Interval potential modeling and optimization regulation and control method for adjustable resources of power distribution network industry

Abstract

The invention provides an interval potential modeling and optimization regulation and control method for industrial adjustable resources of a power distribution network, and relates to the technical field of power systems, and the method comprises the steps: extracting a multi-dimensional resource feature set based on industrial load operation data, calculating a potential interval through employing self-organizing mapping, and generating a potential certificate; node feature vectors are constructed for partitioning, a hierarchical regulation and control framework is established, and a standardized contract template and a resource priority index are generated; based on the hierarchical regulation and control architecture and the resource priority index, constructing a regulation and control objective function which aims at meeting the predicted future demand of the power distribution network and takes a potential interval as a constraint condition, solving and generating an optimal regulation and control scheme, and writing the optimal regulation and control scheme into a block chain smart contract; actual execution power is collected, settlement is carried out through the block chain intelligent contract, the execution fulfillment rate is calculated, and the standardized contract template and the resource priority index are updated according to the execution fulfillment rate. According to the method, accurate quantification and interval representation of industrial adjustable resource potential can be realized, and the robustness of a regulation and control strategy and the credibility of an execution process are improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of power systems, in particular to an interval potential modeling and optimal regulation method for industrial adjustable resources of distribution networks. BACKGROUND

[0002] With the continuous increase of new energy penetration, the uncertainty and volatility of distribution network operation are significantly enhanced, and the traditional regulation mode relying on centralized power supply and peak regulation units has been difficult to meet the operation demand of safety and economy. Under this background, industrial load, as an important adjustable resource in the distribution network, has gradually become an important part of demand response and auxiliary service due to its large scale and strong flexibility. How to accurately tap the potential of industrial adjustable resources and realize optimal regulation has become an important research direction to improve the operational resilience of distribution networks and reduce system operation costs.

[0003] Existing researches mainly focus on two aspects: one is the evaluation of adjustable resource potential, which is usually based on static parameter modeling or empirical prediction to quantify the interruptibility, transferability and economy of industrial load; the other is the regulation and settlement mechanism, which mostly adopts centralized optimization, heuristic algorithm or regional division method based on electrical distance, and realizes resource scheduling with static priority sorting strategy. However, these methods have obvious limitations in practical application: the potential evaluation often lacks the description of uncertainty and dynamics, and the contract mechanism generally relies on predefined templates, which is difficult to adapt to diversified resource characteristics; the existing zoning method is too single and lacks consideration of potential characteristics; the optimization model does not explicitly introduce interval constraints, which is not robust enough; and the regulation and settlement rely on centralized platform, which is difficult to ensure transparency and credibility. SUMMARY

[0004] The present application provides an interval potential modeling and optimal regulation method for industrial adjustable resources of distribution networks to solve the problems mentioned in the background.

[0005] In the first aspect of the present application, an interval potential modeling and optimal regulation method for industrial adjustable resources of distribution networks is provided, which includes: extracting a set of multi-dimensional resource characteristics based on the operation data of industrial load, classifying the set of multi-dimensional resource characteristics by using self-organizing mapping and calculating the corresponding potential interval to generate a potential certificate; constructing a node feature vector and zoning the distribution network, establishing a hierarchical regulation architecture, generating a standardized contract template based on the potential certificate and calculating a resource priority index; based on the hierarchical regulation architecture and the resource priority index, constructing a regulation objective function with the goal of meeting the predicted future demand of the distribution network and the constraint condition of the potential interval, solving to generate an optimal regulation scheme and writing it into a blockchain smart contract; Collect actual execution power in response to the optimal regulation scheme, execute settlement and calculate execution compliance rate through the blockchain smart contract, and update the standardized contract template and resource priority index by using the actual execution power and the execution compliance rate.

[0006] Optionally, in a possible implementation manner of the first aspect, the operation data of the industrial load includes power curve data and process constraint parameters. The multi-dimensional resource feature set includes interruptability, transferability, operation cost, process constraint intensity, fluctuation, and mode stability. The interruptability represents a ratio of allowed period reduction energy to total energy consumption. The transferability represents a ratio of transferable energy to total energy consumption. The operation cost represents marginal adjustment cost value per unit of adjustment power. The process constraint intensity represents a ratio of locked period to total period. The fluctuation represents a ratio of power curve standard deviation to mean value. The mode stability represents an entropy value of daily operation curve clustering distribution.

[0007] Optionally, in a possible implementation manner of the first aspect, the multi-dimensional resource feature set is extracted based on the operation data of the industrial load, including: Performing statistical analysis and parameter extraction on the power curve data and the process constraint parameters to obtain overall features of the industrial load, the overall features including power mean value parameters, power dispersion parameters, energy efficiency indicators, and response failure rates. Dividing the power curve data into multiple process stage intervals according to the process constraint parameters, and collecting stage features of each process stage interval, the stage features including power mean value parameters, power dispersion parameters, process minimum start-stop time, process stage labels, and process constraint parameter sets. Integrating the collected overall features and stage features to obtain a basic feature set; and calculating the multi-dimensional resource feature set based on the basic feature set.

[0008] Optionally, in a possible implementation manner of the first aspect, the multi-dimensional resource feature set is classified and corresponding potential intervals are calculated by using self-organizing mapping, including: Constructing a self-organizing mapping two-dimensional grid network, calculating the Euclidean distance between the multi-dimensional resource feature set and each node in the self-organizing mapping two-dimensional grid network, and determining the node with the minimum distance as the best matching node. Mapping the multi-dimensional resource feature set to the best matching node to form a category set. For each category in the category set, power samples in the allowed adjustment period are extracted from the operation data, and the upper and lower limits of the potential of the category are calculated by using the quantile method to obtain the potential interval; The energy consumption proportion of the single industrial adjustable resource is calculated based on the operation data, and the potential interval is allocated to the single industrial adjustable resource according to the energy consumption proportion.

[0009] Optionally, in a possible implementation manner of the first aspect, the constructing the node feature vector and partitioning the power distribution network, and establishing the hierarchical regulation architecture, comprises: Obtaining node electrical parameters of the power distribution network, the node electrical parameters comprising node equivalent impedance, voltage response degree parameters and node load power parameters; Calculating the average adjustable potential and the potential uncertainty parameter of the in-node resource based on the potential certificate; Constructing a comprehensive feature vector and performing normalization processing to obtain a node feature matrix, the comprehensive feature vector comprising the node electrical parameters, the average adjustable potential and the potential uncertainty parameter; Performing two-dimensional clustering on the node feature matrix, respectively calculating the distance of the node to the clustering center in the electrical dimension and the distance in the potential dimension, and determining a comprehensive distance, and dividing the node to the corresponding regional control unit according to the comprehensive distance; Establishing the hierarchical regulation architecture based on the regional control unit; the regional control unit comprising a scheduling center level, a regional control level and a terminal resource level.

[0010] Optionally, in a possible implementation manner of the first aspect, the generating the standardized contract template based on the potential certificate comprises: Extracting the potential interval, the potential mean parameter and the potential uncertainty parameter from the potential certificate; Obtaining a preset regulation generation value function and a response time window parameter; Generating the standardized contract template by using the potential interval, the potential mean parameter, the potential uncertainty parameter, the regulation generation value function and the response time window parameter; The regulation generation value function is constructed based on a benchmark generation value and a slope coefficient; and the response time window parameter comprises an allowed response delay time and a duration.

[0011] Optionally, in a possible implementation manner of the first aspect, the calculating the resource priority index comprises: Extracting a potential level index and a reliability index from the potential certificate, and extracting a response speed index and an economic index from the standardized contract template; Performing standardization processing on the potential level index, the reliability index, the response speed index and the economic index; performing weighted summation on each index after normalization processing based on a preset proportion parameter vector to obtain an initial priority index; calculating a risk correction parameter according to the potential interval, and performing correction on the initial priority index by using the risk correction parameter to obtain the resource priority index; The risk correction parameter is used to reduce the priority of a resource whose fluctuation amplitude of the potential interval exceeds a preset range.

[0012] Optionally, in a possible implementation manner of the first aspect, the construction of a regulation target function based on the resource priority index and subject to the potential interval, and aiming to meet a predicted future demand of the power distribution network, specifically comprises establishing a regulation target function that takes into account system load tracking accuracy, operation cost and risk cost; The system load tracking accuracy represents the matching degree of the adjusted power and the future demand. The operation cost is calculated based on an adjustment cost value function in the standardized contract template, and the risk cost is a correction term deviating from the potential interval. The potential interval is taken as a constraint condition of the regulation target function, and a response time constraint, a node voltage constraint and a regional power balance constraint are set.

[0013] Optionally, in a possible implementation manner of the first aspect, the settlement is performed by using the smart contract of the blockchain, and the settlement comprises: The standardized contract template is invoked by using the smart contract of the blockchain. A deviation value between an actual execution power and a planned power indicated by the optimal regulation scheme is calculated. A settlement interaction value is calculated based on an adjustment cost value function in the standardized contract template and the deviation value. The execution compliance rate is calculated based on a ratio relationship between the deviation value and the planned power.

[0014] Optionally, in a possible implementation manner of the first aspect, the updating of the standardized contract template and the resource priority index by using the actual execution power and the execution compliance rate comprises: A deviation mean value and a deviation fluctuation amount are calculated based on the deviation value, and the deviation mean value and the deviation fluctuation amount are combined to form an execution error parameter. The potential uncertainty parameter in the standardized contract template is corrected by using the execution error parameter. The resource priority index is iteratively updated according to a preset memory decay parameter and in combination with the execution compliance rate.

[0015] The present application has the following advantages: 1. The application realizes the fine and interval characterization of the potential of industrial adjustable resources. By extracting a multi-dimensional resource feature set based on operation data, the self-organizing mapping and quantile method are used to calculate the potential interval and generate the potential certificate. The application not only breaks the information barrier of traditional single-dimensional load modeling, but also converts the originally fuzzy load curve into a digital image with clear upper and lower limit boundaries, thereby giving the power distribution network microscopic perception of resource interruptibility, transferability and operation cost, providing standardized data support for precise scheduling.

[0016] 2. The application writes the standardized contract template and the optimal regulation scheme directly into the blockchain smart contract, and uses the smart contract to automatically collect the actual execution power and calculate the execution compliance rate. This automatic execution based on on-chain code establishes an unalterable trust anchor between the supply and demand parties, eliminates the opaque link in the traditional scheduling execution process, ensures that each power regulation instruction has high traceability and execution certainty, and thus creates a highly transparent and automatically running trusted regulation environment.

[0017] 3. The application constructs a regulation target function containing potential interval constraints and resource priority index, and dynamically adjusts the priority by combining a risk correction parameter. The application effectively isolates the operation risk caused by resource heterogeneity. At the same time, the contract template parameters and priority index are iteratively updated using the execution compliance rate, so that the regulation system can evolve itself in a dynamically changing power grid environment, achieving a balance between safety and economy, and enhancing the elastic recovery ability of the power distribution network in the face of source and load fluctuations. BRIEF DESCRIPTION OF DRAWINGS

[0018] Figure 1 is a flowchart of the interval potential modeling and optimal regulation method for industrial adjustable resources of the power distribution network provided by the embodiment of the application; Figure 2 is a data-driven interval potential partition and evaluation mechanism diagram of the interval potential modeling and optimal regulation method for industrial adjustable resources of the power distribution network provided by the embodiment of the application; Figure 3 is a two-dimensional partition method diagram of the interval potential modeling and optimal regulation method for industrial adjustable resources of the power distribution network provided by the embodiment of the application; Figure 4 is a hardware structure diagram of an electronic device provided by the embodiment of the application. DETAILED DESCRIPTION

[0019] To make the purposes, technical solutions, and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by a person of ordinary skill in the art without creative effort belong to the scope of protection of the present application.

[0020] The technical solutions of the present application will be described in detail below with specific embodiments. The following specific embodiments can be combined with each other, and some embodiments can not be described again for the same or similar concepts or processes.

[0021] Referring to Figure 1 is a flowchart of an interval potential modeling and optimal regulation and control method for industrial adjustable resources of a power distribution network provided by the embodiments of the present application, Figure 1 The execution subject of the method shown in FIG. 1 can be a software and / or hardware device. The execution subject of the present application can include but is not limited to at least one of the following: a user equipment, a network equipment, and the like. The user equipment can include but is not limited to a computer, a smart phone, a personal digital assistant (PDA), and the above-mentioned electronic devices, and the like. The network equipment can include but is not limited to a single network server, a server group composed of multiple network servers, or a cloud composed of a large number of computers or network servers based on cloud computing, wherein the cloud computing is a kind of distributed computing, and a super virtual computer composed of a loose coupled computer group. The embodiments of the present application do not make any limitation in this regard. The steps 100 to 400 are included, and are specifically as follows: Step 100: Extracting a multi-dimensional resource feature set based on the operation data of the industrial load, classifying the multi-dimensional resource feature set by using self-organizing mapping and calculating the corresponding potential interval, and generating a potential certificate.

[0022] Specifically, the operation data of the industrial load includes power curve data and process constraint parameters.

[0023] In some embodiments, the "extracting a multi-dimensional resource feature set based on the operation data of the industrial load" in step 100 is specifically collecting power mean parameters, power dispersion parameters, process minimum start-stop time, process stage labels, a set of process constraint parameters, energy efficiency indicators, and response failure rates of the industrial load, and integrating the collected overall features and stage features.

[0024] Specifically, statistical analysis and parameter extraction are performed on the power curve data and the process constraint parameters to obtain the overall features of the industrial load.

[0025] The overall characteristics include power mean parameters, power discrete parameters, energy efficiency indicators, and response failure rate.

[0026] The power curve data is divided into multiple process stage intervals based on process constraint parameters, and the stage characteristics of each process stage interval are collected.

[0027] The stage characteristics include the average power parameter, power discrete parameter, minimum process start-up and shutdown time, process stage label, and set of process constraint parameters within the stage.

[0028] The collected overall features and stage features are integrated to obtain a basic feature set; a multidimensional resource feature set is then calculated based on the basic feature set.

[0029] For example, to address the issues of diverse industrial load types, complex process constraints, and heterogeneous data sources in distribution networks, a fusion modeling and unified extraction method is proposed. By constructing a process-load joint feature model, the traditional method relies solely on load curves while ignoring process constraints, thus achieving a complete expression of multi-dimensional adjustable attributes and providing a solid data foundation for subsequent potential assessment and contract construction.

[0030] Collect industrial operation data from different levels: (1) Electrical side data: Active power curves provided by smart meters The sampling period is , i represents the index number of the i-th industrial load, i=1,2,...,N, where N is the total number of industrial loads; t represents the discrete-time index; m indicates that the data is collected through a smart meter; (2) Operation monitoring data: Equipment start-up and shutdown status collected by the SCADA system With cumulative runtime The sampling period is ;in, Indicates the first The industrial load at any time The device's operating status is indicated by a value of 1, which represents the device being in operation, and a value of 0, which represents the device being stopped. Indicates the first Industrial load cutoff time Cumulative runtime; This indicates the sampling time interval of the SCADA system; s indicates that the data is the operating status data collected by the SCADA system. (3) Process production data: Production stage labels provided by the manufacturing execution system. With process constraint parameters ,in, Minimum start-stop time, Due to production constraints, Energy efficiency factor.

[0031] To eliminate the sampling frequency differences between data from different sources, linear interpolation and moving average methods were used to unify all data to the same time resolution. To create standardized multi-source time-series datasets: ; Based on a standardized dataset, a fusion feature reflecting the electrical characteristics and process constraints of industrial loads is constructed. For industrial loads... Its eigenvectors are represented as: ; in, The average power is represented by T, which represents the total number of sampling periods within the statistical period. Indicates the standard deviation of power fluctuation. , These represent the minimum start-up and shutdown times of the process, respectively. Labels indicating process stages Represents the set of process constraint parameters; Indicates energy efficiency indicators; This indicates the historical response failure rate, among which, These represent the total number of failed data and the total number of data, respectively, reflecting the reliability level.

[0032] To ensure the physical interpretability of the features, a process tagging mechanism is introduced. For each power curve, based on... It is divided into multiple process stage intervals: ; in, Indicates the first The start and end times of an industrial load in the first process interval; Indicates the first The total number of process stages per industrial load; The label number represents the current process stage, and its value range is [value range missing]. to .

[0033] Within each stage, average power, fluctuation coefficient, and constraint parameters are extracted to obtain a staged feature vector: in, These represent the i-th industrial load in the i-th... Average power and standard deviation of power fluctuation within each process stage; Indicates the first Each process stage; , These represent the minimum start-up and shutdown times corresponding to each process stage; , These represent the production constraints and energy efficiency factors corresponding to this process stage, respectively.

[0034] In this way, each resource not only has overall characteristics It also has phased characteristics. This is more suitable for subsequent potential range assessment.

[0035] By integrating the overall characteristics and stage characteristics of all resources, a global feature set is obtained: ; Where F represents the global feature set formed by integrating the overall and stage characteristics of all industrial loads; N represents the total number of industrial loads; Indicates the first The overall characteristic vector of an industrial load; Indicates the first A staged feature vector of an industrial load at each process stage.

[0036] Z-score normalization is applied to the feature set: ; in, This represents the original value of resource i in feature dimension j. feature dimensions The mean and standard deviation. This represents the standardized feature values. Std indicates standardization. The standardized feature set obtained through Z-score standardization not only facilitates clustering and modeling but also ensures the comparability of different feature dimensions.

[0037] To address the problems in assessing the adjustable resource potential of industry, such as the reliance on single indicators, strong subjectivity in clustering, and a lack of uncertainty in potential values, this application constructs a multi-dimensional indicator system, employs self-organizing mapping clustering, and uses interval estimation methods to achieve zonal quantification and interval representation of resource potential. This provides standardized input for subsequent contract design and regulation optimization. Figure 2 As shown.

[0038] It should be noted that the multidimensional resource feature set includes interruptibility indicators, transferability indicators, operating cost indicators, process constraint strength indicators, volatility indicators, and mode stability indicators.

[0039] Among them, the interruptibility index represents the ratio of allowable energy reduction to total energy consumption; the transferability index represents the ratio of transferable energy to total energy consumption; the operating cost index represents the marginal adjustment cost per unit of adjustable power; the process constraint strength index represents the ratio of locked-in time period to total time period; the volatility index represents the ratio of the standard deviation to the mean of the power curve; and the model stability index represents the entropy value of the cluster distribution of the daily operating curve.

[0040] To address the problem of insufficient representation of resource characteristics, six types of indicators (i.e., interruptibility indicators, transferability indicators, operating cost indicators, process constraint strength indicators, fluctuation indicators, and mode stability indicators) are selected, covering three aspects of adjustability, economic characteristics, and operating mode. For each industrial adjustable resource , a vector of indicators is defined as follows: ; wherein represents an interruptibility indicator, defined as the ratio of allowed period reduction energy to total energy consumption ; represents a transferability indicator, defined as the ratio of transferable energy to total energy consumption; represents an operating cost indicator, defined as the marginal cost of unit adjustment power ; represents a process constraint strength indicator, defined as the ratio of locked period to total period ; represents a fluctuation indicator, defined as the ratio of standard deviation to mean of power curve; represents a mode stability indicator, defined as the entropy value of daily operation curve clustering distribution .

[0041] The six types of indicators are standardized by Z-score: ; wherein represents the original indicator vector of industrial adjustable resource r in feature dimension j. , are the mean and standard deviation of the th original indicator vector, respectively; represents the indicator value of the rth industrial adjustable resource after standardization in feature dimension j.

[0042] Further, the standardized indicator matrix M is obtained after standardization: ; wherein is the standardized indicator vector; R represents the total number of industrial adjustable resources.

[0043] In some embodiments, the step of "classifying the multi-dimensional resource characteristic set and calculating the corresponding potential interval by using self-organizing mapping" in step 100 specifically includes steps 110 to 130: Step 110: Construct a self-organizing map two-dimensional grid network, calculate the Euclidean distance between the multidimensional resource feature set and each node in the self-organizing map two-dimensional grid network, and determine the node with the smallest distance as the best matching node.

[0044] Step 120: Map the multidimensional resource feature set to the best matching node to form a category set.

[0045] Step 130: For each category in the category set, extract the power samples that are in the allowable adjustment period from the running data, and use the quantile method to calculate the upper and lower limits of the potential of the category to obtain the potential range.

[0046] Step 140: Calculate the energy consumption ratio of a single industrial adjustable resource based on the operating data, and allocate the potential range to the single industrial adjustable resource according to the energy consumption ratio.

[0047] To eliminate the subjectivity of manually specifying the number and boundaries of categories, a self-organizing map (SOM) is used for adaptive clustering. A two-dimensional grid network is constructed. ,in, Let be the weight vector of the j-th node, with a dimension of 6. N represents a two-dimensional grid network of self-organizing maps; j represents the index number of a node in the network; then, find the distance input index vector. The nearest node : ; in, Let be the standardized index vector of the r-th resource; This represents the Euclidean distance.

[0048] For the nearest node and its neighboring nodes Perform weight updates: ; in, Indicates the first The node at the th The weight vector at the next iteration; This represents the updated weight vector; For the first Learning rate at the next iteration; For the first The neighborhood radius at the next iteration; when the quantization error converges or the number of iterations reaches the upper limit. Training should be stopped at this time. Represents the nearest node With neighboring nodes The topological distance between them on the grid. All resources are mapped to their best matching cell node, i.e., the nearest node. , form a category set wherein represents the industrial adjustable resource set contained by the kth category, is the category index number.

[0049] To solve the problem that the traditional point value potential evaluation ignores uncertainty, the application introduces interval type potential representation. For the category set , collect the power samples of all member resources in the allowed adjustment period : ; wherein represents the power sample set of the kth category; represents the power value of the rth industrial adjustable resource at time t.

[0050] The lower and upper limits of the category potential are calculated by using the quantile method, and the estimated interval is obtained: ; ; wherein respectively represent the lower quantile and the upper quantile, represents the quantile coefficient, which is 0.2 in the application; represents the lower limit of the potential of the kth category, represents the upper limit of the potential of the kth category.

[0051] For a single resource r in the interval, the energy consumption ratio is allocated: ; wherein represents the potential interval of the rth industrial adjustable resource; represents the energy consumption ratio weight of the rth resource in the category k.

[0052] In this way, the adjustable potential of each resource is expanded from a single value to an upper and lower limit interval.

[0053] For the convenience of subsequent scheduling and contract mechanism, the resources are classified. Define the resource potential mean value: ; wherein represents the potential mean value of the rth industrial adjustable resource; represents the lower limit of the potential interval of the rth industrial adjustable resource; represents the upper limit of the potential interval of the rth industrial adjustable resource.

[0054] Set a threshold set​ wherein, , , is a preset potential grade division threshold, and satisfies The resources are divided into four categories: : low potential; : medium potential; : high potential; : very high potential; The uncertainty coefficient is also defined: ; wherein, represents the uncertainty coefficient of the rthindustrial adjustable resource, used to measure the relative fluctuation degree of the potential interval of the resource; represents the upper limit of the potential interval of the rthindustrial adjustable resource; represents the lower limit of the potential interval of the rthindustrial adjustable resource. Further, in order to ensure that the results can be directly called later, the interval, grade and uncertainty parameter are packaged as a potential certificate and bound with the partition result. The potential certificate of each industrial adjustable resource r is generated: ;

[0055] wherein, is the grade label of the rthindustrial adjustable resource, is the potential mean of the rthindustrial adjustable resource. The potential certificate of the rthindustrial adjustable resource is bound with the cluster to which the resource belongs to form an interval potential label: ; wherein, represents the interval potential label of the rthindustrial adjustable resource. All are uniformly stored in the potential database as the only input interface of the contract mechanism and priority control in the subsequent steps.

[0056] Step 200: constructing node feature vectors and partitioning the power distribution network, establishing a hierarchical control architecture, generating a standardized contract template based on the potential certificate and calculating a resource priority index.

[0057] Step 200: constructing node feature vectors and partitioning the power distribution network, establishing a hierarchical control architecture, generating a standardized contract template based on the potential certificate and calculating a resource priority index.

[0058] ​​In view of the problems of inflexible matching mode of industrial adjustable resources in regulation and control execution process and insufficient contract execution credibility, the embodiments of the application form a complete closed-loop regulation and settlement mechanism through standardized self-execution contract template modeling, prediction-driven dynamic matching mechanism, on-chain credible execution of contracts and result feedback iterative optimization, to ensure the matching effect and contract credibility under dynamic changes of supply and demand.

[0059] In some embodiments, step 200 includes steps 210 to 230: Step 210: Construct a node feature vector and partition the power distribution network to establish a hierarchical regulation architecture.

[0060] Specifically, step 210 includes steps 211 to 215: Step 211: Obtain the node electrical parameters of the power distribution network, including node equivalent impedance, voltage response parameter and node load power parameter.

[0061] The node electrical parameters of each node are obtained from the power distribution network topology data and the power flow calculation results. The node equivalent impedance is extracted from the corresponding diagonal element in the power distribution network impedance matrix, reflecting the electrical distance between the node and the system power source. The voltage response parameter includes the active voltage response parameter and the reactive voltage response parameter. The active voltage response parameter represents the amount of change in node voltage caused by a unit change in active power, and the reactive voltage response parameter represents the amount of change in node voltage caused by a unit change in reactive power. Both the active voltage response parameter and the reactive voltage response parameter are obtained from the corresponding elements of the sensitivity matrix obtained by inverting the Jacobian matrix. The node load power parameter includes the active load power parameter and the reactive load power parameter, which represent the active power and reactive power consumed by the node, respectively.

[0062] The node equivalent impedance, active voltage response parameter, reactive voltage response parameter, active load power parameter and reactive load power parameter are combined to form a node electrical parameter vector.

[0063] Step 212: Calculate the average adjustable potential and potential uncertainty parameter of the resources within the node based on the potential certificate.

[0064] The same node in the power distribution network often connects multiple industrial adjustable resources, and the potential certificate of each industrial adjustable resource records the average potential and uncertainty coefficient of each resource. In order to facilitate zoning and regulation at the node level, the potential information of all industrial adjustable resources within the node needs to be aggregated.

[0065] Read the potential certificate of all industrial adjustable resources in the node from the potential database, extract the potential mean and uncertainty coefficient of each industrial adjustable resource. Calculate the arithmetic mean of the potential mean of all industrial adjustable resources in the node to obtain the average adjustable potential of the node. Calculate the arithmetic mean of the uncertainty coefficient of all industrial adjustable resources in the node to obtain the node potential uncertainty parameter. The average adjustable potential represents the size of the adjustment ability of the node as a whole, and the node potential uncertainty parameter represents the stability of the adjustment ability of the node.

[0066] Step 213: Construct a comprehensive feature vector and perform normalization to obtain a node feature matrix. The comprehensive feature vector includes node electrical parameters, average adjustable potential, and potential uncertainty parameters.

[0067] The traditional power distribution network partitioning method only considers electrical characteristics and divides nodes into different regions according to electrical distance or voltage sensitivity. This method ignores the difference in potential distribution of adjustable resources in the node, which may lead to a large difference in resource potential in the same region, making it difficult for the regional control unit to coordinate and dispatch. Therefore, the present application considers electrical parameters and potential parameters jointly to construct a comprehensive feature vector.

[0068] The node electrical parameter vector, average adjustable potential, and node potential uncertainty parameter are spliced to form a comprehensive feature vector of the node. The comprehensive feature vector contains seven components, the first five components come from the node electrical parameter vector, and the last two components are the average adjustable potential and the node potential uncertainty parameter.

[0069] Due to the differences in the dimensions and numerical ranges of node electrical parameters, average adjustable potential, and node potential uncertainty parameters, normalization processing needs to be performed on the comprehensive feature vector. For each component of the comprehensive feature vector, calculate the maximum and minimum values of the component among all nodes. Subtract the minimum value from the value of each node in the component and divide by the difference between the maximum and minimum values, so that the normalized component value falls within the range of 0 to 1. Arrange the normalized comprehensive feature vectors of all nodes by row to form a node feature matrix.

[0070] Step 214: Perform two-dimensional clustering on the node feature matrix, calculate the distance of the node to the cluster center in the electrical dimension and the distance in the potential dimension, and determine the comprehensive distance, and divide the node into the corresponding regional control unit according to the comprehensive distance.

[0071] Specifically, single-dimensional clustering cannot balance electrical characteristics and potential characteristics. If clustering is performed only in the electrical dimension, nodes with a large difference in potential may be classified into the same region, leading to difficulties in regional regulation and coordination. If clustering is performed only in the potential dimension, nodes with a large electrical distance may be classified into the same region, leading to increased transmission delay of control instructions and increased risk of voltage out-of-limit.

[0072] The node feature matrix is divided into an electrical dimension sub-matrix and a potential dimension sub-matrix according to columns. The electrical dimension sub-matrix includes five columns corresponding to the node equivalent impedance, the active voltage responsibility parameter, the reactive voltage responsibility parameter, the active load power parameter and the reactive load power parameter. The potential dimension sub-matrix includes two columns corresponding to the average adjustable potential and the node potential uncertainty parameter.

[0073] The K-means method is used to perform clustering on the electrical dimension sub-matrix and the potential dimension sub-matrix respectively, to obtain an electrical dimension clustering center set and a potential dimension clustering center set. The number of clustering centers is equal to the preset number of regional control units.

[0074] For each node, the Euclidean distances of the corresponding row vector of the node in the electrical dimension sub-matrix to each electrical dimension clustering center are calculated, and the Euclidean distances of the corresponding row vector of the node in the potential dimension sub-matrix to each potential dimension clustering center are calculated. For the same clustering center number, the electrical dimension Euclidean distance and the potential dimension Euclidean distance are weighted and summed based on a balance parameter to obtain the comprehensive distance of the node to the clustering center. The balance parameter ranges from 0 to 1. The greater the balance parameter, the higher the importance of the electrical dimension in the partition. The smaller the balance parameter, the higher the importance of the potential dimension in the partition. The balance parameter ranges from 0 to 1 and is used to adjust the relative importance of the electrical dimension and the potential dimension in the partition.

[0075] All clustering center numbers are traversed to determine the clustering center number with the minimum comprehensive distance, and the node is divided into the regional control unit corresponding to the number.

[0076] Step 215: Establish a hierarchical regulation and control architecture based on the regional control unit; the regional control unit includes a dispatch center level, a regional control level and a terminal resource level.

[0077] As shown in Figure 3 , the present application establishes a three-layer hierarchical regulation and control architecture based on the regional control unit.

[0078] The dispatch center level is located at the top layer of the hierarchical regulation and control architecture, is responsible for receiving power distribution network operation state information and load prediction data, formulating global regulation and control targets, and decomposing the regulation and control targets into regional regulation and control instructions for each regional control unit and issuing the regional regulation and control instructions to the regional control level.

[0079] The regional control unit is located at the middle layer of the hierarchical regulation and control architecture, and each regional control unit corresponds to a regional controller. After receiving the regional regulation and control instructions issued by the dispatch center level, the regional controller further decomposes the regional regulation and control instructions into execution instructions for each industrial adjustable resource according to the potential certificates and the standardized contract templates of each node in the region, and issues the execution instructions to the terminal resource level.

[0080] The terminal resource layer is located at the bottom of the hierarchical regulation architecture, and contains all the industrial adjustable resources. Each industrial adjustable resource receives the execution instruction issued by the regional control layer, executes the adjustment action, and feeds back the actual execution power and execution state to the regional control layer. The regional control unit reports to the dispatch center layer after summarizing the feedback information of all industrial adjustable resources in the region, forming a closed loop of regulation instruction issuance and execution feedback.

[0081] Step 220: generating a standardized contract template based on the potential certificate.

[0082] Specifically, step 220 includes steps 221 to 223: Step 221: extracting the potential interval, potential mean parameter and potential uncertainty parameter from the potential certificate.

[0083] The potential certificate of the industrial adjustable resource is read from the potential database, and the potential interval is extracted. The potential interval is composed of a potential lower limit and a potential upper limit. The potential lower limit represents the minimum adjustable power of the industrial adjustable resource under conservative estimation, and the potential upper limit represents the maximum adjustable power of the industrial adjustable resource under optimistic estimation.

[0084] The potential mean parameter represents the expected adjustable power of the industrial adjustable resource.

[0085] The potential uncertainty parameter is the ratio of the difference between the potential upper limit and the potential lower limit to the sum of the potential upper limit and the potential lower limit, representing the relative fluctuation amplitude of the potential interval of the industrial adjustable resource. The larger the value of the potential uncertainty parameter, the larger the range of the actual adjustable capacity of the industrial adjustable resource, and the lower the certainty of the regulation result.

[0086] Step 222: obtaining a preset regulation cost value function and a response time window parameter.

[0087] The preset regulation cost value function and the response time window parameter are obtained from the operation parameter database of the industrial adjustable resource.

[0088] The regulation cost value function is used to calculate the regulation cost of the industrial adjustable resource under a given regulation power. Different types of industrial adjustable resources have different cost structures. The regulation cost of a metallurgical furnace is large due to the high requirement of process continuity, and the regulation cost of an air conditioning load is small due to the strong flexibility. The regulation cost value function is constructed based on a benchmark cost value and a slope coefficient. The benchmark cost value represents the fixed cost overhead before regulation, and the slope coefficient represents the additional marginal cost required for each unit increase in regulation power. The regulation cost value function multiplies the regulation power by the slope coefficient and adds the benchmark cost value to obtain the total regulation cost.

[0089] The response time window parameters include an allowed response delay time and a duration. The allowed response delay time represents a maximum allowed time interval for the industrial adjustable resource to start executing a response from receiving a regulation instruction. Some industrial loads cannot immediately respond to the regulation instruction due to process flow constraints and need to reserve start-stop preparation time. The duration represents the length of time that the industrial adjustable resource can maintain the adjusted state, subject to equipment thermal capacity and process cycle limitations.

[0090] Step 223: generating a standardized contract template using the potential interval, the potential mean parameter, the potential uncertainty parameter, the regulation generation cost function, and the response time window parameters.

[0091] The regulation generation cost function is constructed based on a benchmark generation cost and a slope coefficient. The response time window parameters include an allowed response delay time and a duration.

[0092] The potential interval, the potential mean parameter, the potential uncertainty parameter, the regulation generation cost function, and the response time window parameters are combined and packaged to form a standardized contract template for the industrial adjustable resource.

[0093] The standardized contract template is stored in a unified data structure and includes five fields: a potential mean parameter field that records the expected adjustable power of the industrial adjustable resource; a potential interval field that records the upper and lower limit boundaries of the adjustable power of the industrial adjustable resource; a potential uncertainty parameter field that records the relative fluctuation amplitude of the potential interval of the industrial adjustable resource; a regulation generation cost function field that records the benchmark generation cost and the slope coefficient for calculating the regulation generation cost in subsequent settlement; and a response time window parameter field that records the allowed response delay time and the duration for checking the timing constraints in subsequent regulation scheme generation.

[0094] To ensure the tamper resistance and traceability of the standardized contract template, a hash digest of the content of the standardized contract template is calculated and written into the blockchain in combination with the digital signature of the industrial adjustable resource to form a unique index on the chain. In subsequent regulation scheme execution and settlement, the standardized contract template is called up through the unique index on the chain to ensure that the contract parameters used by the supply and demand parties are consistent and irrevocable.

[0095] For example, based on the potential certificate output by the foregoing steps, the resource generates a standardized contract template The standardized contract template includes a potential interval, a mean, an uncertainty parameter, a price function, and a response time window. Its structure is defined as: wherein, represents the potential mean; represents the interval potential; ​​​denotes the uncertainty coefficient; denotes the reference price and the slope coefficient, respectively; denotes the response time parameter, wherein denotes the allowed response delay, denotes the duration. All contract templates are stored in a structured format and written on-chain with a hash digest and a digital signature for unique indexing.

[0096] Step 230: Calculate the resource priority index.

[0097] Specifically, step 230 specifically includes steps 231 to 234: Step 231: Extract the potential level indicator and reliability indicator from the potential certificate, and extract the response speed indicator and economic indicator from the standardized contract template.

[0098] The resource priority index is used to sort the industrial adjustable resources when regulating resource selection. The conventional method only sorts according to the adjustable power size, ignoring the reliability, response speed and economic difference of the resources, which may lead to the selected resource having large potential but low execution compliance rate or high adjustment cost. Therefore, the resource priority index is calculated by comprehensively considering multiple dimensional indicators.

[0099] The potential level indicator and reliability indicator are extracted from the potential certificate. The potential level indicator is determined according to the comparison result of the potential mean parameter and the preset threshold value. The larger the potential mean parameter, the higher the potential level indicator. The reliability indicator is calculated according to the historical execution compliance rate. The higher the historical execution compliance rate, the higher the reliability indicator.

[0100] The response speed indicator and economic indicator are extracted from the standardized contract template. The response speed indicator is calculated according to the allowed response delay time. The shorter the allowed response delay time, the higher the response speed indicator. The economic indicator is calculated according to the slope coefficient in the adjustment cost value function. The smaller the slope coefficient, the lower the cost per unit of adjustable power, and the higher the economic indicator.

[0101] Step 232: Perform standardization processing on the potential level indicator, reliability indicator, response speed indicator, and economic indicator.

[0102] Since the potential level indicator, reliability indicator, response speed indicator, and economic indicator have different dimensions and numerical ranges, directly performing weighted summation will lead to the dominance of indicators with large numerical ranges in the priority result. Therefore, standardization processing needs to be performed on the four indicators respectively.

[0103] ​​For each index, the mean and the standard deviation of the index in all industrial adjustable resources are calculated, and the value of each industrial adjustable resource on the index is subtracted from the mean and divided by the standard deviation, so that the standardized index value is subject to a distribution with a mean of zero and a standard deviation of 1.

[0104] Step 233: Perform weighted summation on the standardized indicators based on a preset proportion parameter vector to obtain an initial priority index.

[0105] The preset proportion parameter vector includes four components corresponding to the weighting proportions of the potential level indicator, the reliability indicator, the response speed indicator, and the economy indicator. The sum of the four weighting proportions is 1, and the size of each weighting proportion reflects the emphasis of the dispatch center on different evaluation dimensions. When emphasizing the adjustment capability, the weighting proportion of the potential level indicator is increased; when emphasizing the execution certainty, the weighting proportion of the reliability indicator is increased; when emphasizing the fast response, the weighting proportion of the response speed indicator is increased; and when emphasizing the economy, the weighting proportion of the economy indicator is increased.

[0106] The standardized potential level indicator is multiplied by the corresponding weighting proportion, the product of the standardized reliability indicator and the corresponding weighting proportion is calculated, the product of the standardized response speed indicator and the corresponding weighting proportion is calculated, and the product of the standardized economy indicator and the corresponding weighting proportion is calculated. The four products are added to obtain the initial priority index of the industrial adjustable resource.

[0107] Step 234: Calculate a risk correction parameter according to the potential interval, and perform correction on the initial priority index using the risk correction parameter to obtain a resource priority index.

[0108] The risk correction parameter is used to reduce the priority of the resource whose fluctuation amplitude of the potential interval exceeds the preset range.

[0109] The initial priority index only reflects the comprehensive performance of the industrial adjustable resource in each evaluation dimension, and does not consider the regulation risk brought by the fluctuation amplitude of the potential interval. If the fluctuation amplitude of the potential interval of the industrial adjustable resource is too large, there may be a large deviation between the actual adjustable power and the expected adjustable power, resulting in an unexpected execution effect of the regulation scheme.

[0110] The risk correction parameter is calculated according to the potential interval. The difference between the potential upper limit and the potential lower limit is divided by the potential mean parameter to obtain a relative fluctuation amplitude. The relative fluctuation amplitude is compared with a preset risk threshold value. If the relative fluctuation amplitude exceeds the preset risk threshold value, the risk correction parameter takes a value less than 1, which is used to reduce the initial priority index. If the relative fluctuation amplitude does not exceed the preset risk threshold value, the risk correction parameter takes a value equal to 1, which does not change the initial priority index. The more the relative fluctuation amplitude exceeds the preset risk threshold value, the smaller the value of the risk correction parameter, and the greater the punishment of the initial priority index.

[0111] The initial priority index is multiplied by a risk correction parameter to obtain a resource priority index. The higher the resource priority index, the higher the ranking of the industrial adjustable resource in the selection of the regulation resource, and the greater the possibility of being selected.

[0112] Step 300: Based on the hierarchical regulation architecture and the resource priority index, a regulation target function is constructed to meet the predicted future demand of the power distribution network as the target and the potential interval as the constraint condition, and an optimal regulation scheme is solved and written into a blockchain smart contract.

[0113] In view of the problems of uneven distribution of resources, inconsistent regulation granularity and uncertainty of potential in the power distribution network, a hierarchical regulation model is established by combining electrical characteristics and potential certificates to realize hierarchical management of the dispatching center, the regional control unit and the terminal resource.

[0114] In some embodiments, step 300 includes steps 310 to 330: Step 310: Obtain the future demand of the power distribution network and determine the target regulation power of each period in the regulation period.

[0115] Specifically, step 310 includes steps 311 to 313: Step 311: Obtain the predicted load power of the power distribution network in each period in the regulation period from the load prediction module.

[0116] The dispatching center level receives the future demand data of the power distribution network from the load prediction module, and the future demand data includes the predicted load power of each period in the regulation period. The time length of the regulation period and the period division granularity are pre-set by the dispatching center level, and the time length of the regulation period can be one hour, four hours or twenty-four hours, and the period division granularity can be fifteen minutes or thirty minutes.

[0117] Step 312: Obtain the base power supply power of the power distribution network in each period in the regulation period.

[0118] The base power supply power represents the power that can be provided by the power distribution network without starting the industrial adjustable resource regulation, and the base power supply power is obtained by superimposing the conventional power output and the new energy predicted output.

[0119] Step 313: Calculate the power gap between the predicted load power and the base power supply power, and take the power gap as the target regulation power of each period.

[0120] The difference between the predicted load power of each period and the benchmark power supply is taken as the power gap of each period. When the power gap is positive, it indicates insufficient power supply, and the industrial adjustable resource needs to reduce load; when the power gap is negative, it indicates excess power supply, and the industrial adjustable resource needs to increase load consumption. The power gap is taken as the target adjustment power of each period, and the target adjustment power is the future demand to be tracked in the regulation target function.

[0121] Step 320: Establish a regulation target function considering system load tracking accuracy, operation cost and risk cost, and set constraint conditions.

[0122] Specifically, step 320 includes steps 321 to 325: Step 321: Establish a system load tracking accuracy term.

[0123] The traditional regulation method only takes the absolute value of the difference between the adjustment power and the target value as the tracking accuracy index, and does not distinguish the adjustment reliability of different resources. The resource priority index is introduced in the present application to weight the tracking accuracy term, so that the adjustment contribution of high priority resources occupies a larger share in the tracking accuracy calculation.

[0124] The system load tracking accuracy term represents the matching degree of the adjusted power and the target adjustment power. For each period, the product of the planned adjustment power of each industrial adjustable resource and the corresponding resource priority index is calculated, and then summed to obtain the weighted adjustment power. The deviation between the weighted adjustment power and the target adjustment power is calculated, and the square of the deviation is taken as the single-period component of the system load tracking accuracy term. The single-period components of all periods are accumulated to obtain the system load tracking accuracy term.

[0125] Step 322: Establish an operation cost term.

[0126] The operation cost term is used to measure the economic expenditure generated by enabling the industrial adjustable resource to perform adjustment. The adjustment value function is called from the standardized contract template of each industrial adjustable resource, and the planned adjustment power is substituted into the adjustment value function to obtain the adjustment cost of a single industrial adjustable resource. The adjustment costs of all industrial adjustable resources in all periods are accumulated to obtain the operation cost term.

[0127] It should be noted that the benchmark value and the slope coefficient in the adjustment value function are derived from the standardized contract template, and the adjustment value function parameters of different industrial adjustable resources are different, and the slope coefficient of metallurgical load is usually higher than that of air conditioning load.

[0128] Step 323: Establish a risk cost term.

[0129] The potential interval represents the upper and lower boundaries of the adjustable power of the industrial adjustable resource. If the planned adjustment power exceeds the potential interval, the actual execution may not reach the planned value, resulting in deviation of the regulation effect from the expectation. The traditional regulation method treats the potential boundary as a hard constraint, and once it is violated, the scheme is not feasible. The application introduces a risk cost term as a soft constraint correction method, allowing the planned adjustment power to deviate from the potential interval to a certain extent, but needs to bear the corresponding risk cost.

[0130] The risk cost term is a correction term for deviation from the potential interval. For each industrial adjustable resource at each time period, the deviation of the planned adjustment power from the potential interval is calculated. If the planned adjustment power is between the potential lower limit and the potential upper limit, the deviation is zero; if the planned adjustment power is less than the potential lower limit, the deviation is the difference between the potential lower limit and the planned adjustment power; if the planned adjustment power is greater than the potential upper limit, the deviation is the difference between the planned adjustment power and the potential upper limit. Multiply the deviation by a preset risk penalty parameter and take the square to obtain the risk cost component of a single industrial adjustable resource at a single time period. Add up the risk cost components of all industrial adjustable resources at all time periods to obtain the risk cost term.

[0131] Step 324: Establish the regulation target function.

[0132] The system load tracking accuracy term, the operation cost term and the risk cost term are weighted and summed to obtain the regulation target function. The optimization objective of the regulation target function is minimization. The weighting parameter of the system load tracking accuracy term, the weighting parameter of the operation cost term and the weighting parameter of the risk cost term are preset by the dispatch center level according to the current power grid operation state and the dispatch strategy. Increase the weighting parameter of the system load tracking accuracy term when focusing on the adjustment effect, increase the weighting parameter of the operation cost term when focusing on the economy, and increase the weighting parameter of the risk cost term when focusing on the safety margin.

[0133] Step 325: Set the constraint condition.

[0134] The potential interval is set as the constraint condition of the regulation target function, and the response time constraint, the node voltage constraint and the regional power balance constraint are set.

[0135] The potential interval constraint requires that the planned adjustment power of each industrial adjustable resource at each time period does not exceed the potential lower limit and the potential upper limit recorded in the potential certificate. Since the risk cost term has already punished the deviation from the potential interval, the potential interval constraint is treated as a soft constraint in the application, allowing moderate boundary crossing in the optimization solution process.

[0136] The response time constraint requires that the time interval between the start time of the adjustment action of each industrial adjustable resource and the time when the regulation instruction is issued is not less than the allowed response delay time recorded in the standardized contract template, and the duration of the adjustment action does not exceed the duration recorded in the standardized contract template.

[0137] The node voltage constraint requires the voltage amplitude of each node after adjustment to be between the allowed upper voltage limit and lower voltage limit. The voltage sensitivity parameters of each node are obtained from the power distribution network power flow calculation module, and the node voltage change after adjustment is calculated based on the voltage sensitivity parameters and the planned adjustment power. The node voltage change is added to the node voltage reference before adjustment to check whether the added node voltage meets the upper voltage limit and lower voltage limit constraint.

[0138] The regional power balance constraint requires the sum of the planned adjustment power of all industrial adjustable resources in each regional control unit to be equal to the regional adjustment power instruction issued by the dispatch center level to the regional control unit. The regional adjustment power instruction is allocated by the dispatch center level according to the proportion of the average adjustable potential of each regional control unit to the average adjustable potential of the whole network.

[0139] Step 330: solving the control target function to generate the optimal control scheme and writing it into the blockchain smart contract.

[0140] Specifically, step 330 includes steps 331 to 334: Step 331: performing optimization solving on the control target function to obtain the optimal planned adjustment power of each industrial adjustable resource in each time period.

[0141] The quadratic programming method is used to perform optimization solving on the control target function. The system load tracking accuracy term and the risk cost term in the control target function are both quadratic functions of the planned adjustment power, and the operation cost term is a linear function of the planned adjustment power. The control target function as a whole conforms to the standard form of the quadratic programming problem. The potential interval constraint, response time constraint, node voltage constraint and regional power balance constraint are converted into linear inequality constraints and linear equality constraints, and a quadratic programming solver is called to solve them to obtain the optimal planned adjustment power of each industrial adjustable resource in each time period.

[0142] Step 332: generating the optimal control scheme based on the optimal planned adjustment power.

[0143] The optimal planned adjustment power of each industrial adjustable resource in each time period is summarized to form the optimal control scheme. The optimal control scheme includes five fields: resource identification, time period identification, optimal planned adjustment power, adjustment direction and execution time. The resource identification is the unique number of the industrial adjustable resource, which is consistent with the resource identification in the potential certificate and the standardized contract template. The time period identification is the serial number of the time period in the control period. The optimal planned adjustment power is the power value obtained by optimization solving. The adjustment direction identifies reduction or increase, indicating that the industrial adjustable resource needs to reduce the load power or increase the load power. The execution time is the timestamp when the industrial adjustable resource starts to execute the adjustment action.

[0144] Step 333: Calculate the hash digest of the optimal regulation scheme and write it into the blockchain smart contract.

[0145] The hash digest of the optimal regulation scheme content is calculated, and the hash digest of the optimal regulation scheme, the generation timestamp, and the digital signature of the dispatch center level are written into the blockchain smart contract. The blockchain smart contract assigns a unique on-chain index to the optimal regulation scheme, which is stored in association with the unique on-chain index of the standardized contract template, facilitating subsequent settlement.

[0146] Step 334: Distribute the optimal regulation scheme to each regional control unit and industrial adjustable resource through the blockchain smart contract.

[0147] The blockchain smart contract splits the optimal regulation scheme into regional regulation sub-schemes for each regional control unit according to the resource identifiers in the optimal regulation scheme. After receiving the regional regulation sub-scheme, the regional control unit further splits the regional regulation sub-scheme into execution instructions for each industrial adjustable resource and distributes them to the terminal resource level. After receiving the execution instructions, the industrial adjustable resource adjusts the power according to the execution time and optimal plan to execute the adjustment action.

[0148] It is worth mentioning that the optimal regulation scheme is distributed through the blockchain smart contract, and each participant can verify the integrity and authenticity of the scheme content, avoiding the risk of instruction tampering in traditional centralized scheduling platforms. Step 400: Collect the actual execution power in response to the optimal regulation scheme, perform settlement through the blockchain smart contract, and calculate the execution compliance rate. Update the standardized contract template and resource priority index using the actual execution power and execution compliance rate.

[0149] In some embodiments, step 400 includes steps 410 to 430: Step 410: Collect the actual execution power in response to the optimal regulation scheme.

[0150] It should be noted that the terminal collection device is deployed at the metering point of each industrial adjustable resource, and the terminal collection device includes a smart meter and a power transducer. When the execution time recorded in the optimal regulation scheme arrives, the terminal collection device samples the instantaneous power of the industrial adjustable resource according to the preset sampling interval. The real-time power data of all sampling points in each period is processed by arithmetic average to obtain the actual execution power of the industrial adjustable resource in the period. The terminal collection device uploads the actual execution power to the regional control level through the node gateway, and the regional control level reports to the dispatch center level after aggregation.

[0151] Step 420: Perform settlement through the blockchain smart contract.

[0152] Specifically, step 420 includes steps 421 to 423: Step 421: Call the standardized contract template through the blockchain smart contract.

[0153] The blockchain smart contract reads the standardized contract template of each industrial adjustable resource from the chain according to the resource identifier in the optimal regulation scheme. The on-chain unique index of the standardized contract template and the on-chain unique index of the optimal regulation scheme have been associated and stored in step 330, and the blockchain smart contract completes the call of the standardized contract template through the association of the on-chain unique index.

[0154] Step 422: Calculate the deviation value between the actual execution power and the planned power indicated by the optimal regulation scheme.

[0155] For each industrial adjustable resource in each period, read the actual execution power from the execution record data set, and read the optimal planned adjustment power from the optimal regulation scheme. The actual execution power is subtracted from the optimal planned adjustment power to obtain the deviation value. The positive deviation value indicates that the actual adjustment amount exceeds the planned adjustment amount, and the negative deviation value indicates that the actual adjustment amount does not reach the planned adjustment amount.

[0156] Step 423: Calculate the settlement interaction value based on the adjustment value function in the standardized contract template and the deviation value.

[0157] The reference value and slope coefficient of the adjustment value function are read from the standardized contract template. The optimal planned adjustment power is substituted into the adjustment value function to obtain the planned settlement reference value. The planned settlement reference value is adjusted according to the deviation value to obtain the settlement interaction value. When the deviation value is zero, the planned settlement reference value is settled; when the deviation value is positive, the excess part is compensated; and when the deviation value is negative, the shortage part is deducted. The blockchain smart contract writes the settlement interaction value and the deviation value on the chain to form an unalterable settlement certificate.

[0158] Further, the execution performance rate is calculated based on the ratio relationship between the deviation value and the planned power. Specifically, the execution performance rate is used to measure the overall execution performance of the industrial adjustable resource in the regulation period. For each industrial adjustable resource, the deviation values of all periods in the regulation period are counted, and the execution performance rate is calculated based on the ratio relationship between the deviation value and the optimal planned adjustment power. The execution performance rate ranges from 0 to 1, and the closer the execution performance rate is to 1, the better the execution performance.

[0159] Step 430: Update the standardized contract template and the resource priority index using the actual execution power and the execution performance rate.

[0160] Specifically, step 430 includes steps 431 to 433: Step 431: Calculate the deviation mean and the deviation fluctuation based on the deviation value, and combine the deviation mean and the deviation fluctuation to form the execution error parameter.

[0161] For each industrial adjustable resource, the deviation mean and the deviation volatility are calculated based on the deviation values of each period in the regulation period. The deviation mean reflects the direction and size of systematic execution deviation, and the deviation volatility reflects the stability of execution. The deviation mean and the deviation volatility are combined to form the execution error parameter.

[0162] Step 432: using the execution error parameter to perform correction on the potential uncertainty parameter in the standardized contract template.

[0163] The deviation volatility is extracted from the execution error parameter, and the execution volatility is calculated based on the ratio relationship between the deviation volatility and the potential mean parameter. Based on the preset correction smoothing parameter, a weighted average is performed on the original potential uncertainty parameter and the execution volatility to obtain the corrected potential uncertainty parameter, which is written into the standardized contract template and updated on the chain.

[0164] The correction smoothing parameter is preset by the dispatch center level according to the regulation scene, and the value range of the correction smoothing parameter is 0 to 1. The larger the correction smoothing parameter, the higher the proportion of the execution volatility in the corrected potential uncertainty parameter, and the smaller the influence of the original potential uncertainty parameter. The smaller the correction smoothing parameter, the higher the retention degree of the original potential uncertainty parameter, and the smaller the influence of the execution volatility on the correction result.

[0165] It should be noted that if the execution volatility of the industrial adjustable resource is continuously high in multiple regulation periods, the corrected potential uncertainty parameter will gradually increase, resulting in an increase in the punishment intensity of the risk cost item on the industrial adjustable resource, thereby reducing the possibility of the industrial adjustable resource being selected in the optimal regulation scheme.

[0166] Step 433: according to the preset memory decay parameter, the resource priority index is iteratively updated in combination with the execution compliance rate.

[0167] The preset memory decay parameter is used to control the retention degree of the historical resource priority index in the iterative update, and the value range of the memory decay parameter is 0 to 1. Based on the memory decay parameter, a weighted average is performed on the historical resource priority index and the execution compliance rate to obtain the updated resource priority index. The updated resource priority index is written into the potential database for calling in the next regulation period.

[0168] Through the iterative update of the resource priority index by the execution compliance rate, the resource priority index of the industrial adjustable resource with a high execution compliance rate will gradually increase, and the resource priority index of the industrial adjustable resource with a low execution compliance rate will gradually decrease, forming a resource screening closed loop of survival of the fittest. On the basis of the above steps, the present application further includes the following embodiments: Referring to Figure 4Fig. 1 is a schematic diagram of a hardware structure of an electronic device according to an embodiment of the present application. The electronic device 40 comprises a processor 41, a memory 42 and a computer program; wherein The memory 42 is configured to store the computer program, and the memory can also be a flash memory. The computer program is, for example, an application program, a functional module or the like for implementing the above method.

[0169] The processor 41 is configured to execute the computer program stored in the memory, so as to implement each step of the method performed by the device. For details, refer to the related description in the method embodiments.

[0170] Optionally, the memory 42 can be independent or integrated with the processor 41.

[0171] When the memory 42 is independent of the processor 41, the device can further comprise: A bus 43 is configured to connect the memory 42 and the processor 41.

[0172] Finally, it should be noted that: the above embodiments are only used to illustrate the technical solutions of the present application, but not to limit them; although the present application has been described in detail with reference to the above embodiments, those skilled in the art should understand: the technical solutions recorded in the above embodiments can still be modified, or some or all of the technical features can be replaced by equivalents; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the scope of the technical solutions of the embodiments of the present application.

Claims

1. A method for interval potential modeling and optimal regulation and control of power distribution grid industrial adjustable resources, characterized in that, Comprise: Extracting a multi-dimensional resource feature set based on industrial load operation data, using self-organizing mapping to classify the multi-dimensional resource feature set and calculate the corresponding potential interval, and generating a potential certificate; Constructing a node feature vector and partitioning the distribution network, establishing a hierarchical control architecture, generating a standardized contract template based on the potential certificate and calculating a resource priority index; Based on the hierarchical control architecture and the resource priority index, a control objective function is constructed to meet the predicted future demand of the distribution network as the target and the potential interval as the constraint condition, and the optimal control scheme is solved and written into the smart contract of the blockchain; Collecting the actual execution power in response to the optimal control scheme, executing settlement through the smart contract of the blockchain and calculating the execution compliance rate, and updating the standardized contract template and resource priority index using the actual execution power and the execution compliance rate.

2. The method of claim 1, wherein The operation data of the industrial load includes power curve data and process constraint parameters; The multi-dimensional resource feature set includes interruptability index, transferability index, operation cost index, process constraint intensity index, fluctuation index, and mode stability index; The interruptability index represents the ratio of allowed period reduction energy to total energy consumption; The transferability index represents the ratio of translatable energy to total energy consumption; The operation cost index represents the marginal adjustment value of unit adjustment power; The process constraint intensity index represents the ratio of locked period to total period; The fluctuation index represents the ratio of power curve standard deviation to mean value; The mode stability index represents the entropy value of daily operation curve clustering distribution.

3. The method of claim 2, wherein The extraction of the multi-dimensional resource feature set based on the operation data of the industrial load comprises: Performing statistical analysis and parameter extraction on the power curve data and the process constraint parameters to obtain overall characteristics of the industrial load, the overall characteristics including power mean value parameters, power dispersion parameters, energy efficiency index, and response failure rate; Divide the power curve data into multiple process stage intervals according to the process constraint parameters, and collect stage characteristics of each process stage interval, the stage characteristics including power mean value parameters, power dispersion parameters, process minimum start-stop time, process stage label, and process constraint parameter set; Integrate the collected overall characteristics and stage characteristics to obtain a basic feature set; calculate the multi-dimensional resource feature set based on the basic feature set.

4. The method of claim 1, wherein The use of self-organizing mapping to classify the multi-dimensional resource feature set and calculate the corresponding potential interval comprises: Constructing a self-organizing mapping two-dimensional grid network, calculating the Euclidean distance between the multi-dimensional resource feature set and each node in the self-organizing mapping two-dimensional grid network, and determining the node with the smallest distance as the best matching node; Map the multi-dimensional resource feature set to the best matching node to form a category set; For each category in the category set, power samples in the allowed adjustment period are extracted from the operation data, and the upper and lower limits of the potential of the category are calculated using the quantile method to obtain the potential interval; Based on the operation data, the energy consumption proportion of the individual industrial adjustable resource is calculated, and the potential interval is allocated to the individual industrial adjustable resource according to the energy consumption proportion.

5. The method of claim 4, wherein, The node feature vector is constructed, and the power distribution network is partitioned, and a hierarchical regulation architecture is established, including: Obtaining node electrical parameters of the power distribution network, the node electrical parameters including node equivalent impedance, voltage response degree parameters and node load power parameters; Based on the potential certificate, the average adjustable potential and the potential uncertainty parameter of the resource in the node are calculated; A comprehensive feature vector is constructed, and normalization processing is performed to obtain a node feature matrix, the comprehensive feature vector containing node electrical parameters, average adjustable potential and potential uncertainty parameters; The node feature matrix is subjected to two-dimensional clustering, the distance of the node to the cluster center in the electrical dimension and the distance in the potential dimension are calculated respectively, and the comprehensive distance is determined, and the node is divided into a corresponding regional control unit according to the comprehensive distance; Based on the regional control unit, the hierarchical regulation architecture is established; the regional control unit includes a dispatch center level, a regional control level and a terminal resource level.

6. The method of claim 5, wherein, The standardized contract template is generated based on the potential certificate, including: Extracting the potential interval, the potential mean parameter and the potential uncertainty parameter from the potential certificate; Obtaining a preset adjustment value function and a response time window parameter; Using the potential interval, the potential mean parameter, the potential uncertainty parameter, the adjustment value function and the response time window parameter to generate the standardized contract template; Wherein, the adjustment value function is constructed based on the benchmark value and the slope coefficient; the response time window parameter includes the allowed response delay time and the duration.

7. The method of claim 1, wherein, The resource priority index is calculated, including: Extracting the potential level index and the reliability index from the potential certificate, and extracting the response speed index and the economic index from the standardized contract template; Standardization processing is performed on the potential level index, the reliability index, the response speed index and the economic index; Based on a preset proportion parameter vector, a weighted sum is performed on each index after standardization processing to obtain an initial priority index; A risk correction parameter is calculated according to the potential interval, and the initial priority index is corrected using the risk correction parameter to obtain the resource priority index; The risk correction parameter is used to reduce the priority of the resource whose fluctuation amplitude of the potential interval exceeds the preset range.

8. The method of claim 6, wherein, The regulation objective function is constructed based on the resource priority index and the potential interval to meet the predicted future demand of the power distribution network, specifically, a regulation objective function considering system load tracking accuracy, operation cost and risk cost is established; The system load tracking accuracy represents a matching degree of the adjusted power and the future demand; The operation cost is calculated based on an adjustment cost value function in the standardized contract template; and the risk cost is a correction term deviating from the potential interval. The potential interval is taken as a constraint condition of the control target function, and a response time constraint, a node voltage constraint and a regional power balance constraint are set.

9. The method of claim 1, wherein, The settlement is performed by the blockchain smart contract, including: calling the standardized contract template by the blockchain smart contract; calculating a deviation value between the actual execution power and a planned power indicated by the optimal control scheme; calculating a settlement interaction value based on an adjustment cost value function in the standardized contract template and the deviation value; calculating the execution performance rate based on a ratio relationship between the deviation value and the planned power.

10. The method of claim 9, wherein, The standardized contract template and the resource priority index are updated based on the actual execution power and the execution performance rate, including: calculating a deviation mean and a deviation fluctuation amount based on the deviation value, and combining the deviation mean and the deviation fluctuation amount to form an execution error parameter; performing correction on a potential uncertainty parameter in the standardized contract template by using the execution error parameter; performing iterative update on the resource priority index according to a preset memory decay parameter and the execution performance rate.

Images