Green electricity energy storage allocation system based on artificial intelligence

Abstract

The invention proposes a green electricity energy storage allocation system based on artificial intelligence, and relates to the technical field of green electricity energy storage scheduling, and the system comprises a power transmission and distribution network which is used for achieving the transmission and distribution of power; the green electricity and energy storage facility comprises a green electricity facility used for generating clean electric energy and an energy storage facility used for storing and releasing energy; the management and decision-making platform comprises a power grid management system; a user management system; an auxiliary decision-making system; the artificial intelligence platform is used for collecting and analyzing the power grid operation data and the external environment data, generating optimization and adjustment suggestions through a large model, and sending the suggestions to the auxiliary decision making system; wherein the external power introduction equipment, the energy storage facility, the green power facility and the power grid distribution equipment are connected by the power switching and fusion equipment. According to the invention, intelligent regulation and control of green power and energy storage equipment can be realized, the energy utilization efficiency is improved, the use cost is reduced, the power grid stability is enhanced, and green low-carbon operation is realized.

Description

Technical Field

[0001] The present invention relates to the technical field of green electricity energy storage scheduling, and in particular to a green electricity energy storage scheduling system based on artificial intelligence. Background Art

[0002] As global climate change intensifies and energy crises become increasingly prominent, the development and utilization of green energy has become a core issue in social development. Green energy such as wind power and photovoltaics are highly favored because of their clean, renewable and low-carbon properties. However, these green energy sources are inherently volatile, random and have anti-peak characteristics, which poses a huge challenge to the safe and stable operation of the power grid. At present, the power system is facing the opportunities and challenges of how to efficiently absorb large-scale green energy and achieve the complementarity of multiple energy sources.

[0003] In order to meet these challenges, energy storage technology is increasingly being used in power systems. Energy storage systems can store excess electricity when green energy is in sufficient supply, and release electricity when demand peaks or green energy supply is insufficient, thereby smoothing the volatility of green energy and improving the stability and reliability of the power grid. At the same time, energy storage systems can also provide auxiliary services such as frequency regulation and voltage regulation to further enhance the operation quality of the power grid.

[0004] In recent years, with the rapid development of artificial intelligence technology, its application in power systems has become increasingly widespread. Through advanced technical means such as data analysis, model prediction, and optimization control, artificial intelligence technology can significantly improve the power system's ability to absorb and coordinate different types of power sources. In the field of green energy, the primary role of artificial intelligence is energy management and optimization. With the help of intelligent monitoring and analysis tools, AI can accurately predict the peak and valley periods of energy demand, thereby flexibly adjusting energy supply, ensuring the maximum use of renewable energy, and reducing dependence on traditional energy.

[0005] However, existing green electricity storage dispatch systems often lack the ability to conduct comprehensive analysis and decision-making on multi-source data, making it difficult to achieve truly intelligent dispatch and optimized control in a complex and changing power grid environment. Summary of the invention

[0006] In view of this, the present invention proposes a green electricity energy storage dispatching system based on artificial intelligence, which realizes intelligent regulation of green electricity and energy storage equipment by integrating the power transmission and distribution network, green electricity and energy storage facilities, management decision-making platform and artificial intelligence platform, improves energy utilization efficiency, reduces use costs, enhances grid stability, and realizes green and low-carbon operation.

[0007] The technical solution of the present invention is implemented as follows: The present invention provides a green electricity storage allocation system based on artificial intelligence, comprising:

[0008] Power transmission and distribution network, used to achieve power transmission and distribution, including external power introduction equipment, power switching and fusion equipment, power grid distribution equipment and user access equipment;

[0009] Green electricity and energy storage facilities, including green electricity facilities for generating clean electricity and energy storage facilities for storing and releasing energy;

[0010] Management and decision-making platform, including:

[0011] Power grid management system, used to collect power equipment information and execute dispatching decisions;

[0012] User management system, used to collect user information and interact with users;

[0013] A decision support system to process the recommendations of the AI ​​platform and generate decision instructions;

[0014] Artificial intelligence platform, which is used to collect and analyze power grid operation data and external environment data, generate optimization and adjustment suggestions through large models, and send the suggestions to the auxiliary decision-making system;

[0015] Among them, power switching and fusion equipment connects external power introduction equipment, energy storage facilities, green power facilities and grid distribution equipment.

[0016] On the basis of the above technical solution, preferably, the artificial intelligence platform is also used for:

[0017] Dynamically adjust the charging and discharging strategies of energy storage facilities according to the power supply and demand situation; predict changes in green power supply and user power consumption; provide capacity and layout recommendations for green power and energy storage facilities; manage energy storage batteries; analyze power grid anomalies and propose fault solutions.

[0018] On the basis of the above technical solution, preferably, in an energy storage environment without green energy supply, the artificial intelligence platform calculates the energy storage absorption capacity C and the energy storage discharge capacity G by the following formula:

[0019]

[0020]

[0021] In the formula, ε is the power conversion efficiency; is the power transmission efficiency; S is the power supply capacity; St is the total power supplied within a certain period of time; D(t) is the power usage; τ is the energy storage conversion efficiency; t1, t2, t3, t4, t5, t6 are time nodes, in hours;

[0022] The artificial intelligence platform regulates the charging and discharging cycles of the energy storage facilities based on the above calculation results.

[0023] On the basis of the above technical solution, preferably, in an energy storage environment with green energy supply, the artificial intelligence platform adjusts the energy storage absorption capacity C' and the energy storage discharge capacity G' according to the following formula:

[0024]

[0025]

[0026] Where G(t) is the green electricity supply; θ is the efficiency of converting green energy into electrical energy; t'1, t'2, t'3, t'4, t'5, t'6 are the time nodes after considering the green electricity supply, in hours;

[0027] Based on the above calculation results, the artificial intelligence platform optimizes and controls the charging and discharging strategies of energy storage facilities to maximize the efficiency of green electricity utilization.

[0028] On the basis of the above technical solutions, preferably, the artificial intelligence platform manages the energy storage battery, including the energy storage battery capacity design, optimization of energy balance and charging and discharging strategies, and implementation of temperature management and thermal safety control.

[0029] On the basis of the above technical solution, preferably, the artificial intelligence platform considers the following factors when designing the energy storage battery capacity:

[0030] Meet the initial impact discharge current of accident discharge;

[0031] Meet the continuous discharge capacity requirements in the event of a total power outage;

[0032] Load current at different stages;

[0033] Reliability coefficients of the energy storage release part and the accident impact part;

[0034] Capacity conversion factors for each calculation stage.

[0035] On the basis of the above technical solution, preferably, in order to meet the requirements of the initial impact discharge current capacity of the final stage of energy storage discharge superimposed on the accident discharge, the initial 1min impact battery 10h or 5h discharge rate calculation capacity is calculated according to the following formula:

[0036]

[0037] In the formula, C cho Calculate the capacity for the initial 1-minute impact battery with a 10-hour or 5-hour discharge rate; I is the reliability coefficient of the energy storage release part; t K is the discharge current of the energy storage release part t hours; c Conversion factor for the released portion of the energy storage capacity; is the reliability coefficient of the accident impact part; Icho K is the impulse discharge current at the initial stage of the accident for 1 minute; cho It is the capacity conversion factor of the impact load in the initial 1 minute of the accident.

[0038] On the basis of the above technical solution, preferably, in order to meet the continuous discharge capacity requirements of energy storage discharge in the middle stage of superimposed accident full power outage state, excluding the initial 1min impact discharge current, the calculated capacity of each stage is calculated as follows:

[0039] Phase 1 calculation capacity:

[0040]

[0041] Calculate the capacity at stage n, n ≥ 2:

[0042]

[0043] In the formula, C c1 The calculated capacity of the battery for the first stage accident current at a 10h or 5h discharge rate; C cn I is the calculated capacity of the battery at the nth stage of the accident current at a 10h or 5h discharge rate; tm The discharge current of the energy storage release part tm hours; I1~I n is the load current at each stage; K c1 ~K cn K is the capacity conversion factor of the corresponding discharge time in each calculation stage; k is the reliability coefficient;

[0044] Random load calculation capacity:

[0045]

[0046] In the formula, C r Calculate capacity for random loads; I r is the random load current; K cr is the capacity conversion factor for random impact load;

[0047] C r Superimposed on C c2 ~C cn The largest stage, with C c1 Compare and take the larger value, and add them together to calculate the battery emergency current capacity.

[0048] On the basis of the above technical solution, preferably, the artificial intelligence platform adopts the following energy balance equation to model when optimizing energy balance and charging and discharging strategy:

[0049] E(t)=E(tt p )+η ch ·Pch (t)·Δt-η dis P dis (t)·Δt-P loss (t)·Δt

[0050] Where, E(t) is the remaining battery energy at time t, E(tt p ) is the remaining battery energy at the previous moment, η ch and η dis are the charging and discharging efficiencies, P ch (t) and P dis (t) are the charging and discharging powers at time t, Δt is the time step, P loss (t) is the internal power loss of the battery at time t;

[0051] Based on the energy balance equation, combined with real-time grid load, green power supply forecast and electricity price information, the charging and discharging power P is dynamically adjusted. ch (t) and P dis (t).

[0052] On the basis of the above technical solution, preferably, the artificial intelligence platform performs temperature management and thermal safety control:

[0053] The following heat balance equation is used to estimate the change in battery temperature:

[0054]

[0055] Where, T(t) is the battery temperature at time t; P gen (t) is the total heat power generated by charging, discharging and other internal processes; h is the heat transfer coefficient; A is the battery surface area; T amb is the ambient temperature; m is the battery mass; C p is the specific heat capacity;

[0056] To ensure that the battery temperature does not exceed safe limits:

[0057] T(t)≤T max,safe

[0058] Among them, T max,safe The upper limit of battery safety temperature;

[0059] Dynamically adjust the charging and discharging strategy based on temperature management results:

[0060] When the temperature approaches the upper safety limit, reduce the charging power or increase the cooling intensity;

[0061] Under extreme temperature conditions, charging and discharging operations are temporarily interrupted to prioritize battery safety.

[0062] Compared with the prior art, the present invention has the following beneficial effects:

[0063] (1) The present invention realizes the intelligent control of green electricity and energy storage equipment by integrating the power transmission and distribution network, green electricity and energy storage facilities, management decision-making platform and artificial intelligence platform. The system can effectively improve energy utilization efficiency, reduce usage costs, enhance grid stability, and achieve green and low-carbon operation. At the same time, the system's adaptive learning ability enables it to continuously optimize decision-making strategies and adapt to complex and changing grid environments, providing a comprehensive intelligent solution for regional power management;

[0064] (2) The present invention adopts a storage capacity design method based on multi-stage calculation, taking into account the capacity requirements of the energy storage release part and the accident impact part. By introducing the reliability coefficient and capacity conversion coefficient, the system can more accurately estimate the required energy storage capacity to ensure that sufficient power support can be provided in normal operation and accident situations. This design method improves the reliability and stability of the system, while avoiding over-design of energy storage facilities and optimizing investment costs;

[0065] (3) The present invention uses the energy balance equation to model the energy storage system and develops an intelligent charging and discharging strategy based on it. By considering factors such as the remaining energy of the battery, the charging and discharging efficiency, and the internal loss, the system can optimize the charging and discharging power in real time, maximizing economic benefits while ensuring the stability of the power grid. This method significantly improves the utilization efficiency of the energy storage system, extends the battery life, and enhances the system's ability to respond to power grid fluctuations;

[0066] (4) The present invention introduces a temperature management and thermal safety control mechanism based on the thermal balance equation. By real-time monitoring and predicting battery temperature changes, the system can dynamically adjust the charging and discharging strategy to ensure that the battery temperature always remains within a safe range. This active temperature management method not only improves the safety of the system, but also extends the service life of the battery, reduces maintenance costs, and ensures the stable operation of the energy storage system under various environmental conditions;

[0067] (5) The grid monitoring optimization process proposed in the present invention integrates real-time monitoring, intelligent analysis and automatic decision-making functions. By continuously monitoring the operation status of the grid, the artificial intelligence platform can promptly detect anomalies or predict potential faults. The system automatically analyzes the cause of the fault and proposes prioritized solutions based on multiple indicators. For solutions that can be operated remotely, the system can execute quickly; for solutions that require on-site operation, the system will generate detailed instructions. This intelligent monitoring and decision-making process greatly improves the fault response speed, reduces human errors, and improves the overall reliability and operating efficiency of the grid. BRIEF DESCRIPTION OF THE DRAWINGS

[0068] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0069] Figure 1 is a system architecture diagram of the present invention;

[0070] Figure 2 This is a flow chart of power grid monitoring optimization according to the present invention. DETAILED DESCRIPTION

[0071] The following will be combined with the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0072] like Figure 1 As shown, the present invention provides a green electricity storage allocation system based on artificial intelligence, comprising:

[0073] Power transmission and distribution network, used to achieve power transmission and distribution, including external power introduction equipment, power switching and fusion equipment, power grid distribution equipment and user access equipment;

[0074] Green electricity and energy storage facilities, including green electricity facilities for generating clean electricity and energy storage facilities for storing and releasing energy;

[0075] Management and decision-making platform, including:

[0076] Power grid management system, used to collect power equipment information and execute dispatching decisions;

[0077] User management system, used to collect user information and interact with users;

[0078] A decision support system to process the recommendations of the AI ​​platform and generate decision instructions;

[0079] Artificial intelligence platform, which is used to collect and analyze power grid operation data and external environment data, generate optimization and adjustment suggestions through large models, and send the suggestions to the auxiliary decision-making system;

[0080] Among them, power switching and fusion equipment connects external power introduction equipment, energy storage facilities, green power facilities and grid distribution equipment.

[0081] The AI ​​platform is also used to:

[0082] Dynamically adjust the charging and discharging strategies of energy storage facilities according to the power supply and demand situation; predict changes in green power supply and user power consumption; provide capacity and layout recommendations for green power and energy storage facilities; manage energy storage batteries; analyze power grid anomalies and propose fault solutions.

[0083] In this embodiment, the green electricity storage dispatching system based on artificial intelligence consists of four main parts: power transmission and distribution network, green electricity and energy storage facilities, management and decision-making platform, and artificial intelligence platform (i.e. Figure 1 These four parts work closely together to realize intelligent green power storage deployment.

[0084] The power transmission and distribution network is the infrastructure of the entire system, responsible for the transmission and distribution of electricity. It includes the following components:

[0085] a) External power introduction equipment: connect to the external power grid and introduce power.

[0086] b) Power switching and integration equipment: This is the core connection point of the system, responsible for connecting external power introduction equipment, energy storage facilities, green power facilities and grid distribution equipment. It consists of transformers, circuit breakers, disconnectors, rectifiers, inverters and other equipment and controllers, and plays the role of switching and integration.

[0087] c) Grid distribution equipment: responsible for distributing electricity to different users or areas.

[0088] d) User access equipment: connects to end users and realizes the final distribution of electricity.

[0089] Green electricity and energy storage facilities include two key facilities:

[0090] a) Green power facilities: Equipment used to generate clean electricity, which may include wind turbines, solar panels, hydroelectric power generation equipment, etc. These facilities convert renewable energy into electricity.

[0091] b) Energy storage facilities: devices used to store and release energy. They are able to store excess electricity when the electricity supply is sufficient and release electricity when needed, thereby balancing supply and demand and improving the stability and flexibility of the system.

[0092] The management and decision-making platform is the brain of the system, responsible for coordinating the operation of various parts. It includes three subsystems:

[0093] a) Grid management system: responsible for collecting power equipment information and executing dispatching decisions. It monitors the operating status of power switching and fusion equipment, grid distribution equipment, user access equipment, energy storage facilities and green power facilities, and adjusts their operating parameters according to the decision results.

[0094] b) User management system: responsible for collecting user information and interacting with users. It collects information such as user electricity demand and preferences, and provides users with relevant services and feedback.

[0095] c) Decision-making support system: responsible for processing the recommendations of the artificial intelligence platform and generating decision-making instructions. It converts the analysis results of the artificial intelligence platform into specific operation instructions and passes these instructions to the power grid management system for execution.

[0096] The AI ​​platform is the intelligent core of the system, responsible for advanced analysis and optimization. Its main functions include:

[0097] a) Collect and analyze power grid operation data and external environment data.

[0098] b) Generate optimization and adjustment suggestions through large models.

[0099] c) Send the recommendations to the decision support system.

[0100] d) Dynamically adjust the charging and discharging strategies of energy storage facilities according to electricity supply and demand.

[0101] e) Predict changes in green electricity supply and user electricity consumption.

[0102] f) Provide capacity and layout recommendations for green power and energy storage facilities.

[0103] g) Perform energy storage battery management.

[0104] h) Analyze power grid anomalies and propose fault solutions.

[0105] This artificial intelligence platform continuously improves the system's operating efficiency and reliability through continuous learning and optimization.

[0106] Through the coordinated work of these four parts, the system can realize the intelligent control of green electricity and energy storage equipment, improve energy efficiency, reduce usage costs, enhance grid stability, and achieve green and low-carbon operation. The design of the system fully considers the characteristics of green energy and the needs of modern power grids, and provides a comprehensive solution for building an intelligent, efficient and sustainable power system.

[0107] Specifically, in one embodiment of the present invention, the artificial intelligence platform effectively improves energy utilization efficiency, reduces usage costs, and improves green and low-carbon levels by intelligently regulating the operation cycle of green electricity and energy storage equipment. This process is mainly divided into three parts: energy storage environment without green energy supply, energy storage environment with green energy supply, and intelligent suggestions for green electricity and energy storage facilities.

[0108] 1. Energy storage environment without green energy supply

[0109] In this case, energy storage mainly comes from the power grid supply. The artificial intelligence platform regulates through the following steps:

[0110] 1. Calculate the energy storage absorption capacity and discharge capacity

[0111] The AI ​​platform calculates the energy storage absorption capacity C and energy storage discharge capacity G using the following formula:

[0112]

[0113]

[0114] In the formula, ε is the power conversion efficiency; is the power transmission efficiency; S is the power supply capacity; St is the total power supplied within a certain period of time; D(t) is the power usage; τ is the energy storage conversion efficiency; t1, t2, t3, t4, t5, t6 are time nodes, in hours.

[0115] 2. Ensure that energy storage capacity meets demand

[0116] The system needs to meet the following conditions: C ≥ ωG, where ω is the redundancy factor, to ensure that the energy supply of the energy storage facility can meet the power load under certain emergencies. The value is determined based on the probability of the development of emergencies and the peak value. It can be 1.3 in the early stage, and then adjusted by the artificial intelligence platform based on the risk probability and consequences.

[0117] 3. Calculate the electricity cost of external power supply

[0118] Assuming a two-stage charging system, let the electricity price of unit price 0-T1 and T2-24 be P1, and the electricity price of T1-T2 be P2, then the external power supply fee is

[0119] 4. Dynamic optimization and adjustment

[0120] Since D(t) changes dynamically every day, the values ​​of t1 to t6 can be dynamically adjusted through the artificial intelligence platform according to the changes in D(t), so that the energy storage facilities can reasonably store electricity in the low electricity price stage and release electricity in the high electricity price stage, thereby maximizing electricity bill savings.

[0121] 5. Energy storage capacity recommendations

[0122] The platform combines factors such as seasonality and cyclical patterns of electricity consumption, as well as investment costs, to make recommendations on the capacity of energy storage facilities to maximize cost savings.

[0123] 2. Energy storage environment with green energy supply

[0124] For energy storage environments with green energy supplies such as photovoltaics and wind power, the energy storage source comes from the power grid and the green energy supply. The source of green energy needs to take into account changes in the natural environment and is related to factors such as climate, season, and time.

[0125] Since the type and frequency of electricity produced by green energy are different from those used for electricity, it is stored in energy storage facilities and then sent to the distribution network after being inverted, and the capacity of energy storage facilities is expanded to further reduce the external electricity supply.

[0126] Let the green electricity supply be G(t), then a curve of D(t)-θG(t) will be formed (θ is the efficiency of converting green energy into electrical energy). For the part of the curve less than 0, electrical energy is stored, and for the part of the curve greater than 0, power is supplied by energy storage facilities and the external power grid.

[0127] 1. When the green power supply is less than the power consumption, the power supply during the peak period S' will be reduced, and t1-t6 will also change accordingly to t'1-t'6, widening the range of t'2-t'3, t'4-t'5, and narrowing the range of 0-t'1 and t'6-24. The artificial intelligence platform uses the following modified formula to calculate the energy storage absorption capacity C' and energy storage discharge capacity G':

[0128]

[0129]

[0130] Where G(t) is the green electricity supply; θ is the efficiency of converting green energy into electrical energy; t'1, t'2, t'3, t'4, t'5, t'6 are the time nodes after considering the green electricity supply, in hours.

[0131] Calculate the electricity cost of external power supply:

[0132]

[0133] 2. When the green electricity supply is greater than the electricity consumption, in addition to supplying power to the region, green electricity can also provide external energy with the cooperation of energy storage facilities. Calculate the external energy supply:

[0134]

[0135] 3. Prediction and Optimization

[0136] The AI ​​platform predicts changes in green power supply G(t) and user power consumption D(t) based on historical data and external factors (such as weather forecasts). Based on these predictions, the platform can optimize charging and discharging strategies in advance to better balance supply and demand.

[0137] In fact, the supply of green electricity and user electricity consumption are irregular curves affected by multiple factors such as year, season, time and even economy and technology. The shape of the curve is not exactly the same every day. Energy storage power supply and discharge will also form a changing state under various conditions. Therefore, it is necessary to analyze through an artificial intelligence platform. On the one hand, the status of each power supply and distribution facilities and energy storage facilities can be adjusted according to the changes in green electricity supply and user electricity consumption. On the other hand, based on the relationship between the external environment and electricity consumption and power generation, a large model can be trained and used for future curve prediction to reasonably expand the capacity of green electricity and energy storage facilities.

[0138] 3. Intelligent recommendations for green electricity and energy storage facilities

[0139] 1. Energy storage facility planning

[0140] The artificial intelligence platform proposes capacity and layout recommendations for energy storage facilities based on the energy supply and demand of the regional power grid, ensuring sufficient support during peak electricity demand and storage of excess electricity during low electricity demand periods.

[0141] 2. Energy storage technology selection

[0142] The platform combines various types of energy utilization efficiency and discharge efficiency, considers the types and technical routes of energy storage facilities, such as battery energy storage, compressed air energy storage, etc., and makes recommendations to the auxiliary decision-making system.

[0143] 3. Green power facility planning

[0144] Based on the natural environment's capabilities and the supply and demand of electricity, the platform proposes recommendations on the capacity and layout of green power facilities.

[0145] 4. Green power technology selection

[0146] The platform combines the energy supply, conversion efficiency, etc. of various types of green power facilities, considers the types and technical routes of green power facilities, such as photovoltaic, wind power, hydropower, potential energy, etc., and makes recommendations to the auxiliary decision-making system.

[0147] 5. Collaborative planning of green electricity and energy storage facilities

[0148] The platform rationally matches the siting and scale of green power projects with the capacity and location of energy storage facilities to ensure efficient use of energy and stable operation of the power grid.

[0149] Through this comprehensive intelligent control process, the system can maximize the utilization of green electricity, optimize the use of energy storage facilities, significantly improve energy efficiency, reduce operating costs, and achieve a higher level of green and low-carbon operation. The continuous learning and optimization capabilities of the artificial intelligence platform enable the system to continuously adapt to the complex and changing power grid environment, providing strong support for building an intelligent, efficient and sustainable power system.

[0150] Specifically, in one embodiment of the present invention, intelligent management of energy storage batteries is a key component of the green power storage allocation system based on artificial intelligence. This process involves multiple aspects, including capacity design, energy balance, temperature management, etc. The following is a detailed process of the system performing intelligent management of energy storage batteries:

[0151] 1. Energy storage battery capacity design

[0152] When designing the capacity of the energy storage battery, the system considers the following factors: meeting the initial impact discharge current of the accident discharge; meeting the continuous discharge capacity requirements in the state of total power outage; load current at different stages; reliability coefficient of the energy storage release part and the accident impact part; capacity conversion coefficient of each calculation stage.

[0153] When an accident occurs, the battery system needs to be able to respond quickly and provide high discharge current. On the one hand, the energy storage battery needs to meet the initial (1 minute) impact discharge current of the accident discharge, and on the other hand, it needs to meet the continuous discharge capacity requirements under the state of total power outage, excluding the initial 1 minute impact discharge current.

[0154] 1. Calculation of impulse discharge current capacity at the initial stage of accident discharge (1min)

[0155] The system uses the following formula to calculate the initial (1min) impact battery 10h (or 5h) discharge rate capacity:

[0156]

[0157] In the formula, C cho Calculate the capacity for the initial 1-minute impact battery with a 10-hour or 5-hour discharge rate; I is the reliability coefficient of the energy storage release part; t K is the discharge current of the energy storage release part t hours; c Conversion factor for the released portion of the energy storage capacity; is the reliability coefficient of the accident impact part; I cho K is the impulse discharge current at the initial stage of the accident for 1 minute; cho It is the capacity conversion factor of the impact load in the initial 1 minute of the accident.

[0158] 2. Calculation of continuous discharge capacity in the event of a total power outage

[0159] The system calculates the capacity of each stage according to the following formula:

[0160] Phase 1 calculation capacity:

[0161]

[0162] Calculate the capacity at stage n, n ≥ 2:

[0163]

[0164] In the formula, C c1 The calculated capacity of the battery for the first stage accident current at a 10h or 5h discharge rate; C cn I is the calculated capacity of the battery at the nth stage of the accident current at a 10h or 5h discharge rate; tm The discharge current of the energy storage release part tm hours; I1~I n is the load current at each stage; K c1 ~K cn K is the capacity conversion factor of the corresponding discharge time in each calculation stage; k is the reliability coefficient;

[0165] Random load calculation capacity:

[0166]

[0167] In the formula, C r Calculate capacity for random loads; I r is the random load current; K cr is the capacity conversion factor for random impact loads.

[0168] 3. Capacity determination

[0169] C r Superimposed on C c2 ~C cn The largest stage, with C c1 Compare and take the larger value, and add them together to calculate the battery emergency current capacity.

[0170] The capacity conversion coefficient and reliability coefficient of each stage are set with initial values ​​based on historical experience, and then the actual value and predicted value are obtained by training the model based on big data input. For example, the battery reliability coefficient is composed of the margin coefficient, aging coefficient and temperature correction coefficient. The aging coefficient can be further decomposed into time coefficient, air quality, climate coefficient and other components. The AI ​​big model makes trend judgments based on the actual usage scenarios and obtains the battery capacity conversion coefficient and reliability coefficient that meet the actual usage environment.

[0171] 2. Energy balance and charging and discharging strategies

[0172] First, it is necessary to ensure that the battery system can charge efficiently when there is sufficient green electricity and provide sufficient discharge current when needed (including accident situations). This can be modeled by the following energy balance equation:

[0173] E(t)=E(tt p )+η ch ·P ch (t)·Δt-η dis P dis (t)·Δt-P loss (t)·Δt

[0174] Where, E(t) is the remaining battery energy at time t, E(tt p ) is the remaining battery energy at the previous moment, η ch and η dis are the charging and discharging efficiencies, P ch (t) and P dis (t) are the charging and discharging powers at time t, Δt is the time step, P loss (t) is the internal power loss of the battery at time t;

[0175] Based on the energy balance equation, combined with real-time grid load, green power supply forecast and electricity price information, the charging and discharging power P is dynamically adjusted. ch (t) and P dis (t).

[0176] 3. Temperature Management and Thermal Safety

[0177] High discharge currents generate a lot of heat, so effective temperature management is necessary to ensure battery safety. The change in battery temperature can be estimated using the following heat balance equation:

[0178]

[0179] Where, T(t) is the battery temperature at time t; P gen (t) is the total heat power generated by charging, discharging and other internal processes; h is the heat transfer coefficient; A is the battery surface area; T amb is the ambient temperature; m is the battery mass; C p is the specific heat capacity.

[0180] The system ensures that the battery temperature does not exceed safe limits:

[0181] T(t)≤T max,safe

[0182] Among them, T max,safe The upper limit of battery safety temperature;

[0183] Dynamically adjust the charging and discharging strategy based on temperature management results:

[0184] When the temperature approaches the upper safety limit, reduce the charging power or increase the cooling intensity;

[0185] Under extreme temperature conditions, charging and discharging operations are temporarily interrupted to prioritize battery safety.

[0186] Specifically, in another embodiment of the present invention, the system also needs safety control for intelligent management of energy storage batteries, and the specific contents are as follows:

[0187] 4. Battery Management System (BMS) Function

[0188] The system's battery management system (BMS) implements the following functions:

[0189] 1. Battery state estimation: estimate the state of charge (SOC); estimate the state of health (SOH); estimate the state of power (SOP).

[0190] 2. Battery balancing: realize passive balancing and active balancing; optimize the consistency of the battery pack.

[0191] 3. Fault diagnosis and early warning: monitor voltage, current, temperature and other parameters; identify abnormal conditions and issue early warnings.

[0192] 4. Thermal management: control cooling system; optimize battery operating temperature.

[0193] 5. Predictive Maintenance

[0194] The system uses artificial intelligence algorithms for predictive maintenance: analyzing historical data and current status; predicting potential failures and performance degradation; and developing an optimal maintenance plan.

[0195] 6. Intelligent charging and discharging control

[0196] The system realizes intelligent charge and discharge control: adjusts the charge and discharge strategy according to the grid demand and electricity price; optimizes the charge and discharge rate to extend the battery life; realizes peak and valley filling and improves economic benefits.

[0197] 7. Safety Management

[0198] The system implements comprehensive safety management measures: real-time monitoring of key parameters such as voltage, current, and temperature; setting up multiple protection mechanisms, including overcharging, over-discharging, over-temperature protection, etc.; and realizing emergency cut-off and isolation functions.

[0199] 8. Data Analysis and Optimization

[0200] The system continuously performs data analysis and optimization: collects and analyzes operational data; uses machine learning algorithms to optimize management strategies; and regularly updates model parameters to improve system performance.

[0201] 9. Life Cycle Management

[0202] The system manages the entire battery life cycle: tracking the usage history of each battery cell; predicting the remaining service life; and formulating the optimal replacement and recycling plan.

[0203] Through this comprehensive intelligent management process, the system can significantly improve the efficiency and life of energy storage batteries, reduce operating costs, and ensure the safety and reliability of the system. The continuous learning and optimization capabilities of the artificial intelligence platform enable the system to continuously adapt to complex and changing operating environments, providing strong support for building efficient, reliable, and economical energy storage systems.

[0204] like Figure 2 As shown, the dispatching system of the present invention is also used for power grid monitoring optimization, including operation monitoring, fault detection, solution proposal and implementation, etc. The specific process is as follows:

[0205] 1. Operation monitoring and fault detection

[0206] The power grid management system continuously monitors the operation of the power grid in real time, including voltage level monitoring, current load monitoring, frequency stability monitoring, power factor monitoring, and equipment operation status monitoring.

[0207] The system continuously sends real-time monitoring data to the artificial intelligence platform for analysis. These data include: time series data, equipment status data, and environmental parameter data (such as temperature, humidity, etc.).

[0208] The AI ​​platform uses anomaly detection algorithms, time series analysis, etc. to analyze the received data in real time to identify potential anomalies or failures.

[0209] Based on historical data and current trends, AI platforms are able to predict impending failures. This predictive analysis can help the system take preventive measures before a failure actually occurs.

[0210] 2. Fault analysis and solution generation

[0211] When a fault is detected or predicted to occur, the system enters the next stage:

[0212] The artificial intelligence platform conducts in-depth analysis of the causes of faults based on the grid operation status and abnormal data. This involves: equipment failure analysis, system overload analysis, and external factors impact analysis (such as weather conditions).

[0213] Based on the fault analysis results, the system generates multiple possible solutions. During the generation process, the system considers the following factors: convenience, reliability, safety, and economy of the solution.

[0214] The system prioritizes the generated solutions, taking into account factors including implementation difficulty, expected effect, potential risks, and cost-benefit ratio.

[0215] 3. Propose and implement operational plans

[0216] If the top priority solution is an operational solution, the system enters the following process:

[0217] The system determines whether the solution can be operated remotely.

[0218] If remote operation is possible: the artificial intelligence platform analyzes the feasibility and safety of remote operation; generates detailed remote operation steps; submits the plan to the auxiliary decision system; after the auxiliary decision system passes, the computer room personnel will perform the remote switching operation.

[0219] If on-site operation is required: the artificial intelligence platform generates detailed on-site operation instructions; the plan is submitted to the auxiliary decision-making system; after the auxiliary decision-making system approves it, it is sent to the on-duty personnel for on-site operation.

[0220] If the decision support system rejects the proposed plan: the system will feed back the reason for rejection to the artificial intelligence platform; the artificial intelligence platform will re-analyze and generate a new plan based on the feedback.

[0221] 4. Proposal and implementation of maintenance plan

[0222] If the top priority solution is the maintenance solution, the system enters the following process:

[0223] The artificial intelligence platform develops a detailed maintenance plan, including: specific maintenance steps; a list of required tools and materials; safety precautions; and an estimated maintenance time.

[0224] The system simultaneously generates a required list of safety equipment for maintenance to ensure the safety of maintenance personnel.

[0225] Submit the maintenance plan to the auxiliary decision-making system for review; after the auxiliary decision-making system approves it, the plan will be sent to the on-duty personnel for on-site maintenance.

[0226] If the auxiliary decision-making system rejects the maintenance plan: the system will feedback the reason for rejection to the artificial intelligence platform; the artificial intelligence platform will re-analyze and generate a new maintenance plan based on the feedback.

[0227] 5. Plan implementation monitoring and effect evaluation

[0228] Whether it is an operational solution or a maintenance solution, the system will monitor its implementation and evaluate its effects:

[0229] The system monitors each step of the plan implementation in real time; collects data and feedback during the implementation process.

[0230] After the program is implemented, the system evaluates its effectiveness; comparing actual results with expected goals.

[0231] Incorporate implementation experience and effect evaluation results into the system database; the artificial intelligence platform uses these new data to update and optimize its decision-making model.

[0232] Through this comprehensive grid monitoring and optimization process, the system can quickly identify and solve grid problems and improve the reliability and stability of the grid. The continuous learning and optimization capabilities of the artificial intelligence platform enable the system to continuously improve its problem-solving capabilities and provide strong support for the safe and stable operation of the grid.

[0233] In summary, the green electricity storage allocation system based on artificial intelligence provided by the present invention has the following advantages:

[0234] 1. Through machine learning and deep learning algorithms, the system can model and optimize the power system and realize automatic control and dispatch of green power storage equipment. This can not only predict and meet power demand more accurately, but also reduce energy waste and improve energy utilization efficiency and economy.

[0235] 2. It can collect historical data, real-time data, and external natural environment, economic environment, and social environment data, and use advanced algorithms to accurately predict power load, so as to more effectively deploy green electricity storage facilities and optimize energy supply.

[0236] 3. The AI ​​platform can realize intelligent monitoring and management of the power grid. Through real-time analysis of power grid data and fault reporting of the power grid management system, the AI ​​platform system can infer abnormal development trends and causes of faults, and propose reasonable solutions for repair. This helps reduce the failure rate of the power grid and improve the stability and reliability of the power grid.

[0237] 4. Using AI technology, the system can achieve intelligent control and management of energy storage facilities. The AI ​​system can intelligently adjust the operating status and charging and discharging strategies of energy storage equipment according to energy supply conditions and user needs. This helps to achieve optimal distribution and utilization of energy and improve the flexibility and reliability of the power grid.

[0238] 5. By controlling the energy exchange between the substation and the upper-level power grid, energy and electricity can be stored by the external power supply system when electricity is insufficient, and external power can be empowered when electricity is sufficient. This will help to better utilize renewable energy and increase the proportion of renewable energy in the power grid.

[0239] 6. Based on the fault rate, energy storage efficiency, green electricity usage and external environment, the artificial intelligence platform is used to put forward grid transformation suggestions to further improve energy conservation and efficiency.

[0240] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. The green power storage dispatching system based on artificial intelligence is characterized by: include: Power transmission and distribution network, used to achieve power transmission and distribution, including external power introduction equipment, power switching and fusion equipment, power grid distribution equipment and user access equipment; Green electricity and energy storage facilities, including green electricity facilities for generating clean electricity and energy storage facilities for storing and releasing energy; Management and decision-making platform, including: Power grid management system, used to collect power equipment information and execute dispatching decisions; User management system, used to collect user information and interact with users; A decision support system to process the recommendations of the AI ​​platform and generate decision instructions; Artificial intelligence platform, which is used to collect and analyze power grid operation data and external environment data, generate optimization and adjustment suggestions through large models, and send the suggestions to the auxiliary decision-making system; Among them, power switching and fusion equipment connects external power introduction equipment, energy storage facilities, green power facilities and grid distribution equipment.

2. The green electricity storage allocation system based on artificial intelligence according to claim 1, characterized in that: The AI ​​platform is also used to: Dynamically adjust the charging and discharging strategies of energy storage facilities according to the power supply and demand situation; predict changes in green power supply and user power consumption; provide capacity and layout recommendations for green power and energy storage facilities; manage energy storage batteries; analyze power grid anomalies and propose fault solutions.

3. The artificial intelligence-based green electricity storage dispatching system according to claim 2, characterized in that: In an energy storage environment without green energy supply, the artificial intelligence platform calculates the energy storage absorption capacity C and energy storage discharge capacity G through the following formula: In the formula, ε is the power conversion efficiency; is the power transmission efficiency; S is the power supply capacity; St is the total power supplied within a certain period of time; D(t) is the power usage; τ is the energy storage conversion efficiency; t1, t2, t3, t4, t5, t6 are time nodes, in hours; The artificial intelligence platform regulates the charging and discharging cycles of the energy storage facilities based on the above calculation results.

4. The artificial intelligence-based green electricity storage dispatching system according to claim 3, characterized in that: In an energy storage environment with green energy supply, the artificial intelligence platform adjusts the energy storage absorption capacity C' and energy storage discharge capacity G' according to the following formula: Where G(t) is the green electricity supply; θ is the efficiency of converting green energy into electrical energy; t'1, t'2, t'3, t'4, t'5, t'6 are the time nodes after considering the green electricity supply, in hours; Based on the above calculation results, the artificial intelligence platform optimizes and controls the charging and discharging strategies of energy storage facilities to maximize the efficiency of green electricity utilization.

5. The artificial intelligence-based green electricity storage dispatching system according to claim 2, characterized in that: When managing energy storage batteries, the artificial intelligence platform includes energy storage battery capacity design, optimization of energy balance and charging and discharging strategies, and implementation of temperature management and thermal safety control.

6. The artificial intelligence-based green electricity storage dispatching system according to claim 5, characterized in that: The artificial intelligence platform considers the following factors when designing the energy storage battery capacity: Meet the initial impact discharge current of accident discharge; Meet the continuous discharge capacity requirements in the event of a total power outage; Load current at different stages; Reliability coefficients of the energy storage release part and the accident impact part; Capacity conversion factors for each calculation stage.

7. The artificial intelligence-based green electricity storage dispatching system according to claim 6, characterized in that: In order to meet the requirements of the initial impact discharge current capacity of the final stage of energy storage discharge and the initial stage of accident discharge, the initial 1min impact battery 10h or 5h discharge rate calculation capacity is calculated according to the following formula: In the formula, C cho Calculate the capacity for the initial 1-minute impact battery with a 10-hour or 5-hour discharge rate; I is the reliability coefficient of the energy storage release part; t K is the discharge current of the energy storage release part t hours; c Conversion factor for the released portion of the energy storage capacity; is the reliability coefficient of the accident impact part; I cho K is the impulse discharge current at the initial stage of the accident for 1 minute; cho It is the capacity conversion factor of the impact load in the initial 1 minute of the accident.

8. The artificial intelligence-based green electricity storage dispatching system according to claim 7, characterized in that: In order to meet the continuous discharge capacity requirements of energy storage in the mid-term superimposed accident state of total power outage, excluding the initial 1min impact discharge current, the calculated capacity at each stage is calculated as follows: Phase 1 calculation capacity: Calculate the capacity at stage n, n ≥ 2: In the formula, C c1 The calculated capacity of the battery for the first stage accident current at a 10h or 5h discharge rate; C cn I is the calculated capacity of the battery at the nth stage of the accident current at a 10h or 5h discharge rate; tm The discharge current of the energy storage release part tm hours; I1~I n is the load current at each stage; K c1 ~K cn K is the capacity conversion factor of the corresponding discharge time in each calculation stage; k is the reliability coefficient; Random load calculation capacity: In the formula, C r Calculate capacity for random loads; I r is the random load current; K cr is the capacity conversion factor for random impact load; C r Superimposed on C c2 ~C cn The largest stage, with C c1 Compare and take the larger value, and add them together to calculate the battery emergency current capacity.

9. The artificial intelligence-based green electricity storage dispatching system according to claim 5, characterized in that: When optimizing energy balance and charging and discharging strategies, the artificial intelligence platform uses the following energy balance equation to model: E(t)=E(tt p )+η ch ·P ch (t)·Δt-η dis P dis (t)·Δt-P loss (t)·Δt Where, E(t) is the remaining battery energy at time t, E(tt p ) is the remaining battery energy at the previous moment, η ch and η dis are the charging and discharging efficiencies, P ch (t) and P dis (t) are the charging and discharging powers at time t, Δt is the time step, P loss (t) is the internal power loss of the battery at time t; Based on the energy balance equation, combined with real-time grid load, green power supply forecast and electricity price information, the charging and discharging power P is dynamically adjusted. ch (t) and P dis (t).

10. The artificial intelligence-based green electricity storage dispatching system according to claim 5, characterized in that: When performing temperature management and thermal safety control, the artificial intelligence platform: The following heat balance equation is used to estimate the change in battery temperature: Where, T(t) is the battery temperature at time t; P gen (t) is the total heat power generated by charging, discharging and other internal processes; h is the heat transfer coefficient; A is the battery surface area; T amb is the ambient temperature; m is the battery mass; C p is the specific heat capacity; To ensure that the battery temperature does not exceed safe limits: T(t)≤T max,safe Among them, T max,safe The upper limit of battery safety temperature; Dynamically adjust the charging and discharging strategy based on temperature management results: When the temperature approaches the upper safety limit, reduce the charging power or increase the cooling intensity; Under extreme temperature conditions, charging and discharging operations are temporarily interrupted to prioritize battery safety.

Images