid microgrid and the distribution network; The energy storage system constraints are used to control the microgrid energy cache system to meet its own charging and discharging dynamic characteristics.

Images