Medium and long term spot green certificate fused intelligent power transaction management platform

Abstract

The invention discloses an intelligent power transaction management platform for medium-and-long-term spot green certificate fusion, relates to the technical field of power transaction management, and aims at realizing the purpose of realizing high-speed power transaction by synchronously collecting real-time data and generating a dynamic reference vector by adopting linear optimization as a unified benchmark price sequence of cross-time scale transaction. Calculating a cross fluctuation coupling index and an evidence power synchronization deviation index by using the vector, and generating a collaborative risk adjustment coefficient through a Gaussian-Laplacian mixed risk model to guide risk management; assembling a hedging packet based on the smart contract, atomizing and locking power and a corresponding green certificate, and ensuring compliance and traceability by means of a block chain; the hedging packet profit and loss and the deposit state are tracked in real time, and a self-adaptive threshold value is adopted to trigger addition or release of the deposit; iteratively correcting the reference vector by using settlement profit and loss data through the prediction model; price discovery, renewable energy source integration and market stability are remarkably improved, and economic and environmental double benefits are provided.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of power transaction management, in particular to an intelligent power transaction management platform integrating medium and long-term spot green certificates. BACKGROUND

[0002] In recent years, the power industry has undergone significant changes, driven by the rapid integration of renewable energy sources such as wind and solar power. While these renewable energy sources are beneficial to the environment, they have introduced intermittency and unpredictability into power supply, increasing the complexity of grid management. At the same time, the rise of electric vehicles, smart technology, and industrial automation has led to changing consumption patterns, requiring more flexible and responsive power transaction mechanisms. Against this background, medium and long-term contracts, spot markets, and green certificates (green certificates) each play a role in providing price stability, enabling real-time adjustments, and promoting sustainability. However, these transaction components usually operate independently under different platforms and regulatory frameworks, limiting their overall effectiveness. This fragmentation raises a key technical problem: the lack of an integrated platform that unifies medium and long-term contracts, spot markets, and green certificates. This deficiency is particularly evident in practical application scenarios. For example, when wind power output fluctuates dramatically due to sudden weather changes, spot market prices may drop rapidly, while medium and long-term contract prices cannot be adjusted in time based on static benchmarks, leading to risks of price misalignment and improper resource allocation for market participants. At the same time, the independent trading of green certificates makes it difficult for enterprises to match power consumption with renewable energy certificates in real time, especially when strict environmental compliance requirements need to be met, and may face penalties for non-compliance due to untimely verification.

[0003] In addition, this problem is further exacerbated in scenarios of high demand (such as summer peak electricity consumption) or supply shortages (such as insufficient wind power), as the lack of an integrated platform makes it impossible to effectively coordinate different market types, which may lead to real-time imbalance between supply and demand in the power grid, threatening system stability. If this problem is not addressed, market participants will face higher transaction costs and risks, weakening incentives for investment in renewable energy.

[0004] Therefore, the present application provides an intelligent power transaction management platform integrating medium and long-term spot green certificates. SUMMARY

[0005] (I) Technical problems solved In view of the deficiencies of the prior art, the present application provides a medium and long-term spot green certificate integrated intelligent power transaction management platform, which synchronously collects real-time data, generates a dynamic reference vector by linear optimization, uses the vector to calculate a cross-volatility coupling index and a certificate-power synchronous deviation index, and generates a synergistic risk adjustment coefficient by a Gaussian-Laplacian hybrid risk model to guide risk management; assembles a hedging package based on a smart contract, atomically locks power and its corresponding green certificates, and ensures compliance and traceability by means of a blockchain; tracks the profit and loss and margin state of the hedging package in real time, and triggers additional or released margin by using an adaptive threshold; iteratively corrects the reference vector by using settlement profit and loss data through a prediction model; significantly improves price discovery, renewable energy integration and market stability, and solves the technical problems described in the background art.

[0006] (Two) Technical solutions To achieve the above object, the present application is implemented by the following technical solutions: a medium and long-term spot green certificate integrated intelligent power transaction management platform, comprising a data optimization module, which collects unit operation data, weather forecast data and matching instructions, generates a dynamic reference vector by linear optimization, and uses the vector as a benchmark price sequence for cross-year, monthly, day-ahead and real-time transactions; A risk modeling module generates a cross-volatility coupling index and a certificate-power synchronous deviation index based on the dynamic reference vector, inputs the index into a Gaussian-Laplacian hybrid risk model, and outputs a synergistic risk adjustment coefficient; A contract assembly module assembles a smart contract hedging package that atomically locks power and green certificates according to the synergistic risk adjustment coefficient, and ensures the unalterability and traceability of the hedging package by recording through a blockchain; A real-time adjustment module tracks the profit and loss and margin state of the hedging package in real time, triggers additional or released margin according to an adaptive threshold, and writes the updated results into a risk pool; A price correction module iteratively corrects the dynamic reference vector by using settlement profit and loss trajectories and the cross-volatility coupling index and the certificate-power synchronous deviation index, and writes the benchmark price to the next round of transactions.

[0007] Further, the unit operation data, weather forecast data and matching instructions comprise: The operation state of the unit is monitored in real time by a sensor to obtain unit operation data; weather forecast data is obtained from a weather station or satellite data; matching instructions are obtained from a transaction platform; and the unit operation data, weather forecast data and matching instructions are synchronized to a unified time sequence event bus.

[0008] Furthermore, the step of generating the dynamic reference vector through linear optimization includes: taking the unit operation data, meteorological forecast data, and matching instructions as inputs, using a linear programming algorithm to solve the objective function to minimize price fluctuations and satisfy supply and demand balance constraints, thereby generating the dynamic reference vector.

[0009] Furthermore, the generation of the cross-fluctuation coupling index includes: performing rolling cross-correlation calculation on the spot node electricity price and the high-pass filtered renewable power prediction error, applying an exponential decay kernel, and generating the cross-fluctuation coupling index to reflect the coupling relationship between electricity price and power fluctuation.

[0010] Furthermore, the generation of the certificate-electricity synchronization deviation index includes: calculating the standardized difference between the green certificate equivalent price and the nodal electricity price, and then multiplying it by the local renewable energy penetration rate to generate the certificate-electricity synchronization deviation index, so as to quantify the synchronization deviation between green certificates and electricity prices.

[0011] Furthermore, the Gaussian-Laplace hybrid risk model uses the cross-volatility coupling index and the securities-electronic synchronization deviation index as inputs, employs a hybrid model of Gaussian and Laplace distributions to calculate the risk probability, and outputs the collaborative risk adjustment coefficient to adjust trading risk.

[0012] Furthermore, the smart contract hedging package for atomically locking electricity and green certificates includes: extracting electricity contracts and corresponding green certificates from the trading pool according to the collaborative risk adjustment coefficient, and atomically locking the electricity contracts and green certificates through a smart contract to form an indivisible hedging package.

[0013] Furthermore, ensuring the immutability and traceability of the hedging package through blockchain records includes: applying a hash function to the data of the hedging package to generate a unique identifier, recording the hedging package and its unique identifier in the distributed ledger of the blockchain, and reaching consensus among all network nodes through a consensus mechanism.

[0014] Furthermore, the adaptive threshold is dynamically adjusted based on market volatility and the profit and loss of the hedging package, including: calculating market volatility, setting a margin call threshold and a release threshold, wherein the margin call threshold is the minimum margin requirement plus the product of the risk coefficient, market volatility, and risk exposure, and the release threshold is the margin call threshold minus the adjustment parameter.

[0015] Furthermore, the iterative correction of the dynamic reference vector includes: using the gradient descent method, based on the correlation between the settlement profit and loss trajectory and the cross-volatility coupling index and the securities-electronic synchronization deviation index, calculating the adjustment amount, and updating the benchmark price of the dynamic reference vector to optimize the accuracy of the next round of trading.

[0016] (III) Beneficial Effects The application provides a long-term spot green certificate integrated intelligent power transaction management platform, which has the following beneficial effects: The cross-volatility coupling index and the certificate-power synchronization deviation index quantize market volatility and certificate-power decoupling risk in real time, and generate a synergistic risk adjustment coefficient through a Gaussian-Laplacian hybrid risk model, accurately trigger the generation of an intelligent contract hedge package, and significantly improve the accuracy of price discovery.

[0017] The intelligent contract hedge package realizes the unique mapping of electricity and green certificates through atomic locking technology, ensuring that the correspondence between each unit of electricity and green certificates is clear and accurate. The risk pool centrally stores risk data, supports model training and verification, and further improves the accuracy of accounting.

[0018] The dynamic reference vector provides a stable price benchmark for new energy transactions by smoothing price fluctuations. The cross-volatility coupling index and the synergistic risk adjustment coefficient help identify and respond to risks caused by new energy output fluctuations, reducing transaction uncertainty. The adaptive threshold mechanism dynamically manages margin, optimizing capital utilization and reducing the cost pressure on market participants. The prediction model continuously corrects the benchmark price, further improving the adaptability of the price and significantly reducing the risk exposure of new energy transactions.

[0019] The intelligent contract hedge package provides an efficient risk hedging tool for market participants, reducing transaction uncertainty. The adaptive threshold mechanism dynamically adjusts margin requirements, ensuring the flexibility of capital management. The risk pool and the prediction model continuously optimize transaction strategies, further enhancing market stability.

[0020] The dynamic reference vector provides a unified price benchmark for the entire transaction system, the cross-volatility coupling index and the certificate-power synchronization deviation index quantize risks in real time, the synergistic risk adjustment coefficient accurately triggers the hedging strategy, the intelligent contract hedge package ensures transaction compliance, the adaptive threshold optimizes capital utilization efficiency, and the prediction model continuously improves price accuracy. BRIEF DESCRIPTION OF DRAWINGS

[0021] Figure 1 The figure is a structural schematic diagram of the intelligent power transaction management platform of the application. DETAILED DESCRIPTION

[0022] The technical solutions in the embodiments of the application will be described clearly and completely below with reference to the drawings in the embodiments of the application. Obviously, the described embodiments are only part of the embodiments of the application, not all embodiments. Based on the embodiments in the application, all other embodiments obtained by those of ordinary skill in the art without creative labor fall within the scope of the application.

[0023] Referring to Figure 1 The present application provides a long-term spot green certificate integrated intelligent power trading management platform, comprising, Step one, using high-frequency data acquisition technology to obtain real-time unit operation data, weather forecast data and market matching instructions, and aligning them by time stamp, integrating them into a time sequence event bus to form a unified time sequence data stream; based on this time sequence data stream, a linear optimization algorithm is applied to generate a dynamic reference vector as a benchmark price sequence, which meets the supply and demand balance, price smoothing and market rule constraints; the benchmark price sequence is directly applied to the pricing mechanism of annual trading, monthly trading, day-ahead trading and real-time trading to unify the pricing standards of different trading cycles.

[0024] Step 101, data synchronization acquisition Through high-frequency data acquisition technology, real-time unit operation data, weather forecast data and market matching instructions are obtained to ensure the real-time and consistency of the data. Unit operation data includes power generation and load level, which reflects the actual operation state of the generator set; weather forecast data includes wind speed and solar irradiance, which determines the power generation capacity of new energy; market matching instructions include transaction volume and transaction price, which reflect the dynamic changes of market transactions. In the acquisition process, a time stamp is added to each set of data to ensure that all data are recorded under the same time reference. This time alignment eliminates data bias caused by time difference in acquisition, providing accurate input basis for subsequent time series processing.

[0025] Through high-frequency data acquisition technology and time stamp alignment, the real-time and consistency of unit operation data, weather forecast data and market matching instructions are ensured.

[0026] The collected unit operation data, weather forecast data and market matching instructions are integrated into a time sequence event bus to form a unified time sequence data stream. The time sequence event bus adopts a high-concurrency processing mechanism, arranges all data in chronological order, and marks the corresponding time stamp for each data. This mechanism ensures the continuity and time consistency of the data stream. By integrating multi-source data into structured time sequence data stream, the system can efficiently process heterogeneous data from different sources, providing reliable input support for subsequent optimization calculation, thereby improving the overall processing efficiency.

[0027] Multi-source data is integrated into time sequence data stream by using high-concurrency processing mechanism to ensure its time sequence and continuity. It can improve the efficiency and structure of data processing, so that the system can quickly respond to the input needs of multi-source data.

[0028] Step 102, generation of dynamic reference vector Based on the time series data stream in the time series event bus, a linear optimization algorithm is applied to generate a dynamic reference vector as a benchmark price sequence. The linear optimization algorithm achieves this by balancing the relationship between power generation and market demand and reducing the sharp changes in price. Specifically, the difference between the total power generation of the generator set and the market demand is calculated at each time point, and the difference is required to be as close to zero as possible to meet the balance between supply and demand.

[0029] At the same time, by minimizing the amplitude of the price change between adjacent time points, the smooth transition of the price sequence is ensured. In addition, the price range is set as a constraint according to market rules, ensuring that the generated benchmark price sequence is within a reasonable range. This method generates a benchmark price sequence that not only reflects the market supply and demand dynamics but also maintains price stability.

[0030] Using a linear optimization algorithm to generate a benchmark price sequence can simultaneously meet the requirements of supply and demand balance, price smoothing, and market rule constraints, and the generated benchmark price sequence can reduce the sharp fluctuations in price, providing a stable and reasonable price reference for transactions of different time scales.

[0031] Step 103, application of the benchmark price sequence The generated dynamic reference vector as a benchmark price sequence is directly used in the pricing mechanism of annual transactions, monthly transactions, day-ahead transactions, and real-time transactions. For annual transactions and monthly transactions, the static quotes of long-term contracts are adjusted based on the benchmark price sequence; for day-ahead transactions and real-time transactions, the node price deviation of the spot market is corrected based on the benchmark price sequence.

[0032] Through a unified benchmark price sequence, different types of transactions of different time scales can be effectively connected, reducing the price difference between long-term transactions and short-term transactions. This consistent application supports the operation of transaction subjects under a unified price system, improving the efficiency and accuracy of market transactions. Applying the benchmark price sequence to multiple transaction types and unifying the pricing standards of different transaction periods can reduce the price deviation across periods.

[0033] Step one, through data synchronization acquisition, real-time consistent input data is obtained, structured time series data stream is formed through time series event bus, and then linear optimization algorithm is used to generate benchmark price sequence, finally the sequence is applied to transaction pricing of multiple time scales. This process design is closely connected, ensuring that every step from data acquisition to price application serves the unified transaction optimization goal.

[0034] Step two, using the dynamic reference vector to extract the spot market node price sequence and renewable energy power prediction error, processing the power prediction error through high-pass filtering to extract the high-frequency fluctuation component, calculating the cross-correlation coefficient of the spot node price and the high-frequency fluctuation component within the rolling time window and applying an exponential decay kernel to generate a cross-fluctuation coupling index; The spot node electricity price and the green certificate equivalent price are extracted, the standardized difference value of the two is calculated and multiplied by the local renewable penetration rate to generate a certificate-electricity synchronization deviation index; the cross volatility coupling index and the certificate-electricity synchronization deviation index are input into a Gaussian-Laplace hybrid risk model, the distribution parameters are determined by fitting historical data, the cumulative distribution values of the two indexes are calculated and weighted to generate a collaborative risk adjustment coefficient, which is input into the risk engine.

[0035] Step 201, generating a cross volatility coupling index First, the electricity price sequence of a certain node in the spot market and the power prediction error of renewable energy are extracted using the dynamic reference vector generated in step one. Next, the difference between the power prediction value and the actual output of renewable energy is calculated to obtain the power prediction error. Then, high-pass filtering is applied to the power prediction error to extract the high-frequency fluctuation component reflecting the rapid change of new energy output. On this basis, within a predetermined rolling time window, the cross correlation coefficient of the spot node electricity price and the high-frequency fluctuation component is calculated to quantify the dynamic correlation between the two.

[0036] The calculation method of the cross correlation coefficient is to sum the product of the electricity price sequence and the high-frequency fluctuation component, and then divide the result by the product of the respective fluctuation amplitudes. Subsequently, the cross correlation coefficient is subjected to exponential decay kernel processing, so that the weight of recent data within the time window is greater, and finally the cross volatility coupling index is generated. The cross volatility coupling index can reflect the sensitivity of spot electricity price to new energy output fluctuation in real time, and is used as a quantitative indicator of market volatility characteristics for subsequent risk assessment.

[0037] The sensitivity of spot electricity price to new energy output fluctuation is an important factor affecting market price fluctuation, and the dynamic correlation between the two needs to be quantified in real time. The cross volatility coupling index provides an accurate measure of market volatility characteristics, which can provide reliable market support for risk assessment, support the accurate input of the Gaussian-Laplace hybrid risk model, and enhance the accuracy of risk assessment.

[0038] Step 202, generating a certificate-electricity synchronization deviation index Based on the dynamic reference vector generated in step one, the spot node electricity price and the green certificate equivalent price are extracted.

[0039] Then, the difference between the green certificate price and the spot node electricity price is calculated, and the average amplitude of the difference in the rolling time window is standardized to obtain the standardized difference, which is used to reflect the deviation degree of the two prices. Then, the standardized difference is multiplied by the local renewable penetration rate, i.e. the proportion of renewable energy generation to total power generation, to generate a certificate-electricity synchronization deviation index. The certificate-electricity synchronization deviation index, by combining the renewable penetration rate, makes the risk degree of certificate-electricity decoupling related to the importance of renewable energy in the power system, as a measure of certificate-electricity synchronization, for subsequent risk analysis.

[0040] The decoupling of green certificate price and electricity price directly affects the compliance and accuracy of enterprise accounting, and the risk characteristics need to be quantified. The certificate-electricity synchronization deviation index provides a key measure of certificate-electricity synchronization, which can provide necessary data support for the Gaussian-Laplace mixed risk model to improve the comprehensiveness of risk analysis.

[0041] Step 203, Gaussian-Laplace mixed risk model calculation The generated cross volatility coupling index and certificate-electricity synchronization deviation index are input into the Gaussian-Laplace mixed risk model for processing. This model assumes that the risk distribution is composed of Gaussian distribution and Laplace distribution, where Gaussian distribution is used to capture the normal volatility characteristics of the market, and Laplace distribution is used to capture the extreme event characteristics of the market.

[0042] The distribution parameters are determined by fitting historical data, and the cumulative distribution values of the cross volatility coupling index and the certificate-electricity synchronization deviation index are calculated respectively. Subsequently, the cumulative distribution values of the two are weighted and averaged to generate a synergistic risk adjustment coefficient as a measure of comprehensive risk. The Gaussian-Laplace mixed risk model can comprehensively evaluate the risks brought by market volatility and certificate-electricity decoupling, and provide accurate risk parameters for subsequent risk management.

[0043] Market risk contains both normal volatility and extreme events, and a single distribution model cannot fully describe the risk distribution, while a mixed model can comprehensively capture these two characteristics. By generating a synergistic risk adjustment coefficient, this model can provide an accurate measure of comprehensive risk.

[0044] The synergistic risk adjustment coefficient calculated by the Gaussian-Laplace mixed risk model is used as the output result and directly transmitted to the risk engine in step three. The synergistic risk adjustment coefficient integrates the information of market volatility and certificate-electricity decoupling risk, which is used to guide the generation of hedge packs and the formulation of risk management strategies, ensuring that step three can be adjusted according to the real-time market risk state. The synergistic risk adjustment coefficient integrates the multi-dimensional risk information of market volatility and certificate-electricity decoupling, which can provide guidance for hedge pack generation and risk strategy formulation, ensuring the pertinence and real-time of risk management, and improving the risk control ability.

[0045] Step two quantifies the dynamic correlation between spot electricity price and new energy output fluctuation and the risk level of electricity price decoupling by generating cross- volatility coupling index and certificate-electricity synchronization deviation index. Subsequently, the above indexes are processed using a Gaussian-Laplacian hybrid risk model to generate a coordinated risk adjustment coefficient, providing a comprehensive risk measurement for the risk engine in step three.

[0046] Step three, the risk engine receives the coordinated risk adjustment coefficient in real time, determines whether to extract electricity contracts and corresponding green certificates from the transaction pool according to the preset threshold, executes atomic locking through the smart contract to generate hedging packages, processes the hedging package data through a hash function, writes it to the blockchain, records it to the distributed ledger through the consensus mechanism, and continuously monitors the changes in the coordinated risk adjustment coefficient, dynamically adjusts the locking conditions or generation frequency of the hedging package according to its numerical value, executes the adjustment through the conditional update function of the smart contract, and rewrites it to the blockchain.

[0047] Step 301, the risk engine receives the coordinated risk adjustment coefficient The risk engine receives the coordinated risk adjustment coefficient output by the Gaussian-Laplacian hybrid risk model generated in step two in real time. The coordinated risk adjustment coefficient is a comprehensive risk indicator derived from the analysis of cross-volatility coupling index and certificate-electricity synchronization deviation index, used to reflect the coupling degree of electricity price and green certificate price fluctuation and the risk level of electricity and green certificate decoupling.

[0048] The calculation process is as follows: first, extract the historical fluctuation data of electricity price and green certificate price, analyze their synchronization and deviation, then integrate these data into a numerical value to reflect the dynamic changes of market risk. The risk engine takes the coordinated risk adjustment coefficient as the input of the dynamic threshold, which is used to determine whether to generate a hedging package.

[0049] The risk engine receives the coordinated risk adjustment coefficient in real time, which can timely perceive the coupling degree of electricity price and green certificate price fluctuation and the changes in decoupling risk. The coordinated risk adjustment coefficient integrates the cross-volatility coupling index and the certificate-electricity synchronization deviation index, providing a comprehensive risk quantification basis, enabling the risk engine to dynamically adjust the strategy according to the market state, ensuring that the hedging package is generated to match the market risk level.

[0050] Step 302, assembly of smart contract hedging package The risk engine assembles a smart contract hedging package containing electricity and corresponding green certificates in real time according to the numerical value of the coordinated risk adjustment coefficient. The specific process is as follows: set a preset threshold based on historical market data and risk tolerance as the judgment standard for the coordinated risk adjustment coefficient. When the numerical value of the coordinated risk adjustment coefficient exceeds the preset threshold, the risk engine extracts electricity contracts and corresponding green certificates from the transaction pool to ensure that the quantities and sources of the two are matched one by one.

[0051] Then, the electricity contract and the green certificate are atomically locked by the smart contract, forming a hedge package. The structure of the hedge package includes the electricity contract, the green certificate, and the locking condition, which is determined by the value of the synergistic risk adjustment coefficient, for example, it is stipulated that the hedge package cannot be split when the synergistic risk adjustment coefficient maintains a high level. The locking process is automatically completed by the pre-compiled logic of the smart contract, ensuring that the binding of electricity and green certificates is irreversible.

[0052] By assembling the hedge package through the smart contract, its automated execution capability ensures the efficiency and consistency of the binding of electricity contracts and green certificates. The atomic locking mechanism prevents the separation of electricity and green certificates in transactions, realizes the unique correspondence of electricity and green certificates, and reduces the risk of market participants due to price fluctuations and policy requirements.

[0053] Step 303, blockchain writing and traceability The assembled hedge package is written into the blockchain to ensure the non-tamperability and traceability of transaction data. The specific steps are as follows: apply a hash function to the data of the hedge package (including the electricity contract, the green certificate, and the locking condition) to generate a unique identifier. The process of generating a unique identifier is to concatenate the serialized data of the electricity contract, the green certificate, and the locking condition, and then calculate a fixed-length hash value through the SHA-256 hash function. Record the hedge package and its unique identifier to the distributed ledger of the blockchain, and reach an agreement through the consensus mechanism (such as proof of work or proof of stake) among all network nodes. And provide a query interface to allow market participants to retrieve the transaction history, status, and source information of the hedge package through the unique identifier.

[0054] Writing the hedge package into the blockchain ensures the security of transaction data using its tamper-proof feature, and the distributed ledger and consensus mechanism provide transparency and consistency of transactions.

[0055] Step 304, dynamic management of hedge package The risk engine continuously monitors market risks and the status of the hedge package, and dynamically adjusts the strategy of the hedge package according to the real-time update of the synergistic risk adjustment coefficient. Among them: when the value of the synergistic risk adjustment coefficient drops below the preset threshold, the risk engine removes part of the locking conditions of the hedge package, releasing the liquidity of the electricity contract or the green certificate.

[0056] When the value of the synergistic risk adjustment coefficient rises above a higher threshold, the risk engine increases the generation frequency of the hedge package or strengthens the constraints of the locking condition. The adjustment process is executed through the condition update function of the smart contract, and the updated hedge package is re-written into the blockchain to ensure that the adjusted state is recorded and verified.

[0057] According to the real-time changes of the synergistic risk adjustment coefficient, the hedge package is dynamically adjusted, so that the strategy can adapt to the fluctuations of market risk. When the risk decreases, liquidity is released to avoid excessive locking of resources; when the risk increases, the constraints are strengthened to enhance the protection and improve the flexibility of risk management and the efficiency of resource utilization, reducing the cash flow pressure on market participants due to market fluctuations, while maintaining the effectiveness of the hedging measures.

[0058] Step three, through the risk engine, the intelligent contract hedge package of electricity and green certificates is assembled in real time according to the synergistic risk adjustment coefficient, and the blockchain technology is used to ensure the non-tamperability and traceability of the transaction, effectively solving the risk problems caused by the price fluctuations and disconnection of electricity and green certificates. The atomic locking of the smart contract realizes the unique mapping of electricity and green certificates, the writing and tracing functions of the blockchain provide transparency and compliance guarantee for the transaction, and the dynamic management mechanism optimizes the hedging strategy according to the changes of market risk.

[0059] Step four, continuously monitor the profit and loss of the hedge package and the margin account state of the market participants, calculate the profit and loss of the hedge package by multiplying the difference between the market electricity price and the locked electricity price by the electricity quantity, plus the difference between the market green certificate price and the locked green certificate price by the green certificate quantity, determine the margin account balance and the frozen amount; according to the market volatility and the profit and loss of the hedge package, dynamically adjust the additional threshold and the release threshold of the margin, the market volatility is calculated using the rolling average absolute deviation of the recent price change rate, the additional threshold is set to the minimum margin requirement plus the product of the risk coefficient, the market volatility and the risk exposure, the release threshold is set to the additional threshold minus the adjustment parameter; when the margin account balance is lower than the additional threshold, the additional operation is triggered, the additional amount is the difference between the additional threshold and the margin account balance, when the margin account balance is higher than the release threshold and the profit and loss of the hedge package is positive, the release operation is triggered, the release amount is the difference between the margin account balance and the release threshold, the operation is automatically executed through the smart contract and recorded to the blockchain; write the margin adjustment record and the profit and loss data of the hedge package into the risk pool for the prediction model to call.

[0060] Step 401, real-time tracking of the profit and loss of the hedge package and the margin state Real-time monitoring of the profit and loss of each hedge package and the margin account state of the market participants. The calculation process of the profit and loss is based on the difference between the current market price and the locked price of the electricity contract and green certificate in the hedge package. Among them: first, take the current market electricity price minus the locked electricity price of the electricity contract in the hedge package, multiply this difference by the electricity quantity in the hedge package to get the profit and loss of the electricity part; then take the current market green certificate price minus the locked price of the green certificate in the hedge package, multiply this difference by the number of green certificates in the hedge package to get the profit and loss of the green certificate part; finally, add the profit and loss of the electricity part and the profit and loss of the green certificate part to get the total profit and loss of the hedge package.

[0061] The determination of the margin state is achieved by checking the relationship between the margin account balance and the frozen amount of the market subject. The reason for real-time tracking of the hedging package profit and loss and the margin state is that this process can timely reflect the risk exposure and financial pressure of the market subject, providing data support for subsequent dynamic adjustment. Its benefits include ensuring that the financial performance of the hedging package and the margin level remain consistent with market dynamics, and improving the response speed of risk management.

[0062] Real-time tracking of the hedging package profit and loss and the margin state can timely reflect the risk exposure and financial pressure of the market subject, ensure that the financial performance of the hedging package and the margin level remain consistent with market dynamics, and improve the response speed of risk management.

[0063] Step 402, adaptive threshold setting According to market fluctuations and hedging package profit and loss, the additional threshold and release threshold of the margin are dynamically adjusted. The market volatility is calculated using the rolling average absolute deviation of recent price changes, that is, by calculating the fluctuation range of market prices in a certain period of time, taking the average of the absolute values to represent the degree of market volatility. The setting process of the margin additional threshold is as follows: based on the minimum margin requirement, add a risk factor multiplied by the market volatility, and then multiply by the risk exposure of the market subject to obtain the additional threshold. The setting of the margin release threshold is to subtract an adjustment parameter from the additional threshold to ensure that the release threshold is lower than the additional threshold. By dynamically adjusting, the fixed threshold can avoid the low efficiency of funds or insufficient risk coverage caused by market changes, improve the flexibility of margin management, and ensure that the funds occupied are matched with the risk level.

[0064] Step 403, triggering the addition or release of the margin According to the results of real-time tracking of the hedging package profit and loss and the margin state, and the adaptive threshold setting standard, the addition or release of the margin is executed. The specific rules are as follows: when the margin account balance is lower than the additional threshold, the addition operation is triggered, and the amount of addition is the difference between the additional threshold and the current margin account balance; when the margin account balance is higher than the release threshold and the hedging package profit and loss is positive, the release operation is triggered, and the amount of release is the difference between the current margin account balance and the release threshold. The addition or release operation is automatically completed through the smart contract, and the operation record is stored in the blockchain.

[0065] Triggering the addition or release of the margin can quickly respond to market changes, ensure that the margin level and risk exposure are adjusted synchronously, reduce the cash flow pressure caused by excessive freezing of funds, and at the same time, supplement the margin in a timely manner when the risk rises, ensuring transaction safety.

[0066] Step 404, updating the risk pool and providing model training calls The margin adjustment record and the hedge package profit and loss data are written into the risk pool to support subsequent model training. Among them: after each execution of margin addition or release, the operation details (including operation time, amount and trigger reason) are recorded to the risk pool; the profit and loss data of the hedge package and the market volatility rate data are regularly updated to the risk pool; the data in the risk pool are called by the prediction model of step five through a preset interface, and are used for iterative correction of the dynamic reference vector.

[0067] By centrally storing risk-related data, the prediction model can obtain market feedback, improve prediction accuracy, provide real-time data support for step five, and enhance the self-adaptive ability of the prediction model and the intelligent level of the trading platform.

[0068] By tracking the profit and loss of the hedge package and the margin state in real time, combining the adaptive threshold setting mechanism, dynamically triggering the addition or release of the margin, and updating the related data to the risk pool, the fine and dynamic optimization of the margin management is realized in view of the characteristics of the market volatility and dynamic change of risk exposure in new energy trading. Through real-time tracking and threshold adjustment, the standby cost pressure of market participants is effectively reduced, while the safety and compliance of trading are ensured.

[0069] Step five, the profit and loss data of the smart contract hedge package are extracted from the risk pool to generate a profit and loss trajectory; the correlation coefficients of the cross volatility coupling index and the profit and loss trajectory, and the correlation coefficients of the certificate-electricity synchronization deviation index and the profit and loss trajectory are calculated, which are used to evaluate the influence of market volatility and certificate-electricity decoupling risk on the profit and loss trajectory; the dynamic reference vector is corrected based on the gradient descent method, and the correction amount is determined by the weighted sum of the adjustment contributions of the cross volatility coupling index and the certificate-electricity synchronization deviation index; the dynamic reference vector is updated and written back to the market matching logic, and a new round of trading is started.

[0070] Step 501, extract the profit and loss trajectory of the hedge package The profit and loss data of the smart contract hedge package are extracted from the risk pool of step four to form a time series of profit and loss trajectory.

[0071] The calculation process of the profit and loss trajectory is as follows: first, subtract the locking price of the electricity quantity contract in the hedge package from the current market electricity price, multiply the obtained difference by the electricity quantity in the hedge package, and obtain the profit and loss of the electricity quantity part; then subtract the locking price of the green certificate in the hedge package from the current market green certificate price, multiply the obtained difference by the number of green certificates in the hedge package, and obtain the profit and loss of the green certificate part; finally, add the profit and loss of the electricity quantity part and the profit and loss of the green certificate part to obtain the total profit and loss of the hedge package at that time point.

[0072] The profit and loss data directly reflects the deviation between market price and the hedge package locking price, and can be used as the core basis for evaluating the accuracy of the dynamic reference vector. By quantifying the relationship between market price deviation and hedge package performance, it provides reliable data support for the correction of the dynamic reference vector based on actual trading results.

[0073] Step 502, evaluate the correlation between cross-volatility coupling index and certificate-electricity synchronization deviation index Using the cross-volatility coupling index and the certificate-electricity synchronization deviation index generated in step two, calculate the correlation between the two indexes and the profit and loss trajectory. Among them: Set a rolling time window, within which first calculate the covariance between the cross-volatility coupling index and the profit and loss trajectory, then calculate the standard deviation of the cross-volatility coupling index within the window and the standard deviation of the profit and loss trajectory within the window, divide the covariance by the product of the two standard deviations to obtain the correlation coefficient between the cross-volatility coupling index and the profit and loss trajectory; then in the same way, calculate the covariance between the certificate-electricity synchronization deviation index and the profit and loss trajectory, divide by the product of the standard deviation of the certificate-electricity synchronization deviation index within the window and the standard deviation of the profit and loss trajectory within the window, to obtain the correlation coefficient between the certificate-electricity synchronization deviation index and the profit and loss trajectory.

[0074] The evaluation of the cross-volatility coupling index and the certificate-electricity synchronization deviation index respectively quantifies the market volatility and the certificate-electricity decoupling risk. By analyzing their correlation with the profit and loss, the main driving factors of the benchmark price deviation can be revealed, and the influence of the cross-volatility coupling index and the certificate-electricity synchronization deviation index on the profit and loss can be determined, providing a clear directional basis for the adjustment of the dynamic reference vector.

[0075] Step 503, iterative optimization of dynamic reference vector Based on the correlation between the profit and loss trajectory and the cross-volatility coupling index and the certificate-electricity synchronization deviation index, the dynamic reference vector in step one is corrected by gradient descent method.

[0076] The specific optimization process is as follows: taking the minimization of the sum of absolute values of profit and loss as the goal, first calculate the correlation coefficient between the cross-volatility coupling index and the profit and loss, multiply it by the value of the cross-volatility coupling index to obtain the adjustment contribution of the cross-volatility coupling index; Then calculate the correlation coefficient between the certificate-electricity synchronization deviation index and the profit and loss, multiply it by the value of the certificate-electricity synchronization deviation index to obtain the adjustment contribution of the certificate-electricity synchronization deviation index; add the two adjustment contributions, then multiply by a preset learning rate (used to control the adjustment step) to obtain the adjustment amount of the dynamic reference vector; Finally, the benchmark price of the current dynamic reference vector is added to the adjustment amount to obtain the corrected benchmark price. The gradient descent method can gradually reduce the profit and loss deviation through multiple adjustments, and the correlation between the cross-volatility coupling index and the certificate-synchronous deviation index ensures that the correction direction is consistent with market risk. The dynamic reference vector can gradually approach the actual market price, thereby improving the adaptability and accuracy of the benchmark price.

[0077] Step 504, writing back the benchmark price and starting the transaction The corrected dynamic reference vector is written back to the market matching logic to update the transaction benchmark price sequence, wherein the corrected benchmark price is used as the benchmark for the next round of transactions, the market matching logic generates transaction instructions according to the new benchmark price, and a new round of transaction cycle is started, and the complete process of steps one to five is repeated. By updating the benchmark price in a timely manner, the transaction platform can quickly reflect market dynamics, improve price discovery efficiency, and enhance the trading confidence of market participants and market activity through continuous optimization of the benchmark price.

[0078] By extracting the profit and loss trajectory of the hedge package in step four, combining the correlation analysis of the cross-volatility coupling index and the certificate-synchronous deviation index generated in step two, using the gradient descent method to iteratively correct the dynamic reference vector in step one, and writing back the corrected benchmark price to the market matching logic, the adaptive optimization of the transaction platform is realized. In the scenario of rapid grid connection of new energy leading to severe supply and demand fluctuations, step five effectively solves the deviation problem between the benchmark price and the actual market demand, and improves the accuracy of the cross-time scale price sequence.

[0079] Those of ordinary skill in the art can realize that the units and algorithm steps of the examples described in combination with the embodiments disclosed herein can be implemented in electronic hardware or a combination of computer software and electronic hardware. Whether the functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the present application.

[0080] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the system, device and unit described above can refer to the corresponding process in the foregoing method embodiments, which will not be described here.

[0081] In several embodiments provided in the present application, it should be understood that the disclosed system, device and method can be implemented in other manners. For example, the division of the above-described device embodiment is only a logical function division, and there can be another division manner for actual implementation, for example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the displayed or discussed mutual couplings or direct couplings or communication connections between different units, or the among different units, can be indirect couplings or communication connections through some interfaces, devices or units, and can be in electrical, mechanical or other forms.

[0082] The units described as separated components can or can not be physically separated, and the components displayed as units can or can not be physical units, i.e., can be located in one place, or can be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purposes of the embodiments of the present application.

[0083] The above describes only specific embodiments of the present application, but the protection scope of the present application is not limited thereto, and any person skilled in the art can easily think of changes or replacements within the technical scope disclosed in the present application, which should be covered in the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. A smart power trading management platform that integrates medium and long-term spot green certificate, characterized in that: comprising, a data optimization module that collects unit operation data, weather forecast data, and matching instructions, generates a dynamic reference vector through linear optimization as a benchmark price sequence for cross-year, monthly, day-ahead, and real-time transactions; a risk modeling module that generates a cross-volatility coupling index and a certificate-power synchronization deviation index based on the dynamic reference vector, inputs a Gaussian-Laplace hybrid risk model, and outputs a synergistic risk adjustment coefficient; a contract assembly module that assembles a smart contract hedge package for power and green certificate atomic locking according to the synergistic risk adjustment coefficient and ensures the hedge package is tamper-proof and traceable through blockchain records; a real-time adjustment module that tracks the profit and loss and margin status of the hedge package in real time, triggers margin addition or release according to an adaptive threshold, and writes the update results to a risk pool; a price correction module that iteratively corrects the dynamic reference vector using the settlement profit and loss trajectory, the cross-volatility coupling index, and the certificate-power synchronization deviation index, and writes the benchmark price to the next round of transactions.

2. The intelligent power trading management platform for medium and long-term spot green certificate fusion according to claim 1, wherein: the collection of unit operation data, weather forecast data, and matching instructions includes: real-time monitoring of the operating state of the unit through sensors to obtain unit operation data; obtaining weather forecast data through weather stations or satellite data; obtaining matching instructions through a trading platform; synchronizing the unit operation data, weather forecast data, and matching instructions to a unified time sequence event bus.

3. The intelligent power trading management platform for medium and long-term spot green certificate fusion according to claim 2, wherein: the generation of the dynamic reference vector through linear optimization includes: taking the unit operation data, weather forecast data, and matching instructions as input, using a linear programming algorithm to solve the objective function to minimize price fluctuations and satisfy supply and demand balance constraints, and generating the dynamic reference vector.

4. The intelligent power trading management platform for medium and long-term spot green certificate fusion according to claim 3, wherein: the generation of the cross-volatility coupling index includes: performing rolling cross-correlation calculation on the spot node electricity price and the high-pass filtered renewable power prediction error, applying an exponential decay kernel, and generating the cross-volatility coupling index to reflect the coupling relationship between electricity price and power fluctuation.

5. The intelligent power trading management platform for medium and long-term spot green certificate fusion according to claim 4, wherein: the certificate-power synchronization deviation index includes: taking the normalized difference between the green certificate equivalent price and the node electricity price, and multiplying it by the local renewable penetration rate to generate the certificate-power synchronization deviation index to quantify the synchronization deviation between green certificates and electricity prices.

6. The intelligent power trading management platform for medium and long-term spot green certificate fusion according to claim 5, wherein: the Gaussian-Laplace hybrid risk model takes the cross-volatility coupling index and the certificate-power synchronization deviation index as input, uses a hybrid model of Gaussian distribution and Laplace distribution to calculate the risk probability, and outputs the synergistic risk adjustment coefficient for adjusting transaction risk.

7. The medium and long-term spot green certificate integrated intelligent power transaction management platform of claim 6, wherein: The assembled power and green certificate atomic locked smart contract hedge package comprises: extracting power contracts and corresponding green certificates from a transaction pool according to the cooperative risk adjustment coefficient, atomically locking the power contracts and green certificates through a smart contract to form an indivisible hedge package.

8. The medium and long-term spot green certificate integrated intelligent power transaction management platform of claim 7, wherein: The unalterable and traceable hedge package through blockchain recording comprises: applying a hash function to the data of the hedge package to generate a unique identifier, recording the hedge package and the unique identifier to a distributed ledger of a blockchain, and reaching an agreement through a consensus mechanism on all network nodes.

9. The medium and long-term spot green certificate integrated intelligent power transaction management platform of claim 8, wherein: The adaptive threshold dynamically adjusts according to market fluctuations and hedge package profit and loss, comprising: calculating a market volatility rate, setting a margin call threshold and a release threshold, the call threshold being the minimum margin requirement plus the product of the risk coefficient and the market volatility rate and the risk exposure, and the release threshold being the call threshold minus an adjustment parameter.

10. The medium and long-term spot green certificate integrated intelligent power transaction management platform of claim 9, wherein: The iterative correction of the dynamic reference vector comprises: using a gradient descent method, based on the settlement profit and loss trajectory and the correlation between the cross-volatility coupling index and the certificate-power synchronization deviation index, calculating an adjustment amount, and updating the benchmark price of the dynamic reference vector to optimize the accuracy of the next round of transactions.

Images