Power grid planning optimization method and system based on load characteristics

Abstract

The invention discloses a power grid planning optimization method and system based on load characteristics, relates to the technical field of power system planning, and solves the power grid planning problem of insufficient economic benefits of incremental user access caused by insufficient load prediction and economic analysis in the prior art. The method comprises the steps of collecting load data of power consumers and performing feature extraction; using a clustering algorithm to classify the extracted features, classifying users with similar load modes into one class, and using an average load curve of each class of users as a typical load curve of the class; a typical load curve of the incremental users is determined, and the electric quantity Qall required by the newly-added users is obtained based on the typical load curve; and constructing a target function by taking benefit maximization as a target, and obtaining an optimal access scheme of the incremental users in a mode of solving the target function. The optimal access scheme is solved, data reference is provided for related technicians, and the technicians are helped to make objective decisions reflecting economic benefits.

Description

Technical Field

[0001] The present invention relates to the technical field of power system planning, and particularly to a power grid planning optimization method and system based on load characteristics. Background Art

[0002] Load characteristics refer to the electricity consumption patterns and rules of power users in different time periods, usually described by load curves. It reflects the changes in electricity consumption demands of users on different time scales such as daily, monthly, quarterly, and annually, including key indicators such as the peak value, valley value, average load, and load rate of the load. Load characteristics not only determine the real-time demand of users for the power system but also affect the operation efficiency and stability of the power grid. Accurately grasping load characteristics is of great significance for optimizing power grid planning, improving equipment utilization rate, and reducing operation costs. For the access of incremental users to the power grid, in-depth study of load characteristics is a key link to ensure the scientific, reasonable, economic, and efficient access plan, which can effectively avoid the power grid operation risks and resource waste caused by the mismatch of load characteristics.

[0003] Incremental users refer to the users newly connected to the power grid. These users have not yet had business dealings with the power grid or enterprise and are new users introduced by the power grid or enterprise through market expansion, new project construction, etc. The process of incremental user access needs to comprehensively consider the carrying capacity of the power grid, the selection of access points, and the economy and reliability after access. However, in the actual operation of incremental user access at present, due to the inaccurate grasp of the actual load situation of users and the insufficient economic control in the access planning process, the access results are not ideal. On the one hand, the deviation of load forecasting may cause problems such as local overload or low equipment utilization rate in the power grid after the access of incremental users; on the other hand, the access plan lacks economic analysis and fails to fully consider the return on investment and long-term operation costs, resulting in the failure to maximize the economic benefits after access. These problems not only affect the operation efficiency of the power grid but also restrict the sustainable development of incremental user access, and there is an urgent need to improve the access effect through optimized planning and refined management.

[0004] In view of this, a power grid planning optimization method and system based on load characteristics are needed. Summary of the Invention

[0005] Aiming at the power grid planning problem of insufficient economic benefits of incremental user access due to insufficient load forecasting and economic analysis in the prior art, the present invention provides a power grid planning optimization method and system based on load characteristics, which can use a clustering algorithm to classify the extracted features, group users with similar load patterns into one category, and based on this, determine the typical load curve of incremental users according to different situations, and then construct an objective function with the goal of maximizing benefits, and obtain the best access plan for incremental users by solving the objective function. The specific technical solutions are as follows:

[0006] A power grid planning optimization method based on load characteristics, comprising the following steps:

[0007] Collect the load data of power users and perform feature extraction;

[0008] Use a clustering algorithm to classify the extracted features, group users with similar load patterns into one category, and use the average load curve of each category of users as the typical load curve of that category;

[0009] Determine the typical load curve of incremental users, and obtain the required electricity Q of new users based on the typical load curve all ;

[0010] Construct an objective function with the goal of maximizing benefits, and obtain the optimal access plan for incremental users by solving the objective function. The specific objective function is as follows:

[0011]

[0012] In the formula, Z is the benefit function, R e is the electricity price, Q all is the required electricity of new users within the calculation period, C l_i is the unit length line cost of the i-th line, L i is the length of the i-th line, n is the total number of lines, C f is the cost per unit electricity of distributed power generation, and Q1 is the electricity provided by the access power station.

[0013] Preferably, the load rate of the access power station is also considered in the objective function, and the specific expression is as follows:

[0014]

[0015] In the formula, δ u is the load rate of the access power station, η is the load rate penalty coefficient, and is a constant.

[0016] Preferably, in the objective function, the importance degrees of the line cost and the distributed power generation construction cost are adjustable to adapt to different objective biases, and the specific expression is as follows:

[0017]

[0018] In the formula, k1 is the weight coefficient of using the existing power grid, k2 is the weight coefficient of newly built distributed power generation, both k1 and k2 are constants, and by default they are 1. According to the objective bias, k1 and k2 are set as two constants with different magnitudes to reflect the different influence degrees of the two directions in the decision-making process.

[0019] Preferably, in the solution strategy process, voltage constraints are included, and the specific expression is as follows:

[0020] V min ≤V d ≤V max

[0021] Wherein, V d is the actual voltage of the access point, V min and V max are the upper and lower voltage limits specified by the power grid respectively.

[0022] Preferably, it further includes a voltage drop constraint, specifically as follows:

[0023] ΔU total ≤ΔU max

[0024]

[0025] Wherein, ΔU total is the total voltage drop, ΔU max is the maximum allowable voltage drop. I i , R i , L i are the current, resistance and length of the i-th line segment respectively.

[0026] Preferably, during the solution strategy process, it includes a load rate, specifically expressed as follows:

[0027] δ u ≤δ max

[0028] Wherein, δ max is the maximum load rate.

[0029] Preferably, during the solution strategy process, it includes a distributed power source access constraint, specifically as follows:

[0030] P DG ≤P DG_max

[0031] cosφ≥cosφ min

[0032] Wherein, P DG is the access power of the distributed power source, P DG_max is the maximum allowable access power of the distributed power source, cosφ is the power factor of the distributed power source, cosφ min is the minimum allowable power factor.

[0033] A power grid planning optimization system based on load characteristics, which is applied to a power grid planning optimization method based on load characteristics as described above, includes:

[0034] The data acquisition module collects the load data of power users, including active power, reactive power, current, and voltage, and performs data cleaning, normalization, and feature extraction on the collected data;

[0035] The classification module uses the K-means clustering algorithm to classify the extracted features, grouping users with similar load patterns into one category, and the average load curve of each category of users is the typical load curve of that category;

[0036] The typical load curve acquisition module determines the typical load curve of incremental users. When historical electricity consumption data exists for incremental users, the average load curve of this user is used as the typical load curve of this user; if historical electricity consumption data does not exist for incremental users, the industry type of incremental users is first determined, and the typical load curve of the corresponding type is selected as the typical load curve of the current incremental user's industry type;

[0037] The decision output module constructs an objective function with the goal of maximizing benefits, and obtains the optimal access plan for incremental users by solving the objective function. The specific objective function is as follows:

[0038]

[0039] In the formula, Z is the benefit function, R e is the electricity price, Q all is the required electricity consumption of new users within the calculation period, C l_i is the unit length line cost of the i-th line, L i is the length of the i-th line, n is the total number of lines, C f is the cost per unit electricity of distributed power generation, Q1 is the electricity provided by the access power station. Among them, distributed power generation includes three situations: wind power, thermal power, and photovoltaic power generation, that is:

[0040] C f ∈[C 光电 ,C 风电 ,C 火电

[0041] In the formula, C 光电 is the cost per unit electricity of photovoltaic power generation, C 风电 is the cost per unit electricity of wind power generation, C 火电 is the cost per unit electricity of thermal power generation.

[0042] The cost per unit electricity of each form is given below. During the solution process of the objective function, one of them is selected and substituted each time.

[0043]

[0044] Among them, P dynamic_cost_g is the dynamic investment cost of the photovoltaic power field, T​O&M_g is the operation duration of the photovoltaic power plant, D deprectation_g is the depreciation amount of the fixed assets of the photovoltaic power plant, P O&M_g is the operation and maintenance cost of the photovoltaic power plant, R tax_g is the income tax rate of the photovoltaic power plant, R discount is the discount rate, V restdualvaiue_g is the salvage value of the fixed assets of the photovoltaic power plant, E annual_g is the annual power generation of the photovoltaic power plant.

[0045]

[0046] Among them, P dynamic_cost is the dynamic investment cost of the wind farm, T O&M is the operation duration of the wind farm, D deprectation is the depreciation amount of the fixed assets of the wind farm, P O&M is the operation and maintenance cost of the wind farm, R tax is the income tax rate of the wind farm, R discount is the discount rate, V restdualvaiue is the salvage value of the fixed assets of the wind farm, E annual is the annual power generation of the wind farm.

[0047]

[0048] In the formula, C n represents the cost expenditure in the nth year, Q n represents the power generation in the nth year, r represents the internal rate of return, or the discount rate, Q 火电_发电 is the output thermal power.

[0049] A computer-readable storage medium, the computer-readable storage medium includes a stored program, wherein, when the program runs, it controls the device where the computer-readable storage medium is located to execute the grid planning optimization method based on load characteristics as described above.

[0050] A processor, the processor is used to run a program, wherein, when the program runs, it executes the grid planning optimization method based on load characteristics as described above.

[0051] Compared with the prior art, the beneficial effects of the present invention are:

[0052] 1. The present invention collects the load data of power users and performs feature extraction; uses a clustering algorithm to classify the extracted features, groups users with similar load patterns into one category, and uses the average load curve of each category of users as the typical load curve of the category; determines the typical load curve of incremental users, and based on the typical load curve, obtains the required power Q of new users all; Construct an objective function with the goal of maximizing benefits, and obtain the optimal access plan for incremental users by solving the objective function. Provide data reference for relevant technicians based on the obtained optimal access plan to help them make objective decisions that reflect economic benefits.

[0053] 2. The present invention considers the load factor in the benefit function and adds the load coefficient to the cost of the access power station, so that this concept is reflected in the form of cost. The higher the load factor, the higher the cost of the access power station, and it is not easy for this access power station to be determined as the optimal access power station, which plays a role in responding to the access principle and access trend. In addition, according to the tolerance of the load factor and the degree of deployment preference under the current policy, by setting the specific value of the load factor penalty coefficient η, the role played by the load factor in the benefit function can be further changed.

[0054] 3. In the process of solving the objective function, the present invention considers voltage constraints to ensure that the voltage at the access point of incremental users meets the requirements of power grid operation and the voltage does not exceed the allowable range after access; it also considers voltage drop constraints, and fully considers the impact brought by lines with different costs, materials, etc. in the calculation of the total voltage drop due to economic benefits. In addition, load factor constraints are also considered to ensure the safe operation of the power grid and the economy of equipment. Distributed power access constraints and economic constraints are also considered. In short, through the constraints of each constraint condition, the strategy obtained by solving the objective function not only meets the economic requirements, but also meets the requirements of practical applications, maximizing economic benefits while ensuring access performance. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] In order to more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the following will briefly introduce the drawings required for the description of the specific embodiments or the prior art. In all the drawings, similar elements or parts are generally identified by similar reference numerals. In the drawings, the elements or parts are not necessarily drawn to actual scale.

[0056] Figure 1 It is the flowchart of the method of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0057] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the drawings in the embodiments of the present invention. Obviously, the described embodiments are some but not all of the embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0058] It should be understood that when used in this specification and the appended claims, the terms "comprising" and "including" indicate the presence of the described features, wholes, steps, operations, elements and / or components, but do not preclude the presence or addition of one or more other features, wholes, steps, operations, elements, components and / or their combinations.

[0059] It should also be understood that the terms used in the specification of the present invention are for the purpose of describing specific embodiments only and are not intended to limit the present invention. As used in the specification of the present invention and the appended claims, unless the context clearly indicates otherwise, the singular forms "a", "an" and "the" are intended to include the plural forms.

[0060] It should be further understood that the term "and / or" used in the specification of the present invention and the appended claims refers to any combination and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0061] In one embodiment of the present invention, there is provided an optimization method for power grid planning based on load characteristics, including the following steps:

[0062] Step 1: Collect the load data of power users, including active power, reactive power, current, and voltage, and perform data cleaning, normalization, and feature extraction on the collected data.

[0063] In this step, the original collection of data is specifically carried out by using intelligent metering terminal devices (such as load characteristic recording devices, data acquisition and monitoring systems, wide area measurement systems, fault recording and monitoring devices, etc., which can collect users' electricity consumption information in real time).

[0064] Data cleaning: Remove outliers, duplicate values, and missing values in the data. For missing data, a method based on the decomposition and reconstruction of the electricity consumption pattern can be used for repair.

[0065] Data normalization: Normalize the data to the interval [0, 1] for subsequent processing.

[0066] Feature extraction: Extract features related to load characteristics, including daily electricity consumption, hourly electricity consumption, peak-to-valley ratio of electricity consumption, peak-valley difference, and load factor.

[0067] Step 2: Use the K-means clustering algorithm to classify the extracted features, and group users with similar load patterns into one category. The average load curve of each category of users is the typical load curve of this category.

[0068] Step 3: Determine the typical load curve of incremental users, and obtain the electricity demand situation of users based on the typical load curve (the electricity required by new users Q all )

[0069] When the incremental user has historical power consumption data, the average load curve of the user is used as the typical load curve of the user; if the incremental user does not have historical power consumption data, the industry type of the incremental user is first determined, and the typical load curve of the corresponding type is selected as the typical load curve of the current incremental user industry type.

[0070] Step 4: Construct an objective function with the goal of maximizing benefits, and obtain the optimal access plan for incremental users by solving the objective function.

[0071] In the acquisition of the incremental user access plan, from an economic perspective, what needs to be considered is the benefit after the incremental user is connected, and the economic cost that needs to be paid after the incremental user is connected. Since there are mainly two ways for incremental users to obtain electric energy: accessing existing grid resources and building new distributed power sources. Therefore, the economic cost of this embodiment includes the economic cost of using existing grid resources and the cost of building new distributed power sources, or the cost generated by the combination of the two.

[0072] Among them, the objective function is specifically as follows:

[0073]

[0074] In the formula, Z is the benefit function, R e is the electricity price, Q all is the required electricity quantity within the calculation period of the new user, C l_i is the unit length line cost of the i-th line, L i is the length of the i-th line, n is the total number of lines, δ u is the load factor of the access power station, η is the load factor penalty coefficient, which is a constant, defaulting to 1, C f is the cost per kilowatt-hour of the distributed power source, Q1 is the electricity quantity provided by the access power station, k1 is the weight coefficient of using the existing grid, k2 is the weight coefficient of building a new distributed power source, k1 and k2 are both constants, and default to 1. According to the bias degree of real-time policies, k1 and k2 can be set as two constants with different sizes to reflect the different influence degrees of the two directions in the decision-making process. Among them, the load factor is calculated by the following formula:

[0075]

[0076] In the formula, Q 原负荷 is the actual electricity consumption of the access power station before the incremental user is connected, Q1 is the electricity quantity obtained by the incremental user from the access power station, Q 额定 is the maximum possible electricity consumption of the access power station.

[0077] The reason for considering the load factor in the benefit function is that, considering the current general trend of incremental user access, which is to preferentially access substations with a lower load factor. Therefore, the load factor is added to the cost of the access substation, enabling this concept to be reflected in the form of cost. The higher the load factor, the higher the cost of the access substation, and this access substation is less likely to be determined as the optimal access substation, thus playing a role in responding to the access principle and access trend. In addition, according to the tolerance of the load factor and the degree of deployment preference under the current policy, by setting the specific value of the load factor penalty coefficient η, the role played by the load factor in the benefit function can be further changed.

[0078] In this embodiment, the distributed power sources include three cases: wind power, thermal power, and photovoltaic power generation, namely:

[0079] C f ∈[C 光电 ,C 风电 ,C 火电

[0080] In the formula, C 光电 is the cost per kilowatt-hour of photovoltaic power generation, C 风电 is the cost per kilowatt-hour of wind power generation, C 火电 is the cost per kilowatt-hour of thermal power generation.

[0081] The cost per kilowatt-hour of each form is given below. During the solution process of the objective function, one of them can be selected and substituted at a time.

[0082]

[0083] Among them, P dynamic_cost_g is the dynamic investment cost of the photovoltaic power plant, T O&M_g is the operation duration of the photovoltaic power plant, D deprectation_g is the fixed asset depreciation amount of the photovoltaic power plant, P O&M_g is the operation and maintenance cost of the photovoltaic power plant, R tax_g is the income tax rate of the photovoltaic power plant, R discount is the discount rate, V restdualvaiue_g is the fixed asset salvage value of the photovoltaic power plant, E annual_g is the annual power generation of the photovoltaic power plant.

[0084]

[0085] Among them, P dynamic_cost is the dynamic investment cost of the wind power plant, T O&M is the operation duration of the wind power plant, D deprectation is the fixed asset depreciation amount of the wind power plant, P O&M is the operation and maintenance cost of the wind power plant, R tax is the income tax rate of the wind power plant, R discount is the discount rate, V restdualvaiue ​is the residual value of the fixed assets of the wind farm, E annual is the annual power generation of the wind farm.

[0086]

[0087] In the formula, C n represents the cost expenditure in the nth year, Q n represents the power generation in the nth year, r represents the internal rate of return, or the discount rate, Q 火电_发电 is the output thermal power.

[0088] In the process of solving the specific strategy, the following constraints also need to be noted:

[0089] 1. Voltage constraint

[0090] The voltage at the incremental user access point needs to meet the requirements of grid operation to ensure that the voltage does not exceed the allowable range after access. Therefore, there is a voltage constraint, which is specifically as follows:

[0091] V min ≤V d ≤V max

[0092] In the formula, V d is the actual voltage at the access point, V min , V max are the upper and lower voltage limits specified by the grid respectively.

[0093] 2. Voltage drop constraint

[0094] Since the costs of different lines (C l_i ) are considered in the decision-making acquisition stage, and the voltage drops brought by different lines are different while the costs are different. Therefore, the voltage drop of each different line segment needs to be considered separately. After obtaining the total voltage drop, it is then checked whether it exceeds the maximum allowable voltage drop based on the total voltage drop. Therefore, the voltage drop constraint is specifically as follows:

[0095] ΔU total ≤ΔU max

[0096]

[0097] In the formula, ΔU total is the total voltage drop, ΔU max is the maximum allowable voltage drop. I i , R i , L i are the current, resistance, and length of the ith line segment respectively.

[0098] 3. Load rate constraint

[0099] During the incremental user access process, it is necessary to consider the load rate constraint of the access power station to ensure the safe operation of the power grid and the economy of the equipment. Therefore, during the policy solution process, attention should be paid to the load rate constraint, which is specifically as follows:

[0100] δ u ≤δ max

[0101] In the formula, δ max is the maximum load rate, usually set to 85%.

[0102] 4. Distributed power source access constraint

[0103] If the incremental user includes a distributed power source (such as a small hydropower station), it is necessary to meet the access capacity and power factor requirements, which are specifically as follows:

[0104] P DG ≤P DG_max

[0105] cosφ≥cosφ min

[0106] In the formula, P DG is the access power of the distributed power source, P DG_max is the maximum allowable access power of the distributed power source, cosφ is the power factor of the distributed power source, and cosφ min is the minimum allowable power factor to ensure the power quality.

[0107] 5. Economic constraint

[0108] NPV≥0

[0109] In the formula, NPV is the net present value, indicating the economic benefit of the incremental user access.

[0110] To sum up, the present invention collects the load data of power users and performs feature extraction; uses a clustering algorithm to classify the extracted features, groups users with similar load patterns into one category, and uses the average load curve of each category of users as the typical load curve of that category; determines the typical load curve of the incremental user, and based on the typical load curve, obtains the required electricity quantity Q of the new user all; A target function is constructed with the goal of maximizing benefits, and the optimal access plan for incremental users is obtained by solving the target function. The obtained optimal access plan provides data reference for relevant technical personnel to help them make objective decisions that reflect economic benefits. Moreover, in the benefit function of the present invention, the load rate is considered, and the load coefficient is added to the cost of the access power station, so that this concept is reflected in the form of cost. The higher the load rate, the higher the cost of the access power station, and it is not easy for this access power station to be determined as the optimal access power station, which plays a role in responding to the access principle and access trend. In addition, according to the tolerance of the load rate and the degree of deployment preference under the current policy, by setting the specific value of the load rate penalty coefficient η, the role of the load rate in the benefit function can be further changed. In addition, during the process of solving the target function, the present invention considers voltage constraints to ensure that the voltage at the incremental user access point meets the requirements of power grid operation and does not exceed the allowable range after access; it also considers voltage drop constraints, and fully considers the impact brought by lines with different costs, materials, etc. that may exist due to economic benefits reasons during the calculation of the total voltage drop. In addition, load rate constraints are also considered to ensure the safe operation of the power grid and the economy of equipment. Distributed power access constraints and economic constraints are also considered. All in all, through the constraints of each constraint condition, the strategy obtained by solving the target function not only meets the economic requirements but also meets the requirements in practical applications, maximizing economic benefits while ensuring access performance.

[0111] Those of ordinary skill in the art can realize that the units of each example described in combination with the embodiments disclosed herein can be implemented by electronic hardware, computer software, or a combination of the two. To clearly illustrate the interchangeability of hardware and software, the components of each example have been generally described according to their functions in the above description. Whether these functions are executed in hardware or software depends on the specific application and design constraints of the technical solution. Professional technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the present invention.

[0112] In the embodiments provided by the present invention, it should be understood that the division of units is only a logical function division, and there may be other division methods in actual implementation. For example, multiple units can be combined into one unit, one unit can be split into multiple units, or some features can be ignored, etc.

[0113] In addition, the functional units in each embodiment of the present invention can be integrated in one processing unit, or each unit can exist physically alone, or two or more units can be integrated in one unit. The above integrated units can be implemented in the form of hardware or in the form of software functional units.

[0114] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in various embodiments of the present invention. The aforementioned storage medium includes: various media that can store program codes, such as USB flash drives, read-only memories (ROMs), random access memories (RAMs), mobile hard disks, magnetic disks, or optical discs.

[0115] Finally, it should be noted that: the above embodiments are only used to illustrate the technical solutions of the present invention, and are not intended to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that: they can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements on some or all of the technical features; and these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of various embodiments of the present invention, and they should all be covered by the scope of the claims and the description of the present invention.

Claims

1. A power grid planning optimization method based on load characteristics, characterized in that Including the following steps: Collect the load data of power users and perform feature extraction; Use a clustering algorithm to classify the extracted features, group users with similar load patterns into one category, and use the average load curve of each category of users as the typical load curve of that category; Determine the typical load curve of incremental users, and obtain the required electricity quantity Q of new users based on the typical load curve all ; Construct an objective function with the goal of maximizing benefits, and obtain the optimal access plan for incremental users by solving the objective function. The specific objective function is as follows: where Z is the benefit function, R e is the electricity price, Q all is the required electricity quantity within the calculation period of new users, C l_i is the unit length line cost of the i-th line, L i is the length of the i-th line, n is the total number of lines, C f is the cost per unit electricity of the distributed power source, and Q1 is the electricity quantity provided by the connected power station.

2. The grid planning optimization method based on load characteristics according to claim 1, wherein The load factor of the access power station is also considered in the objective function, and the specific expression is as follows: where δ u is the load factor of the connected power station, η is the load factor penalty coefficient, and it is a constant 3. A grid planning optimization method based on load characteristics according to claim 1, characterized in that, In the objective function, the importance levels of the line cost and the distributed power source construction cost are adjustable to adapt to different objective biases. The specific details are as follows: In the formula, k1 is the weight coefficient for using the existing power grid, and k2 is the weight coefficient for newly built distributed power sources. Both k1 and k2 are constants and are defaulted to 1. According to the objective bias, k1 and k2 are set as two constants with different magnitudes to reflect the different influence degrees of the two directions in the decision-making process.

4. A power grid planning optimization method based on load characteristics according to claim 1, characterized in that During the solution strategy process, voltage constraints are included, and the specific expression is as follows: V min ≤V d ≤V max Where, V d is the actual voltage of the access point, V min , V max are the upper and lower voltage limits specified by the power grid, respectively.

5. The grid planning optimization method based on load characteristics according to claim 4, characterized in that, Voltage drop constraints are also included, and the details are as follows: ΔU total ≤ΔU max Where ΔU total is the total pressure drop, and ΔU max is the maximum allowable pressure drop. I i , R i , and L i are the current, resistance, and length of the i-th line segment, respectively.

6. A grid planning optimization method based on load characteristics according to claim 2, characterized in that During the solution strategy process, load factor is included, and the specific expression is as follows: δ u ≤δ max where δ max is the maximum load factor.

7. A power grid planning optimization method based on load characteristics according to claim 1, characterized in that During the solution strategy process, distributed power source access constraints are included, and the details are as follows: P DG ≤P DG_max cosφ≥cosφ min Wherein, P DG is the access power of the distributed power source, P DG_max is the maximum allowable access power of the distributed power source, cosφ is the power factor of the distributed power source, and cosφ min is the minimum allowable power factor.

8. A power grid planning optimization system based on load characteristics, which is applied to a power grid planning optimization method based on load characteristics as described in any one of claims 1-7, characterized in that, Including: A data collection module that collects the load data of power users, including active power, reactive power, current, and voltage, and performs data cleaning, normalization, and feature extraction on the collected data; A classification module that uses the K-means clustering algorithm to classify the extracted features, groups users with similar load patterns into one category, and the average load curve of each category of users is the typical load curve of that category; A typical load curve acquisition module that determines the typical load curve of incremental users. When historical electricity consumption data exists for incremental users, the average load curve of this user is used as the typical load curve of this user; if historical electricity consumption data does not exist for incremental users, then first determine the industry type of the incremental user, and select the typical load curve of the corresponding type as the typical load curve of the current incremental user's industry type; A decision output module that constructs an objective function with the goal of maximizing benefits, and obtains the optimal access plan for incremental users by solving the objective function. The specific objective function is as follows: Where Z is the benefit function, R e is the electricity price, Q all is the required electricity consumption within the calculation period of new users, C l_i is the unit length line cost of the i-th line, L i is the length of the i-th line, n is the total number of lines, C f is the cost per unit electricity of distributed power sources, and Q1 is the electricity quantity provided by the connected power station.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes a stored program. When the program runs, it controls the device where the computer-readable storage medium is located to execute the grid planning optimization method based on load characteristics described in any one of claims 1 to 7.

10. A processor, characterized in that, The processor is used to run the program. When the program runs, it executes the grid planning optimization method based on load characteristics described in any one of claims 1 to 7.

Images