Implementation method of energy storage EMS system based on recommendation algorithm

Abstract

The application belongs to the field of new energy, and specifically discloses an implementation method of an energy storage EMS system based on a recommendation algorithm, connects all generator sets and energy storage devices to the system, initializes the devices, forms device portraits, and each device portrait stores the label of the device; when the power grid dispatch sends an AGC instruction to the power plant, the energy storage EMS system will transmit parameters into the recommendation system after collecting signals and analyzing data, all online generator sets and energy storage devices perform real-time data collection, part of the portraits are updated in real time, and are input into the recommendation system; the recommendation system ranks (or uses other algorithms) through the weighted average judgment of the portrait parameters of the units, outputs the recommended ranking, controls the devices in order through the recommended ranking to meet the requirements of the dispatch instruction, provides the device calling priority order in the AGC frequency modulation process, helps the energy storage EMS system to make better decisions, and improves the examination income.

Description

Technical Field

[0001] This invention relates to the field of new energy, specifically to an implementation method for an energy storage EMS system based on a recommendation algorithm. Background Technology

[0002] With the rapid development of my country's new energy industry and the deepening of the energy revolution, energy storage, as a key support for the development of future energy systems, is increasingly becoming a focus of attention. Energy storage will be a key technology influencing the future energy landscape, and is of great significance for the safe, stable, and efficient operation of its integration into energy systems, improving the comprehensive utilization efficiency of energy, promoting the development of new energy industries, and driving energy strategic transformation. Energy storage has wide applications in power systems, covering all aspects of power generation, transmission, distribution, and end users.

[0003] The Energy Management System (EMS) is the brain of the energy storage system, primarily responsible for the safe and optimized scheduling of energy. Addressing current issues such as wind and solar power curtailment, load instability, and peak-valley price differences, the EMS system optimizes energy storage control, distributed power generation output, and load activation / deactivation to achieve safe, economical, and efficient energy management across different application scenarios (power source side, grid side, user side, and ancillary services) and operating modes.

[0004] Throughout the entire power grid operation, frequency is a crucial constraint for ensuring the safety of electricity supply to generating units and users. While small-scale frequency fluctuations are generally acceptable to the grid, large-scale fluctuations can cause unexpected events such as power outages and generator shutdowns, resulting in losses. In power plant applications, energy storage systems (EMS) assist in maintaining grid frequency stability and perform secondary frequency regulation. Also known as Automatic Generation Control (AGC), this refers to the ability of generator units and energy storage to adjust capacity and a certain rate, tracking the frequency in real time within permissible deviations to meet the grid's frequency requirements.

[0005] Under normal circumstances, secondary frequency regulation can achieve error-free frequency regulation. Typically, the power grid sends dispatch instructions to power plants through remote control devices, and the power plants then distribute the signals to generator sets and energy storage. The conventional solution is to calculate the power demand of the dispatch signal and control the generator sets and energy storage devices to adjust the power output. The power plant will also evaluate the profitability of this process, with indicators including regulation rate K1, response time K2, and regulation accuracy K3.

[0006] The above-mentioned method is relatively mechanical in its invocation and cannot form dynamic equipment status and equipment performance maintenance through equipment profiling. As a result, when equipment performance deteriorates in the later stages of the algorithm operation, the three benefit assessment parameters of adjustment rate K1, response time K2, and adjustment accuracy K3 cannot be guaranteed. Moreover, the efficiency is low, the response time is slow, and it is difficult to achieve the highest assessment standards and the highest benefits. In addition, this process calls almost all units and energy storage equipment, and the adjustment actions are numerous, resulting in significant equipment wear and tear. Summary of the Invention

[0007] The purpose of this invention is to provide an implementation method for an energy storage EMS system based on a recommendation algorithm, so as to solve the problems mentioned in the background art.

[0008] To achieve the above objectives, the present invention provides the following technical solution: an implementation method for an energy storage EMS system based on a recommendation algorithm, wherein the energy storage EMS system is written in Java and its database is MySQL, specifically including the following steps:

[0009] S1. After connecting the energy storage device and generator set to the energy storage EMS system, collect data into the system in real time and store the data in the MySQL database;

[0010] S2. Initialize the energy storage devices and generator sets to form device profiles, including offline profiles and real-time profiles. The offline profiles represent relatively stable device parameters, while the real-time profiles represent fluctuating device parameters. In addition to some basic device parameters, the profiles also perform real-time maintenance on the current performance of the devices. Each device profile stores the device's tag.

[0011] S3. When the power dispatch sends an AGC command to the energy storage EMS system, the energy storage EMS system analyzes the parameters of the command through data analysis and transmits the parameters to the recommendation system with a recommendation algorithm. At the same time, all online generator sets and energy storage devices collect data in real time, update some profiles in real time, and input them into the recommendation system.

[0012] S4. After receiving the device profile and frequency modulation parameters, the recommendation system calculates and ranks the devices according to the pre-defined recommendation algorithm and outputs the recommendation ranking.

[0013] S5. After receiving the recommended ranking, the equipment control function converts it into equipment instructions and sends them to the energy storage equipment or generator set. The equipment is controlled in sequence according to the recommended ranking to meet the requirements of the dispatching instructions, thereby completing a closed loop of AGC frequency regulation operation.

[0014] As a preferred technical solution of the present invention, the energy storage device includes a BMS system and a battery stack. The generator set is a thermal power unit. The energy storage device and the generator set are connected to the system via network cable and RS485 twisted pair cable. The communication protocol is Modbus or IEC104.

[0015] As a preferred technical solution of the present invention, in the device profile, the offline profile refers to the fixed parameters or relatively fixed parameters corresponding to the device. When the device is connected in the early stage, the offline profile of the device is synchronously maintained in the system, and the offline profile is maintained periodically in the later stage; the real-time profile refers to the data obtained by real-time data collection and calculation after the device is connected to the energy storage EMS system.

[0016] As a preferred technical solution of the present invention, in the energy storage device, the parameters that can be used as offline profiles include: battery stack SOH, battery discharge capacity AH, battery rated maximum capacity, and battery maximum discharge depth CC; the parameters that can be used as real-time profiles include: battery stack maximum allowable discharge power, battery stack maximum allowable discharge current, battery stack maximum allowable discharge voltage, and internal charge and discharge status.

[0017] As a preferred technical solution of the present invention, in the generator set equipment, the parameters that can be used as offline profiles include: the number of thermal power units, the unit start-up time, the load control accuracy, the maximum output power, the maximum adjustment range, and the dead zone; the parameters that can be used as real-time profiles include: the current fan speed of the unit, the current motor current, the fan inlet and outlet pressure, and the temperature.

[0018] Compared with the prior art, the beneficial effects of the present invention are:

[0019] This invention provides a more efficient, economical, and stable way to empower energy storage EMS and achieve maximum economic benefits. It connects all generator sets and energy storage devices to the system, initializes these devices to form device profiles, and uses a recommendation algorithm to provide device call priority order during AGC frequency regulation, helping the energy storage EMS system to make better decisions and improve performance. Attached Figure Description

[0020] Figure 1 This is a schematic diagram of the overall process of the present invention. Detailed Implementation

[0021] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0022] Please see Figure 1 This invention provides a technical solution: an implementation method for an energy storage EMS system based on a recommendation algorithm. The energy storage EMS system is written in Java and uses MySQL as its database. The method specifically includes the following steps:

[0023] S1. After connecting the energy storage device and generator set to the energy storage EMS system, collect data into the system in real time and store the data in the MySQL database;

[0024] S2. Initialize the energy storage devices and generator sets to form device profiles, including offline profiles and real-time profiles. The offline profiles represent relatively stable device parameters, while the real-time profiles represent fluctuating device parameters. In addition to some basic device parameters, the profiles also perform real-time maintenance on the current performance of the devices. Each device profile stores the device's tag.

[0025] S3. When the power dispatch sends an AGC command to the energy storage EMS system, the energy storage EMS system analyzes the parameters of the command through data analysis and transmits the parameters to the recommendation system with a recommendation algorithm. At the same time, all online generator sets and energy storage devices collect data in real time, update some profiles in real time, and input them into the recommendation system.

[0026] S4. After receiving the device profile and frequency modulation parameters, the recommendation system calculates and ranks the devices according to the pre-defined recommendation algorithm and outputs the recommendation ranking.

[0027] S5. After receiving the recommended ranking, the equipment control function converts it into equipment instructions and sends them to the energy storage equipment or generator set. The equipment is controlled in sequence according to the recommended ranking to meet the requirements of the dispatching instructions, thereby completing a closed loop of AGC frequency regulation operation.

[0028] Furthermore, the energy storage device includes a BMS system, battery stacks, etc., and the generator set is a thermal power unit. The energy storage device and the generator set are connected to the system via network cable or RS485 twisted pair cable, and the communication protocol is Modbus or IEC104.

[0029] Furthermore, in the device profile, the offline profile refers to the fixed parameters or relatively fixed parameters corresponding to the device. When the device is initially connected, the offline profile of the device is synchronously maintained in the system, and the offline profile is maintained periodically in the later stages. The real-time profile refers to the data collected and calculated in real time after the device is connected to the energy storage EMS system.

[0030] Furthermore, in the energy storage device, parameters that can be used as offline profiles include: battery stack SOH, battery discharge capacity AH, battery rated maximum capacity, battery maximum discharge depth CC, etc.; parameters that can be used as real-time profiles include: battery stack maximum allowable discharge power, battery stack maximum allowable discharge current, battery stack maximum allowable discharge voltage, internal charge and discharge status, etc.

[0031] Furthermore, in the generator set equipment, parameters that can be used as offline profiles include: the number of thermal power units, unit start-up time, load control accuracy, maximum output power, maximum adjustment range, dead zone, etc.; parameters that can be used as real-time profiles include: the current fan speed of the unit, the current motor current, the fan inlet and outlet pressure, temperature, etc.

[0032] Specifically:

[0033] When the power dispatcher sends an AGC command to the system, the system analyzes the parameters of the command through data analysis. For example, if there is a power increase demand of 20MW within 2 minutes, the overall ramp-up capability of the system is 10MW / min. This data is then transmitted to the recommendation system.

[0034] After the recommendation system collects the device profiles and frequency tuning parameters, it maintains them in the system in real time according to the pre-defined algorithm (here, we assume a simple weighted average, but more advanced algorithms can be used later).

[0035] Assuming the weighting factor for energy storage is 0.3 and the weighting factor for thermal power units is 0.7, the power output of thermal power units is calculated first. The offline and real-time profiles of each thermal power unit are called up, and the calculation is performed according to the weighting factor based on the previously configured algorithm (this algorithm is customizable). The recommended score and power generation of each unit are calculated and a list is generated.

[0036] After the recommended score for thermal power units is calculated, the recommended score for energy storage must also be calculated, following the same calculation method mentioned above. Finally, the two scores are combined to form a recommended ranking list, which is then transmitted to the equipment control function.

[0037] Traditional thermal power plants have a slow ramp-up speed. Therefore, to meet the power increase requirement of 10MW / min, a 500MW thermal power unit is needed, while energy storage only requires 20MW. Therefore, when the command requires a fast ramp-up speed, the top recommended items calculated by the system should be energy storage devices, and when the speed requirement is not high, the top recommended items should be generator units.

[0038] After receiving the recommended ranking, the equipment control function converts it into equipment instructions and sends them to the energy storage equipment or generator set, thereby completing a closed loop of AGC frequency regulation operation.

[0039] Although embodiments of the invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the appended claims and their equivalents.

Claims

1. An implementation method for an energy storage EMS system based on a recommendation algorithm, characterized in that, The energy storage EMS system is written in Java and uses MySQL as its database. The specific steps include: S1. After connecting the energy storage device and generator set to the energy storage EMS system, collect data into the system in real time and store the data in the MySQL database; S2. Initialize the energy storage equipment and generator set to create equipment profiles, including offline profiles and real-time profiles; Offline profiles represent relatively stable device parameters, while real-time profiles represent fluctuating device parameters. In addition to some basic device parameters, the profiles also maintain the current performance of the device in real time, and each device profile stores the device's tags. S3. When the power dispatch sends an AGC command to the energy storage EMS system, the energy storage EMS system analyzes the parameters of the command through data analysis and transmits the parameters to the recommendation system with a recommendation algorithm. At the same time, all online generator sets and energy storage devices collect data in real time, update some profiles in real time, and input them into the recommendation system. S4. After receiving the device profile and frequency modulation parameters, the recommendation system calculates and ranks the devices according to the pre-defined recommendation algorithm and outputs the recommendation ranking. S5. After receiving the recommended ranking, the equipment control function converts it into equipment instructions and sends them to the energy storage equipment or generator set. The equipment is controlled in sequence according to the recommended ranking to meet the requirements of the dispatching instructions, thereby completing a closed loop of AGC frequency regulation operation.

2. The implementation method of an energy storage EMS system based on a recommendation algorithm according to claim 1, characterized in that: The energy storage device includes a BMS system and a battery stack. The generator set is a thermal power unit. The energy storage device and the generator set are connected to the system via network cable and RS485 twisted pair cable. The communication protocol is Modbus or IEC104.

3. The implementation method of an energy storage EMS system based on a recommendation algorithm according to claim 1, characterized in that: In the device profile, the offline profile refers to the fixed parameters or relatively fixed parameters corresponding to the device. When the device is connected in the early stage, the offline profile of the device is maintained in the system at the same time, and the offline profile is maintained regularly in the later stage. The real-time profile is data obtained through real-time data collection and calculation after the device is connected to the energy storage EMS system.

4. The implementation method of an energy storage EMS system based on a recommendation algorithm according to claim 1, characterized in that: In the energy storage device, the parameters of the offline profile include: battery stack SOH, battery discharge capacity AH, battery rated maximum capacity, and battery maximum discharge depth CC; the parameters of the real-time profile include: battery stack maximum allowable discharge power, battery stack maximum allowable discharge current, battery stack maximum allowable discharge voltage, and internal charge / discharge status.

5. The implementation method of an energy storage EMS system based on a recommendation algorithm according to claim 1, characterized in that: In the aforementioned generator set equipment, the parameters for offline profiling include: the number of thermal power units, unit start-up time, load control accuracy, maximum output power, maximum adjustment range, and dead zone; the parameters for real-time profiling include: the current fan speed of the unit, the current motor current, the fan inlet and outlet pressure, and temperature.

Images