Multi-type energy storage coordination control method and device for low-voltage distribution area

Abstract

The invention relates to the technical field of energy storage of a power system, and particularly provides a multi-type energy storage coordination control method and device for a low-voltage power distribution area, and the method comprises the steps: enabling a current observation state of the low-voltage power distribution area to serve as the input of a pre-trained intelligent agent, the charging and discharging power, output by a pre-trained intelligent agent, of each current stored energy in the low-voltage distribution area is obtained; and performing coordination control on each stored energy by using the current charging and discharging power of each stored energy in the low-voltage distribution area. According to the technical scheme provided by the invention, through deep integration of characteristics of multiple types of energy storage systems and implementation of cooperative control, power load optimization management and efficient utilization of renewable energy sources of the low-voltage distribution transformer area are realized, and the economical efficiency, safety and sustainability of system operation are improved.

Description

Technical Field

[0001] This invention relates to the field of power system energy storage technology, specifically to a method and device for coordinated control of multiple types of energy storage in a low-voltage distribution substation. Background Technology

[0003] The large-scale grid connection of renewable energy sources such as wind and solar power has exacerbated the operational pressure on power distribution areas. These energy sources exhibit significant randomness and volatility, often resulting in a "curve imbalance" phenomenon where peak power generation times mismatch with off-peak demand. Due to the lack of flexible adjustment capabilities in traditional power grids, a large amount of surplus renewable energy cannot be utilized locally, leading not only to resource waste but also to reduced overall economic efficiency of the power system.

[0004] To address these challenges, deploying various types of energy storage systems (such as lithium batteries, supercapacitors, flow batteries, and flywheel energy storage) in low-voltage distribution substations has become a key solution. These energy storage devices possess millisecond-level response capabilities and flexible charge / discharge characteristics, effectively acting as power regulators. They absorb surplus renewable energy during off-peak periods and release stored energy to support the grid during peak periods. Therefore, how to scientifically coordinate multiple types of energy storage, optimize renewable energy utilization, alleviate equipment overload pressure, and improve system stability has become a key research direction. Summary of the Invention

[0005] To overcome the above-mentioned defects, this invention proposes a method and device for coordinated control of multiple types of energy storage in low-voltage distribution substations.

[0006] Firstly, a method for coordinated control of multiple types of energy storage in a low-voltage distribution transformer area is provided, the method comprising:

[0007] The current observation state of the low-voltage distribution substation is used as the input to the pre-trained agent to obtain the charging and discharging power of each energy storage in the low-voltage distribution substation, which is output by the pre-trained agent.

[0008] The charging and discharging power of each energy storage unit in the low-voltage distribution area is used to coordinate and control each energy storage unit.

[0009] Preferably, the Markov decision process corresponding to the intelligent agent is: (S t A t ,S t+1 ,r t ), where S t Let A be the observed state of the low-voltage distribution station area at time t. t Let S be the action vector at time t. t+1 The observation status of the low-voltage distribution radio station area at time t+1, r t Let t be the reward function at time t.

[0010] Furthermore, the observed status includes: the state of charge of each energy storage, the real-time load of the low-voltage distribution substation, the real-time renewable energy generation power, electricity price, the grid power and time information of the previous period, and the action vector includes: the charging and discharging power of each energy storage.

[0011] Furthermore, the reward function at time t is as follows:

[0012]

[0013] In the above formula, β1, β2, β3, and β4 are the first, second, third, and fourth weighting coefficients, respectively, and Cost... t Let t be the component of economic cost in time period t. Let t be the power curtailed during time period t, and LoadRate be the power curtailed during time period t. t Let α be the load factor for time period t. max As a safety threshold, Let t be the power of the power grid during time period t. The power of the power grid during the time period t-1.

[0014] Furthermore, the economic cost components for time period t are as follows:

[0015]

[0016] In the above formula, The price of electricity purchased from the upper-level power grid during time period t. Let be the equivalent usage cost coefficient of the k-th type of energy storage during time period t. Let K be the charging and discharging power of the k-th type of energy storage during time period t, where K is the total number of energy storage types.

[0017] Furthermore, the reward function at time t satisfies the following constraints: system power balance constraint, energy storage device power constraint, energy storage device energy / state of charge constraint, energy storage device energy state dynamic constraint, state of charge first and last state constraint, grid switching power constraint, distribution area main equipment load rate constraint, node voltage constraint, and power change rate constraint.

[0018] Furthermore, the system power balance constraints are as follows:

[0019]

[0020] The power constraints of the energy storage device are as follows:

[0021]

[0022] The energy / state of charge constraints of the energy storage device are as follows:

[0023]

[0024] The dynamic energy state constraints of the energy storage device are as follows:

[0025]

[0026] The first and last state constraints of the charged state are as follows:

[0027]

[0028] The power grid switching power constraints are as follows:

[0029]

[0030] The load rate constraints for the main equipment in the transformer area are as follows:

[0031]

[0032] The node voltage constraints are as follows:

[0033]

[0034] The power change rate constraint is as follows:

[0035] and

[0036] In the above formula, Let t be the total renewable energy power generation during the period. Let t be the total load power during time period t. Let P be the system line loss power during time period t. chg,max,k P is the maximum allowable charging power for the k-th type of energy storage. disch,max,k The maximum allowable discharge power for the k-th type of energy storage is... The minimum allowable energy for the k-th type of energy storage. Let be the remaining energy of the k-th type of energy storage during time period t. The maximum allowable energy for the k-th type of energy storage. This represents the remaining energy of the k-th type of energy storage during time period t-1. Let η be the discharge power component of the k-th type of energy storage during time period t, where Δt is the time step and η is the discharge power component of the k-th type of energy storage. disch,k Let k be the energy storage discharge efficiency. For the charging power component, η chg,k For the charging efficiency of the k-th type of energy storage, The initial energy for scheduling the k-th type of energy storage, The initial preset energy for the k-th type of energy storage scheduling, For the energy at the end of the k-th type of energy storage dispatch, The preset energy for the end of the k-th type of energy storage dispatch is P. feed-in,max P is the maximum power that the distribution substation is allowed to feed back into the grid. draw,maxThe maximum power allowed to flow from the grid into the distribution substation area. S represents the total apparent power flowing through the main device during time period t. rated Main equipment rated capacity, V min The lower limit of the allowable voltage. Let V be the voltage amplitude at node i during time period t. max The upper limit of the allowable voltage, SOC min,k For the minimum allowable state of charge of the k-th type of energy storage, C ess,k For the rated energy capacity of the k-th type of energy storage, SOC max,k For the k-th type of energy storage, the maximum allowable state of charge is... Let ΔP be the charging and discharging power of the k-th type of energy storage during time period t-1. grid,max ΔP represents the maximum value of the power grid change. ess,k,max This represents the maximum change in charging and discharging power for the k-th type of energy storage.

[0037] Preferably, before using the current observed state of the low-voltage distribution substation as input to the pre-trained agent to obtain the charging and discharging power of each energy storage unit in the low-voltage distribution substation output by the pre-trained agent, the following steps are included:

[0038] When a low-voltage distribution area is at risk of severe overload, the energy storage type participating in the coordinated dispatch should be set to power-type energy storage.

[0039] When a low-voltage distribution area is in a period of power curtailment risk, the energy storage type participating in the coordinated dispatch should be set as energy storage.

[0040] Furthermore, the power-type energy storage includes supercapacitors and flywheel energy storage, and the energy-type energy storage includes lithium batteries and flow batteries.

[0041] Secondly, a multi-type energy storage coordination control device for a low-voltage distribution substation is provided, the low-voltage distribution substation multi-type energy storage coordination control device comprising:

[0042] The analysis module is used to take the current observation state of the low-voltage distribution substation as the input of the pre-trained agent and obtain the charging and discharging power of each energy storage in the low-voltage distribution substation as output by the pre-trained agent.

[0043] The scheduling module is used to coordinate and control each energy storage unit by utilizing the current charging and discharging power of each energy storage unit in the low-voltage distribution area.

[0044] Preferably, the Markov decision process corresponding to the intelligent agent is: (S t A t ,S t+1 ,r t ), where S t Let A be the observed state of the low-voltage distribution station area at time t.t Let S be the action vector at time t. t+1 The observation status of the low-voltage distribution radio station area at time t+1, r t Let t be the reward function at time t.

[0045] Furthermore, the observed status includes: the state of charge of each energy storage, the real-time load of the low-voltage distribution substation, the real-time renewable energy generation power, electricity price, the grid power and time information of the previous period, and the action vector includes: the charging and discharging power of each energy storage.

[0046] Furthermore, the reward function at time t is as follows:

[0047]

[0048] In the above formula, β1, β2, β3, and β4 are the first, second, third, and fourth weighting coefficients, respectively, and Cost... t Let t be the component of economic cost in time period t. Let t be the power curtailed during time period t, and LoadRate be the power curtailed during time period t. t Let α be the load factor for time period t. max As a safety threshold, Let t be the power of the power grid during time period t. The power of the power grid during the time period t-1.

[0049] Furthermore, the economic cost components for time period t are as follows:

[0050]

[0051] In the above formula, The price of electricity purchased from the upper-level power grid during time period t. Let be the equivalent usage cost coefficient of the k-th type of energy storage during time period t. Let K be the charging and discharging power of the k-th type of energy storage during time period t, where K is the total number of energy storage types.

[0052] Furthermore, the reward function at time t satisfies the following constraints: system power balance constraint, energy storage device power constraint, energy storage device energy / state of charge constraint, energy storage device energy state dynamic constraint, state of charge first and last state constraint, grid switching power constraint, distribution area main equipment load rate constraint, node voltage constraint, and power change rate constraint.

[0053] Furthermore, the system power balance constraints are as follows:

[0054]

[0055] The power constraints of the energy storage device are as follows:

[0056]

[0057] The energy / state of charge constraints of the energy storage device are as follows:

[0058]

[0059] The dynamic energy state constraints of the energy storage device are as follows:

[0060]

[0061] The first and last state constraints of the charged state are as follows:

[0062]

[0063] The power grid switching power constraints are as follows:

[0064]

[0065] The load rate constraints for the main equipment in the transformer area are as follows:

[0066]

[0067] The node voltage constraints are as follows:

[0068]

[0069] The power change rate constraint is as follows:

[0070] and

[0071] In the above formula, Let t be the total renewable energy power generation during the period. Let t be the total load power during time period t. Let P be the system line loss power during time period t. chg,max,k P is the maximum allowable charging power for the k-th type of energy storage. disch,max,k The maximum allowable discharge power for the k-th type of energy storage is... The minimum allowable energy for the k-th type of energy storage. Let be the remaining energy of the k-th type of energy storage during time period t. The maximum allowable energy for the k-th type of energy storage. This represents the remaining energy of the k-th type of energy storage during time period t-1. Let η be the discharge power component of the k-th type of energy storage during time period t, where Δt is the time step and η is the discharge power component of the k-th type of energy storage. disch,k Let k be the energy storage discharge efficiency. For the charging power component, η chg,k For the charging efficiency of the k-th type of energy storage, The initial energy for scheduling the k-th type of energy storage, The initial preset energy for the k-th type of energy storage scheduling, For the energy at the end of the k-th type of energy storage dispatch, The preset energy for the end of the k-th type of energy storage dispatch is P. feed-in,max P is the maximum power that the distribution substation is allowed to feed back into the grid. draw,max The maximum power allowed to flow from the grid into the distribution substation area. S represents the total apparent power flowing through the main device during time period t. rated Main equipment rated capacity, V min The lower limit of the allowable voltage. Let V be the voltage amplitude at node i during time period t. max The upper limit of the allowable voltage, SOC min,k For the minimum allowable state of charge of the k-th type of energy storage, C ess,k For the rated energy capacity of the k-th type of energy storage, SOC max,k For the k-th type of energy storage, the maximum allowable state of charge is... Let ΔP be the charging and discharging power of the k-th type of energy storage during time period t-1. grid,max ΔP represents the maximum value of the power grid change. ess,k,max This represents the maximum change in charging and discharging power for the k-th type of energy storage.

[0072] Preferably, before using the current observed state of the low-voltage distribution substation as input to the pre-trained agent to obtain the charging and discharging power of each energy storage unit in the low-voltage distribution substation output by the pre-trained agent, the following steps are included:

[0073] When a low-voltage distribution area is at risk of severe overload, the energy storage type participating in the coordinated dispatch should be set to power-type energy storage.

[0074] When a low-voltage distribution area is in a period of power curtailment risk, the energy storage type participating in the coordinated dispatch should be set as energy storage.

[0075] Furthermore, the power-type energy storage includes supercapacitors and flywheel energy storage, and the energy-type energy storage includes lithium batteries and flow batteries.

[0076] Thirdly, a computer device is provided, comprising: one or more processors;

[0077] The processor is used to store one or more programs;

[0078] When the one or more programs are executed by the one or more processors, the method for coordinated control of multiple types of energy storage in low-voltage distribution substations is implemented.

[0079] Fourthly, a computer-readable storage medium is provided, on which a computer program is stored, wherein when the computer program is executed, the method for coordinated control of multiple types of energy storage in low-voltage distribution substations is implemented.

[0080] The above-described technical solutions of the present invention have at least one or more of the following beneficial effects:

[0081] This invention provides a method and apparatus for coordinated control of multiple types of energy storage in a low-voltage distribution transformer area, comprising: using the current observed state of the low-voltage distribution transformer area as input to a pre-trained intelligent agent to obtain the charging and discharging power of each energy storage in the low-voltage distribution transformer area output by the pre-trained intelligent agent; and using the charging and discharging power of each energy storage in the low-voltage distribution transformer area to perform coordinated control of each energy storage. The technical solution provided by this invention significantly improves equipment safety and power supply reliability while greatly increasing the local absorption efficiency of renewable energy and reducing resource waste. Through intelligent data-driven decision-making, the system optimizes the balance of power supply and demand, reduces operating costs, and enhances system stability, laying a solid foundation for the safe, efficient, green, and intelligent operation of low-voltage distribution transformer areas, and strongly supporting the construction of new power systems and the realization of sustainable development goals. Attached Figure Description

[0082] Figure 1 This is a schematic diagram of the main steps of the low-voltage distribution substation multi-type energy storage coordinated control method according to an embodiment of the present invention. Detailed Implementation

[0083] The specific embodiments of the present invention will be further described in detail below with reference to the accompanying drawings.

[0084] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, 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, 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.

[0085] As disclosed in the background section, the large-scale grid connection of renewable energy sources such as wind and solar power has exacerbated the operational pressure on power distribution areas. Power generation from these sources exhibits significant randomness and volatility, often resulting in a "curve imbalance" phenomenon where peak generation times coincide with off-peak consumption periods. Due to the lack of flexible adjustment capabilities in traditional power grids, a large amount of surplus renewable energy cannot be utilized locally, leading not only to resource waste but also to reduced overall economic efficiency of the power system.

[0087] To address these challenges, deploying various types of energy storage systems (such as lithium batteries, supercapacitors, flow batteries, and flywheel energy storage) in low-voltage distribution substations has become a key solution. These energy storage devices possess millisecond-level response capabilities and flexible charging and discharging characteristics, effectively acting as power regulators: absorbing surplus renewable energy during off-peak periods and releasing stored energy to support the grid during peak periods. Therefore, how to scientifically coordinate multiple types of energy storage, optimize renewable energy utilization, alleviate equipment overload pressure, and improve system stability has become a key research direction.

[0088] To address the aforementioned issues, this invention provides a method and apparatus for coordinated control of multiple types of energy storage in a low-voltage distribution transformer area. The method includes: using the current observed state of the low-voltage distribution transformer area as input to a pre-trained intelligent agent to obtain the charging and discharging power of each energy storage unit in the low-voltage distribution transformer area, output by the pre-trained intelligent agent; and using the charging and discharging power of each energy storage unit in the low-voltage distribution transformer area to perform coordinated control of each energy storage unit. The technical solution provided by this invention significantly improves equipment safety and power supply reliability while greatly increasing the local absorption efficiency of renewable energy and reducing resource waste. Through intelligent data-driven decision-making, the system optimizes the balance between power supply and demand, reduces operating costs, and enhances system stability. This lays a solid foundation for achieving safe, efficient, green, and intelligent operation of low-voltage distribution transformer areas, and strongly supports the construction of new power systems and the realization of sustainable development goals. Specifically:

[0089] (1) Precisely alleviate the pressure of heavy overload in distribution areas: By monitoring the load (current, voltage, power) of distribution areas in real time and combining it with high-precision forecasting, various types of energy storage devices (especially fast-responding power storage devices such as supercapacitors) are intelligently dispatched during peak load periods to discharge and replenish the power grid, actively reducing peak load. The optimized dispatch module strictly follows the load rate constraints of the main equipment (such as transformers) in the distribution area, ensuring that they operate within a safe threshold (such as 80%-90% of rated capacity). This directly reduces the temperature rise, failure risk, and power outage probability caused by equipment overload, significantly extends the service life of power distribution facilities, and ensures power supply continuity and user power safety.

[0090] (2) Effectively enhance the renewable energy absorption capacity: By monitoring the power generation and fluctuation characteristics of renewable energy (photovoltaic and wind power) in real time, and combining it with prediction models, when the renewable energy power generation exceeds the local load demand (i.e., during periods of low load and high power generation), intelligent dispatching of energy storage devices (especially large-capacity energy storage such as lithium batteries and flow batteries) is used to charge the devices, actively absorbing the surplus renewable energy power. The optimized dispatching module aims to minimize the penalty for curtailment, significantly reducing the "wind curtailment" and "solar curtailment" phenomena caused by insufficient grid regulation capacity or unreasonable dispatching, and greatly improving the local absorption ratio and utilization efficiency of wind and solar energy at the distribution substation level.

[0091] (3) Optimizing system operating efficiency and economy: Through the above-mentioned intelligent coordinated control of energy storage charging and discharging, the system effectively balances power supply and demand, smooths the load curve, and reduces the peak-valley difference. Under the premise of meeting various constraints (power balance, SOC limit, equipment safety, voltage stability, etc.), the optimized scheduling model makes scheduling decisions with the goal of minimizing operating costs (electricity purchase cost + energy storage loss cost), which significantly reduces the overall line loss and operating cost of the system.

[0092] (4) Enhance system stability and power quality: The rapid response capability of energy storage devices, combined with the optimized scheduling of the system, effectively mitigates power fluctuations caused by load fluctuations and the intermittency of renewable energy, improves the voltage stability of distribution substations (meets node voltage constraints), reduces the impact of power fluctuations on the power grid, and enhances power supply reliability and power quality.

[0093] The above plan will be explained in detail below.

[0094] Example 1

[0095] See appendix Figure 1 , Figure 1 This is a schematic flowchart illustrating the main steps of a low-voltage distribution substation multi-type energy storage coordinated control method according to an embodiment of the present invention. Figure 1 As shown, the coordinated control method for multiple types of energy storage in low-voltage distribution substations in this embodiment of the invention mainly includes the following steps:

[0096] Step S101: Use the current observation state of the low-voltage distribution station area as the input of the pre-trained agent to obtain the charging and discharging power of each energy storage in the low-voltage distribution station area output by the pre-trained agent.

[0097] Step S102: Use the current charging and discharging power of each energy storage in the low-voltage distribution area to coordinate and control each energy storage.

[0098] In this embodiment, it is first necessary to acquire real-time operating status data of the distribution transformer substation. Therefore, this invention constructs a data acquisition and monitoring module responsible for comprehensively and in real-time monitoring of key power parameters of the distribution transformer substation, providing data support for subsequent analysis and decision-making. By deploying intelligent sensors and data acquisition equipment, this module acquires the following core data:

[0099] (1) Power grid operating parameters: three-phase voltage, line voltage, three-phase current, active power, reactive power, apparent power, power factor, and system operating frequency.

[0100] (2) Energy storage equipment status: State of charge (SOC), State of health (SOH), total battery pack voltage, charging and discharging current, temperature distribution of individual battery cells / modules, charging and discharging power (kW), cumulative charging and discharging capacity (kWh), operating mode, protection status, and fault status (covering various types such as lithium batteries, supercapacitors, and flow batteries).

[0101] (3) Renewable energy power generation data: photovoltaic power generation, wind power generation, etc.

[0102] (4) Meteorological information: Environmental data related to renewable energy power generation forecasts (such as light intensity and wind speed).

[0103] The deployment of data acquisition equipment includes:

[0104] (1) Current sensor: Real-time monitoring of current flow and changes, and evaluation of load dynamic characteristics.

[0105] (2) Voltage sensor: measures the voltage of the power distribution system to ensure the safe operation of equipment.

[0106] (3) Power measurement equipment: Combine current and voltage measurements to calculate instantaneous power and power factor.

[0107] (4) Energy storage device monitoring unit: provides real-time data support for various energy storage devices, and tracks electricity, power flow, internal temperature and operating status.

[0108] (5) Renewable energy power generation monitoring device: collects power generation and related meteorological information in real time.

[0109] For data transmission and storage:

[0110] The collected data is uploaded in real time and reliably to the multi-type energy storage coordination and control APP of the low-voltage distribution substation intelligent fusion terminal via wired or wireless communication protocols. The data is stored in a structured format according to a predefined information model for easy retrieval and processing. The system employs encryption technology to ensure data security, strictly controls access permissions, and implements a regular backup strategy to prevent data loss.

[0111] Data preprocessing and cleaning include:

[0112] (1) Data integration: unify data from different monitoring devices into a standardized format.

[0113] (2) Handling missing values: Use appropriate imputation methods to ensure data integrity.

[0114] (3) Outlier detection and removal: Statistical methods are used to identify and process outlier data points.

[0115] (4) Data standardization / normalization: Convert data of different dimensions and ranges to a comparable scale.

[0116] Data analysis includes:

[0117] (1) Load characteristic analysis: In-depth mining of historical and real-time load data to identify load patterns and regularities for different date types (weekdays / weekends), seasons, and time periods.

[0118] (2) Analysis of renewable energy power generation characteristics: Analyze the historical and real-time data of wind and solar power generation to understand their fluctuation patterns, correlation with load, and potential periods of power curtailment risk.

[0119] 5.3.3 Prediction Model Construction:

[0120] (1) Model selection and training: Based on machine learning algorithms such as long short-term memory networks, the prediction model is trained using processed historical load data and renewable energy power generation data. Cross-validation and other techniques are used to evaluate and improve the generalization ability of the model.

[0121] (2) Predictive Execution: Real-time data is input into the trained model to generate short-term (e.g., hourly) and long-term (e.g., daily) electricity load demand forecasts and renewable energy generation forecasts. These high-precision forecasts are key inputs for developing forward-looking energy storage dispatch strategies.

[0122] In this embodiment, the Markov decision process corresponding to the agent is: (S t A t ,S t+1 ,r t ), where S t Let A be the observed state of the low-voltage distribution station area at time t. t Let S be the action vector at time t. t+1 The observation status of the low-voltage distribution radio station area at time t+1, r t Let t be the reward function at time t.

[0123] In one embodiment, the observed state includes: the state of charge of each energy storage unit, the real-time load of the low-voltage distribution substation, the real-time renewable energy generation power, the electricity price, the grid power and time information of the previous period, and the action vector includes: the charging and discharging power of each energy storage unit.

[0124] In one implementation, the reward function at time t is as follows:

[0125]

[0126] In the above formula, β1, β2, β3, and β4 are the first, second, third, and fourth weighting coefficients, respectively, and Cost... t Let t be the component of economic cost in time period t. Let t be the power curtailed during time period t, and LoadRate be the power curtailed during time period t. t Let α be the load factor for time period t. max As a safety threshold, Let t be the power of the power grid during time period t. The power of the power grid during the time period t-1.

[0127] In one implementation, the economic cost components for time period t are as follows:

[0128]

[0129] In the above formula, The price of electricity purchased from the upper-level power grid during time period t. Let be the equivalent usage cost coefficient of the k-th type of energy storage during time period t. Let K be the charging and discharging power of the k-th type of energy storage during time period t, where K is the total number of energy storage types.

[0130] In one implementation, the reward function at time t satisfies the following constraints: system power balance constraint, energy storage device power constraint, energy storage device energy / state of charge constraint, energy storage device energy state dynamic constraint, state of charge first and last state constraint, grid switching power constraint, distribution area main equipment load rate constraint, node voltage constraint, and power change rate constraint.

[0131] In one implementation, the system power balance constraint is as follows:

[0132]

[0133] The power constraints of the energy storage device are as follows:

[0134]

[0135] The energy / state of charge constraints of the energy storage device are as follows:

[0136]

[0137] The dynamic energy state constraints of the energy storage device are as follows:

[0138]

[0139] The first and last state constraints of the charged state are as follows:

[0140]

[0141] The power grid switching power constraints are as follows:

[0142]

[0143] The load rate constraints for the main equipment in the transformer area are as follows:

[0144]

[0145] The node voltage constraints are as follows:

[0146]

[0147] The power change rate constraint is as follows:

[0148] and

[0149] In the above formula, Let t be the total renewable energy power generation during the period. Let t be the total load power during time period t. Let P be the system line loss power during time period t. chg,max,k P is the maximum allowable charging power for the k-th type of energy storage. disch,max,k The maximum allowable discharge power for the k-th type of energy storage is... The minimum allowable energy for the k-th type of energy storage. Let be the remaining energy of the k-th type of energy storage during time period t. The maximum allowable energy for the k-th type of energy storage. This represents the remaining energy of the k-th type of energy storage during time period t-1. Let η be the discharge power component of the k-th type of energy storage during time period t, where Δt is the time step and η is the discharge power component of the k-th type of energy storage. disch,k Let k be the energy storage discharge efficiency. For the charging power component, η chg,k For the charging efficiency of the k-th type of energy storage, The initial energy for scheduling the k-th type of energy storage, The initial preset energy for the k-th type of energy storage scheduling, For the energy at the end of the k-th type of energy storage dispatch, The preset energy for the end of the k-th type of energy storage dispatch is P. feed-in,max P is the maximum power that the distribution substation is allowed to feed back into the grid. draw,max The maximum power allowed to flow from the grid into the distribution substation area. S represents the total apparent power flowing through the main device during time period t. rated Main equipment rated capacity, V min The lower limit of the allowable voltage. Let V be the voltage amplitude at node i during time period t. max The upper limit of the allowable voltage, SOC min,k For the minimum allowable state of charge of the k-th type of energy storage, C ess,k For the rated energy capacity of the k-th type of energy storage, SOC max,k For the k-th type of energy storage, the maximum allowable state of charge is... Let ΔP be the charging and discharging power of the k-th type of energy storage during time period t-1. grid,max ΔP represents the maximum value of the power grid change. ess,k,max This represents the maximum change in charging and discharging power for the k-th type of energy storage.

[0150] In this embodiment, before using the current observation state of the low-voltage distribution substation as input to the pre-trained agent to obtain the charging and discharging power of each energy storage unit in the low-voltage distribution substation output by the pre-trained agent, the following steps are included:

[0151] When a low-voltage distribution area is at risk of heavy overload, the energy storage type participating in the coordinated dispatch is set to power-type energy storage. This step aims to prioritize the use of power-type energy storage (such as supercapacitors and flywheels) for rapid discharge, utilizing their millisecond-level response speed and high power density to quickly reduce peak load and ensure that the load rate of critical equipment does not exceed the safety threshold.

[0152] When a low-voltage distribution area is at risk of power curtailment, the energy storage type participating in the coordinated dispatch is designated as energy-type energy storage. This step aims to prioritize the dispatch of energy-type energy storage (such as lithium batteries and flow batteries) for charging, utilizing their higher energy density to maximize the absorption of surplus renewable energy and minimize power curtailment.

[0153] In one embodiment, the power-type energy storage includes supercapacitors and flywheel energy storage, and the energy-type energy storage includes lithium batteries and flow batteries.

[0154] Based on the above inventive concept, this invention provides a low-voltage distribution transformer area intelligent fusion terminal multi-type energy storage coordination control APP, which is an embedded software program deployed in the intelligent fusion terminal equipment of the transformer area. As the local control core of the system, it realizes the automated coordination control of multi-type energy storage through data integration, strategy execution and communication coordination.

[0155] Main functions include:

[0156] (1) Multi-source data integration and standardized processing: Real-time reception and parsing of raw data (grid parameters, energy storage status, renewable energy power generation, meteorological information, etc.) from the data acquisition module; performing data format standardization conversion and encapsulating it into a structured data stream according to a predefined information model; local caching of high-frequency acquired data (such as second-level / minute-level) and support for network interruption resume mechanism.

[0157] (2) Optimize command parsing and security verification: Receive energy storage charging and discharging strategy commands issued by the cloud / local optimization module; perform command security prediction and verify the compatibility between the command and the real-time status of the energy storage device; verify whether the power command value exceeds the device safety limit; detect the risk of conflict between the command and the load rate constraint of the main equipment in the distribution area.

[0158] (3) Multi-type energy storage coordinated control: Dynamically allocate charging and discharging tasks to different types of energy storage units according to instructions. During periods of heavy overload, prioritize sending millisecond-level discharge instructions to power-type energy storage (such as supercapacitors and flywheel energy storage); during periods of power curtailment risk, prioritize scheduling energy-type energy storage (lithium batteries and flow batteries) to perform charging tasks; realize the time-series coordinated control of power instructions, such as superimposing and matching the target value of charging and discharging power of multiple energy storage devices.

[0159] (4) Edge computing and emergency autonomy: When the network is interrupted, the local backup control strategy is activated, and rolling optimization is performed based on the last valid instruction and real-time load data. Preset rule base is triggered, such as forced discharge to alleviate overload when SOC>80%.

[0160] (5) Operation status reporting and remote interaction: Compressed and encrypted upload of key operation indicators (minute-level load rate, curtailment rate, energy storage health status); supports remote parameter configuration updates (such as constraint thresholds, communication protocols, strategy weight coefficients); provides API interfaces for cloud systems to call real-time data.

[0161] Example 2

[0162] Based on the same inventive concept, the present invention also provides a multi-type energy storage coordinated control device for a low-voltage distribution substation, the multi-type energy storage coordinated control device for a low-voltage distribution substation comprising:

[0163] The analysis module is used to take the current observation state of the low-voltage distribution substation as the input of the pre-trained agent and obtain the charging and discharging power of each energy storage in the low-voltage distribution substation as output by the pre-trained agent.

[0164] The scheduling module is used to coordinate and control each energy storage unit by utilizing the current charging and discharging power of each energy storage unit in the low-voltage distribution area.

[0165] Preferably, the Markov decision process corresponding to the intelligent agent is: (S t A t ,S t+1 ,r t ), where S t Let A be the observed state of the low-voltage distribution station area at time t. t Let S be the action vector at time t. t+1 The observation status of the low-voltage distribution radio station area at time t+1, r t Let t be the reward function at time t.

[0166] Furthermore, the observed status includes: the state of charge of each energy storage, the real-time load of the low-voltage distribution substation, the real-time renewable energy generation power, electricity price, the grid power and time information of the previous period, and the action vector includes: the charging and discharging power of each energy storage.

[0167] Furthermore, the reward function at time t is as follows:

[0168]

[0169] In the above formula, β1, β2, β3, and β4 are the first, second, third, and fourth weighting coefficients, respectively, and Cost... t Let t be the component of economic cost in time period t. Let t be the power curtailed during time period t, and LoadRate be the power curtailed during time period t. t Let α be the load factor for time period t. max As a safety threshold, Let t be the power of the power grid during time period t. The power of the power grid during the time period t-1.

[0170] Furthermore, the economic cost components for time period t are as follows:

[0171]

[0172] In the above formula, The price of electricity purchased from the upper-level power grid during time period t. Let be the equivalent usage cost coefficient of the k-th type of energy storage during time period t. Let K be the charging and discharging power of the k-th type of energy storage during time period t, where K is the total number of energy storage types.

[0173] Furthermore, the reward function at time t satisfies the following constraints: system power balance constraint, energy storage device power constraint, energy storage device energy / state of charge constraint, energy storage device energy state dynamic constraint, state of charge first and last state constraint, grid switching power constraint, distribution area main equipment load rate constraint, node voltage constraint, and power change rate constraint.

[0174] Furthermore, the system power balance constraints are as follows:

[0175]

[0176] The power constraints of the energy storage device are as follows:

[0177]

[0178] The energy / state of charge constraints of the energy storage device are as follows:

[0179]

[0180] The dynamic energy state constraints of the energy storage device are as follows:

[0181]

[0182] The first and last state constraints of the charged state are as follows:

[0183]

[0184] The power grid switching power constraints are as follows:

[0185]

[0186] The load rate constraints for the main equipment in the transformer area are as follows:

[0187]

[0188] The node voltage constraints are as follows:

[0189]

[0190] The power change rate constraint is as follows:

[0191] and

[0192] In the above formula, Let t be the total renewable energy power generation during the period. Let t be the total load power during time period t. Let P be the system line loss power during time period t. chg,max,k P is the maximum allowable charging power for the k-th type of energy storage. disch,max,k The maximum allowable discharge power for the k-th type of energy storage is... The minimum allowable energy for the k-th type of energy storage. Let be the remaining energy of the k-th type of energy storage during time period t. The maximum allowable energy for the k-th type of energy storage. This represents the remaining energy of the k-th type of energy storage during time period t-1. Let η be the discharge power component of the k-th type of energy storage during time period t, where Δt is the time step and η is the discharge power component of the k-th type of energy storage. disch,k Let k be the energy storage discharge efficiency. For the charging power component, η chg,k For the charging efficiency of the k-th type of energy storage, The initial energy for scheduling the k-th type of energy storage, The initial preset energy for the k-th type of energy storage scheduling, For the energy at the end of the k-th type of energy storage dispatch, The preset energy for the end of the k-th type of energy storage dispatch is P. feed-in,max P is the maximum power that the distribution substation is allowed to feed back into the grid. draw,max The maximum power allowed to flow from the grid into the distribution substation area. S represents the total apparent power flowing through the main device during time period t. rated Main equipment rated capacity, V min The lower limit of the allowable voltage. Let V be the voltage amplitude at node i during time period t.max The upper limit of the allowable voltage, SOC min,k For the minimum allowable state of charge of the k-th type of energy storage, C ess,k For the rated energy capacity of the k-th type of energy storage, SOC max,k For the k-th type of energy storage, the maximum allowable state of charge is... Let ΔP be the charging and discharging power of the k-th type of energy storage during time period t-1. grid,max ΔP represents the maximum value of the power grid change. ess,k,max This represents the maximum change in charging and discharging power for the k-th type of energy storage.

[0193] Preferably, before using the current observed state of the low-voltage distribution substation as input to the pre-trained agent to obtain the charging and discharging power of each energy storage unit in the low-voltage distribution substation output by the pre-trained agent, the following steps are included:

[0194] When a low-voltage distribution area is at risk of severe overload, the energy storage type participating in the coordinated dispatch should be set to power-type energy storage.

[0195] When a low-voltage distribution area is in a period of power curtailment risk, the energy storage type participating in the coordinated dispatch should be set as energy storage.

[0196] Furthermore, the power-type energy storage includes supercapacitors and flywheel energy storage, and the energy-type energy storage includes lithium batteries and flow batteries.

[0197] Example 3

[0198] Based on the same inventive concept, this invention also provides a computer device, which includes a processor and a memory. The memory stores a computer program, which includes program instructions. The processor executes the program instructions stored in the computer storage medium. The processor may be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. It is the computing and control core of the terminal, and is suitable for implementing one or more instructions. Specifically, it is suitable for loading and executing one or more instructions in the computer storage medium to realize the corresponding method flow or corresponding function, so as to realize the steps of the low-voltage distribution substation multi-type energy storage coordinated control method in the above embodiments.

[0199] Example 4

[0200] Based on the same inventive concept, this invention also provides a storage medium, specifically a computer-readable storage medium (Memory), which is a memory device in a computer device used to store programs and data. It is understood that the computer-readable storage medium here can include both the built-in storage medium in the computer device and extended storage media supported by the computer device. The computer-readable storage medium provides storage space that stores the terminal's operating system. Furthermore, this storage space also stores one or more instructions suitable for loading and execution by a processor. These instructions can be one or more computer programs (including program code). It should be noted that the computer-readable storage medium here can be a high-speed RAM memory or a non-volatile memory, such as at least one disk storage device. The processor can load and execute one or more instructions stored in the computer-readable storage medium to implement the steps of the low-voltage distribution substation multi-type energy storage coordinated control method in the above embodiments.

[0201] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0202] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0203] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0204] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0205] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit it. Although the present invention has been described in detail with reference to the above embodiments, those skilled in the art should understand that modifications or equivalent substitutions can still be made to the specific implementation of the present invention. Any modifications or equivalent substitutions that do not depart from the spirit and scope of the present invention should be covered within the scope of protection of the claims of the present invention.

Claims

1. A low-voltage power distribution area multi-type energy storage coordination control method, characterized in that, The method comprises: The current observation state of the low-voltage power distribution area is taken as the input of the pre-trained agent, and the current charging and discharging power of each energy storage of the low-voltage power distribution area output by the pre-trained agent is obtained; The charging and discharging power of each energy storage is used to coordinate and control each energy storage.

2. The method of claim 1, wherein, The Markov decision process corresponding to the intelligent agent is: (S t ,A t ,S t+1 ,r t ), wherein S t is an observation state of a low-voltage distribution area at time t, A t is an action vector at time t, S t+1 is an observation state of the low-voltage distribution area at time t+1, and r t is a reward function at time t.

3. The method of claim 2, wherein, The observation state comprises the state of charge of each energy storage, the real-time load of the low-voltage power distribution area, the real-time renewable energy power generation, the electricity price, the power grid power of the last period and the time information, and the action vector comprises the charging and discharging power of each energy storage.

4. The method of claim 2, wherein, The reward function at the t time is as follows: In the above formula, β1, β2, β3, β4 are the first, second, third, and fourth weight coefficients, respectively, Cost t is the economic cost component of the t period, is the abandoned power of the t period, LoadRate t is the load rate of the t period, Δ max is a safety threshold, is the grid power of the t period, is the grid power of the t-1 period.

5. The method of claim 4, wherein, The economic cost component of the t period is as follows: In the above formula, is the electricity price of purchasing electricity from the upper grid for the t period, is the equivalent use cost coefficient of the kth type of energy storage for the t period, is the charging and discharging power of the kth type of energy storage for the t period, and K is the total number of energy storage types.

6. The method of claim 5, wherein, The reward function at the t time satisfies the following constraints: system power balance constraint, energy storage device power constraint, energy storage device energy / state of charge constraint, energy storage device energy state dynamic constraint, state of charge first / last state constraint, grid exchange power constraint, area main device load rate constraint, node voltage constraint, and power change rate constraint.

7. The method of claim 6, wherein, The system power balance constraint is as follows: The energy storage device power constraint is as follows: The energy storage device energy / state of charge constraint is as follows: The energy storage device energy state dynamic constraint is as follows: The state of charge first / last state constraint is as follows: The grid exchange power constraint is as follows: The area main device load rate constraint is as follows: The node voltage constraint is as follows: The power change rate constraint is as follows: and In the above formula, is the total renewable power generation of the t period, is the total load power of the t period, is the system line loss power of the t period, P chg,max,k is the maximum allowed charging power of the kth energy storage, disch,max,k is the maximum allowed discharging power of the kth energy storage, is the minimum energy allowed for the kth energy storage, is the residual energy of the kth energy storage in the t period, is the maximum energy allowed for the kth energy storage, is the residual energy of the kth energy storage in the t-1 period, is the discharging power component of the kth energy storage in the t period, Δt is the time step, η disch,k is the discharging efficiency of the kth energy storage, is the charging power component, η chg,k is the charging efficiency of the kth energy storage, is the starting energy of the kth energy storage for scheduling, is the starting preset energy of the kth energy storage for scheduling, is the ending energy of the kth energy storage for scheduling, is the ending preset energy of the kth energy storage for scheduling, P feed-in,max is the maximum power allowed to be sent back to the grid by the distribution area, P draw,max is the maximum power allowed to flow from the grid, is the total apparent power flowing through the main device in the t period, S rated is the rated capacity of the main device, V min is the lower limit of the allowed voltage, is the voltage amplitude of node i in the t period, V max is the upper limit of the allowed voltage, SOC min,k is the minimum state of charge allowed for the kth energy storage, C ess,k is the rated energy capacity of the kth energy storage, SOC max,k is the maximum state of charge allowed for the kth energy storage, is the charging and discharging power of the kth energy storage in the t-1 period, ΔP grid,max is the maximum value of the grid power change, ΔP ess,k,max is the maximum value of the charging and discharging power of the kth energy storage.

8. The method of claim 1, wherein, Before the current observation state of the low-voltage power distribution area is taken as the input of the pre-trained agent, and the current charging and discharging power of each energy storage of the low-voltage power distribution area output by the pre-trained agent is obtained, the method comprises: When the low-voltage power distribution area is in a heavy overload risk period, the type of energy storage participating in coordinated scheduling is set to power-type energy storage; When the low-voltage power distribution area is in a power curtailment risk period, the type of energy storage participating in coordinated scheduling is set to energy-type energy storage.

9. The method of claim 8, wherein, The power-type energy storage comprises supercapacitors and flywheel energy storage, and the energy-type energy storage comprises lithium batteries and flow batteries.

10. A low-voltage power distribution area multi-type energy storage coordinated control device, characterized in that, The device comprises: An analysis module is configured to take the current observation state of the low-voltage power distribution area as the input of the pre-trained agent, and obtain the charging and discharging power of each energy storage of the low-voltage power distribution area output by the pre-trained agent; A scheduling module is configured to coordinate and control each energy storage by using the charging and discharging power of each energy storage of the low-voltage power distribution area.

11. The apparatus of claim 10, wherein, The Markov decision process corresponding to the intelligent agent is: (S t , A t , S t+1 , r t ), wherein S t is the observation state of the low-voltage distribution substation area at time t, A t is the action vector at time t, S t+1 is the observation state of the low-voltage distribution substation area at time t+1, and r t is the reward function at time t.

12. The apparatus of claim 11, wherein, The observation state comprises the state of charge of each energy storage, the real-time load of the low-voltage power distribution area, the real-time renewable energy power generation, the electricity price, the power grid power of the last period and the time information, and the action vector comprises the charging and discharging power of each energy storage.

13. The apparatus of claim 11, wherein, The reward function at the t time is as follows: In the above formula, β1, β2, β3, β4 are the first, second, third, and fourth weight coefficients, respectively, Cost t is the economic cost component for the t period, is the curtailed power for the t period, LoadRate t is the load rate for the t period, Δ max is the safety threshold, is the grid power for the t period, is the grid power for the t-1 period.

14. The apparatus of claim 13, wherein, The economic cost component of the t period is as follows: In the above formula, is the electricity price of purchasing electricity from the upper grid for the t period, is the equivalent use cost coefficient of the kth type of energy storage for the t period, is the charging and discharging power of the kth type of energy storage for the t period, and K is the total number of energy storage types.

15. The apparatus of claim 14, wherein, The reward function at the t time satisfies the following constraints: system power balance constraint, energy storage device power constraint, energy storage device energy / state of charge constraint, energy storage device energy state dynamic constraint, state of charge first / last state constraint, grid exchange power constraint, area main device load rate constraint, node voltage constraint, and power change rate constraint.

16. The apparatus of claim 15, wherein, The system power balance constraint is as follows: The energy storage device power constraint is as follows: The energy storage device energy / state of charge constraint is as follows: The energy storage device energy state dynamic constraint is as follows: The state of charge first / last state constraint is as follows: The grid exchange power constraint is as follows: The area main device load rate constraint is as follows: The node voltage constraint is as follows: The power change rate constraint is as follows: The state-of-charge first and last state constraints are as follows: The power exchange constraints of the power grid are as follows: The load rate constraints of the main device of the low-voltage distribution area are as follows: The node voltage constraints are as follows: The power change rate constraints are as follows: and In the above formula, is the total renewable power generation of the t period, is the total load power of the t period, is the system line loss power of the t period, P chg,max,k is the maximum allowed charging power of the kth energy storage, disch,max,k is the maximum allowed discharging power of the kth energy storage, is the minimum energy allowed for the kth energy storage, is the residual energy of the kth energy storage in the t period, is the maximum energy allowed for the kth energy storage, is the residual energy of the kth energy storage in the t-1 period, is the discharging power component of the kth energy storage in the t period, Δt is the time step, η disch,k is the discharging efficiency of the kth energy storage, is the charging power component, η chg,k is the charging efficiency of the kth energy storage, is the dispatch starting energy of the kth energy storage, is the dispatch starting preset energy of the kth energy storage, is the dispatch ending energy of the kth energy storage, is the dispatch ending preset energy of the kth energy storage, P feed-in,max is the maximum power allowed to be sent back to the grid by the distribution area, P draw,max is the maximum power allowed to flow from the grid, is the total apparent power flowing through the main device in the t period, S rated is the rated capacity of the main device, V min is the lower limit of the allowed voltage, is the voltage amplitude of node i in the t period, V max is the upper limit of the allowed voltage, SOC min,k is the minimum state of charge allowed for the kth energy storage, C ess,k is the rated energy capacity of the kth energy storage, SOC max,k is the maximum state of charge allowed for the kth energy storage, is the charging and discharging power of the kth energy storage in the t-1 period, ΔP grid,max is the maximum value of the grid power change, ΔP ess,k,max is the maximum value of the charging and discharging power of the kth energy storage.

17. The apparatus of claim 10, wherein, Before the low-voltage distribution area current observation state is taken as the input of the pre-trained agent, and the pre-trained agent output low-voltage distribution area current each energy storage charging and discharging power is obtained, the following is included: When the low-voltage distribution area is in a heavy overload risk period, the type of energy storage participating in coordinated scheduling is set to power type energy storage; When the low-voltage distribution area is in a power abandonment risk period, the type of energy storage participating in coordinated scheduling is set to energy type energy storage.

18. The apparatus of claim 17, wherein, The power type energy storage includes super capacitor and flywheel energy storage, and the energy type energy storage includes lithium battery and flow battery.

19. A computer device, comprising: It includes: One or more processors; The processor is used to execute one or more programs; When the one or more programs are executed by the one or more processors, the low-voltage distribution area multi-type energy storage coordinated control method as claimed in any one of claims 1 to 9 is implemented.

20. A computer-readable storage medium, characterized in that, The computer program is stored thereon, and when the computer program is executed, the low-voltage distribution area multi-type energy storage coordinated control method as claimed in any one of claims 1 to 9 is implemented.

Images