Virtual power plant automatic response tracking method and device based on energy storage EMS system

Abstract

The invention discloses a virtual power plant automatic response tracking method based on an energy storage EMS system. The method comprises the following steps: S1, acquiring real-time load consumption data of the lower end of an energy storage system; s2, acquiring historical load consumption data; s3, obtaining an order demand of the virtual power plant in a future prediction time period; s4, obtaining a historical order demand of a virtual power plant; s5, predicting future load demand data according to the historical load consumption data and the prediction model; s6, predicting future order influence factors of the virtual power plant according to historical virtual power plant orders and execution results, determining future order response feasibility, formulating a control strategy, and enabling an energy storage system to execute; and S7, predicting future load demand data according to the historical load consumption data and the prediction model, cleaning the historical load consumption data, deleting abnormal data in the historical load consumption data, obtaining the cleaned historical load consumption data, importing the cleaned historical load consumption data into the prediction model, and outputting the future load demand data. According to the virtual power plant automatic response tracking method and device based on the energy storage EMS system, model matching derivation can be continuously carried out on the acquired data, a scheduling strategy is corrected, the complex workload of manual analysis is effectively reduced, the order response efficiency of the virtual power plant is improved, the prediction accuracy is improved, the total power consumption cost is reduced, and the method and device are suitable for popularization and application. And the benefit effect of total grid connection is improved.

Description

Technical Field

[0001] The present invention belongs to the technical field of energy storage device management, and in particular relates to a virtual power plant automatic response tracking method and device based on an energy storage EMS system. Background Art

[0002] A virtual power plant (VPP) is a power coordination management system that uses advanced information and communication technologies and software systems to achieve the aggregation and coordinated optimization of distributed energy resources (DER) to participate in the power market and power grid operation as a special power plant. The core of a virtual power plant is to integrate different types of distributed energy resources such as distributed power sources, energy storage systems, controllable loads, electric vehicles, etc. into a virtual power plant through communication and aggregation technologies, so as to participate in power market transactions and provide grid ancillary services.

[0003] In the traditional mode, power plants urgently activate backup power generation resources and force some users to stop using electricity to ensure the safe and stable operation of the power grid. Now, through "virtual power plants", distributed power sources, transferable, adjustable, load reduction and energy storage devices can be gathered.

[0004] During peak electricity consumption or when emergency load demand occurs, distributed power sources, adjustable, transferable, reducible loads and energy storage devices are aggregated into a virtual "power plant" through the relevant information aggregation platform, and a large number of scattered interruptible and transferable electricity loads are aggregated. Refined and unified management is implemented, and power supply and use operations and scheduling are carried out to resolve the contradiction between power supply and demand, absorb distributed energy and reduce power supply and use costs, bringing higher economic and social benefits.

[0005] Virtual power plants are gradually becoming an application model that combines power generation, energy storage, and electricity consumption with low implementation costs. Enterprises can actively participate in the operation of virtual power plants through self-built energy storage systems to obtain greater benefits. Existing energy storage EMS systems cannot automatically respond to and track the needs of virtual power plants, and are usually manually analyzed and calculated, which requires a large workload. Therefore, how to effectively combine energy storage systems with virtual power plant systems, give full play to the effectiveness of energy storage systems, and increase their own revenue is an urgent problem to be solved.

[0006] The usual energy dispatch strategy of the energy storage EMS system is to simply set the charging and discharging time period of the energy storage battery according to the peak and valley prices of electricity where the energy storage system is located. The electricity demand is usually also arranged according to the peak and valley prices of electricity. Although this method can make full use of the profits brought by the price difference, it cannot reasonably arrange the electricity demand, or it cannot maximize the profits from the price difference in order to ensure the reasonable arrangement of electricity demand.

[0007] Especially after connecting with the virtual power plant system, it becomes very complicated to rely solely on manpower to adjust the control strategy of the energy storage EMS system, and it is difficult to update it dynamically. Summary of the invention

[0008] The present invention provides a method and device for automatic response tracking of a virtual power plant based on an energy storage EMS system.

[0009] The technical solution adopted by the present invention to solve the above technical problems is: A virtual power plant automatic response tracking method based on an energy storage EMS system comprises the following steps: S1. Obtain real-time load consumption data at the lower end of the energy storage system; S2. Obtain historical load consumption data; S3, obtaining the order demand of the virtual power plant in the future forecast time period; S4. Obtain historical order requirements of virtual power plants; S5. Predict future load demand data based on historical load consumption data and prediction models; S6. Predict the factors affecting future orders of virtual power plants based on historical virtual power plant orders and execution results, determine the feasibility of future order responses, formulate control strategies, and enable the energy storage system to execute; S7. Predict future load demand data based on historical load consumption data and the prediction model, clean the historical load consumption data, delete abnormal data therein, obtain the cleaned historical load consumption data, import it into the prediction model, and output future load demand data.

[0010] Preferably, the load consumption data in step S1 includes power, voltage and current.

[0011] Preferably, the load consumption data in step S2 includes historical power, historical voltage and historical current within a historical preset time period.

[0012] Preferably, the order demand in step S3 includes the start time of the electricity demand, the end time of the electricity demand, the electricity consumption and the compensation electricity price information.

[0013] Preferably, the historical order demand of the virtual power plant in step S4 includes the electricity price subsidy amount and the energy demand for the time period, and the electricity demand distribution corresponding to the energy storage system includes the electricity consumption in each time period, the grid electricity price corresponding to each time period, the energy balance of the energy storage system, and the average electricity cost of the last full charge.

[0014] Preferably, the load consumption data in step S5 includes the amount of electricity used by the electrical equipment directly through the power grid in each time period every day and the amount of electricity used by the electrical equipment through the energy storage system in each time period every day, and the load demand data is the amount of electricity that may be required by the electrical equipment in each future time period.

[0015] Preferably, the prerequisites of the strategy in step S6 include: the current electricity cost of the energy balance of the energy storage system is lower than the virtual power plant order electricity price; the electricity price for recharging after the order response is lower than the virtual power plant order electricity price; the electricity price of the system is at a low level before recharging after the order response; the system will not have an emergency power supply demand before recharging after the order response, or the energy surplus of the energy storage system can meet the emergency needs when an emergency power supply demand occurs.

[0016] A virtual power plant automatic response tracking device based on an energy storage EMS system, the virtual power plant automatic response tracking device is used to implement a virtual power plant automatic response tracking method, wherein the virtual power plant automatic response tracking device comprises: a processor and a memory connected in sequence, the memory stores a computer program and is executed by the processor, the computer program is an execution control logic, and the memory is connected to the energy storage EMS system through a communication line interface.

[0017] Preferably, a historical data model is stored in the memory.

[0018] Preferably, the memory obtains the required real-time data and historical data from the energy storage EMS system through the communication line interface, and automatically generates a scheduling strategy after analysis and calculation by a computer program configured in the corresponding processor, which is fed back to the energy storage EMS system through the communication line interface, and finally the energy storage EMS system executes the linkage strategy related to the virtual power plant.

[0019] Compared with the prior art, the virtual power plant automatic response tracking method and device based on the energy storage EMS system of the present invention can continuously perform model matching and deduction on the acquired data, and correct the scheduling strategy, effectively reducing the complex workload of manual analysis, improving the order response efficiency of the virtual power plant, improving the prediction accuracy, reducing the total electricity cost, and improving the total grid-connected revenue effect. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] Figure 1 This is a partial flow chart of the automatic response tracking method of a virtual power plant based on an energy storage EMS system of the present invention.

[0021] Figure 2 It is a structural diagram of the automatic response tracking device of a virtual power plant based on an energy storage EMS system of the present invention. DETAILED DESCRIPTION

[0022] The present invention is further described in detail below with reference to the accompanying drawings.

[0023] like Figure 1 As shown, a virtual power plant automatic response tracking method based on an energy storage EMS system includes the following steps: S1. Obtain real-time load consumption data at the lower end of the energy storage system, including power, voltage, and current; S2. Obtain historical load consumption data, including historical power, historical voltage, and historical current within a preset historical time period; S3. Obtain the order demand of the virtual power plant in the future forecast time period. The order demand includes information such as the start time of electricity demand, the end time of electricity demand, electricity consumption, and the compensation electricity price. The order demand can be fully responded to, partially responded to, or not responded to. A full response means outputting all electricity consumption to the virtual power plant according to the start and end time and electricity consumption required by the order; a partial response means outputting a part of the electricity consumption within the start and end time required by the order. Usually, after the virtual power plant issues an order, the energy storage EMS system will make an appropriate response based on its own situation. After the virtual power plant confirms the response, the energy storage EMS system can supply power according to the agreed result of the order response.

[0024] S4. Obtain the historical order demands of the virtual power plant. The historical order demands of the virtual power plant include the electricity price subsidy amount and the energy demand in the time period. The distribution of electricity demand corresponding to the energy storage system includes the electricity consumption in each time period, the grid electricity price corresponding to each time period, the energy balance of the energy storage system and the average electricity cost of the last full charge. The energy storage system conducts a comprehensive calculation of the time consumed for charging and discharging, the charging cost after the order response, etc., selects the time period and power supply that can respond to the virtual power plant order, and then forms a strategy record and submits it to the energy storage EMS system for execution.

[0025] S5. Predict future load demand data based on historical load consumption data and prediction models; load consumption data includes the amount of electricity used by electrical equipment directly through the power grid at each time period every day and the amount of electricity used by electrical equipment through the energy storage system at each time period every day. Load demand data is the amount of electricity that may be required by electrical equipment at each time period in the future.

[0026] S6. Predict the factors affecting future orders of virtual power plants based on historical virtual power plant orders and execution results, determine the feasibility of future order responses and formulate control strategies, and enable the energy storage system to execute.

[0027] S7. Predict future load demand data based on historical load consumption data and the prediction model, clean the historical load consumption data, delete abnormal data therein, obtain the cleaned historical load consumption data, import it into the prediction model, and output future load demand data.

[0028] The prerequisites of the strategy include: the current electricity cost of the energy balance of the energy storage system must be lower than the virtual power plant order electricity price; the electricity price of recharging after the order is responded to must be lower than the virtual power plant order electricity price; the electricity price of the system is at a low level before recharging after the order is responded to; the system will not have emergency power supply demand before recharging after the order is responded to, or the energy surplus of the energy storage system can meet the emergency needs when emergency power supply demand occurs.

[0029] There may be errors, duplicates, incomplete or inaccurate data in the historical load consumption data. Before cleaning, select the original data and use missing value screening, outlier screening, duplicate value screening, data conversion and standardization, data consistency check and other means to filter the data, so as to find abnormal data and delete it. If there is missing data, use the mean / median / mode and other statistical values ​​of the two adjacent data to fill the missing data. Input the cleaned historical load consumption data into the forecasting model to obtain the output of future load demand data.

[0030] Electronic devices pre-apply machine learning algorithms to train prediction models, such as LSTM (Long Short-Term Memory) and GRU (Gated Recurrent Unit) and other recurrent neural network models, or MLP (Multi-Layer Perceptron) and DNN (Deep Neural Network), etc., which can be used to process complex feature combinations and interactions in power loads, and then predict power loads.

[0031] The real-time load consumption data corresponding to the current cycle is obtained based on the obtained charging operation data, and the deviation value is calculated between the real-time load consumption data and the corresponding estimated load consumption data to obtain the corresponding actual load deviation; Set the actual deviation threshold, compare the corresponding actual load deviation with the actual deviation threshold, and judge whether the corresponding power distribution process meets the requirements based on the comparison result. If not, use the actual load deviation value to correct the actual deviation threshold.

[0032] Building a prediction model involves the following steps: The standard reference data includes the electricity price table for each time period of the power grid, the historical charging and discharging time and electricity price distribution table of this energy storage system, the electricity consumption time and electricity price distribution table of the deployment environment of this energy storage system, the time and electricity price table corresponding to the historical order response execution results of the virtual power plant, and the response strategy label.

[0033] Use standard reference data to segment grid electricity prices, charging and discharging status, power consumption status, and order execution status according to time periods to form a multi-dimensional distributed data grid.

[0034] The reference data of influencing factors include historical orders of virtual power plants and corresponding results of orders from other systems, social information including holidays, and electricity usage information including production peak and off-peak seasons and fluctuations, forming an influencing factor data grid.

[0035] The input parameters of the prediction model include the start time, end time, electricity consumption, and compensation electricity price in the virtual power plant order. The model matches the input parameters in the distributed data grid to obtain the corresponding strategy label with the highest match with the historical data.

[0036] The prediction model calculates the final strategy value based on the input parameters and strategy labels, and imports the weighted values ​​of the influencing factor data grid. The output parameters include order response status, response start time, response end time, power supply, profit, etc. At the same time, a new response strategy is created and the strategy label is added to the prediction model.

[0037] The prediction model submits the response strategy including the output parameters to the energy storage EMS system for execution.

[0038] Factors influencing future orders of virtual power plants include the development trend of virtual power plant scale, the trend of power consumption and power supply, the trend of power grid price adjustment, the historical overall order response rate and completion ratio of the access power supplier, etc. By obtaining these influencing factors, we can analyze and determine the change trend corresponding to the historical data, including stability, increase or decrease, calculate the expected changes in the factors affecting future orders based on the relevant change trends, and adjust the control strategy in combination with real-time load consumption data and future load demand data, and send the relevant strategies to the energy storage system EMS through the execution device for final execution.

[0039] like Figure 2 As shown, a virtual power plant automatic response tracking device based on an energy storage EMS system includes a processor 1 and a memory 2 connected in sequence, the memory 2 stores a computer program 3 and is executed by the processor 1, the computer program 3 is an execution control logic, and the memory 2 is connected to the energy storage EMS system through a communication line interface 4.

[0040] An automatic response tracking device for a virtual power plant based on an energy storage EMS system obtains relevant required real-time data and historical data from the energy storage EMS system through a communication line interface 4. The historical data model is stored in a memory 2. After being analyzed and calculated by a computer program configured in the corresponding processor 1, a scheduling strategy is automatically generated and fed back to the energy storage EMS system through the communication line interface 4. Finally, the energy storage EMS system executes the linkage strategy related to the virtual power plant.

[0041] Virtual power plants usually publish supply and demand lists, through which the trend of future electricity demand orders can be determined. The automatic response tracking method of virtual power plants based on the energy storage EMS system can adjust the response strategy by adjusting the increase or decrease in electricity demand and the time distribution of electricity demand. It can even give adjustment suggestions for the power arrangement of the system and the charging and discharging time of the energy storage system.

[0042] Normally, the peak and valley electricity prices of the power grid are relatively fixed in time periods and are not adjusted frequently. The order demand time periods and electricity consumption of virtual power plants are not fixed and are adjusted dynamically in accordance with changes in market electricity demand. The power consumption environment in which the energy storage system is deployed may have periodic requirements for electricity consumption, and may also be adjusted dynamically according to circumstances (including time changes, holidays, production off-seasons, etc.). The automatic response tracking method for virtual power plants based on the energy storage EMS system of the present invention mainly responds to the dynamic changes in orders of virtual power plants and the dynamic changes in their own electricity demand, effectively automatically responds to and tracks orders of virtual power plants, gives full play to the peak-shaving advantages of the energy storage system, and maximizes additional profits.

[0043] The virtual power plant automatic response tracking device can obtain users' power demand information in real time through the smart grid monitoring system. By analyzing and studying users' power consumption behavior, the power consumption characteristics of different user groups can be classified and modeled, and then the future power demand can be predicted.

[0044] The virtual power plant automatic response tracking device can integrate and optimize the power generation capacity by connecting with distributed power generation equipment. For example, solar power generation equipment can autonomously adjust the output according to weather forecast information to maximize the use of solar energy resources. Wind power generation equipment can also adjust the power generation capacity in real time according to wind speed and direction. Through the coordination of the intelligent management system, the virtual power plant can integrate the output capacity of different power generation equipment to ensure the reliable supply of energy.

[0045] As a new energy supply model, virtual power plants can integrate and manage decentralized power resources to achieve flexible adjustment of power demand response by combining automatic response tracking devices based on energy storage EMS systems. By obtaining user demand information, optimizing the use of power generation equipment and energy storage devices, and flexibly adjusting power demand, virtual power plants can achieve balance and optimization of the power system and provide users with reliable and efficient power supply.

[0046] The virtual power plant automatic response tracking method and device based on the energy storage EMS system of the present invention can continuously perform model matching and deduction on the acquired data, and correct the scheduling strategy, effectively reducing the complex workload of manual analysis, improving the order response efficiency of the virtual power plant, improving the prediction accuracy, reducing the total electricity cost, and improving the total grid-connected revenue effect.

[0047] Finally, it should be noted that the above embodiments only illustrate the technical solutions of the present invention, rather than limiting it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A virtual power plant automatic response tracking method based on energy storage EMS system, characterized in that: The following steps are involved: S1. Obtain real-time load consumption data at the lower end of the energy storage system; S2. Obtain historical load consumption data; S3, obtaining the order demand of the virtual power plant in the future forecast time period; S4. Obtain historical order requirements of virtual power plants; S5. Predict future load demand data based on historical load consumption data and prediction models; S6. Predict the factors affecting future orders of virtual power plants based on historical virtual power plant orders and execution results, determine the feasibility of future order responses, formulate control strategies, and enable the energy storage system to execute; S7. Predict future load demand data based on historical load consumption data and the prediction model, clean the historical load consumption data, delete abnormal data therein, obtain the cleaned historical load consumption data, import it into the prediction model, and output future load demand data.

2. According to claim 1, a virtual power plant automatic response tracking method based on energy storage EMS system is characterized in that: The load consumption data in step S1 includes power, voltage and current.

3. The method for automatically responding to and tracking a virtual power plant based on an energy storage EMS system according to claim 1 is characterized in that: The load consumption data in step S2 includes historical power, historical voltage and historical current within a historical preset time period.

4. The method for automatically responding to and tracking a virtual power plant based on an energy storage EMS system according to claim 1 is characterized in that: The order demand in step S3 includes the start time of the electricity demand, the end time of the electricity demand, the electricity consumption and the compensation electricity price information.

5. The method for automatic response tracking of a virtual power plant based on an energy storage EMS system according to claim 1, characterized in that: The historical order demand of the virtual power plant in step S4 includes the electricity price subsidy amount and the energy demand in the time period. The electricity demand distribution corresponding to the energy storage system includes the electricity consumption in each time period, the grid electricity price corresponding to each time period, the energy balance of the energy storage system, and the average electricity cost of the last full charge.

6. The method for automatic response tracking of a virtual power plant based on an energy storage EMS system according to claim 1, characterized in that: The load consumption data in step S5 includes the amount of electricity used by the electrical equipment directly through the power grid in each time period every day and the amount of electricity used by the electrical equipment through the energy storage system in each time period every day. The load demand data is the amount of electricity that may be required by the electrical equipment in each time period in the future.

7. The method for automatic response tracking of a virtual power plant based on an energy storage EMS system according to claim 1, characterized in that: The prerequisites of the strategy in step S6 include: the current electricity cost of the energy balance of the energy storage system must be lower than the virtual power plant order electricity price; the electricity price for recharging after the order response is lower than the virtual power plant order electricity price; the electricity price of the system is at a low level before recharging after the order response; the system will not have an emergency power supply demand before recharging after the order response, or the energy surplus of the energy storage system can meet the emergency needs when an emergency power supply demand occurs.

8. A virtual power plant automatic response tracking device based on energy storage EMS system, characterized in that: The virtual power plant automatic response tracking device is used to implement the virtual power plant automatic response tracking method according to any one of claims 1 to 7, wherein the virtual power plant automatic response tracking device comprises: a processor (1) and a memory (2) connected in sequence, wherein the memory (2) stores a computer program (3) and is executed by the processor (1), wherein the computer program (3) is an execution control logic, and the memory (2) is connected to an energy storage EMS system via a communication line interface (4).

9. The automatic response tracking device for a virtual power plant based on an energy storage EMS system according to claim 8, characterized in that: The memory (2) stores a historical data model.

10. The automatic response tracking device for a virtual power plant based on an energy storage EMS system according to claim 8, characterized in that: The memory (2) obtains relevant required real-time data and historical data from the energy storage EMS system via the communication line interface (4), and automatically generates a dispatch strategy after analysis and calculation by a computer program configured in the corresponding processor (1), and feeds back to the energy storage EMS system via the communication line interface (4), and finally the energy storage EMS system executes the linkage strategy related to the virtual power plant.

Images