Active power distribution network planning method

Abstract

The invention discloses an active power distribution network planning method, and relates to the technical field of active power distribution network planning, and the method comprises the steps: constructing a distributed energy transaction platform based on a block chain, building a distributed energy transaction network through the decentralization characteristic of the block chain, and designing an intelligent contract to standardize the energy transaction process and rule. According to the invention, the distributed energy transaction platform of the block chain is constructed, the smart contract is designed to standardize the transaction process and rule, the security and transparency of the energy transaction are improved, the authenticity, reliability, publicity and transparency of the transaction data are ensured, the energy distribution scheme is formulated by using the optimization algorithm based on the energy transaction data on the block chain and the user demand, and the user experience is improved. According to the method, local requirements are preferably met, energy distribution is optimized, transmission loss is reduced, line layout and capacity configuration of the power distribution network are re-planned according to energy transaction conditions, access factors of distributed energy are fully considered, site selection and distribution of transformer substations are optimized, and electric energy transmission efficiency can be effectively improved.

Description

Technical Field

[0001] The invention relates to the technical field of active distribution network planning, and in particular to an active distribution network planning method. Background Art

[0002] The active distribution network is a network for energy exchange and distribution, and its current and fault current can flow in both directions. This distribution network achieves flexible distribution and efficient use of electric energy by accessing distributed power sources (such as solar energy, wind energy and other renewable energy sources). The access of a large number of distributed power sources makes the power structure of the distribution network more diversified. Compared with the traditional distribution network, the power of the active distribution network can flow in both directions, which requires the distribution network to make corresponding adjustments in planning, design, operation, etc. The active distribution network emphasizes that the distributed power sources actively adjust their reactive and active outputs, and use modern communication means to coordinate and control the distribution network to achieve the optimized operation of the distribution network.

[0003] Active distribution network planning is a kind of planning for distribution networks that are connected to a large number of distributed power sources (such as solar energy, wind energy, etc.) in the power system to meet the requirements of future load growth and power grid development. This planning aims to achieve the optimal operation of the distribution network through reasonable layout and scheduling, improve energy utilization efficiency, reduce operating costs, and meet users' requirements for the reliability and quality of power supply. Active distribution network planning is a complex and important process that requires comprehensive consideration of multiple factors and technical means. Through scientific and reasonable planning, design and implementation, the optimized operation and sustainable development of active distribution networks can be achieved.

[0004] With the continuous development of the energy field, the widespread application of distributed energy has become a significant trend. However, the current distribution network planning and management system still has certain defects in dealing with distributed energy. The decentralization and diversity of distributed energy increase the complexity of energy transactions, resulting in a lack of efficient, safe and transparent mechanisms for energy transactions between users, which seriously hinders the effective configuration and utilization of energy. The existing distribution network planning methods have limitations when considering the access of distributed energy, and it is difficult to give full play to the potential of distributed energy. The line layout and capacity configuration often cannot adapt well to the distribution and changes of distributed energy, resulting in low efficiency of power transmission and increased network losses. Therefore, it is necessary to propose an active distribution network planning method to solve the problems in the existing technology. Summary of the invention

[0005] The purpose of the present invention is to make up for the shortcomings of the existing technology and provide an active distribution network planning method, which can utilize the decentralization, immutability and smart contract characteristics of blockchain to achieve safe and efficient trading and management of distributed energy. By building a blockchain platform, it optimizes energy distribution, provides new ideas for distribution network planning, and significantly improves the operating efficiency and stability of the distribution network.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions: an active distribution network planning method, the method comprising:

[0007] Build a distributed energy trading platform based on blockchain, use the decentralized characteristics of blockchain to establish a distributed energy trading network, and design smart contracts to standardize energy trading processes and rules;

[0008] Install high-precision energy metering equipment to collect data related to distributed energy, encrypt and upload it to the blockchain, and verify and process the data;

[0009] Based on the energy transaction data and user needs on the blockchain, an optimization algorithm is used to formulate an energy distribution plan, giving priority to local consumption and optimizing cross-regional transactions;

[0010] According to the energy trading situation, combined with geographic information systems and load forecasting models, re-plan the line layout and capacity configuration of the distribution network and optimize the site selection and distribution of substations;

[0011] Establish a distributed energy quality assessment system to monitor and assess the power quality of distributed energy in real time, and take corresponding adjustment measures in energy trading and distribution network planning based on the assessment results;

[0012] Build a risk warning and response mechanism, use machine learning algorithms to make predictions and warnings based on transaction data and distribution network operation data on the blockchain, and formulate corresponding emergency plans and response strategies;

[0013] Develop user-friendly energy trading and management applications, establish a user feedback mechanism, and optimize distribution network planning and energy trading strategies based on user feedback;

[0014] Establish interfaces and coordination mechanisms with traditional energy supply systems, realize the coordinated operation of distributed energy and traditional energy, and comprehensively consider the characteristics and advantages of both in energy trading and distribution network planning.

[0015] Furthermore, the distributed energy trading platform based on blockchain is constructed, a distributed energy trading network is established by utilizing the decentralized characteristics of blockchain, and smart contracts are designed to standardize energy trading processes and rules. The method includes:

[0016] First, the distributed energy trading network architecture is designed, the network node type is determined, and the network topology is designed using the P2P network architecture;

[0017] Next, we design smart contracts and define the basic process of energy trading, including energy measurement rules, price negotiation mechanism, transaction confirmation method and settlement process;

[0018] Select the blockchain type, use the practical Byzantine fault-tolerant algorithm, and the probability of nodes reaching consensus P consensus It is estimated by the following formula: consensus＝ (1-f) n Where, f is the proportion of failed nodes, n is the total number of nodes;

[0019] Design the data structure of the blockchain and use encryption technology to ensure data security;

[0020] Conduct simulated trading tests to evaluate platform performance and stability, and optimize network architecture, smart contracts, and algorithm parameters based on test results.

[0021] Furthermore, the method of installing high-precision energy metering equipment to collect data related to distributed energy, encrypting and uploading it to the blockchain, and verifying and processing the data includes:

[0022] Select smart meters and sensors with high-precision measurement capabilities, and install metering equipment appropriately based on the access points of distributed energy and the locations of power-consuming devices;

[0023] Set the collection frequency and obtain energy-related parameter values ​​in real time through sensors and electricity meters;

[0024] Use the median filter algorithm to remove noise interference in the collected data, and use the encryption algorithm to encrypt the pre-processed data;

[0025] Encapsulate the encrypted data into blockchain transactions and broadcast the transaction information to nodes in the blockchain network;

[0026] Calculate the hash value of the data and compare it with the hash value when it was uploaded. Verify the legitimacy of the data source through digital signatures and use threshold judgment methods to detect abnormal data.

[0027] Store verified data on the blockchain and create an index.

[0028] Furthermore, based on the energy transaction data and user needs on the blockchain, an optimization algorithm is used to formulate an energy distribution plan, give priority to local consumption, and optimize cross-regional transactions. The method includes:

[0029] Obtain historical data on energy transactions from the blockchain and collect real-time demand data from users;

[0030] Establish an optimization model, define the objective function, and set constraints;

[0031] Use particle swarm optimization algorithm to develop energy allocation plan;

[0032] According to the needs of local users and energy supply, give priority to meeting the energy needs of local users and calculate the local energy surplus and shortage;

[0033] For local surplus energy, the optimal cross-regional transaction objects and transaction quantities are determined based on the optimization algorithm, and the cross-regional transmission costs and transaction price factors are considered to optimize the transaction plan.

[0034] Furthermore, the specific process of formulating the energy allocation plan using the particle swarm optimization algorithm includes:

[0035] Initialize the particle swarm and randomly generate a set of particle positions and velocities, each particle represents an energy allocation scheme;

[0036] Calculate the fitness value, and calculate the fitness value of each particle according to the objective function;

[0037] Update individual optimal and global optimal, compare the current fitness value of each particle with the individual historical optimal fitness value, update the individual optimal position, compare the fitness values ​​of all particles, and update the global optimal position;

[0038] Update the velocity and position of the particle according to the following formula: i+1 =w×v i +c1×r1×(pbest i -x i )+c2×r2×(gbest-x i ), x i+1 =x i +v i+1 Among them, v i and x i are the velocity and position of particle i, w is the inertia weight, c1 and c2 are learning factors, r1 and r2 are random numbers in the range [0, 1], and pbest i is the individual optimal position of particle i, and gbest is the global optimal position.

[0039] Furthermore, the method replans the line layout and capacity configuration of the distribution network and optimizes the site selection and distribution of substations according to the energy trading situation, combined with the geographic information system and the load forecasting model. The method includes:

[0040] Obtain the flow, scale and trend data of energy transactions from the blockchain, conduct time series analysis on the data, and extract periodicity and trend characteristics;

[0041] Using the load forecasting model, the ARIMA model based on time series is used to predict the future load demand in different regions. The forecasting formula is expressed as: in, is the load forecast value at time t, φ i and θ j is the model parameter, ∈ tIt is white noise;

[0042] Integrate geographic information data to analyze geographical restrictions and potential route channels in different regions;

[0043] Based on the energy transaction flow and load distribution, the line direction is preliminarily determined, and the minimum spanning tree algorithm is used to determine the optimal line connection method to minimize the line construction cost. The line construction cost function is C(L), where L is the line set. The goal is to find (L * ) makes C(Lw)=min L C(L);

[0044] According to the predicted load and distributed energy output, the capacity required for lines and equipment is calculated. Considering the safety margin and future development needs, the capacity configuration is appropriately increased. The capacity calculation formula is expressed as: C required =max(Load predicted ,Output distributed) ×(1+Margin);

[0045] With the goal of minimizing line loss and maximizing power supply reliability, the particle swarm optimization algorithm is used to optimize the location of substations in combination with the access location and capacity of distributed energy resources;

[0046] Use simulation software to simulate the planning scheme, evaluate its performance indicators, and adjust and optimize the scheme based on the evaluation results.

[0047] Furthermore, the distributed energy quality assessment system is established to monitor and assess the power quality of distributed energy in real time, and corresponding adjustment measures are taken in energy trading and distribution network planning according to the assessment results. The method includes:

[0048] Install high-precision power quality monitoring equipment to collect voltage and current electrical parameters of distributed energy in real time;

[0049] Calculate the voltage fluctuation value V using the root mean square change method fluc , the formula is: Among them, V i is the voltage value at each sampling moment, V avg is the average voltage value, N is the number of sampling points;

[0050] By measuring the actual frequency f actual With standard frequency f standard The difference between the two is the frequency deviation Δf, that is: Δf = f actual -f standard ;

[0051] The voltage and current signals are decomposed into fundamental and harmonic components using the fast Fourier transform algorithm.n It is expressed as: Among them, A n is the amplitude of the nth harmonic, A1 is the amplitude of the fundamental wave;

[0052] Set weight w for each indicator i , comprehensively evaluate the power quality score Q, the formula is: Q = w1 × V fluc +w2×|Δf|+w3×Σ n H n ;

[0053] Compare the comprehensive evaluation score with the preset threshold to determine whether the power quality is qualified;

[0054] Based on the evaluation results, prices and transaction priorities are adjusted in energy trading, and in distribution network planning, reactive power compensation equipment is added and line parameters are optimized for areas with poor power quality.

[0055] Furthermore, the risk warning and response mechanism is constructed, based on the transaction data and distribution network operation data on the blockchain, using machine learning algorithms for prediction and warning, and formulating corresponding emergency plans and response strategies. The method includes:

[0056] Obtain energy transaction data from blockchain and collect distribution network operation data;

[0057] Preprocess and extract features from the collected data to extract power fluctuation features from distribution network operation data;

[0058] The decision tree machine learning algorithm is used for risk prediction. The optimal features are selected for splitting through information gain and Gini coefficient to build a decision tree model. The calculation formula of feature X, category Y, and information gain IG(Y,X) is: Among them, H(Y) is the entropy of data set Y, Y v It is the data set corresponding to the value of feature X when it is v;

[0059] Build a supply shortage prediction model based on historical energy supply and demand data;

[0060] Analyze the fluctuation of historical transaction price data, establish a price fluctuation model, and use the GARCH model to capture the volatility and aggregation of prices. The formula of the GARCH model is: in, is the conditional variance, ω is a constant term, α and β are model parameters, ∈ t-1 is the residual;

[0061] Monitor network traffic, abnormal access data, and use intrusion detection algorithms to predict risks;

[0062] Based on historical data and experience, a warning threshold is set for each risk. When the predicted risk exceeds the warning threshold, a warning signal is issued.

[0063] Furthermore, the method comprises developing a user-friendly energy trading and management application, establishing a user feedback mechanism, and optimizing distribution network planning and energy trading strategies based on user feedback.

[0064] Collect user functional requirements and expectations for energy trading and management applications;

[0065] Design a simple and intuitive user interface, develop an energy trading module, support users in energy buying and selling operations, and establish a transaction record storage and query system;

[0066] Obtain real-time operation data from the distribution network monitoring system and use data visualization technology to display the distribution network operation status to users in the form of charts and maps;

[0067] Set up a feedback portal in the application to categorize and organize user feedback;

[0068] Use text analysis algorithms to process the text content of user feedback, extract key information, and optimize distribution network planning and energy trading strategies based on the analysis results of user feedback;

[0069] Regularly collect new user feedback to continuously improve applications and strategies.

[0070] Furthermore, the interface and coordination mechanism with the traditional energy supply system is established to realize the coordinated operation of distributed energy and traditional energy, and the characteristics and advantages of both are comprehensively considered in energy trading and distribution network planning. The method includes:

[0071] Define the data exchange format and communication protocol with traditional energy supply systems, and determine the frequency and real-time requirements of data transmission;

[0072] Collect energy supply data from traditional energy systems, integrate it with data from distributed energy systems, and establish a unified data warehouse;

[0073] Formulate energy allocation rules and use optimization algorithms to determine the best energy allocation plan to minimize costs and maximize energy efficiency;

[0074] In energy trading, the price and supply stability of distributed energy and traditional energy are comprehensively considered, and the weight of each factor is determined using the hierarchical analysis method. The price weight is w p , the stability weight is w s , then the comprehensive score S is calculated as: S = w p ×P+w s ×S, where P represents the price score and S represents the stability score;

[0075] In distribution network planning, optimize line layout and equipment configuration according to the output characteristics and location distribution of distributed energy and traditional energy;

[0076] Monitor the operating status and supply and demand of distributed energy and traditional energy in real time, and dynamically adjust coordination strategies and energy trading plans based on actual conditions.

[0077] Compared with the existing technology, the active distribution network planning method has the following beneficial effects:

[0078] The present invention improves the security and transparency of energy transactions by constructing a distributed energy trading platform based on blockchain and designing smart contracts to standardize transaction processes and rules, ensuring the authenticity, reliability, openness and transparency of transaction data. Based on energy transaction data and user needs on blockchain, an energy allocation plan is formulated using an optimization algorithm to give priority to meeting local needs, optimize energy allocation, reduce transmission losses, re-plan the line layout and capacity configuration of the distribution network according to the energy trading situation, fully consider the access factors of distributed energy, optimize the site selection and distribution of substations, and effectively improve the efficiency of power transmission.

[0079] Other advantages, objectives and features of the present invention will be set forth in part in the following description and, in part, will be apparent to those skilled in the art based on an examination of the following or may be taught from the practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0080] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the prior art descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention, and for ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0081] Figure 1 A flow chart of an active distribution network planning method. DETAILED DESCRIPTION

[0082] The technical solutions in the embodiments of the present invention are described clearly and completely below. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0083] Embodiment 1

[0084] A method for planning an active distribution network, the method comprising: building a distributed energy trading platform based on blockchain, establishing a distributed energy trading network using the decentralized characteristics of blockchain, and designing smart contracts to standardize energy trading processes and rules, covering energy metering, price negotiation, transaction confirmation, settlement and other links.

[0085] The specific process of this method includes: firstly, designing the distributed energy trading network architecture, determining the network node types, including distributed energy producers (such as residential solar energy users), consumers (such as electricity users) and intermediate coordinators (such as distribution network operators), and using the P2P (Peer-to-Peer) network architecture to design the network topology to ensure equal connection between nodes and the connection strength C between nodes. ij Calculated by the following formula: C ij =k i ×k j / ∑ m k m Among them, k i and k j are the connectivity of nodes i and j, ∑ m k m It is the sum of the connectivity of all nodes in the network.

[0086] Then, we design smart contracts and define the basic process of energy trading, including energy measurement rules, price negotiation mechanism, transaction confirmation method and settlement process. The energy measurement formula is: the energy measurement value E is expressed as E=P×t, where P is power and t is time. The dynamic pricing algorithm based on market supply and demand balance is adopted. The market demand is D and the supply is S. The adjustment formula of price P is: P t+1 =P t +α×(DS) where P t is the current price, α is the adjustment coefficient, digital signatures and hash algorithms are used to ensure the non-repudiation and integrity of transactions, and fund settlement is automatically executed based on smart contracts. The calculation of the settlement amount A is expressed as: A=E×P.

[0087] Select the blockchain type, including public chain, consortium chain or private chain, balance openness and security according to actual needs, adopt the Practical Byzantine Fault Tolerance (PBFT) algorithm, and the consensus probability of nodes is P consensus It is estimated by the following formula: consensus =(1-f) n Among them, f is the proportion of faulty nodes, n is the total number of nodes, and the data structure of the blockchain is designed, including block headers and block bodies, to store transaction information and related metadata. Encryption technology is used to ensure data security, simulated transaction tests are conducted, platform performance and stability are evaluated, and network architecture, smart contracts and algorithm parameters are optimized according to the test results to improve transaction efficiency and user experience.

[0088] Install high-precision energy metering equipment to collect relevant data on distributed energy, including distributed energy generation, electricity consumption, power generation, power consumption and other data, encrypt and upload them to the blockchain to verify and process the data.

[0089] The specific process of this method includes: selecting smart meters and sensors with high-precision measurement capabilities, which can accurately measure the parameters of power generation, power consumption, power generation and power consumption; reasonably installing metering equipment according to the access points of distributed energy and the locations of power consumption equipment to ensure comprehensive and accurate data collection; setting the collection frequency; determining the collection intervals per second, per minute and per hour according to actual needs; and obtaining energy-related parameter values ​​in real time through sensors and meters, such as the power generation power P gen (t) and power consumption P use (t) The collected value at time t.

[0090] Use the median filter algorithm to remove noise interference in the collected data, use the encryption algorithm to encrypt the preprocessed data, upload the data to the blockchain, encapsulate the encrypted data into blockchain transactions, broadcast the transaction information to the nodes in the blockchain network, calculate the hash value of the data, and compare it with the hash value when uploading to ensure that the data has not been tampered with. Verify the legitimacy of the data source through digital signatures, and use the threshold judgment method to detect abnormal data. For example, if the power generation or power consumption exceeds the reasonable range [P min ,P max ], it is marked as abnormal data, and the verified data is stored on the blockchain and indexed for quick query and retrieval.

[0091] Embodiment 2

[0092] Based on the energy transaction data and user needs on the blockchain, advanced optimization algorithms such as genetic algorithms and particle swarm optimization algorithms are used to formulate energy distribution plans, give priority to local consumption, optimize cross-regional transactions, give priority to meeting the energy needs of local users, maximize the local consumption of distributed energy, and optimize cross-regional transactions for the remaining energy.

[0093] The specific process of this method includes: obtaining historical energy transaction data from the blockchain, including the time, location and quantity information of energy production and consumption, collecting real-time demand data of users, including electricity demand forecasts in different regions and time periods, establishing an optimization model, defining the objective function, including minimizing energy transmission losses, maximizing energy utilization efficiency and minimizing user electricity costs, and setting constraints, including energy supply capacity restrictions, line transmission capacity restrictions and local energy priority consumption requirements.

[0094] The particle swarm optimization algorithm is used to formulate an energy allocation plan. The specific process includes: initializing the particle swarm, randomly generating a set of particle positions and velocities, each particle represents an energy allocation plan, calculating the fitness value, calculating the fitness value of each particle according to the objective function, updating the individual optimal and global optimal, comparing the current fitness value of each particle with the individual historical optimal fitness value, updating the individual optimal position, comparing the fitness values ​​of all particles, updating the global optimal position, updating the speed and position, and updating the speed and position of the particle according to the following formula: i+1 =w×v i +c1×r1×(pbest i -x i )+c2×r2×(gbest-x i ), x i+1 =x i +v i+1 Among them, v i and x i are the velocity and position of particle i, w is the inertia weight, c1 and c2 are learning factors, r1 and r2 are random numbers in the range [0, 1], and pbest i is the individual optimal position of particle i, and gbest is the global optimal position.

[0095] According to the needs of local users and energy supply conditions, priority is given to meeting the energy needs of local users, calculating the local energy surplus and shortage, and for the local surplus energy, determining the optimal cross-regional transaction objects and transaction quantities based on the optimization algorithm, considering the cross-regional transmission costs and transaction price factors, and optimizing the transaction plan.

[0096] According to the energy trading situation, including the direction, scale and changing trend of energy trading, combined with geographic information systems and load forecasting models, the line layout and capacity configuration of the distribution network are replanned, and the siting and distribution of substations are optimized. The siting and distribution of substations are optimized to fully consider factors such as the access location, capacity size, and output characteristics of distributed energy.

[0097] The specific process of this method includes: obtaining the flow, scale and change trend data of energy transactions from the blockchain, performing time series analysis on the data, extracting periodicity and trend characteristics, using the load forecasting model, and adopting the ARIMA model based on time series to predict the load demand in different regions in the future. The forecasting formula is expressed as: in, is the load forecast value at time t, φ i and θ j is the model parameter, ∈ t It's white noise.

[0098] Integrate geographic information data, including terrain, building distribution, and road planning, analyze geographical restrictions and potential line channels in different regions, preliminarily determine the line direction based on energy trading flow and load distribution, and use the minimum spanning tree algorithm (such as Prim algorithm or Kruskal algorithm) to determine the optimal line connection method to minimize the line construction cost. The line construction cost function is C(L), where L is the line set. The goal is to find (L * ) makes C(L * )=min L C(L), based on the predicted load and distributed energy output, calculate the capacity required for lines and equipment, consider safety margins and future development needs, and appropriately increase capacity configuration. The capacity calculation formula is expressed as: C required =max(Load predicted ,Output distributed )×(1+Margin).

[0099] With the goal of minimizing line loss and maximizing power supply reliability, the particle swarm optimization algorithm is used to optimize the location of substations in combination with the access location and capacity of distributed energy sources. The planning scheme is simulated and run using simulation software to evaluate its performance indicators, such as voltage stability and power factor. The scheme is adjusted and optimized based on the evaluation results.

[0100] Embodiment 3

[0101] Establish a distributed energy quality assessment system to conduct real-time monitoring and assessment of the power quality of distributed energy, including indicators such as voltage fluctuation, frequency deviation, and harmonic content, and take corresponding adjustment measures in energy trading and distribution network planning based on the assessment results.

[0102] The specific process of this method includes: installing high-precision power quality monitoring equipment, collecting the voltage and current electrical parameters of distributed energy in real time, and using the root mean square change method to calculate the voltage fluctuation value V fluc , the formula is: Among them, V i is the voltage value at each sampling moment, V avg is the average voltage value, N is the number of sampling points, and by measuring the actual frequency f actual With standard frequency f standard The difference between the two is the frequency deviation Δf, that is: Δf = f actual -f standard , the voltage and current signals are decomposed into fundamental and harmonic components using the fast Fourier transform (FFT) algorithm. n It is expressed as: Among them, A n is the amplitude of the nth harmonic, A1 is the amplitude of the fundamental wave, and weight w is set for each indicator i, comprehensively evaluate the power quality score Q, the formula is: Q = w1 × V fluc +w2×|Δf|+w3×ΣxH n .

[0103] The comprehensive evaluation score is compared with the preset threshold to determine whether the power quality is qualified. According to the evaluation results, the price and transaction priority are adjusted in energy trading. In the distribution network planning, for areas with poor power quality, reactive compensation equipment is added and line parameters are optimized. For example, if the power quality score is lower than the threshold, the transaction price of the distributed energy is reduced in the energy transaction. The formula is expressed as: Among them, P adjusted is the adjusted price, P original is the original price and k is the adjustment factor.

[0104] Build a risk warning and response mechanism, based on the transaction data on the blockchain and the distribution network operation data, use machine learning algorithms to predict and warn of possible risks, such as energy supply shortages, excessive price fluctuations, network security threats, etc., and formulate corresponding emergency plans and response strategies.

[0105] The specific process of this method includes: obtaining energy transaction data from the blockchain, including transaction quantity, price, and information of both parties to the transaction; collecting distribution network operation data, such as voltage, current, power, and equipment status; preprocessing and feature extraction of the collected data, such as calculating the mean, standard deviation, trend and other features of the energy transaction price; extracting the power fluctuation characteristics in the distribution network operation data; using the machine learning algorithm of the decision tree for risk prediction; selecting the optimal features for splitting through information gain and Gini coefficient; and building a decision tree model. The calculation formula of feature X, category Y, and information gain IG(Y,X) is: Among them, H(Y) is the entropy of data set Y, Y v It is the data set corresponding to when the value of feature X is v.

[0106] Based on historical energy supply and demand data, a supply shortage prediction model is established. For example, a time series prediction algorithm, such as ARIMA or SARIMA model, is used to predict the difference between future energy supply and demand. The fluctuation of historical transaction price data is analyzed to establish a price fluctuation model. A GARCH model is used to capture the volatility and aggregation of prices. The formula of the GARCH model is: in, is the conditional variance, ω is a constant term, α and β are model parameters, ∈ t-1 It is the residual, monitoring network traffic and abnormal access data, and using intrusion detection algorithms to predict risks.

[0107] Based on historical data and experience, warning thresholds are set for each risk. When the risk is predicted to exceed the warning threshold, a warning signal is issued. Corresponding emergency plans are formulated for different risk types, such as adjusting energy supply strategies, initiating price stabilization mechanisms, strengthening network security protection, etc. When risks occur, response strategies are implemented and the effects are monitored in real time. Based on the effect evaluation results, the risk warning and response mechanisms are optimized and adjusted.

[0108] Promote user participation and interaction, develop user-friendly energy trading and management applications, enable users to easily participate in energy trading, view transaction records and distribution network operation status, establish a user feedback mechanism, and optimize distribution network planning and energy trading strategies based on user feedback.

[0109] The specific process of this method includes: collecting users' functional requirements and expectations for energy trading and management applications, such as transaction convenience, clarity of information display, etc., designing a simple and intuitive user interface to ensure easy operation, developing an energy trading module to support users in energy buying and selling operations, establishing a transaction record storage and query system to facilitate users to view historical transactions, obtaining real-time operating data from the distribution network monitoring system, including voltage, current, and power, and using data visualization technology to display the distribution network operation status to users in the form of charts and maps.

[0110] A feedback portal is set up in the application to facilitate users to submit opinions and suggestions. User feedback is classified and organized, for example, into transaction process issues, distribution network planning suggestions, etc. Text analysis algorithms are used to process the text content of user feedback and extract key information. Based on the analysis results of user feedback, distribution network planning and energy trading strategies are optimized. For example, if users generally report that the transaction process is complicated, the transaction steps can be simplified, the operation links can be reduced, new user feedback can be collected regularly, and the application and strategies can be continuously improved.

[0111] Strengthen coordination with traditional energy systems, establish interfaces and coordination mechanisms with traditional energy supply systems, realize the complementarity and coordinated operation of distributed energy and traditional energy, and comprehensively consider the characteristics and advantages of both in energy trading and distribution network planning.

[0112] The specific process of this method includes: defining the data exchange format and communication protocol with the traditional energy supply system, determining the frequency and real-time requirements of data transmission, collecting energy supply data from the traditional energy system, such as power generation, reserves, costs, etc., integrating it with the data of the distributed energy system, establishing a unified data warehouse, and formulating energy allocation rules. For example, when the distributed energy supply is insufficient, traditional energy is used as a supplement first, and the optimization algorithm is used to determine the best energy allocation plan to minimize costs and maximize energy utilization efficiency.

[0113] In energy trading, the price and supply stability of distributed energy and traditional energy are comprehensively considered, and the analytic hierarchy process (AHP) is used to determine the weight of each factor. The price weight is w p , the stability weight is w s , then the comprehensive score S is calculated as: S = w p ×P+w s ×S, where P represents the price score and S represents the stability score. In the distribution network planning, the line layout and equipment configuration are optimized according to the output characteristics and location distribution of distributed energy and traditional energy. For example, a genetic algorithm is used to search for the optimal planning scheme. The fitness function can consider factors such as line loss and investment cost, monitor the operating status and supply and demand of distributed energy and traditional energy in real time, and dynamically adjust the coordination strategy and energy trading plan according to the actual situation.

[0114] It will be apparent to those skilled in the art that the invention is not limited to the details of the exemplary embodiments described above and that the invention can be implemented in other specific forms without departing from the spirit or essential features of the invention. Therefore, the embodiments should be considered in all respects as exemplary and non-limiting, and the scope of the invention is defined by the appended claims rather than the foregoing description, and it is intended that all variations falling within the meaning and scope of the same elements of the claims be included in the invention. Any reference numeral in a claim should not be considered as limiting the claim to which it relates.

Claims

1. A method for planning an active distribution network, characterized in that: The method includes: Build a distributed energy trading platform based on blockchain, use the decentralized characteristics of blockchain to establish a distributed energy trading network, and design smart contracts to standardize energy trading processes and rules; Install high-precision energy metering equipment to collect data related to distributed energy, encrypt and upload it to the blockchain, and verify and process the data; Based on the energy transaction data and user needs on the blockchain, an optimization algorithm is used to formulate an energy distribution plan, giving priority to local consumption and optimizing cross-regional transactions; According to the energy trading situation, combined with geographic information systems and load forecasting models, re-plan the line layout and capacity configuration of the distribution network and optimize the site selection and distribution of substations; Establish a distributed energy quality assessment system to monitor and assess the power quality of distributed energy in real time, and take corresponding adjustment measures in energy trading and distribution network planning based on the assessment results; Build a risk warning and response mechanism, use machine learning algorithms to make predictions and warnings based on transaction data and distribution network operation data on the blockchain, and formulate corresponding emergency plans and response strategies; Develop user-friendly energy trading and management applications, establish a user feedback mechanism, and optimize distribution network planning and energy trading strategies based on user feedback; Establish interfaces and coordination mechanisms with traditional energy supply systems, realize the coordinated operation of distributed energy and traditional energy, and comprehensively consider the characteristics and advantages of both in energy trading and distribution network planning.

2. The active distribution network planning method according to claim 1, characterized in that: The method of constructing a distributed energy trading platform based on blockchain, establishing a distributed energy trading network by utilizing the decentralized characteristics of blockchain, and designing smart contracts to standardize energy trading processes and rules includes: First, the distributed energy trading network architecture is designed, the network node type is determined, and the network topology is designed using the P2P network architecture; Next, we design smart contracts and define the basic process of energy trading, including energy measurement rules, price negotiation mechanism, transaction confirmation method and settlement process; Select the blockchain type, use the practical Byzantine fault-tolerant algorithm, and the probability of nodes reaching consensus P consensus It is estimated by the following formula: consensus =(1-f) n Where, f is the proportion of failed nodes, n is the total number of nodes; Design the data structure of the blockchain and use encryption technology to ensure data security; Conduct simulated trading tests to evaluate platform performance and stability, and optimize network architecture, smart contracts, and algorithm parameters based on test results.

3. The active distribution network planning method according to claim 1, characterized in that: The method of installing high-precision energy metering equipment to collect data related to distributed energy, encrypting and uploading the data to the blockchain, and verifying and processing the data includes: Select smart meters and sensors with high-precision measurement capabilities, and install metering equipment appropriately based on the access points of distributed energy and the locations of power-consuming devices; Set the collection frequency and obtain energy-related parameter values ​​in real time through sensors and electricity meters; Use the median filter algorithm to remove noise interference in the collected data, and use the encryption algorithm to encrypt the pre-processed data; Encapsulate the encrypted data into blockchain transactions and broadcast the transaction information to nodes in the blockchain network; Calculate the hash value of the data and compare it with the hash value when it was uploaded. Verify the legitimacy of the data source through digital signatures and use threshold judgment methods to detect abnormal data. Store verified data on the blockchain and create an index.

4. The active distribution network planning method according to claim 1, characterized in that: The method comprises: formulating an energy distribution plan based on energy transaction data and user needs on the blockchain using an optimization algorithm, giving priority to local consumption, and optimizing cross-regional transactions. Obtain historical data on energy transactions from the blockchain and collect real-time demand data from users; Establish an optimization model, define the objective function, and set constraints; Use particle swarm optimization algorithm to develop energy allocation plan; According to the needs of local users and energy supply, give priority to meeting the energy needs of local users and calculate the local energy surplus and shortage; For local surplus energy, the optimal cross-regional transaction objects and transaction quantities are determined based on the optimization algorithm, and the cross-regional transmission costs and transaction price factors are considered to optimize the transaction plan.

5. The active distribution network planning method according to claim 4, characterized in that: The specific process of using the particle swarm optimization algorithm to formulate an energy allocation plan includes: Initialize the particle swarm and randomly generate a set of particle positions and velocities, each particle represents an energy allocation scheme; Calculate the fitness value, and calculate the fitness value of each particle according to the objective function; Update individual optimal and global optimal, compare the current fitness value of each particle with the individual historical optimal fitness value, update the individual optimal position, compare the fitness values ​​of all particles, and update the global optimal position; Update the velocity and position of the particle according to the following formula: i+1 =w×v i +c1×r1×(pbest i -x i )+c2×r2×(gbest-x i ), x i+1 =x i +v i+1 Among them, v i and x i are the velocity and position of particle i, w is the inertia weight, c1 and c2 are learning factors, r1 and r2 are random numbers in the range [0, 1], and pbest i is the individual optimal position of particle i, and gbest is the global optimal position.

6. The active distribution network planning method according to claim 1, characterized in that: The method of replanning the line layout and capacity configuration of the distribution network and optimizing the location and distribution of substations based on the energy trading situation, combined with the geographic information system and the load forecasting model, includes: Obtain the flow, scale and trend data of energy transactions from the blockchain, conduct time series analysis on the data, and extract periodicity and trend characteristics; Using the load forecasting model, the ARIMA model based on time series is used to predict the future load demand in different regions. The forecasting formula is expressed as: in, is the load forecast value at time t, φ i and θ j is the model parameter, ∈ t It is white noise; Integrate geographic information data to analyze geographical restrictions and potential route channels in different regions; Based on the energy transaction flow and load distribution, the line direction is preliminarily determined, and the minimum spanning tree algorithm is used to determine the optimal line connection method to minimize the line construction cost. The line construction cost function is C(L), where L is the line set. The goal is to find (L * ) makes C(L * )=min L C(L); According to the predicted load and distributed energy output, the capacity required for lines and equipment is calculated. Considering the safety margin and future development needs, the capacity configuration is appropriately increased. The capacity calculation formula is expressed as: C required =max(Load predicted ,Output distributed ×(1+margin); With the goal of minimizing line loss and maximizing power supply reliability, the particle swarm optimization algorithm is used to optimize the location of substations in combination with the access location and capacity of distributed energy resources; Use simulation software to simulate the planning scheme, evaluate its performance indicators, and adjust and optimize the scheme based on the evaluation results.

7. The active distribution network planning method according to claim 1, characterized in that: The distributed energy quality assessment system is established to monitor and assess the power quality of distributed energy in real time, and corresponding adjustment measures are taken in energy trading and distribution network planning according to the assessment results. The method includes: Install high-precision power quality monitoring equipment to collect voltage and current electrical parameters of distributed energy in real time; Calculate the voltage fluctuation value V using the root mean square change method fluc , the formula is: Among them, V i is the voltage value at each sampling moment, V avg is the average voltage value, N is the number of sampling points; By measuring the actual frequency f actual With standard frequency f standard The difference between the two is the frequency deviation Δf, that is: Δf = f actual -f standard ; The voltage and current signals are decomposed into fundamental and harmonic components using the fast Fourier transform algorithm. n It is expressed as: Among them, A n is the amplitude of the nth harmonic, A1 is the amplitude of the fundamental wave; Set weight w for each indicator i , comprehensively evaluate the power quality score Q, the formula is: Q = w1 × V fluc +w2×|Δf|+w3×Σ n H n ; Compare the comprehensive evaluation score with the preset threshold to determine whether the power quality is qualified; Based on the evaluation results, prices and transaction priorities are adjusted in energy trading, and in distribution network planning, reactive power compensation equipment is added and line parameters are optimized for areas with poor power quality.

8. The active distribution network planning method according to claim 1, characterized in that: The risk warning and response mechanism is constructed based on the transaction data and distribution network operation data on the blockchain, using machine learning algorithms for prediction and warning, and formulating corresponding emergency plans and response strategies. The method includes: Obtain energy transaction data from blockchain and collect distribution network operation data; Preprocess and extract features from the collected data to extract power fluctuation features from distribution network operation data; The decision tree machine learning algorithm is used for risk prediction. The optimal features are selected for splitting through information gain and Gini coefficient to build a decision tree model. The calculation formula of feature X, category Y, and information gain IG(Y,X) is: Among them, H(Y) is the entropy of data set Y, Y v It is the data set corresponding to the value of feature X when it is v; Build a supply shortage prediction model based on historical energy supply and demand data; Analyze the fluctuation of historical transaction price data, establish a price fluctuation model, and use the GARCH model to capture the volatility and aggregation of prices. The formula of the GARCH model is: in, is the conditional variance, ω is a constant term, α and β are model parameters, ∈ t-1 is the residual; Monitor network traffic, abnormal access data, and use intrusion detection algorithms to predict risks; Based on historical data and experience, a warning threshold is set for each risk. When the predicted risk exceeds the warning threshold, a warning signal is issued.

9. The active distribution network planning method according to claim 1, characterized in that: The method comprises developing a user-friendly energy trading and management application, establishing a user feedback mechanism, and optimizing distribution network planning and energy trading strategies based on user feedback. Collect user functional requirements and expectations for energy trading and management applications; Design a simple and intuitive user interface, develop an energy trading module, support users in energy buying and selling operations, and establish a transaction record storage and query system; Obtain real-time operation data from the distribution network monitoring system and use data visualization technology to display the distribution network operation status to users in the form of charts and maps; Set up a feedback portal in the application to categorize and organize user feedback; Use text analysis algorithms to process the text content of user feedback, extract key information, and optimize distribution network planning and energy trading strategies based on the analysis results of user feedback; Regularly collect new user feedback to continuously improve applications and strategies.

10. The active distribution network planning method according to claim 1, characterized in that: The method of establishing an interface and coordination mechanism with the traditional energy supply system to realize the coordinated operation of distributed energy and traditional energy, and comprehensively considering the characteristics and advantages of both in energy trading and distribution network planning, includes: Define the data exchange format and communication protocol with traditional energy supply systems, and determine the frequency and real-time requirements of data transmission; Collect energy supply data from traditional energy systems, integrate it with data from distributed energy systems, and establish a unified data warehouse; Formulate energy allocation rules and use optimization algorithms to determine the best energy allocation plan to minimize costs and maximize energy efficiency; In energy trading, the price and supply stability of distributed energy and traditional energy are comprehensively considered, and the weight of each factor is determined using the hierarchical analysis method. The price weight is w p , the stability weight is w s , then the comprehensive score S is calculated as: S = w p ×P+w s ×S, where P represents the price score and S represents the stability score; In distribution network planning, optimize line layout and equipment configuration according to the output characteristics and location distribution of distributed energy and traditional energy; Monitor the operating status and supply and demand of distributed energy and traditional energy in real time, and dynamically adjust coordination strategies and energy trading plans based on actual conditions.

Images