Power distribution area scheduling method and device based on differentiated edge requirements and storage medium

Abstract

This specification provides a method, apparatus, and storage medium for distribution transformer (DTR) scheduling based on differentiated edge demand. The method includes: acquiring load demand information of electricity users and a differentiated price-based response model of the electricity users; inputting the load demand information and the differentiated price-based response model into a pre-trained price-demand prediction model to obtain price-demand relationship data; and determining a DTR scheduling strategy based on the price-demand relationship data, preset constraints, and preset DTR costs. The technical solution provided in this application addresses the problem that existing technologies, which set a linear relationship between electricity consumption changes and electricity price changes, still struggle to achieve the desired DTR scheduling results.

Description

Technical Field

[0001] This document relates to the field of user marketing, and in particular to a method, device and storage medium for scheduling distribution areas based on differentiated edge needs. Background Technology

[0002] Demand response (DR) is an important means to smooth the output of distributed power sources and improve the absorption rate of new energy sources. The impact of demand response should be fully considered in the optimized scheduling of distribution areas.

[0003] Some scholars have conducted research on the demand response characteristics of distribution substations. Shi Wenchao et al. constructed a user DR model based on the elasticity coefficient matrix of real-time electricity prices, and simultaneously analyzed the charging load demand of electric vehicles, establishing a robust optimization scheduling model for active distribution networks. Liu Jinyuan et al. proposed a two-layer collaborative configuration model for active distribution networks that takes demand response into account, incentivizing electric vehicle charging and discharging to reduce the peak-valley difference in load and adapting to various planning needs of EV charging stations. Jin Peng et al. applied the distribution network substation operation status assessment based on fuzzy comprehensive evaluation to incentive-based demand response, achieving comprehensive optimization of voltage and load in distribution network substations while reducing peak load. Zhu Chaoting et al. considered user participation in demand response and established an active distribution network optimization scheduling model based on price-based and incentive-based demand response, fully leveraging the flexibility of demand response. Qiu Gefei et al. used triangular fuzzy numbers to describe the uncertainty of demand response, and established a master-slave game economic model for distribution networks with the objectives of minimizing load-side user demand and maximizing wind power absorption, achieving game equilibrium by optimizing real-time electricity price strategies and demand response strategies.

[0004] However, existing studies model the relationship between changes in electricity consumption and changes in electricity prices as linear, which does not reflect reality. This results in the incomplete utilization of response resources and makes it difficult for distribution area dispatch to achieve the desired effect. Summary of the Invention

[0005] Based on the above analysis, this application aims to propose a method, device, and storage medium for dispatching distribution transformers based on differentiated edge demand, so that the changes in electricity consumption and electricity price are more consistent with the actual situation.

[0006] Firstly, one or more embodiments of this specification provide a method for scheduling distribution stations based on differentiated edge requirements, including:

[0007] Obtain the load demand information of electricity users and the differentiated price response model of the electricity users;

[0008] The load demand information and the differentiated price response model are input into a pre-trained price-demand forecasting model to obtain price-demand relationship data.

[0009] Based on the price-demand relationship data, preset constraints, and preset distribution area costs, the scheduling strategy for the distribution area is determined.

[0010] Furthermore, the load demand information includes: load type and real-time electricity price data;

[0011] The process of obtaining load demand information from electricity users includes:

[0012] Obtain the load type and real-time electricity price data corresponding to the electricity user.

[0013] Furthermore, the load demand information also includes: user satisfaction;

[0014] The process of obtaining load demand information from electricity users includes:

[0015] The user satisfaction level is obtained according to the following formula;

[0016]

[0017] in, For electricity user satisfaction; , They are respectively Load volume and load transfer volume before demand response during a given period; The scheduling period is [number].

[0018] Furthermore, the load types include one or more of the following: residential electricity load, industrial electricity load, and electric vehicle charging pile electricity load;

[0019] The step of obtaining the differentiated pricing response model for the electricity user includes:

[0020] Obtain the ratio of the load of each load type to the total load of the distribution area, as well as the electricity and electricity price demand balance data corresponding to each load type;

[0021] Based on the ratio of load to total load of each load type and the electricity-price-demand balance data corresponding to each load type, a differentiated price response model is determined for each load type.

[0022] Furthermore, the transformer area includes: multiple edge computing nodes;

[0023] The step of inputting the load demand information and the differentiated pricing response model into a preset price-demand forecasting model to obtain price-demand relationship data includes:

[0024] Acquire user response behavior data to price changes at each of the aforementioned edge computing nodes;

[0025] Based on the response behavior data, each edge computing node is classified to obtain a node cluster;

[0026] Calculate the price-demand relationship data for each of the aforementioned node clusters;

[0027] Based on the price-demand relationship data of each node cluster, the price-demand relationship data of the transformer area is obtained.

[0028] Furthermore, determining the scheduling strategy for the distribution area based on the price-demand relationship data, preset constraints, and preset distribution area operating costs includes:

[0029] Based on the price-demand relationship data, determine the electricity purchase cost for the distribution area;

[0030] The objective function is determined based on the electricity purchase cost and the transformer substation operating cost.

[0031] Based on the constraints and the objective function, determine the minimum total scheduling cost of the distribution area;

[0032] The scheduling strategy for the distribution area is determined based on the minimum total scheduling cost.

[0033] Furthermore, the operating costs of the transformer substation include one or more of the following: operation and maintenance costs, carbon disposal costs, satisfaction loss costs, and revenue from photovoltaic electricity sales;

[0034] The objective function is specifically:

[0035]

[0036] in, The total cost of dispatching in the distribution area; To optimize the scheduling cycle in advance; For electricity purchase costs; For operation and maintenance costs; Cost of carbon processing; Costs incurred for increased satisfaction; Revenue from selling electricity generated from photovoltaic power plants.

[0037] Furthermore, the constraints include one or more of the following: power balance constraints, distribution area acceptance capacity constraints, access point voltage over-limit constraints, photovoltaic inverter capacity constraints, battery charging and discharging constraints, distribution area carbon emission constraints, grid interaction power constraints, and user satisfaction constraints.

[0038] The power balance constraint is:

[0039]

[0040] for Photovoltaic power generation during a given period; , They are respectively for Battery charging and discharging power during different time periods;

[0041] The acceptance capacity constraint of the transformer area is as follows:

[0042]

[0043] This represents the maximum capacity of the low-voltage distribution area to receive photovoltaic power.

[0044] The voltage over-limit constraint at the access point is:

[0045]

[0046] , These are the upper and lower limits of the voltage, respectively. , These are the power-voltage sensitivity coefficients corresponding to purchased electricity power and photovoltaic power generation power, respectively;

[0047] The capacity constraint of the photovoltaic inverter is:

[0048]

[0049] This refers to the rated capacity of the photovoltaic inverter.

[0050] The battery charging and discharging constraints are as follows:

[0051]

[0052]

[0053] , These are the maximum charging and discharging power of the battery, respectively. For the storage battery State of charge over a period of time; , These represent the maximum and minimum states of charge of the battery, respectively. This refers to the rated capacity of the battery. , These are the charging and discharging rates of the battery, respectively.

[0054] The carbon emission constraints for the transformer area are as follows:

[0055]

[0056] for Carbon emissions per time period in the transformer area; This represents the maximum permissible carbon emission limit for the area.

[0057] The power grid interaction constraint is:

[0058]

[0059] , These are the maximum and minimum values ​​of the purchased electricity capacity, respectively. , These are the maximum and minimum values ​​of the electricity sold, respectively.

[0060] The user satisfaction constraint is:

[0061]

[0062] This represents the lowest level of satisfaction with electricity usage.

[0063] Secondly, one or more embodiments of this specification provide a dispatching device for a distribution area based on differentiated edge requirements, including: an acquisition module and a data processing module;

[0064] The acquisition module is used to acquire the load demand information of electricity users and the differentiated price response model of the electricity users;

[0065] The data processing module is used to input the load demand information and the differentiated price response model into a preset price-demand forecasting model to obtain price-demand relationship data; and to determine the scheduling strategy of the distribution area based on the price-demand relationship data, preset constraints and preset distribution area costs.

[0066] Thirdly, one or more embodiments of this specification provide a storage medium, including:

[0067] Used to store computer-executable instructions, which, when executed, implement the method described in the first aspect.

[0068] Compared with the prior art, this application can achieve at least the following technical effects:

[0069] A differentiated pricing response model is used to quantify the differences in price-demand relationships among different users. Simultaneously, using this model as input, a machine learning model (price-demand forecasting model) is employed to determine the price-demand relationship, resulting in data that balances user differences and non-linear price-demand relationships. Finally, based on this price-demand relationship data, a scheduling strategy for the distribution area is determined to enhance its applicability. Attached Figure Description

[0070] To more clearly illustrate the technical solutions in one or more embodiments of this specification or in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in this specification. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0071] Figure 1 A flowchart illustrating a method for scheduling distribution stations based on differentiated edge requirements, provided for one or more embodiments of this specification;

[0072] Figure 2 This is a schematic diagram of the structure of the low-voltage distribution area provided in an embodiment of this application;

[0073] Figure 3 The results of optimized scheduling of residential load under Mode 1;

[0074] Figure 4 The results of industrial load optimization scheduling under Mode 1;

[0075] Figure 5 The result of optimized scheduling of charging pile load under Mode 1;

[0076] Figure 6 The results of optimized scheduling of residential load under Mode 2;

[0077] Figure 7 The results of industrial load optimization scheduling under Mode 2;

[0078] Figure 8 The results of optimized scheduling of charging pile load under Mode 2;

[0079] Figure 9 The curves show a comparison of carbon emissions from residential load under the two modes;

[0080] Figure 10 The curves show a comparison of carbon emissions from industrial load under the two modes;

[0081] Figure 11 The curves show a comparison of carbon emissions from charging pile loads under the two modes. Detailed Implementation

[0082] To enable those skilled in the art to better understand the technical solutions in one or more embodiments of this specification, the technical solutions in one or more embodiments of this specification will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this specification, and not all of the embodiments. Based on one or more embodiments of this specification, all other embodiments obtained by those skilled in the art without creative effort should fall within the protection scope of this document.

[0083] Demand-side response is a crucial means to mitigate the output of distributed power sources and improve the integration rate of renewable energy. However, existing research assumes a linear relationship between changes in electricity consumption and changes in electricity prices, which is not realistic. Furthermore, current technologies do not consider the differences in response resilience coefficients and real-time electricity prices among different users, nor do they classify load types.

[0084] Furthermore, considering the large number of users participating in demand response, building a price-based demand response model for each user would involve excessive computation, while building a uniform price-based demand response model for all users would fail to reflect the differences between them.

[0085] To address the aforementioned technical issues, this application provides a method for scheduling distribution stations based on differentiated edge requirements, comprising the following steps:

[0086] Step 1: Obtain load demand information and differentiated pricing response model for electricity users.

[0087] In this embodiment of the application, the load demand information includes: load type and real-time electricity price data.

[0088] Therefore, step 1 includes: obtaining the load type and real-time electricity price data corresponding to the electricity user.

[0089] Preferably, to further reflect user differences, the load demand information also includes: user satisfaction. The method for calculating user satisfaction is as follows:

[0090]

[0091] in, For electricity user satisfaction; , They are respectively Load volume and load transfer volume before demand response during a given period; This refers to the scheduling cycle. It should be noted that... and It can come from historical data.

[0092] Step 2: Input the load demand information and the differentiated price response model into the pre-trained price-demand forecasting model to obtain price-demand relationship data.

[0093] In this embodiment, the power load of low-voltage distribution areas is divided into three types based on the load's electricity consumption characteristics: residential power load, industrial power load, and electric vehicle charging pile power load. The typical low-voltage distribution area power consumption category is residential power load. This type of load is not subject to grid dispatching, and user consumption behavior greatly influences the load fluctuation of the distribution area. With the widespread use of air conditioning, lighting, and other equipment, the impact of climate change and time factors on residential power load is becoming increasingly significant. Industrial power load is linked to economic factors. The economic situation of the area where the distribution area is located directly affects the industrial load's electricity consumption level, thus affecting the growth or decline trend of the entire distribution area's load. In the electricity market, electricity prices are volatile, and tiered pricing and time-of-use pricing also exhibit complex relationships with the industrial load of the distribution area. Electric vehicle charging pile load is easily affected by many factors, including the parameters of the electric vehicles themselves, the scale and number of charging piles, and many other factors. The daily charging and discharging characteristics of large-scale electric vehicle charging piles will increase the peak-valley difference in load. When electric vehicle charging piles are connected on a large scale during peak load periods, it is detrimental to the safe and economical operation of the low-voltage distribution area. Therefore, the maximum load that a charging pile can be connected to is limited by the capacity of the distribution transformer in the area.

[0094] Because the three types of users have different needs, their corresponding price responses also differ. Therefore, this application creates a differentiated price response model for each type of user. Specifically,

[0095] Obtain the ratio of load for each load type to the total load of the distribution area, as well as the electricity consumption-price-demand balance data for each load type. The electricity consumption-price-demand balance data is related to electricity consumption behavior, real-time electricity prices, and elasticity coefficients.

[0096] Based on the ratio of load to total load of each load type and the electricity-price-demand balance data corresponding to each load type, a differentiated price response model is determined for each load type. In this embodiment, the differentiated price response model is represented by an electricity price elasticity matrix response matrix, wherein each element in the electricity price elasticity matrix response matrix represents the electricity-price-demand balance data for each user type based on electricity consumption behavior, real-time electricity price, and elasticity coefficient.

[0097] In this embodiment of the application, a distribution area refers to a power supply zone of 10kV / 0.4kV provided by several distribution transformers, and the structure of the distribution area is as follows: Figure 2As shown, from top to bottom, the system is divided into a transformer layer, a branch layer, a meter box layer, and a user layer. The transformer layer consists of an energy controller, a photovoltaic energy storage device, and a smart transformer; the branch layer includes branch monitoring terminals, environmental sensors, and single-phase and three-phase smart miniature circuit breakers; the meter box layer mainly consists of smart IoT energy meters, smart reversing switches, and smart locks; the user side includes residential loads, industrial loads, charging pile loads, and photovoltaic and energy storage devices. The edge computing nodes correspond to the smart IoT energy meters; that is, each edge computing node calculates a differentiated pricing response model based on the data collected by the corresponding smart IoT energy meter.

[0098] During computation, considering the significant resource consumption of data-driven price-based demand response modeling for a large number of differentiated users, this invention, before computation, classifies each edge computing node into node clusters based on each response behavior data; then, it calculates the price-demand relationship data for each node cluster. For example, the K-means clustering method is used to cluster users based on their price-based demand response behavior characteristics. The basic idea of ​​the K-means clustering method is to group highly similar samples into a single cluster by measuring the similarity between different samples. Finally, based on the price-demand relationship data of each node cluster, the price-demand relationship data for the distribution area is obtained. For example, the calculation task of the price-demand relationship data for the node clusters is performed on the edge nodes, while the control center only performs the final aggregation, which can greatly reduce the amount of computation.

[0099] In this embodiment, the price-demand forecasting model is specifically the XGBoost model. Edge nodes calculate price-demand relationship data for each node cluster based on the XGBoost model. Specifically, cluster analysis is performed for any edge node... The original training dataset is represented as:

[0100] ,

[0101] in , , These are the number of edge nodes and the number of edge nodes. The number of users and the number of samples in the training dataset; It is an edge node users For the sample Price incentive vector The response vector. The calculation formula is:

[0102]

[0103] In the formula, , users respectively In time period Internal samples Optimized load and fixed load.

[0104] XGBoost is an optimization of boosting algorithms; it's an ensemble algorithm based on trees and linear classifiers. Generally, considering a given dataset... ,in It is the number of training samples; This is the input data for the XGBoost model; These are the preference values ​​of the XGBoost model. The XGBoost model can be represented as:

[0105]

[0106] In the formula, These are the predictions from the XGBoost model; It is a collection of regression trees; It is a set In Regression tree; yes The number of regression trees. The loss function of the XGBoost model consists of two parts: the difference term and the regularization term.

[0107]

[0108]

[0109] In the formula, Preference value Compared with the predicted value The difference between them can be used , To measure; It is a regularization term used to control the complexity of the XGBoot model and prevent overfitting. Number of leaves; Leaf fraction; , is the given parameter; Obj is the price-demand relationship data.

[0110] The XGBoost model uses a cumulative training method, meaning that in each iteration, a new function, or a new tree, is added to the previous model. The specific iterative process is as follows:

[0111]

[0112] In the formula, for The iterative prediction, which preserves Iterative prediction results And added a new function Therefore, the difference term in the XGBoost model loss function can be rewritten as:

[0113]

[0114] Step 3: Determine the scheduling strategy for the distribution area based on the price-demand relationship data, preset constraints, and preset distribution area costs.

[0115] In this embodiment, the total cost of distribution area dispatch includes: electricity purchase cost and operation and maintenance cost. The electricity purchase cost is calculated based on price-demand relationship data, while the operation and maintenance cost can be referenced from historical data. However, with technological advancements, carbon processing costs and photovoltaic power sales revenue also need to be considered in the total cost of distribution area dispatch. Furthermore, to reflect the differences among users, satisfaction loss costs should be included in the total cost of distribution area dispatch. Therefore, the objective function in this application is:

[0116]

[0117] in, The total cost of dispatching in the distribution area; To optimize the scheduling cycle in advance; For electricity purchase costs; For operation and maintenance costs; Cost of carbon processing; Costs incurred for increased satisfaction; Revenue from selling electricity generated from photovoltaic power plants.

[0118] Cost of purchased electricity:

[0119]

[0120] In the formula, for Unit electricity purchase cost during the time period; for Power purchased during specific time periods; This refers to the duration of the scheduling period.

[0121] Operation and maintenance costs:

[0122]

[0123] In the formula, The number of units for which maintenance costs need to be calculated; For unit The unit operation and maintenance cost; for Time period unit Operating power.

[0124] Carbon processing costs:

[0125]

[0126] In the formula, The number of units for which carbon processing costs need to be calculated; Cost per unit of carbon processing; For unit Carbon emission intensity refers to the amount of carbon emissions generated per unit of power increase; for Time period unit . output power.

[0127] Cost of lost satisfaction:

[0128] Users have an optimal energy consumption level for each time period, which is their baseline load. When a user deviates from their baseline load, a loss of satisfaction occurs, which is quantified by the following function:

[0129]

[0130] In the formula, , Indicates a constant coefficient representing energy preference; Indicates low-voltage distribution area exist Time period The actual load of the type of load.

[0131] Revenue from photovoltaic power sales:

[0132]

[0133] In the formula, for Benefits from electricity sales by unit during specific time periods; for Photovoltaic power generation during specific time periods.

[0134] Then, based on the preset constraints and objective function, the minimum total scheduling cost of the distribution area is calculated. Finally, based on the minimum total scheduling cost, the scheduling strategy for the distribution area is determined.

[0135] Specifically, one or more of the following constraints: power balance constraints, distribution area acceptance capacity constraints, access point voltage limit constraints, photovoltaic inverter capacity constraints, battery charging and discharging constraints, distribution area carbon emission constraints, grid interaction power constraints, and user satisfaction constraints.

[0136] The power balance constraint is:

[0137]

[0138] for Photovoltaic power generation during a given period; , They are respectively for Battery charging and discharging power during different time periods;

[0139] The acceptance capacity constraint of the transformer area is as follows:

[0140]

[0141] This represents the maximum capacity of the low-voltage distribution area to receive photovoltaic power.

[0142] The voltage over-limit constraint at the access point is:

[0143]

[0144] , These are the upper and lower limits of the voltage, respectively. , These are the power-voltage sensitivity coefficients corresponding to purchased electricity power and photovoltaic power generation power, respectively;

[0145] The capacity constraint of the photovoltaic inverter is:

[0146]

[0147] This refers to the rated capacity of the photovoltaic inverter.

[0148] The battery charging and discharging constraints are as follows:

[0149]

[0150]

[0151] , These are the maximum charging and discharging power of the battery, respectively. For the storage battery State of charge over a period of time; , These represent the maximum and minimum states of charge of the battery, respectively. This refers to the rated capacity of the battery. , These are the charging and discharging rates of the battery, respectively.

[0152] The carbon emission constraints for the transformer area are as follows:

[0153]

[0154] for Carbon emissions per time period in the transformer area; This represents the maximum permissible carbon emission limit for the area.

[0155] The power grid interaction constraint is:

[0156]

[0157] , These are the maximum and minimum values ​​of the purchased electricity capacity, respectively. , These are the maximum and minimum values ​​of the electricity sold, respectively.

[0158] The user satisfaction constraint is:

[0159]

[0160] This represents the lowest level of satisfaction with electricity usage.

[0161] To illustrate the feasibility of the above embodiments, this application provides a specific example. The application scenario is as follows: the scheduling cycle is 24 hours per day, and the scheduling period is 1 hour, with constant power during the scheduling period. The load-side electricity consumption is divided into three periods: peak, flat, and valley. Peak periods are 10:00-15:00 and 18:00-21:00; flat periods are 7:00-10:00, 15:00-18:00, and 21:00-23:00; and valley periods are 0:00-7:00 and 23:00-24:00. The parameters of each unit in the distribution area are shown in Table 1. The time-of-use electricity prices for residential, industrial, and charging pile loads are shown in Table 2, and the elasticity coefficients for the three types of loads are shown in Table 3. The photovoltaic electricity sales price is 0.68, 0.4, and 0.11 yuan / (units) during the peak, flat, and valley periods, respectively. The maximum allowable carbon emission in the area is 1500 kg.

[0162] Table 1 Operating parameters of each unit in the low-voltage distribution area

[0163]

[0164] Table 23 Time-of-Use Electricity Prices for Load Categories

[0165]

[0166] Table 33 Differentiated Elasticity Coefficients for Load Types

[0167]

[0168] To verify the effectiveness of the proposed low-voltage distribution area dispatching model, three load scenarios under two modes were designed for comparative analysis: Mode 1 is the most basic optimization mode, which does not consider carbon emissions and demand response in the dispatching model; Mode 2 is a comprehensive optimization mode, which considers carbon emission factors in addition to demand response.

[0169] Figures 3-8 The scheduling results are presented under two modes, including load demand for three types of load scenarios, normal output, and battery charging and discharging status under different modes.

[0170] Depend on Figures 3-8 It can be seen that Mode 1 does not consider demand response and carbon emissions, and the load volume of the three types of loads remains unchanged in each time period. When the load is in the off-peak period, the photovoltaic output, in addition to meeting the load demand, also needs to charge the battery. When the battery is charged to its maximum state of charge, the transformer area may experience curtailment. When the load is in the normal period, the battery state of charge remains constant, and the load demand is supplied by both photovoltaic power and grid power purchase. When the load is in the peak period, the photovoltaic output is low, and in addition to discharging the battery, a large amount of electricity needs to be purchased from the external grid to meet the load demand. This mode has a relatively high power purchase capacity and a low photovoltaic absorption rate, only 78.8%, 72.8%, and 77.7%, with a high curtailment rate. This operation mode is not conducive to the safe and stable operation of the transformer area and will also increase the economic cost of the transformer area. Mode 2 considers demand response and carbon emissions. Demand response reduces peak load and increases off-peak load through response tariffs. The photovoltaic power purchase capacity increases, and the photovoltaic absorption rate rises to 86.1%, 82.5%, and 84.9%, which reduces the economic cost of the transformer area. In summary, optimizing the dispatch of low-voltage distribution areas by considering demand response and carbon emissions can improve the photovoltaic absorption rate and demand response resource utilization rate of the distribution areas, and improve the matching degree of source and load measurements.

[0171] Figures 9-11 This represents the carbon emissions for each time period under three load scenarios in two different modes. Figures 9-11It can be seen that Mode 1, due to the lack of consideration for carbon emissions, results in a relatively high overall carbon emission level for the distribution area during the dispatch cycle. Mode 2 considers carbon emissions in its optimization objectives and takes into account carbon emission constraints. Since renewable energy sources like photovoltaic power generation have very low carbon emissions, and the charging and discharging of batteries themselves does not generate much carbon emissions, while the carbon emission intensity of purchasing electricity from outside the distribution area is relatively high, renewable energy generation is prioritized. Batteries store excess energy during periods of low photovoltaic activity for use during photovoltaic off-peak hours. Electricity is only purchased from outside the distribution area if neither photovoltaic nor battery power can meet the load demand. The optimization results show that in the three scenario optimization models, photovoltaic power generation increased by 1.0%, 0.5%, and 0.6%, respectively, while purchased electricity decreased by 11.7%, 20.8%, and 11.0%, respectively. Carbon emissions also decreased, by 13.1%, 18.8%, and 10.7%, respectively. This demonstrates that considering carbon emission targets and constraints in the optimized dispatch of low-voltage distribution areas can reduce the total carbon emissions of the area, contributing to the realization of a low-carbon economy in the area.

[0172] In summary, the scheduling model uses carbon emissions as the optimization objective, reducing the carbon handling cost of the distribution area and further lowering the total scheduling cost. Compared to Mode 1, Mode 2 reduced the total scheduling cost of the distribution area for the three user types by 8.6%, 19.3%, and 11.6%, respectively. The scheduling results demonstrate that considering carbon emissions and node-differentiated edge demand response in the optimized scheduling of low-voltage distribution areas can reduce the total scheduling cost and carbon emissions, proving the correctness of the scheduling model.

[0173] This application provides a dispatching device for transformer substations based on differentiated edge requirements, characterized in that it includes: an acquisition module and a data processing module;

[0174] The acquisition module is used to acquire the load demand information of electricity users and the differentiated price response model of the electricity users;

[0175] The data processing module is used to input the load demand information and the differentiated price response model into a preset price-demand forecasting model to obtain price-demand relationship data; and to determine the scheduling strategy of the distribution area based on the price-demand relationship data, preset constraints and preset distribution area costs.

[0176] This application provides a storage medium, including:

[0177] Used to store computer-executable instructions, which, when executed, implement the methods described in the above embodiments.

[0178] The foregoing has described specific embodiments of this specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims may be performed in a different order than that shown in the embodiments and may still achieve the desired result. Furthermore, the processes depicted in the drawings do not necessarily require the specific or sequential order shown to achieve the desired result. In some embodiments, multitasking and parallel processing are possible or may be advantageous.

[0179] In the 1930s, improvements to a technology could be clearly distinguished as either hardware improvements (e.g., improvements to the circuit structure of diodes, transistors, switches, etc.) or software improvements (improvements to the methodology). However, with technological advancements, many improvements to the methodology today can be considered direct improvements to the hardware circuit structure. Designers almost always obtain the corresponding hardware circuit structure by programming the improved methodology into the hardware circuit. Therefore, it cannot be said that an improvement to the methodology cannot be implemented using hardware physical modules. For example, a Programmable Logic Device (PLD) (such as a Field Programmable Gate Array (FPGA)) is such an integrated circuit whose logic function is determined by the user programming the device. Designers can program and "integrate" a digital system onto a PLD themselves, without needing chip manufacturers to design and manufacture dedicated integrated circuit chips. Furthermore, nowadays, instead of manually manufacturing integrated circuit chips, this programming is mostly implemented using "logic compiler" software. Similar to the software compiler used in program development, the original code before compilation must also be written in a specific programming language, called a Hardware Description Language (HDL). There are many HDLs, such as ABEL (Advanced Boolean Expression Language), AHDL (Altera Hardware Description Language), Confluence, CUPL (Cornell University Programming Language), HDCal, JHDL (Java Hardware Description Language), Lava, Lola, MyHDL, PALASM, and RHDL (Ruby Hardware Description Language). Currently, the most commonly used are VHDL (Very-High-Speed ​​Integrated Circuit Hardware Description Language) and Verilog. Those skilled in the art should also understand that by simply performing some logic programming on the method flow using one of these hardware description languages ​​and programming it into an integrated circuit, the hardware circuit implementing the logical method flow can be easily obtained.

[0180] The controller can be implemented in any suitable manner. For example, it can take the form of a microprocessor or processor and a computer-readable medium storing computer-readable program code (e.g., software or firmware) executable by the (micro)processor, logic gates, switches, application-specific integrated circuits (ASICs), programmable logic controllers, and embedded microcontrollers. Examples of controllers include, but are not limited to, the following microcontrollers: ARC 625D, Atmel AT91SAM, Microchip PIC18F26K20, and Silicon Labs C8051F320. A memory controller can also be implemented as part of the control logic of the memory. Those skilled in the art will also recognize that, in addition to implementing the controller in purely computer-readable program code form, the same functionality can be achieved by logically programming the method steps to make the controller take the form of logic gates, switches, application-specific integrated circuits, programmable logic controllers, and embedded microcontrollers. Therefore, such a controller can be considered a hardware component, and the means included therein for implementing various functions can also be considered as structures within the hardware component. Alternatively, the means for implementing various functions can be considered as both software modules implementing the method and structures within the hardware component.

[0181] The systems, devices, modules, or units described in the above embodiments can be implemented by computer chips or entities, or by products with certain functions. A typical implementation device is a computer. Specifically, a computer can be, for example, a personal computer, laptop computer, cellular phone, camera phone, smartphone, personal digital assistant, media player, navigation device, email device, game console, tablet computer, wearable device, or any combination of these devices.

[0182] For ease of description, the above apparatus is described by dividing it into various functional units. Of course, when implementing the embodiments of this specification, the functions of each unit can be implemented in one or more software and / or hardware.

[0183] Those skilled in the art will understand that one or more embodiments of this specification can be provided as a method, system, or computer program product. Therefore, one or more embodiments of this specification may take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this specification may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0184] This specification is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this specification. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0185] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0186] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0187] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0188] Memory may include non-persistent storage in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0189] Computer-readable media includes both permanent and non-permanent, removable and non-removable media that can store information using any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic magnetic disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.

[0190] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0191] One or more embodiments of this specification can be described in the general context of computer-executable instructions, such as program modules, that are executed by a computer. Generally, program modules include routines, programs, objects, components, data structures, etc., that perform a particular task or implement a particular abstract data type. One or more embodiments of this specification can also be practiced in distributed computing environments where tasks are performed by remote processing devices connected via a communication network. In distributed computing environments, program modules can reside in local and remote computer storage media, including storage devices.

[0192] The various embodiments in this specification are described in a progressive manner. Similar or identical parts between embodiments can be referred to interchangeably. Each embodiment focuses on describing the differences from other embodiments. In particular, the system embodiments are basically similar to the method embodiments, so the description is relatively simple; relevant parts can be referred to the descriptions in the method embodiments.

[0193] The above description is merely an embodiment of this document and is not intended to limit the scope of this document. Various modifications and variations can be made to this document by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this document should be included within the scope of the claims of this document.

Claims

1. A method for scheduling distribution stations based on differentiated edge demands, characterized in that, include: Obtain the load demand information of electricity users and the differentiated price response model of the electricity users; The load demand information and the differentiated price response model are input into a pre-trained price-demand forecasting model to obtain price-demand relationship data. Based on the price-demand relationship data, preset constraints, and preset distribution area costs, determine the distribution area scheduling strategy; The step of determining the dispatching strategy for a distribution area based on the price-demand relationship data, preset constraints, and preset distribution area operating costs includes: Based on the price-demand relationship data, determine the electricity purchase cost for the distribution area; The objective function is determined based on the electricity purchase cost and the transformer substation operating cost. Based on the constraints and the objective function, determine the minimum total scheduling cost of the distribution area; The scheduling strategy for the distribution area is determined based on the minimum total scheduling cost. The load demand information includes: load type and real-time electricity price data; The process of obtaining load demand information from electricity users includes: Obtain the load type and real-time electricity price data corresponding to the electricity user; The load demand information also includes: user satisfaction; The process of obtaining load demand information from electricity users includes: The user satisfaction level is obtained according to the following formula; in, For electricity user satisfaction; , They are respectively Load volume and load transfer volume before demand response during a given period; The scheduling period is [number].

2. The method according to claim 1, characterized in that, The load types include one or more of the following: residential electricity load, industrial electricity load, and electric vehicle charging pile electricity load; The step of obtaining the differentiated pricing response model for the electricity user includes: Obtain the ratio of the load of each load type to the total load of the distribution area, as well as the electricity and electricity price demand balance data corresponding to each load type; Based on the ratio of load to total load of each load type and the electricity-price-demand balance data corresponding to each load type, a differentiated price response model is determined for each load type.

3. The method according to claim 1, characterized in that, The transformer area includes: multiple edge computing nodes; The step of inputting the load demand information and the differentiated pricing response model into a preset price-demand forecasting model to obtain price-demand relationship data includes: Acquire user response behavior data to price changes at each of the aforementioned edge computing nodes; Based on the response behavior data, each edge computing node is classified to obtain a node cluster; Calculate the price-demand relationship data for each of the aforementioned node clusters; Based on the price-demand relationship data of each node cluster, the price-demand relationship data of the transformer area is obtained.

4. The method according to claim 1, characterized in that, The operating costs of the transformer substation include one or more of the following: operation and maintenance costs, carbon disposal costs, satisfaction loss costs, and revenue from photovoltaic electricity sales. The objective function is specifically: in, The total cost of dispatching in the distribution area; To optimize the scheduling cycle in advance; For electricity purchase costs; For operation and maintenance costs; Cost of carbon processing; Costs incurred for increased satisfaction; Revenue from selling electricity generated from photovoltaic power plants.

5. The method according to claim 1, characterized in that, The constraints include one or more of the following: power balance constraints, distribution area acceptance capacity constraints, access point voltage over-limit constraints, photovoltaic inverter capacity constraints, battery charging and discharging constraints, distribution area carbon emission constraints, grid interaction power constraints, and user satisfaction constraints. The power balance constraint is: for Photovoltaic power generation during a given period; , They are respectively for Battery charging and discharging power during different time periods; The acceptance capacity constraint of the transformer area is as follows: This represents the maximum capacity of the low-voltage distribution area to receive photovoltaic power. The voltage over-limit constraint at the access point is: , These are the upper and lower limits of the voltage, respectively. , These are the power-voltage sensitivity coefficients corresponding to purchased electricity power and photovoltaic power generation power, respectively; The capacity constraint of the photovoltaic inverter is: This refers to the rated capacity of the photovoltaic inverter. The battery charging and discharging constraints are as follows: , These are the maximum charging and discharging power of the battery, respectively. For the storage battery State of charge over a period of time; , These represent the maximum and minimum states of charge of the battery, respectively. This refers to the rated capacity of the battery. , These are the charging and discharging rates of the battery, respectively. The carbon emission constraints for the transformer area are as follows: for Carbon emissions per time period in the transformer area; This represents the maximum permissible carbon emission limit for the area. The power grid interaction constraint is: , These are the maximum and minimum values ​​of the purchased electricity capacity, respectively. , These are the maximum and minimum values ​​of the electricity sold, respectively. The user satisfaction constraint is: This represents the lowest level of satisfaction with electricity usage.

6. A distribution area scheduling device based on differentiated edge demand, characterized in that, include: Acquisition module and data processing module; The acquisition module is used to acquire the load demand information of electricity users and the differentiated price response model of the electricity users; The data processing module is used to input the load demand information and the differentiated price response model into a preset price-demand forecasting model to obtain price-demand relationship data; and to determine the scheduling strategy of the distribution area based on the price-demand relationship data, preset constraints and preset distribution area costs. The step of determining the dispatching strategy for a distribution area based on the price-demand relationship data, preset constraints, and preset distribution area operating costs includes: Based on the price-demand relationship data, determine the electricity purchase cost for the distribution area; The objective function is determined based on the electricity purchase cost and the transformer substation operating cost. Based on the constraints and the objective function, determine the minimum total scheduling cost of the distribution area; The scheduling strategy for the distribution area is determined based on the minimum total scheduling cost. The load demand information includes: load type and real-time electricity price data; The process of obtaining load demand information from electricity users includes: Obtain the load type and real-time electricity price data corresponding to the electricity user; The load demand information also includes: user satisfaction; The process of obtaining load demand information from electricity users includes: The user satisfaction level is obtained according to the following formula; in, For electricity user satisfaction; , They are respectively Load volume and load transfer volume before demand response during a given period; The scheduling period is [number].

7. A storage medium, characterized in that, include: Used to store computer-executable instructions, which, when executed, implement the method according to any one of claims 1-5.

Images