Power distribution network energy storage configuration optimization method and system
By designing an energy storage configuration optimization system in the distribution network, using machine learning and deep learning algorithms to establish a load trend model, and automatically generate a load evaluation plan, the problem of uneven load in the distribution network is solved, and load balancing and energy storage equipment are realized The efficient use of the power grid reduces the cost and risk of operating the power grid.
Patent Information
- Application Number
- CN202411085150.7
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-08
- Publication Date
- 2024-11-15
AI Technical Summary
The overload problem caused by uneven load distribution in the distribution network leads to instability of the power grid, increasing the risk of equipment failure and maintenance costs. The traditional load management methods lack flexibility and real-timeness, making it difficult to cope with complex and changing power demands.
A distribution network energy storage configuration optimization system was designed, including equipment acquisition module, data processing module, load prediction module, status evaluation module and decision-making module. Machine learning and deep learning algorithms are used to establish a regional equipment operation load trend model to obtain the region Load optimization index, automatically generates load evaluation plans for energy storage equipment, and performs specific execution and iterative regulation through decision-making modules.
It realizes accurate evaluation and optimized configuration of grid load, improves load balancing and energy storage equipment utilization efficiency, reduces grid operating costs and risks, improves grid management and regulation capabilities, extends equipment service life, and reduces overload risk , improves the overall reliability of the power grid and its ability to deal with dynamic changes.
Smart Images

Figure CN118971091A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of power grid energy storage, and in particular to a distribution network energy storage configuration optimization method and system. Background Art
[0002] The distribution network is an important part of the power system and is responsible for transmitting electricity from substations to end users. With the popularization of renewable energy and the widespread use of electric vehicles, the load management and stability challenges faced by the distribution network are becoming increasingly severe.
[0003] Among them, distribution networks often face the problem of uneven load distribution in actual operation. This imbalance may cause the power grid in some areas to be overloaded, while other areas are in a low-load state. Traditional load management methods often rely on manual scheduling, lack flexibility and real-time performance, and are difficult to cope with complex and changeable electricity demand. It also greatly increases the investment in human resources. In addition, with the access of distributed energy and electric vehicles, the frequency and amplitude of load fluctuations are increasing, further exacerbating the difficulty of power grid scheduling.
[0004] When the load is unevenly distributed and causes overload problems, it will cause voltage fluctuations and frequency deviations in the distribution network, and may even cause equipment damage and power supply interruptions. Equipment in the overloaded area will face a higher risk of failure, increasing the cost of maintenance and replacement. At the same time, the instability of the power grid will also affect the user's power experience, causing economic losses and social inconvenience. For example, industrial users may stop working due to power outages, resulting in production losses; residential users may suffer inconvenience in their lives due to frequent power outages. Summary of the invention
[0005] In view of the deficiencies in the prior art, the present invention provides a method and system for optimizing energy storage configuration in a distribution network, which solves the problems mentioned in the background technology.
[0006] To achieve the above objectives, the present invention is implemented through the following technical solutions: a distribution network energy storage configuration optimization system, including an equipment acquisition module, a data processing module, a load prediction module, a state evaluation module and a decision module;
[0007] The equipment acquisition module collects real-time load data of each area of the power grid, status data of the energy storage device, ambient temperature data and power grid topology information to form a real-time acquisition data group;
[0008] The data processing module preprocesses the real-time collected data group, including data denoising, normalization and missing value filling, and integrates the processed real-time collected data group into a data processing set;
[0009] The load prediction module uses machine learning algorithms and deep learning technologies to establish a regional equipment operation load trend model for the data processing set, and trains and analyzes the regional equipment operation load trend model to obtain the regional load optimization index C total ;
[0010] The status evaluation module uses the preset regional equipment operation load fluctuation threshold B and the regional load optimization index C total Perform matching and obtain regional energy storage equipment load assessment solutions;
[0011] The decision module is specifically executed according to the content of the regional energy storage equipment load assessment plan, and feedbacks, monitors and iteratively regulates the execution results.
[0012] Preferably, the equipment acquisition module includes a regional load unit and an equipment monitoring unit;
[0013] The regional load unit obtains real-time load data from smart meters and load monitoring equipment in various areas of the power grid, including power consumption, instantaneous power and power factor;
[0014] The equipment monitoring unit obtains the energy storage equipment status data through the integrated energy storage system, including equipment positioning, switch status, battery power, charge and discharge rate, battery temperature, number of cycles and health status value, and obtains the equipment operation area environmental information through the environmental monitoring sensor integrated in the equipment operation area, including temperature, humidity, wind speed and particulate matter concentration, and combines it with the real-time collected data of the regional load unit to form a real-time collected data group.
[0015] Preferably, the data processing module includes a preprocessing unit and an integration unit;
[0016] The preprocessing unit preprocesses the real-time collected data group, including data denoising, normalization and missing value filling, wherein data denoising is performed by using statistical methods and machine learning algorithms for identification, and then low-pass filters and median filters are used to remove high-frequency noise and outliers in the data; normalization is dimensionless processing through minimum and maximum normalization and Z-score normalization; missing value filling includes filling, replacing and trend predicting missing values using mean filling, interpolation and prediction model filling methods, and feature extraction and statistical labeling are performed on the preprocessed real-time collected data group to integrate into a data processing set.
[0017] Preferably, the data processing set includes energy storage device discharge power, energy storage device charging power, regional real-time load power, energy storage device charging status, regional ambient temperature, regional peak and valley temperature values, and regional node connection relationships;
[0018] The regional node connection relationship includes node number, connection line, resistance value, connection type and location information.
[0019] Preferably, the load prediction module includes a modeling unit;
[0020] The modeling unit uses machine learning algorithms and deep learning technologies to establish a regional equipment operation load trend model for the data processing set, and performs training and analysis on the regional equipment operation load trend model to obtain the regional load optimization index C total ;
[0021] The regional load optimization index C total Obtained through the following calculation formula:
[0022] C total =α*C balance +β*C health +γ*C temp +δ*C quality ;
[0023] In the formula, C balance represents the power quality assessment index, C health Indicates the equipment area environmental assessment index, C temp Represents the energy storage battery status assessment index, C quality represents the regional equipment load evaluation index, α, β, γ and δ represent the power quality evaluation index C balance , Equipment Area Environmental Assessment Index C health , Energy storage battery status assessment index C temp and regional equipment load assessment index C quality The weight coefficient of .
[0024] Preferably, the power quality assessment index C balance Obtained through the following calculation formula:
[0025]
[0026] In the formula, C balance Represents the power quality assessment index, specifically indicating the stable quality performance of voltage, K represents the total number of measurement points, V e (t) represents the voltage at the eth measurement point at time t, V ref Indicates the preset reference voltage value, including 220V and 110V;
[0027] The equipment area environmental assessment index C health Obtained through the following calculation formula:
[0028]
[0029] In the formula, Chealth Equipment regional environmental assessment index, specifically used to measure the impact of ambient temperature on grid energy storage equipment. N represents the number of regions, W represents the i W(t) represents the regional ambient temperature of the i-th region at time t, W(t) represents the average regional ambient temperature at time t, and W max Indicates the peak ambient temperature of the area, W min Indicates the valley value of regional ambient temperature;
[0030] Where: the average regional ambient temperature at time t pass Obtained by formula calculation.
[0031] Preferably, the energy storage battery status evaluation index C temp Obtained through the following calculation formula:
[0032]
[0033] In the formula, C temp Represents the energy storage battery status evaluation index, specifically indicating the operating status of the energy storage device. M represents the number of energy storage devices, S q S(t) represents the charging state of the qth device at time t, specifically the percentage of the energy currently stored in the battery to the total capacity. S(t) represents the average charging state of the energy storage device at time t. max Indicates the rated state of charge of the energy storage device;
[0034] Among them, the average charge state of the energy storage device at time t is pass Calculation: The charge state S(t) at time t is calculated by the Coulomb counting method:
[0035]
[0036] Where S(t) represents the charging state at time t, which is obtained through full charge and discharge tests and calibration data provided by the manufacturer. 0 ) represents the initial time t 0 The charging state, Cx represents the rated capacity of the energy storage device battery, I(t) represents the charging and discharging current at time t, Represents the time from the initial time t 0 The current integral to time t;
[0037] The regional equipment load evaluation index C quality Obtained through the following calculation formula:
[0038]
[0039] In the formula, C qualityIt represents the power quality assessment index, which specifically indicates the degree of load power balance in several regions. N represents the number of regions, and P i (t) represents the actual load power of the ith region at time t, Average load power at time t;
[0040] Among them, the average load power at time t pass Obtain the calculation formula.
[0041] Preferably, the state assessment module includes a matching unit;
[0042] The matching unit matches the required comparison value through the preset relevant information, including the preset regional equipment operation load fluctuation threshold B and the regional load optimization index C. total Perform matching and obtain regional energy storage equipment load assessment solutions;
[0043] The regional energy storage equipment load assessment scheme is obtained by the following matching method:
[0044] Regional load optimization index C total <Regional equipment operation load fluctuation threshold B, obtain the qualified result of regional energy storage equipment load assessment, and do not adjust the current regional energy storage equipment configuration plan;
[0045] Regional load optimization index C total ≥ Regional equipment operation load fluctuation threshold B, obtain the unqualified result of regional energy storage equipment load assessment, and adjust the current regional energy storage equipment configuration plan, including adjusting the charging and discharging of energy storage equipment, reallocating energy storage equipment capacity adjustment, and optimizing the grid topology structure adjustment;
[0046] Regional load optimization index C total When the load fluctuation threshold value B of the regional equipment operation is ≥ twice, the load assessment warning results of the regional energy storage equipment are obtained, and the warning of the current regional energy storage equipment is synchronously displayed and notified to relevant staff.
[0047] Preferably, the decision module includes an execution unit and a control unit;
[0048] The execution unit performs specific execution according to the content of the regional energy storage device load assessment plan, including receiving and parsing the content of the regional energy storage device load assessment plan, extracting specific measures to be executed, and generating detailed operation instructions according to the specific measures, including charging current, voltage setting and discharge start timing;
[0049] The control unit provides feedback, monitoring and iterative regulation on the specific execution results of the regional energy storage equipment load assessment plan; feedback includes collecting data after execution of each energy storage device, including charge and discharge data, device status data and load data; monitoring includes continuous monitoring of the energy storage device, and real-time collection of equipment operating status and load fluctuation information; iteration includes using the data after each execution for the adjustment of the next regional energy storage equipment load assessment plan through a feedback loop mechanism.
[0050] A method for optimizing energy storage configuration in a distribution network comprises the following steps:
[0051] Step 1: The equipment acquisition module collects real-time load data of each area of the power grid, status data of the energy storage equipment, ambient temperature data, and power grid topology information to form a real-time acquisition data group;
[0052] Step 2: The data processing module preprocesses the real-time collected data group, including data denoising, normalization and missing value filling, and integrates the processed real-time collected data group into a data processing set;
[0053] Step 3: The load prediction module uses machine learning algorithms and deep learning technologies to build a regional equipment operation load trend model for the data processing set, and trains and analyzes the regional equipment operation load trend model to obtain the regional load optimization index C. total ;
[0054] Step 4: The status evaluation unit uses the preset regional equipment load fluctuation threshold B and regional load optimization index C total Perform matching and obtain regional energy storage equipment load assessment solutions;
[0055] Step 5: The decision-making module performs specific actions according to the content of the regional energy storage equipment load assessment plan, and provides feedback, monitoring and iterative regulation on the execution results.
[0056] The present invention provides a method and system for optimizing energy storage configuration in a distribution network, which has the following beneficial effects:
[0057] (1) When the system is running, it realizes the comprehensive collection and processing of information from all regions of the power grid. It uses advanced machine learning and deep learning algorithms to establish a regional equipment operation load trend model and obtain the regional load optimization index C total , so as to accurately evaluate the regional energy storage equipment load, through the preset load fluctuation threshold B and regional load optimization index C totalIt automatically generates a load assessment plan for energy storage equipment through matching, and performs specific execution and iterative regulation through the decision-making module. The real-time feedback mechanism ensures accurate monitoring and continuous optimization of the execution results. Compared with the traditional distribution network system, it significantly improves the load balance and the utilization efficiency of energy storage equipment, reduces the operating cost and risk of the power grid, and solves the problems of large power grid load fluctuations, low utilization of energy storage equipment and lack of real-time regulation methods.
[0058] (2) Through the power quality evaluation index C balance , Equipment Area Environmental Assessment Index C health , Energy storage battery status assessment index C temp and regional equipment load assessment index C quality Acquisition and area load optimization index C total , which comprehensively improves the management and regulation capabilities of the power grid. The equipment regional environmental assessment index takes into account the impact of ambient temperature on energy storage equipment, optimizes the working environment of the equipment, and extends the service life of the equipment. The energy storage battery status assessment index achieves health management of energy storage equipment by accurately calculating the charging status of energy storage equipment, improves energy storage efficiency and system response speed, and the regional equipment load assessment index optimizes the configuration of power grid resources and reduces overload risks by balancing the loads in each region. These comprehensive evaluation indicators enable the system to more accurately predict and optimize load configuration, thereby achieving efficient, stable and intelligent management of power grid operation, and effectively solving the problems of load imbalance, large environmental impact and difficult management of energy storage equipment in power grid operation.
[0059] (3) Based on the preset regional equipment load fluctuation threshold B and regional load optimization index C total Matching is carried out to obtain the regional energy storage equipment load assessment plan. When the energy storage equipment configuration plan is qualified, no adjustment is required, thus avoiding unnecessary waste of resources. When an unqualified assessment result is generated, the charging and discharging strategy of the energy storage equipment is automatically adjusted, the capacity of the energy storage equipment is reallocated, and even the grid topology is optimized to ensure the stable operation of the grid. When it reaches or exceeds twice the regional equipment operating load fluctuation threshold B, the system issues an early warning to notify relevant staff to ensure timely response to potential risks. Through this matching and assessment mechanism, the accuracy and flexibility of grid load management are improved, and the utilization efficiency of energy storage equipment and the overall reliability of the grid and its ability to respond to dynamic changes are greatly improved. BRIEF DESCRIPTION OF THE DRAWINGS
[0060] Figure 1 A schematic diagram of a flow chart of a distribution network energy storage configuration optimization system according to the present invention;
[0061] Figure 2 A schematic diagram of the steps of a method for optimizing energy storage configuration in a distribution network according to the present invention. DETAILED DESCRIPTION
[0062] The technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.
[0063] Example 1
[0064] The present invention provides a distribution network energy storage configuration optimization system, please refer to Figure 1 , including equipment acquisition module, data processing module, load prediction module, status assessment module and decision-making module;
[0065] The equipment acquisition module collects real-time load data of each area of the power grid, status data of the energy storage device, ambient temperature data and power grid topology information to form a real-time acquisition data group;
[0066] The data processing module preprocesses the real-time collected data group, including data denoising, normalization and missing value filling, and integrates the processed real-time collected data group into a data processing set;
[0067] The load prediction module uses machine learning algorithms and deep learning technologies to establish a regional equipment operation load trend model for the data processing set, and trains and analyzes the regional equipment operation load trend model to obtain the regional load optimization index C total ;
[0068] The status evaluation module uses the preset regional equipment operation load fluctuation threshold B and the regional load optimization index C total Perform matching and obtain regional energy storage equipment load assessment solutions;
[0069] The decision module is specifically executed according to the content of the regional energy storage equipment load assessment plan, and feedbacks, monitors and iteratively regulates the execution results.
[0070] In this embodiment, by integrating the equipment acquisition module, data processing module, load prediction module, state evaluation module and decision-making module, comprehensive collection and processing of information from various regions of the power grid are realized. Advanced machine learning and deep learning algorithms are used to establish a regional equipment operation load trend model and obtain the regional load optimization index C. total , so as to accurately evaluate the regional energy storage equipment load, through the preset load fluctuation threshold B and regional load optimization index C totalIt automatically generates a load assessment plan for energy storage equipment through matching, and performs specific execution and iterative regulation through the decision-making module. The real-time feedback mechanism ensures accurate monitoring and continuous optimization of the execution results. Compared with the traditional distribution network system, it significantly improves the load balance and the utilization efficiency of energy storage equipment, reduces the operating cost and risk of the power grid, and solves the problems of large power grid load fluctuations, low utilization of energy storage equipment and lack of real-time regulation methods.
[0071] Example 2
[0072] This embodiment is explained in Example 1, please refer to Figure 1 ,Specifically: the equipment acquisition module includes a regional load unit and an equipment monitoring unit;
[0073] The regional load unit obtains real-time load data from smart meters and load monitoring equipment in various areas of the power grid, including power consumption, instantaneous power and power factor;
[0074] The equipment monitoring unit obtains the energy storage equipment status data through the integrated energy storage system, including equipment positioning, switch status, battery power, charge and discharge rate, battery temperature, number of cycles and health status value, and obtains the equipment operation area environmental information through the environmental monitoring sensor integrated in the equipment operation area, including temperature, humidity, wind speed and particulate matter concentration, and combines it with the real-time collected data of the regional load unit to form a real-time collected data group.
[0075] The data processing module includes a preprocessing unit and an integration unit;
[0076] The preprocessing unit preprocesses the real-time collected data group, including data denoising, normalization and missing value filling, wherein data denoising is performed by using statistical methods and machine learning algorithms for identification, and then low-pass filters and median filters are used to remove high-frequency noise and outliers in the data; normalization is dimensionless processing through minimum and maximum normalization and Z-score normalization; missing value filling includes filling, replacing and trend predicting missing values using mean filling, interpolation and prediction model filling methods, and feature extraction and statistical labeling are performed on the preprocessed real-time collected data group to integrate into a data processing set.
[0077] The data processing set includes energy storage device discharge power, energy storage device charging power, regional real-time load power, energy storage device charging status, regional ambient temperature, regional peak and valley temperature values, and regional node connection relationships;
[0078] The regional node connection relationship includes node number, connection line, resistance value, connection type and location information.
[0079] Example 3
[0080] This embodiment is explained in Example 1, please refer to Figure 1 ,Specifically: the load prediction module includes a modeling unit;
[0081] The modeling unit uses machine learning algorithms and deep learning technologies to establish a regional equipment operation load trend model for the data processing set, and performs training and analysis on the regional equipment operation load trend model to obtain the regional load optimization index C total ;
[0082] The regional load optimization index C total Obtained through the following calculation formula:
[0083] C total =α*C balance +β*C health +γ*C temp +δ*C quality ;
[0084] In the formula, C balance represents the power quality assessment index, C health Indicates the equipment area environmental assessment index, C temp Represents the energy storage battery status assessment index, C quality represents the regional equipment load evaluation index, α, β, γ and δ represent the power quality evaluation index C balance , Equipment Area Environmental Assessment Index C health , Energy storage battery status assessment index C temp and regional equipment load assessment index C quality The weight coefficient of .
[0085] The power quality assessment index C balance Obtained through the following calculation formula:
[0086]
[0087] In the formula, C balance Represents the power quality assessment index, specifically indicating the stable quality performance of voltage, K represents the total number of measurement points, V e (t) represents the voltage at the eth measurement point at time t, V ref Indicates the preset reference voltage value, including 220V and 110V;
[0088] The equipment area environmental assessment index C health Obtained through the following calculation formula:
[0089]
[0090] In the formula, C healthEquipment regional environmental assessment index, specifically used to measure the impact of ambient temperature on grid energy storage equipment. N represents the number of regions, W represents the i (t) represents the regional ambient temperature of the i-th region at time t, represents the average regional ambient temperature at time t, W max Indicates the peak ambient temperature of the area, W min Indicates the valley value of regional ambient temperature;
[0091] Where: the average regional ambient temperature at time t pass Obtained by formula calculation.
[0092] The energy storage battery state evaluation index C temp Obtained through the following calculation formula:
[0093]
[0094] In the formula, C temp Represents the energy storage battery status evaluation index, specifically indicating the operating status of the energy storage device. M represents the number of energy storage devices, S q S(t) represents the charging state of the qth device at time t, specifically the percentage of the energy currently stored in the battery to the total capacity. S(t) represents the average charging state of the energy storage device at time t. max Indicates the rated state of charge of the energy storage device;
[0095] Among them, the average charge state of the energy storage device at time t is pass Calculation: The charge state S(t) at time t is calculated by the Coulomb counting method:
[0096]
[0097] Where S(t) represents the charging state at time t, which is obtained through full charge and discharge tests and calibration data provided by the manufacturer. 0 ) represents the initial time t 0 The charging state, Cx represents the rated capacity of the energy storage device battery, I(t) represents the charging and discharging current at time t, Represents the time from the initial time t 0 The current integral to time t;
[0098] The regional equipment load evaluation index C quality Obtained through the following calculation formula:
[0099]
[0100] In the formula, C qualityIt represents the power quality assessment index, which specifically indicates the degree of load power balance in several regions. N represents the number of regions, and P i (t) represents the actual load power of the ith region at time t, Average load power at time t;
[0101] Among them, the average load power at time t pass Obtain the calculation formula.
[0102] In this embodiment, the power quality evaluation index C balance , Equipment Area Environmental Assessment Index C health , Energy storage battery status assessment index C temp and regional equipment load assessment index C quality Acquisition and area load optimization index C total , which comprehensively improves the management and regulation capabilities of the power grid. The equipment regional environmental assessment index takes into account the impact of ambient temperature on energy storage equipment, optimizes the working environment of the equipment, and extends the service life of the equipment. The energy storage battery status assessment index achieves health management of energy storage equipment by accurately calculating the charging status of energy storage equipment, improves energy storage efficiency and system response speed, and the regional equipment load assessment index optimizes the configuration of power grid resources and reduces overload risks by balancing the loads in each region. These comprehensive evaluation indicators enable the system to more accurately predict and optimize load configuration, thereby achieving efficient, stable and intelligent management of power grid operation, and effectively solving the problems of load imbalance, large environmental impact and difficult management of energy storage equipment in power grid operation.
[0103] Example 4
[0104] This embodiment is explained in Example 1, please refer to Figure 1 ,Specifically: the state evaluation module includes a matching unit;
[0105] The matching unit matches the required comparison value through the preset relevant information, including the preset regional equipment operation load fluctuation threshold B and the regional load optimization index C. total Perform matching and obtain regional energy storage equipment load assessment solutions;
[0106] The regional energy storage equipment load assessment scheme is obtained by the following matching method:
[0107] Regional load optimization index C total <Regional equipment operation load fluctuation threshold B, obtain the qualified result of regional energy storage equipment load assessment, and do not adjust the current regional energy storage equipment configuration plan;
[0108] Regional load optimization index C total≥ Regional equipment operation load fluctuation threshold B, obtain the unqualified result of regional energy storage equipment load assessment, and adjust the current regional energy storage equipment configuration plan, including adjusting the charging and discharging of energy storage equipment, reallocating energy storage equipment capacity adjustment, and optimizing the grid topology structure adjustment;
[0109] Regional load optimization index C total When the load fluctuation threshold value B of the regional equipment operation is ≥ twice, the load assessment warning results of the regional energy storage equipment are obtained, and the warning of the current regional energy storage equipment is synchronously displayed and notified to relevant staff.
[0110] The decision-making module includes an execution unit and a control unit;
[0111] The execution unit performs specific execution according to the content of the regional energy storage device load assessment plan, including receiving and parsing the content of the regional energy storage device load assessment plan, extracting specific measures to be executed, and generating detailed operation instructions according to the specific measures, including charging current, voltage setting and discharge start timing;
[0112] The control unit provides feedback, monitoring and iterative regulation on the specific execution results of the regional energy storage equipment load assessment plan; feedback includes collecting data after execution of each energy storage device, including charge and discharge data, device status data and load data; monitoring includes continuous monitoring of the energy storage device, and real-time collection of equipment operating status and load fluctuation information; iteration includes using the data after each execution for the adjustment of the next regional energy storage equipment load assessment plan through a feedback loop mechanism.
[0113] In this embodiment, the preset regional equipment load fluctuation threshold B and regional load optimization index C are used. total Matching is carried out to obtain the regional energy storage equipment load assessment plan. When the energy storage equipment configuration plan is qualified, no adjustment is required, thus avoiding unnecessary waste of resources. When an unqualified assessment result is generated, the charging and discharging strategy of the energy storage equipment is automatically adjusted, the capacity of the energy storage equipment is reallocated, and even the grid topology is optimized to ensure the stable operation of the grid. When it reaches or exceeds twice the regional equipment operating load fluctuation threshold B, the system issues an early warning to notify relevant staff to ensure timely response to potential risks. Through this matching and assessment mechanism, the accuracy and flexibility of grid load management are improved, and the utilization efficiency of energy storage equipment and the overall reliability of the grid and its ability to respond to dynamic changes are greatly improved.
[0114] Example 5
[0115] A distribution network energy storage configuration optimization method, please refer to Figure 2 , specifically: including the following steps:
[0116] Step 1: The equipment acquisition module collects real-time load data of each area of the power grid, status data of the energy storage equipment, ambient temperature data, and power grid topology information to form a real-time acquisition data group;
[0117] Step 2: The data processing module preprocesses the real-time collected data group, including data denoising, normalization and missing value filling, and integrates the processed real-time collected data group into a data processing set;
[0118] Step 3: The load prediction module uses machine learning algorithms and deep learning technologies to build a regional equipment operation load trend model for the data processing set, and trains and analyzes the regional equipment operation load trend model to obtain the regional load optimization index C. total ;
[0119] Step 4: The status evaluation unit uses the preset regional equipment load fluctuation threshold B and regional load optimization index C total Perform matching and obtain regional energy storage equipment load assessment solutions;
[0120] Step 5: The decision-making module performs specific actions according to the content of the regional energy storage equipment load assessment plan, and provides feedback, monitoring and iterative regulation on the execution results.
[0121] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.
Claims
1. A distribution network energy storage configuration optimization system, Features: It includes equipment acquisition module, data processing module, load prediction module, status assessment module and decision-making module; The equipment acquisition module collects real-time load data of each area of the power grid, status data of the energy storage device, ambient temperature data and power grid topology information to form a real-time acquisition data group; The data processing module preprocesses the real-time collected data group, including data denoising, normalization and missing value filling, and integrates the processed real-time collected data group into a data processing set; The load prediction module uses machine learning algorithms and deep learning technologies to establish a regional equipment operation load trend model for the data processing set, and trains and analyzes the regional equipment operation load trend model to obtain the regional load optimization index C total ; The status evaluation module uses the preset regional equipment operation load fluctuation threshold B and the regional load optimization index C total Perform matching and obtain regional energy storage equipment load assessment solutions; The decision module is specifically executed according to the content of the regional energy storage equipment load assessment plan, and feedbacks, monitors and iteratively regulates the execution results.
2. A distribution network energy storage configuration optimization system according to claim 1, Features: The equipment acquisition module includes a regional load unit and an equipment monitoring unit; The regional load unit obtains real-time load data from smart meters and load monitoring equipment in various areas of the power grid, including power consumption, instantaneous power and power factor; The equipment monitoring unit obtains the energy storage equipment status data through the integrated energy storage system, including equipment positioning, switch status, battery power, charge and discharge rate, battery temperature, number of cycles and health status value, and obtains the equipment operation area environmental information through the environmental monitoring sensor integrated in the equipment operation area, including temperature, humidity, wind speed and particulate matter concentration, and combines it with the real-time collected data of the regional load unit to form a real-time collected data group.
3. A distribution network energy storage configuration optimization system according to claim 1, Features: The data processing module includes a preprocessing unit and an integration unit; The preprocessing unit preprocesses the real-time collected data group, including data denoising, normalization and missing value filling, wherein data denoising is performed by using statistical methods and machine learning algorithms for identification, and then low-pass filters and median filters are used to remove high-frequency noise and outliers in the data; normalization is dimensionless processing through minimum and maximum normalization and Z-score normalization; missing value filling includes filling, replacing and trend predicting missing values using mean filling, interpolation and prediction model filling methods, and feature extraction and statistical labeling are performed on the preprocessed real-time collected data group to integrate into a data processing set.
4. A distribution network energy storage configuration optimization system according to claim 3, Features: The data processing set includes energy storage device discharge power, energy storage device charging power, regional real-time load power, energy storage device charging status, regional ambient temperature, regional peak and valley temperature values, and regional node connection relationships; The regional node connection relationship includes node number, connection line, resistance value, connection type and location information.
5. A distribution network energy storage configuration optimization system according to claim 4, Features: The load prediction module includes a modeling unit; The modeling unit uses machine learning algorithms and deep learning technologies to establish a regional equipment operation load trend model for the data processing set, and performs training and analysis on the regional equipment operation load trend model to obtain the regional load optimization index C total ; The regional load optimization index C total Obtained through the following calculation formula: C total =α*C balance +β*C health +γ*C temp +δ*C quality ; In the formula, C balance represents the power quality assessment index, C health Indicates the equipment area environmental assessment index, C temp Represents the energy storage battery status assessment index, C quality represents the regional equipment load evaluation index, α, β, γ and δ represent the power quality evaluation index C balance , Equipment Area Environmental Assessment Index C health , Energy storage battery status assessment index C temp and regional equipment load assessment index C quality The weight coefficient of .
6. A distribution network energy storage configuration optimization system according to claim 5, Features: The power quality assessment index C balance Obtained through the following calculation formula: In the formula, C balance Represents the power quality assessment index, specifically indicating the stable quality performance of voltage, K represents the total number of measurement points, V e (t) represents the voltage at the eth measurement point at time t, V ref Indicates the preset reference voltage value, including 220V and 110V; The equipment area environmental assessment index C health Obtained through the following calculation formula: In the formula, C health Equipment regional environmental assessment index, specifically used to measure the impact of ambient temperature on grid energy storage equipment. N represents the number of regions, W represents the i (t) represents the regional ambient temperature of the i-th region at time t, represents the average regional ambient temperature at time t, W max Indicates the peak ambient temperature of the area, W min Indicates the valley value of regional ambient temperature; Where: the average regional ambient temperature at time t pass Obtained by formula calculation.
7. A distribution network energy storage configuration optimization system according to claim 5, Features: The energy storage battery status evaluation index C temp Obtained through the following calculation formula: In the formula, C temp Represents the energy storage battery status evaluation index, specifically indicating the operating status of the energy storage device. M represents the number of energy storage devices, S q (t) represents the charging state of the qth device at time t, specifically the percentage of the energy currently stored in the battery to the total capacity, represents the average state of charge of the energy storage device at time t, S max Indicates the rated state of charge of the energy storage device; Among them, the average charge state of the energy storage device at time t is pass Calculation: The charge state S(t) at time t is calculated by the Coulomb counting method: Where S(t) represents the charging state at time t, which is obtained through full charge and discharge tests and calibration data provided by the manufacturer. 0 ) represents the initial time t 0 The charging state, Cx represents the rated capacity of the energy storage device battery, I(t) represents the charging and discharging current at time t, Represents the time from the initial time t 0 The current integral to time t; The regional equipment load evaluation index C quality Obtained through the following calculation formula: In the formula, C quality It represents the power quality assessment index, which specifically indicates the degree of load power balance in several regions. N represents the number of regions, and P i (t) represents the actual load power of the ith region at time t, Average load power at time t; Among them, the average load power at time t pass Obtain the calculation formula.
8. A distribution network energy storage configuration optimization system according to claim 1, Features: The state assessment module includes a matching unit; The matching unit matches the required comparison value through the preset relevant information, including the preset regional equipment operation load fluctuation threshold B and the regional load optimization index C. total Perform matching and obtain regional energy storage equipment load assessment solutions; The regional energy storage equipment load assessment scheme is obtained by the following matching method: Regional load optimization index C total <Regional equipment operation load fluctuation threshold B, obtain the qualified result of regional energy storage equipment load assessment, and do not adjust the current regional energy storage equipment configuration plan; Regional load optimization index C total ≥ Regional equipment operation load fluctuation threshold B, obtain the unqualified result of regional energy storage equipment load assessment, and adjust the current regional energy storage equipment configuration plan, including adjusting the charging and discharging of energy storage equipment, reallocating energy storage equipment capacity adjustment, and optimizing the grid topology structure adjustment; Regional load optimization index C total When the load fluctuation threshold value B of the regional equipment operation is ≥ twice, the load assessment warning result of the regional energy storage equipment is obtained, and the warning of the current regional energy storage equipment is synchronously displayed and notified to the relevant staff.
9. A distribution network energy storage configuration optimization system according to claim 1, Features: The decision-making module includes an execution unit and a control unit; The execution unit performs specific execution according to the content of the regional energy storage device load assessment plan, including receiving and parsing the content of the regional energy storage device load assessment plan, extracting specific measures to be executed, and generating detailed operation instructions according to the specific measures, including charging current, voltage setting and discharge start timing; The control unit provides feedback, monitoring and iterative regulation on the specific execution results of the regional energy storage equipment load assessment plan; feedback includes collecting data after execution of each energy storage device, including charge and discharge data, device status data and load data; monitoring includes continuous monitoring of the energy storage device, and real-time collection of equipment operating status and load fluctuation information; iteration includes using the data after each execution for the adjustment of the next regional energy storage equipment load assessment plan through a feedback loop mechanism.
10. A distribution network energy storage configuration optimization method, comprising a distribution network energy storage configuration optimization system according to any one of claims 1 to 9, Features: The following steps are involved: Step 1: The equipment acquisition module collects real-time load data of each area of the power grid, status data of the energy storage equipment, ambient temperature data, and power grid topology information to form a real-time acquisition data group; Step 2: The data processing module preprocesses the real-time collected data group, including data denoising, normalization and missing value filling, and integrates the processed real-time collected data group into a data processing set; Step 3: The load prediction module uses machine learning algorithms and deep learning technologies to build a regional equipment operation load trend model for the data processing set, and trains and analyzes the regional equipment operation load trend model to obtain the regional load optimization index C. total ; Step 4: The status evaluation unit uses the preset regional equipment load fluctuation threshold B and regional load optimization index C total Perform matching and obtain regional energy storage equipment load assessment solutions; Step 5: The decision-making module performs specific actions according to the content of the regional energy storage equipment load assessment plan, and provides feedback, monitoring and iterative regulation on the execution results.
Citation Information
Patent Citations
Power load scheduling method and system based on big data
CN116646933A
Electric power measurement data security risk assessment method and system
CN117634892A
Configuration operation method of energy storage system for new energy consumption
CN117879018A
Electric energy optimization storage method and system for energy storage power station
CN118117635A
Cited By
Method and system for monitoring running state of intelligent power grid equipment
CN119864805A
Energy storage power station EMS energy monitoring and management system
CN119995144A
An energy storage power station EMS energy monitoring and management system
CN119995144B
Database load dynamic management system
CN120144413A
Reverse discharge control method for virtual energy storage unit of mobile emergency power supply of new energy automobile
CN120185049A
