Power grid frequency modulation and peak regulation method and device based on gravity energy storage and medium

Abstract

The invention relates to a power grid frequency modulation and peak regulation method and device based on gravity energy storage, and a medium. The method comprises the following steps: training an ARIMA model and an LSTM model by using historical load data of a power grid and historical compensated electric energy; monitoring a load state of a power grid according to a real-time load monitoring module, and predicting electric energy needing to be compensated by using an ARIMA model and an LSTM model according to the load state; according to the electric energy which is predicted by the ARIMA model or the LSTM model and needs to be compensated and the multiple linear regression model, an environment correction coefficient is obtained, a control signal that the height of the heavy object needs to be adjusted is obtained, and according to the control signal and real-time feedback of the real-time load monitoring module, the electric lifting device is controlled to adjust the height of the heavy object; the weight is released, and potential energy generated in the weight falling process is converted into electric energy through an energy conversion device; and the generated electric energy is transmitted to the power grid through the power transmission device to realize peak regulation and frequency modulation of the power grid.

Description

Technical Field

[0001] The invention relates to a method, equipment and medium for frequency and peak regulation of a power grid based on gravity energy storage, and belongs to the field of energy technology. Background Art

[0002] With the continuous growth of energy demand and the continuous development of power systems, the stable operation and efficient management of power grids have become an important challenge. In power systems, load demand usually fluctuates over time, while power generation capacity requires a certain response time to adjust. This results in that in some periods, the load of the power grid may exceed the power generation capacity, resulting in tight power supply; while in other periods, the power generation capacity may exceed the load demand, resulting in power waste.

[0003] In order to balance the load demand and power generation capacity in the power grid and ensure the stability and reliability of power supply, the energy storage peak load regulation and frequency regulation principle came into being. The core idea of ​​this principle is to achieve optimal control of the power system by converting electrical energy into other forms of energy (such as potential energy, thermal energy, etc.) and converting it back to electrical energy when needed.

[0004] In the existing technology, the frequency and peak regulation of the power grid mainly rely on battery energy storage systems and pumped storage power stations. Battery energy storage systems store and release electrical energy through electrochemical reactions, and have the advantages of rapid response and flexible deployment, but they also face problems such as limited battery life, high costs, and environmental pollution. Pumped storage power stations store energy by pumping water to a high place and then release energy through hydropower generation. They have the advantages of large-scale energy storage capacity and long-term stable operation, but their construction period is long, the investment is huge, and they are greatly restricted by geographical conditions, making it difficult to promote them on a large scale in cities and other power-intensive areas. In addition, other energy storage methods such as compressed air energy storage and flywheel energy storage are also used to a certain extent in the frequency and peak regulation of the power grid, but each has problems such as complex technology, high cost, and low efficiency.

[0005] The ARIMA model, full name Autoregressive Integrated Moving Average Model, is one of the time series prediction and analysis methods. Long Short-Term Memory (LSTM) is a special recurrent neural network (RNN) structure, which is mainly used to process and predict long-term dependency problems in time series data. LSTM was proposed by Hochreiter and Schmidhuber in 1997, and has been improved and promoted by many researchers since then. LSTM has achieved remarkable success in speech recognition, text generation, machine translation, time series prediction, and stock market prediction.

[0006] Prior art, such as the Chinese patent with patent number "CN117833319A", discloses an Internet of Things-based power peak-shaving system. The system includes: a prediction module, which is used to predict the new energy power generation capacity and power grid load demand using a machine learning algorithm, and transmit the prediction results to the peak-shaving module; an Internet of Things module, including sensors and intelligent metering devices installed at the power grid measurement node, for real-time monitoring of power grid operation data; transmitting the monitored power grid operation data to the peak-shaving module; wherein the power grid operation data includes energy flow, frequency, and voltage; a peak-shaving module, which is used to receive the prediction results provided by the prediction module and the power grid operation data provided by the Internet of Things module; according to the prediction results and the power grid operation data, a mixed integer linear programming model is used to determine the peak-shaving strategy; according to the peak-shaving strategy, the power output of the power grid is adjusted and the charge and discharge strategy of the energy storage module is formulated; according to the charge and discharge strategy, a charge and discharge instruction is sent to the energy storage module; the energy storage module includes a battery energy storage submodule and a pumped energy storage submodule; used to adjust the charge and discharge according to the charge and discharge instructions sent by the peak-shaving module to support the load and supply balance of the power grid.

[0007] The problem with the above-mentioned prior art is that the cost of battery energy storage systems is relatively high, especially high-performance lithium-ion batteries. This is mainly due to the cost of battery materials, the complexity of the production process, and the high requirements of the battery management system. Although the life of battery energy storage systems is constantly increasing, their life is still limited compared to other energy storage methods. For example, the life of lithium-ion batteries is usually around 5-8 years and needs to be replaced regularly. Pumped energy storage systems require specific geographical conditions, such as the height difference between the upper and lower reservoirs and sufficient water resources. This greatly limits the construction and site selection of pumped energy storage systems. Compared with other energy storage methods, pumped energy storage has a lower energy density. This means that in order to store the same amount of energy, pumped energy storage systems need to occupy a larger space. Summary of the invention

[0008] In order to solve the above problems existing in the prior art, the present invention proposes a method, device and medium for frequency and peak regulation of a power grid based on gravity energy storage.

[0009] The technical solution of the present invention is as follows:

[0010] In one aspect, the present invention provides a method for frequency and peak regulation of a power grid based on gravity energy storage, comprising the following steps:

[0011] Use the historical load data of the power grid and the historical compensated electric energy to train the ARIMA model and LSTM model;

[0012] Monitor the load status of the power grid according to the real-time load monitoring module, and use the ARIMA model and LSTM model to predict the electric energy that needs to be compensated according to the load status;

[0013] According to the electric energy that needs to be compensated predicted by the ARIMA model or the LSTM model, and the environmental correction coefficient obtained by the multivariate linear regression model, a control signal that the height of the heavy object needs to be adjusted is obtained, and according to the real-time feedback of the control signal and the real-time load monitoring module, the electric lifting device is controlled to adjust the height of the heavy object;

[0014] Release the weight and convert the potential energy generated by the falling weight into electrical energy through the energy conversion device;

[0015] The generated electric energy is transmitted to the power grid through the power transmission device to achieve peak load and frequency regulation of the power grid.

[0016] As a preferred implementation, the method for predicting the electric energy that needs to be compensated by the ARIMA model or LSTM model is:

[0017] Filter abnormal data in the load data collected in real time by the load sensor of the real-time load monitoring module, and normalize the load data;

[0018] Based on the historical load data and the current load data, the ARIMA model and the LSTM model are input to predict the electric energy that needs to be compensated:

[0019] L demand (t) = f(L hist (tn), L current (t),θ);

[0020] Among them, L demand (t) represents the electric energy predicted by the ARIMA model or LSTM model at time t, f() represents the function model used to predict power demand, θ represents the parameter set in the model, and L current (t) represents the power load data at the current time t, L hist (tn) represents the historical power load data at time tn in the past, and t represents time.

[0021] As a preferred implementation, the environmental correction coefficient a(t) is calculated using a multivariate linear regression model based on the temperature T(t), humidity H(t), and wind speed W(t) collected by the environmental sensor of the real-time load monitoring module:

[0022] a(t)=a 1 T(t)+a 2 H(t)+a 3 W(t)+b;

[0023] Among them, a 1 、a 2 、a 3 , b represents the regression coefficient;

[0024] The power L predicted by the ARIMA model or LSTM model demand (t) and the environmental correction coefficient a(t), and use the PID control algorithm to calculate the release speed V of the weight. release (t) and the height adjustment control signal M release (t):

[0025]

[0026] Among them, e(t) represents the deviation between the load data at the last moment and the current load data, K p Represents proportional gain, K i Indicates the integral gain, K d represents the differential gain, represents the integral of the error, the accumulated error from time 0 to the current time t, and de(t) / dt represents the differential of the error, that is, the rate of change of the error over time;

[0027] Control signal M release The calculation method of (t) is:

[0028] M release (t) = a(t)*L demand (t).

[0029] As a preferred implementation, an error threshold Q is set;

[0030] Calculate the difference between the electric energy predicted by the ARIMA model and the electric energy predicted by the LSTM model:

[0031] L = |FG|;

[0032] Among them, L represents the difference, F represents the electric energy predicted by the ARIMA model, and G represents the electric energy predicted by the LSTM model;

[0033] If Q is less than or equal to L, the electric energy predicted by the ARIMA model is selected;

[0034] If Q is greater than L or there is preset extreme weather, the electric energy predicted by the LSTM model is selected.

[0035] As a preferred embodiment, the method for adjusting the height of the heavy object by the electric lifting device is:

[0036] A sliding gear is installed on the bottom surface of the top of the energy storage bracket, one end of the cable is fixedly connected to the weight, and the other end is connected to the winch through the sliding gear;

[0037] The lifting motor is connected to the winch through a power shaft to provide electrical energy to the winch. The winch lifts the heavy object to a preset height through a cable according to the control signal.

[0038] As a preferred embodiment, the energy conversion device includes a generator, a gear transmission system and a flywheel;

[0039] The gear transmission system is connected to the power shaft, the power shaft drives the gear transmission system to rotate, and the output end of the gear transmission system is connected to the generator through the flywheel;

[0040] The potential energy of the released heavy object is converted into mechanical energy through the power shaft, then transmitted through the gear transmission system and flywheel, and finally converted into electrical energy through the generator.

[0041] As a preferred embodiment, the power transmission device includes a cable, a voltage converter, an overload protection device and a short circuit protection system;

[0042] One end of the cable is connected to the output end of the generator, and the other end is connected to the power grid through a voltage converter, an overload protection device and a short-circuit protection system in sequence.

[0043] As a preferred embodiment, the real-time load monitoring module further includes a height sensor, a speed sensor and a gravity sensor;

[0044] The height sensor is used to obtain the real-time height of the heavy object;

[0045] The speed sensor is used to obtain the falling speed of the heavy object;

[0046] Gravity sensors are used to obtain the weight of heavy objects.

[0047] On the other hand, the present invention further provides an electronic device having a computer program stored thereon, wherein when the computer program is executed by a processor, the method for frequency and peak regulation of a power grid based on gravity energy storage as described in any embodiment of the present invention is implemented.

[0048] On the other hand, the present invention also provides a computer-readable storage medium for storing one or more programs. When the one or more programs are executed by the one or more processors, the one or more processors implement the power grid frequency and peak regulation method based on gravity energy storage as described in any embodiment of the present invention.

[0049] The present invention has the following beneficial effects:

[0050] The present invention combines the ARIMA model with the LSTM model, which can give full play to the advantages of both in processing linear and nonlinear features, thereby improving the accuracy and stability of the prediction. The ARIMA model is responsible for capturing the linear trend and periodicity of the data, while the LSTM is used to extract complex nonlinear features. By combining the outputs of the two and using the correlation coefficient correction, the advantages of the two can be combined to reduce the prediction error. Gravity energy storage is a green and environmentally friendly energy storage method with a simple principle and a low technical threshold. It uses physical media to store energy, does not produce harmful emissions, and meets the requirements of sustainable development. The gravity energy storage system uses physical media to store energy and has a high degree of safety. At the same time, its energy storage efficiency is as high as more than 90%, and its service life can reach more than 30 years, which is highly economical and practical. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] Figure 1 The present invention is a flowchart for implementing the method. DETAILED DESCRIPTION

[0052] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0053] It should be understood that the step numbers used in this document are only for convenience of description and are not intended to limit the order in which the steps are executed.

[0054] It should be understood that the terms used in the present specification are only for the purpose of describing specific embodiments and are not intended to limit the present invention. As used in the present specification and the appended claims, unless the context clearly indicates otherwise, the singular forms "a", "an" and "the" are intended to include plural forms.

[0055] The terms “include” and “comprising” indicate the presence of described features, integers, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or combinations thereof.

[0056] The term "and / or" means and includes any and all possible combinations of one or more of the associated listed items.

[0057] The current large-scale grid connection of new energy sources has exacerbated the curve difference between power sources and loads. Gravity energy storage has a large storage capacity and a long storage time. It can be used as an independent energy storage power station or supporting equipment for a new energy power station. It can adjust the generator output according to the grid dispatching instructions to achieve peak load regulation and solve the problem of mismatch between electricity and load demand. At the same time, gravity energy storage technology can accurately track grid dispatching instructions, improve the secondary frequency regulation capacity of the grid, and cooperate with the grid to achieve frequency regulation services by increasing or decreasing the load of the units. Combined with the method proposed in the present invention, the accuracy of gravity energy storage dispatching can be further improved, and the peak load and frequency regulation services of the grid can be better coordinated.

[0058] Embodiment 1:

[0059] See also Figure 1 The present invention provides a method for frequency and peak regulation of a power grid based on gravity energy storage, comprising the following steps:

[0060] Use the historical load data of the power grid and the historical compensated electric energy to train the ARIMA model and LSTM model;

[0061] Monitor the load status of the power grid according to the real-time load monitoring module, and use the ARIMA model and LSTM model to predict the electric energy that needs to be compensated according to the load status;

[0062] According to the electric energy that needs to be compensated predicted by the ARIMA model or the LSTM model, and the environmental correction coefficient obtained by the multivariate linear regression model, a control signal that the height of the heavy object needs to be adjusted is obtained, and according to the real-time feedback of the control signal and the real-time load monitoring module, the electric lifting device is controlled to adjust the height of the heavy object;

[0063] Release the weight and convert the potential energy generated by the falling weight into electrical energy through the energy conversion device;

[0064] The generated electric energy is transmitted to the power grid through the power transmission device to achieve peak load and frequency regulation of the power grid.

[0065] As a preferred implementation, the method for predicting the electric energy that needs to be compensated by the ARIMA model or LSTM model is:

[0066] Filter abnormal data in the load data collected in real time by the load sensor of the real-time load monitoring module, and normalize the load data;

[0067] Based on the historical load data and the current load data, the ARIMA model and the LSTM model are input to predict the electric energy that needs to be compensated:

[0068] L demand (t) = f(L hist (tn), L current (t),θ);

[0069] Among them, Ldemand (t) represents the electric energy predicted by the ARIMA model or LSTM model at time t, f() represents the function model used to predict power demand, θ represents the parameter set in the model, and L current (t) represents the power load data at the current time t, L hist (tn) represents the historical power load data at the time tn in the past, and t represents time. Combining the ARIMA and LSTM models can give full play to the advantages of both in processing linear and nonlinear features, thereby improving the accuracy and stability of predictions. The ARIMA model is responsible for capturing the linear trend and periodicity of the data, while the LSTM is used to extract complex nonlinear features. By combining the outputs of the two and using the correlation coefficient correction, the advantages of both can be combined to reduce the prediction error.

[0070] As a preferred implementation, the environmental correction coefficient a(t) is calculated using a multivariate linear regression model based on the temperature T(t), humidity H(t), and wind speed W(t) collected by the environmental sensor of the real-time load monitoring module:

[0071] a(t)=a 1 T(t)+a 2 H(t)+a 3 W(t)+b;

[0072] Among them, a 1 、a 2 、a 3 , b represents the regression coefficient;

[0073] The electric energy L predicted by the ARIMA model or LSTM model demand (t) and the environmental correction coefficient a(t), and use the PID control algorithm to calculate the release speed V of the weight. release (t) and the height adjustment control signal M release (t):

[0074]

[0075] Among them, e(t) represents the deviation between the load data at the last moment and the current load data, K p Represents proportional gain, K i Indicates the integral gain, K d represents the differential gain, represents the integral of the error, the accumulated error from time 0 to the current time t, and de(t) / dt represents the differential of the error, that is, the rate of change of the error over time;

[0076] Control signal M release The calculation method of (t) is:

[0077] Mrelease (t) = a(t)*L demand (t).

[0078] As a preferred implementation, an error threshold Q is set;

[0079] Calculate the difference between the electric energy predicted by the ARIMA model and the electric energy predicted by the LSTM model:

[0080] L = |FG|;

[0081] Among them, L represents the difference, F represents the electric energy predicted by the ARIMA model, and G represents the electric energy predicted by the LSTM model;

[0082] If Q is less than or equal to L, the electric energy predicted by the ARIMA model is selected;

[0083] If Q is greater than L or there is preset extreme weather, the electric energy predicted by the LSTM model is selected.

[0084] As a preferred embodiment, the method for adjusting the height of the heavy object by the electric lifting device is:

[0085] A sliding gear is installed on the bottom surface of the top of the energy storage bracket, one end of the cable is fixedly connected to the weight, and the other end is connected to the winch through the sliding gear;

[0086] The lifting motor is connected to the winch through a power shaft to provide electrical energy to the winch. The winch lifts the heavy object to a preset height through a cable according to the control signal.

[0087] As a preferred embodiment, the energy conversion device includes a generator, a gear transmission system and a flywheel;

[0088] The gear transmission system is connected to the power shaft, the power shaft drives the gear transmission system to rotate, and the output end of the gear transmission system is connected to the generator through the flywheel;

[0089] The potential energy of the released heavy object is converted into mechanical energy through the power shaft, then transmitted through the gear transmission system and flywheel, and finally converted into electrical energy through the generator.

[0090] As a preferred embodiment, the power transmission device includes a cable, a voltage converter, an overload protection device and a short circuit protection system;

[0091] One end of the cable is connected to the output end of the generator, and the other end is connected to the power grid through a voltage converter, an overload protection device and a short-circuit protection system in sequence.

[0092] As a preferred embodiment, the real-time load monitoring module further includes a height sensor, a speed sensor and a gravity sensor;

[0093] The height sensor is used to obtain the real-time height of the heavy object;

[0094] The speed sensor is used to obtain the falling speed of the heavy object;

[0095] Gravity sensors are used to obtain the weight of heavy objects.

[0096] In the process of controlling the lifting and releasing of heavy objects, the following formula is used for calculation:

[0097] E p = mgh;

[0098] Among them, E p is the potential energy of the weight (unit: joule, J), m is the mass of the weight (unit: kilogram, kg), g is the acceleration due to gravity (9.8m / s 2 ), h is the height of the weight (unit: meter, m);

[0099] Based on the height h and the mass m of the weight fed back by the height sensor and the gravity sensor, the currently stored potential energy is calculated in real time to decide whether to release the weight.

[0100] When a heavy object falls, potential energy is converted into mechanical energy, and mechanical energy is converted into electrical energy. The energy conversion efficiency can be expressed as:

[0101]

[0102] Where η is the energy conversion efficiency (%), p out is the electrical power output of the generator (unit: watt, W), p in is the input mechanical power, that is, the power generated when the weight falls (unit: watt, W). The current conversion efficiency is calculated by this formula, and the release speed of the weight is dynamically adjusted according to the needs of the power grid to ensure the highest efficiency.

[0103] Through the gear transmission system, the falling speed v of the weight has a certain relationship with the speed ω of the generator. Assuming the gear transmission ratio is r, we can get:

[0104]

[0105] Among them, ω is the speed of the generator (unit: revolutions per second, rps), v is the falling speed of the weight (unit: meters per second, m / s), and r is the gear ratio; by calculating the current falling speed v and the set transmission ratio r, the speed of the generator is adjusted in real time to ensure the stability of the power output.

[0106] The instantaneous load demand of the power grid can be calculated by the following formula:

[0107] P load =V×I×COSθ;

[0108] P load is the grid load (unit: watt, W), V is the grid voltage (unit: volt, V), I is the grid current (unit: ampere, A), and COSθ is the power factor.

[0109] The voltage and current are measured by load sensors to calculate the instantaneous load demand P of the power grid. load , and based on this value decide whether it is necessary to release the heavy objects to generate electricity.

[0110] In order to ensure that the release speed of the weight matches the grid load demand, the release speed of the weight can be dynamically adjusted according to the following formula:

[0111]

[0112] Where m is the mass of the weight (unit: kilograms, kg), g is the acceleration due to gravity (9.8 m / s 2 ).

[0113] According to the load demand of the power grid P load And the mass m of the weight, the falling speed of the weight is adjusted through the calculation formula to ensure stable power supply to the grid.

[0114] Embodiment 2:

[0115] This embodiment provides an electronic device having a computer program stored thereon, and when the computer program is executed by a processor, the method for frequency and peak regulation of a power grid based on gravity energy storage as described in any embodiment of the present invention is implemented.

[0116] Embodiment three:

[0117] This embodiment provides a computer-readable storage medium for storing one or more programs. When the one or more programs are executed by the one or more processors, the one or more processors implement the power grid frequency and peak regulation method based on gravity energy storage as described in any embodiment of the present invention.

[0118] In the embodiments of the present application, "at least one" refers to one or more, and "more than one" refers to two or more. "And / or" describes the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B can represent the existence of A alone, the existence of A and B at the same time, and the existence of B alone. Among them, A and B can be singular or plural. The character " / " generally indicates that the previous and next associated objects are in an "or" relationship. "At least one of the following" and similar expressions refer to any combination of these items, including any combination of single or plural items. For example, at least one of a, b and c can be represented by: a, b, c, a and b, a and c, b and c, or a and b and c, where a, b, c can be single or multiple.

[0119] Those of ordinary skill in the art will appreciate that the various units and algorithm steps described in the embodiments disclosed herein can be implemented in a combination of electronic hardware, computer software, and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0120] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0121] In several embodiments provided in the present application, if any function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (Read-Only Memory; hereinafter referred to as: ROM), random access memory (Random Access Memory; hereinafter referred to as: RAM), disk or optical disk, and other media that can store program codes.

[0122] The above descriptions are merely embodiments of the present invention and are not intended to limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made using the contents of the present invention specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.

Claims

1. A method for frequency and peak regulation of a power grid based on gravity energy storage, characterized in that: The following steps are involved: Use the historical load data of the power grid and the historical compensated electric energy to train the ARIMA model and LSTM model; Monitor the load status of the power grid according to the real-time load monitoring module, and use the ARIMA model and LSTM model to predict the electric energy that needs to be compensated according to the load status; According to the electric energy that needs to be compensated predicted by the ARIMA model or the LSTM model, and the environmental correction coefficient obtained by the multivariate linear regression model, a control signal that the height of the heavy object needs to be adjusted is obtained, and according to the real-time feedback of the control signal and the real-time load monitoring module, the electric lifting device is controlled to adjust the height of the heavy object; Release the weight and convert the potential energy generated by the falling weight into electrical energy through the energy conversion device; The generated electric energy is transmitted to the power grid through the power transmission device to achieve peak load and frequency regulation of the power grid.

2. The method for frequency and peak regulation of a power grid based on gravity energy storage according to claim 1, characterized in that: The method for predicting the electric energy that needs to be compensated by the ARIMA model or LSTM model is: Filter abnormal data in the load data collected in real time by the load sensor of the real-time load monitoring module, and normalize the load data; Based on the historical load data and the current load data, the ARIMA model and the LSTM model are input to predict the electric energy that needs to be compensated: L demand (t)=f(L hist (t-n),L current (t),θ); Among them, L demand (t) represents the electric energy predicted by the ARIMA model or LSTM model at time t, f() represents the function model used to predict power demand, θ represents the parameter set in the model, and L current (t) represents the power load data at the current time t, L hist (tn) represents the historical power load data at time tn in the past, and t represents time.

3. The method for frequency and peak regulation of a power grid based on gravity energy storage according to claim 2, characterized in that: According to the temperature T(t), humidity H(t), and wind speed W(t) collected by the environmental sensors of the real-time load monitoring module, the environmental correction coefficient a(t) is calculated using the multivariate linear regression model: a(t)=a1T(t)+a2H(t)+a3W(t)+b; Among them, a1, a2, a3, and b represent regression coefficients; The electric energy L predicted by the ARIMA model or LSTM model demand (t) and the environmental correction coefficient a(t), and use the PID control algorithm to calculate the release speed V of the weight. release (t) and the height adjustment control signal M release (t): Among them, e(t) represents the deviation between the load data at the last moment and the current load data, K p Represents proportional gain, K i Indicates the integral gain, K d represents the differential gain, represents the integral of the error, the accumulated error from time 0 to the current time t, and de(t) / dt represents the differential of the error, that is, the rate of change of the error over time; Control signal M release The calculation method of (t) is: M release (t)=a(t)*L demand (t)。 4. The method for frequency and peak regulation of a power grid based on gravity energy storage according to claim 2, characterized in that: Set the error threshold Q; Calculate the difference between the electric energy predicted by the ARIMA model and the electric energy predicted by the LSTM model: L = |FG|; Among them, L represents the difference, F represents the electric energy predicted by the ARIMA model, and G represents the electric energy predicted by the LSTM model; If Q is less than or equal to L, the electric energy predicted by the ARIMA model is selected; If Q is greater than L or there is preset extreme weather, the electric energy predicted by the LSTM model is selected.

5. The method for frequency and peak regulation of a power grid based on gravity energy storage according to claim 1, characterized in that: The method for adjusting the height of the heavy object by the electric lifting device is: A sliding gear is installed on the bottom surface of the top of the energy storage bracket, one end of the cable is fixedly connected to the weight, and the other end is connected to the winch through the sliding gear; The lifting motor is connected to the winch through a power shaft to provide electrical energy to the winch. The winch lifts the heavy object to a preset height through a cable according to the control signal.

6. The method for frequency and peak regulation of a power grid based on gravity energy storage according to claim 1, characterized in that: The energy conversion device includes a generator, a gear transmission system and a flywheel; The gear transmission system is connected to the power shaft, the power shaft drives the gear transmission system to rotate, and the output end of the gear transmission system is connected to the generator through the flywheel; The potential energy of the released heavy object is converted into mechanical energy through the power shaft, then transmitted through the gear transmission system and flywheel, and finally converted into electrical energy through the generator.

7. The method for frequency and peak regulation of a power grid based on gravity energy storage according to claim 1, characterized in that: The power transmission device includes a cable, a voltage converter, an overload protection device and a short circuit protection system; One end of the cable is connected to the output end of the generator, and the other end is connected to the power grid through a voltage converter, an overload protection device and a short-circuit protection system in sequence.

8. The method for frequency and peak regulation of a power grid based on gravity energy storage according to claim 1, characterized in that: The real-time load monitoring module also includes a height sensor, a speed sensor and a gravity sensor; The height sensor is used to obtain the real-time height of the heavy object; The speed sensor is used to obtain the falling speed of the heavy object; Gravity sensors are used to obtain the weight of heavy objects.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, the power grid frequency and peak regulation method based on gravity energy storage is implemented as described in any one of claims 1 to 8.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the power grid frequency and peak regulation method based on gravity energy storage as described in any one of claims 1 to 8 is implemented.

Images