Policy-incentive-driven optical storage resource collaborative bidding management method, system and device, and medium

Abstract

The invention discloses a policy-incentive-driven optical storage resource collaborative bidding management method, system and device, and a medium, mainly relates to the technical field of optical storage resource collaboration, and aims to solve the problems that an existing scheme lacks a dynamic incentive response mechanism, a traditional game model only considers a single economic target, and the cost is low. And constraint conditions such as policy incentive coefficients and light abandoning rates are not included in an optimization framework. Comprising the steps of obtaining specific energy storage charging amount, energy storage discharging amount, photovoltaic light abandoning rate and load adjusting amount corresponding to the maximum economic benefit in each time period by utilizing a target game function and constraint conditions, and further generating adjusting instructions about energy storage, photovoltaic and load; obtaining a 24-hour predicted electricity price; calculating the net power of the system in each time period as the bidding electric quantity by using the energy storage charging quantity, the energy storage discharging quantity, the photovoltaic light abandoning rate and the load adjusting quantity; and generating a day-ahead bidding strategy by using the 24-hour predicted electricity price and the bidding electric quantity.

Description

Technical Field

[0001] This application relates to the field of photovoltaic-storage resource synergy technology, and in particular to a policy incentive-driven photovoltaic-storage resource synergy bidding management method, system, equipment and medium. Background Technology

[0002] Currently, the global energy structure is undergoing a profound transformation dominated by renewable energy, and the synergistic application of photovoltaic power generation and energy storage systems has become a key path to achieving dual-carbon goals. Traditional bidding models mostly adopt fixed-ratio allocation or static rules.

[0003] Existing solar and energy storage resources face two core challenges when participating in the electricity market: First, the lack of a dynamic incentive response mechanism. Government-issued subsidy policies and carbon trading rules are often static texts, making it difficult to link them with market bidding strategies in real time. Second, traditional game theory models only consider a single economic objective, failing to incorporate constraints such as policy incentive coefficients and curtailment rates into the optimization framework, resulting in low coordination efficiency between energy storage charging / discharging and solar power output regulation. For example, under the time-of-use pricing mechanism, failure to couple the incentive coefficient with load regulation may lead to missed policy benefits or excessive curtailment rates. Summary of the Invention

[0004] This application provides a policy-incentive-driven collaborative bidding management method, system, equipment, and medium for photovoltaic and energy storage resources, in order to solve the problems of existing solutions lacking a dynamic incentive response mechanism and traditional game models only considering a single economic objective, without incorporating constraints such as policy incentive coefficients and curtailment rates into the optimization framework.

[0005] Firstly, this application provides a policy-incentive-driven collaborative bidding management method for photovoltaic and energy storage resources, the method comprising: Extract the rule keywords from the announcement text and calculate the incentive coefficient; Obtain the objective game function and constraints that maximize economic benefits; the calculation parameters involved in the objective game function and constraints include energy storage charging amount, energy storage discharging amount, photovoltaic curtailment rate, and load adjustment amount, and the calculation parameters of the objective game function also include incentive coefficients; By utilizing the objective game function and constraints, the specific energy storage charging amount, energy storage discharging amount, photovoltaic curtailment rate, and load adjustment amount corresponding to maximizing economic benefits in each time period are obtained, thereby generating adjustment instructions for energy storage, photovoltaics, and load. Obtain the 24-hour forecast electricity price; calculate the system net power for each time period as the bidding amount using energy storage charging amount, energy storage discharging amount, photovoltaic curtailment rate, and load adjustment amount; generate the day-ahead bidding strategy using the 24-hour forecast electricity price and the bidding amount; wherein, the day-ahead bidding strategy includes the forecast electricity price and the bidding amount for each time period.

[0006] In one implementation of this application, obtaining the rule keywords in the announcement text and calculating the incentive coefficient specifically includes: The algorithm extracts specific content corresponding to rule keywords from the announcement text; these rule keywords include at least: quantitative keywords and long subsidy validity period. Maximum number of days for subsidies ; Obtain the preset base coefficients corresponding to the quantitative keywords ; Through the formula: Calculate the excitation coefficient ; in, Indicates the time normalization factor, Indicates effectiveness indicators.

[0007] In one implementation of this application, obtaining the objective game function and constraints that maximize economic benefits specifically includes: Obtain the objective game function that maximizes economic benefits: ; ; in, Indicates the incentive coefficient. This represents the day-ahead market electricity sales volume during time period t. This represents the market electricity price for the day before time period t. This represents the real-time market power purchase volume during time period t. This represents the real-time market electricity price during time period t. Indicates the total number of time periods. Indicates the stability weight factor. This represents the net power of the system during time period t. This represents the net average power. Indicates the maximum allowable power fluctuation; This represents the photovoltaic power generation during time period t. This represents the photovoltaic curtailment rate during time period t. This represents the amount of energy storage charging during time period t. This represents the amount of energy stored and discharged during time period t. This represents the load adjustment amount during time period t. This represents the load power during time period t; Obtaining constraints: SOC_min ≤ SOC(t) ≤ SOC_max; ; When P_PV(t) > P_curtail_thres * rated capacity = min(Bat_cap, P_PV(t) -P_curtail_thres*rated capacity); Pload(t) > ΔPDR(t) > 0; Where SOC_min represents the preset minimum value of SOC, and SOC_max represents the preset maximum value of SOC. , , All are configured with preset initial values, t∈[1,T], Indicates charging efficiency. Indicates discharge efficiency. Indicates the preset time difference. Indicates the rated capacity of energy storage. Indicates the number of cycles allowed per day. This represents the light rejection rate threshold, and Bat_cap represents the battery capacity.

[0008] In one implementation of this application, generating regulation commands regarding energy storage, photovoltaics, and load specifically includes: Based on the specific energy storage charging amount, energy storage discharging amount, photovoltaic curtailment rate, and load adjustment amount, generate energy storage charging amount adjustment instructions, energy storage discharging amount adjustment instructions, photovoltaic curtailment rate adjustment instructions, and load adjustment amount adjustment instructions.

[0009] In one implementation of this application, the net system power for each time period is calculated as the bidding power using energy storage charging capacity, energy storage discharging capacity, photovoltaic curtailment rate, and load regulation capacity. Specifically, this includes: Through the formula: ; Calculate the net power of the system ; in, This represents the photovoltaic power generation during time period t. This represents the photovoltaic curtailment rate during time period t. This represents the amount of energy storage charging during time period t. This represents the amount of energy stored and discharged during time period t. This represents the load adjustment amount during time period t. This represents the load power during time period t.

[0010] Secondly, this application provides a policy-incentive-driven collaborative bidding management system for photovoltaic and energy storage resources, the system comprising: The policy analysis module is used to extract rule keywords from the announcement text and calculate incentive coefficients; The photovoltaic-storage synergistic optimization module is used to obtain the objective game function and constraints for maximizing economic benefits. The calculation parameters involved in the objective game function and constraints include energy storage charging amount, energy storage discharging amount, photovoltaic curtailment rate, and load adjustment amount. The calculation parameters of the objective game function also include incentive coefficients. Using the objective game function and constraints, the module obtains the specific energy storage charging amount, energy storage discharging amount, photovoltaic curtailment rate, and load adjustment amount corresponding to maximizing economic benefits in each time period, and then generates adjustment instructions for energy storage, photovoltaics, and load. The closed-loop decision management module is used to obtain the 24-hour forecast electricity price; calculate the system net power for each time period as the bidding electricity volume using energy storage charging volume, energy storage discharging volume, photovoltaic curtailment rate, and load adjustment volume; and generate the day-ahead bidding strategy using the 24-hour forecast electricity price and the bidding electricity volume; wherein, the day-ahead bidding strategy includes the forecast electricity price and the bidding electricity volume for each time period.

[0011] In one implementation of this application, the policy analysis module includes a coefficient calculation unit. This is used to extract specific content corresponding to rule keywords from announcement text using a keyword extraction algorithm; the rule keywords include at least: quantitative keywords and long subsidy validity period. Maximum number of days for subsidies ; Obtain the preset base coefficients corresponding to the quantitative keywords ; Through the formula: Calculate the excitation coefficient ; in, Indicates the time normalization factor, Indicates effectiveness indicators.

[0012] In one implementation of this application, the optical-storage collaborative optimization module includes a function acquisition unit. Used to obtain the objective game function that maximizes economic benefits: ; ; in, Indicates the incentive coefficient. This represents the day-ahead market electricity sales volume during time period t. This represents the market electricity price for the day before time period t. This represents the real-time market power purchase volume during time period t. This represents the real-time market electricity price during time period t. Indicates the total number of time periods. Indicates the stability weight factor. This represents the net power of the system during time period t. This represents the net average power. Indicates the maximum allowable power fluctuation; This represents the photovoltaic power generation during time period t. This represents the photovoltaic curtailment rate during time period t. This represents the amount of energy storage charging during time period t. This represents the amount of energy stored and discharged during time period t. This represents the load adjustment amount during time period t. This represents the load power during time period t; Obtaining constraints: SOC_min ≤ SOC(t) ≤ SOC_max; ; When P_PV(t) > P_curtail_thres * rated capacity = min(Bat_cap, P_PV(t) -P_curtail_thres*rated capacity); Pload(t) > ΔPDR(t) > 0; Where SOC_min represents the preset minimum value of SOC, and SOC_max represents the preset maximum value of SOC. , , All are configured with preset initial values, t∈[1,T], Indicates charging efficiency. Indicates discharge efficiency. Indicates the preset time difference. Indicates the rated capacity of energy storage. Indicates the number of cycles allowed per day. This represents the light rejection rate threshold, and Bat_cap represents the battery capacity.

[0013] Thirdly, this application provides a fast face recognition device based on a multi-stage convolutional network, the device comprising: processor; And a memory containing executable code, which, when executed, causes the processor to perform a fast face recognition method based on a multi-stage convolutional network, such as one of them.

[0014] Fourthly, this application provides a non-volatile computer storage medium storing computer instructions, which, when executed, implement a policy incentive-driven collaborative bidding management method for photovoltaic and energy storage resources, as described in any one of the above.

[0015] As can be seen from the above technical solutions, this application has the following advantages: By extracting rule keywords and calculating incentive coefficients from announcement texts in real time, policy guidance is directly integrated into the objective game function, enabling the photovoltaic-storage system to respond agilely to dynamic incentive policies. Traditional methods often lag behind policy update cycles due to the lack of a policy parameter quantification mechanism. This application, however, through the automatic calculation of incentive coefficients and the embedding of the objective function, allows core parameters such as energy storage charging and discharging, and photovoltaic curtailment rates to adjust in real time with policy changes. This mechanism not only avoids the time cost and bias risk of manual policy interpretation but also transforms policy incentives into quantifiable optimization variables through algorithms. This makes the current-day bidding strategy inherently policy compliant, significantly improving the probability of winning bids and the ability to obtain subsidies.

[0016] By constructing a target game function incorporating multiple parameters such as incentive coefficients, curtailment rate, and load regulation, the limitations of traditional single-economic-objective game models are overcome. The constraints simultaneously consider the physical limits of energy storage charging and discharging, the photovoltaic absorption rate threshold, and load regulation requirements, ensuring that the generated regulation commands always operate within the technically feasible domain. Specifically, in calculating the system's net power, the linkage optimization of energy storage charging and discharging with the curtailment rate reduces ineffective photovoltaic power reduction, while the addition of load regulation makes the bid electricity volume closer to the actual supply-demand balance point. The binding output of 24-hour forecasted electricity prices and bid electricity volume further transmits the policy incentive effect to the electricity market trading process, forming a closed-loop optimization chain from policy interpretation to market bidding. This collaborative decision-making under a multi-dimensional constraint framework not only ensures the safe operation boundary of the photovoltaic-energy storage system but also maximizes the capture of economic benefits and policy dividends. Attached Figure Description

[0017] To more clearly illustrate the technical solution of the present invention, the accompanying drawings used in the description will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0018] Figure 1 This is a flowchart of a policy incentive-driven collaborative bidding management method for photovoltaic and energy storage resources, provided in an embodiment of this application.

[0019] Figure 2 This is a schematic diagram of the internal structure of a policy incentive-driven collaborative bidding management system for photovoltaic and energy storage resources provided in an embodiment of this application.

[0020] Figure 3 This is a schematic diagram of the internal structure of a policy-incentive-driven collaborative bidding management device for photovoltaic and energy storage resources, provided in an embodiment of this application. Detailed Implementation

[0021] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0022] Those skilled in the art should understand that the embodiments described below are merely preferred embodiments of this disclosure and do not imply that this disclosure can only be implemented through these preferred embodiments. These preferred embodiments are merely used to explain the technical principles of this disclosure and are not intended to limit the scope of protection of this disclosure. Based on the preferred embodiments provided by this disclosure, all other embodiments obtained by those skilled in the art without creative effort should still fall within the scope of protection of this disclosure.

[0023] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element.

[0024] The technical solutions proposed in the embodiments of this application will be described in detail below with reference to the accompanying drawings.

[0025] The embodiment provides a policy incentive-driven collaborative bidding management method for photovoltaic and energy storage resources, such as... Figure 1 As shown in the embodiments of this application, the method mainly includes the following steps: Step 110: Obtain the rule keywords in the announcement text and calculate the incentive coefficient.

[0026] In some embodiments, obtaining rule keywords from the announcement text and calculating incentive coefficients specifically includes: The algorithm extracts specific content corresponding to rule keywords from the announcement text; these rule keywords include at least: quantitative keywords and long subsidy validity period. (Validity period of peak-shaving subsidy policy), maximum number of days for subsidies (Single-project subsidy); Obtain the preset base coefficients corresponding to quantitative keywords. ; Through the formula: Calculate the excitation coefficient ; in, This represents the time normalization factor (based on the monthly settlement standard for subsidies, e.g., 30). Indicates the effectiveness index (policy effective period = 1, otherwise = 0).

[0027] Examples of quantitative keywords include: peak-shaving subsidies and green electricity premium. When the quantitative keyword is identified as peak-shaving subsidy, a preset base coefficient is set. ; When the quantitative keyword is identified as green electricity premium, set .

[0028] Those skilled in the art can adjust the correspondence between quantitative keywords and preset basic coefficients according to actual needs.

[0029] It should be noted that the keyword extraction algorithm can be replaced by the BERT model.

[0030] Based on the above description, this step firstly extracts rule keywords (such as quantitative indicators and subsidy periods) from the announcement automatically, avoiding omissions or misjudgments that may occur during manual interpretation of policy texts, thus ensuring the completeness and accuracy of the incentive coefficient calculation basis. Secondly, the formulaic calculation based on preset base coefficients and time normalization factors dynamically reflects the policy's timeliness (such as subsidy effectiveness status) and settlement cycle (such as monthly standardized processing), ensuring a strict correspondence between the incentive coefficient and actual policy clauses and reducing deviations caused by subjective adjustments. Finally, the use of replaceable keyword extraction techniques (such as the BERT model) preserves the interpretability of the basic algorithm while reserving technical upgrade space for subsequent integration of more advanced natural language processing models, enabling the solution to adapt to the scalability of policy texts with varying complexity. The entire method achieves a stable mapping from policy rules to quantitative indicators without introducing hypothetical data.

[0031] Step 120: Obtain the objective game function and constraints that maximize economic benefits.

[0032] The calculation parameters involved in the objective game function and constraints include energy storage charging amount, energy storage discharging amount, photovoltaic curtailment rate, and load adjustment amount. The calculation parameters of the objective game function also include the excitation coefficient.

[0033] It should be noted that the energy storage charging amount, energy storage discharging amount, photovoltaic curtailment rate, and load adjustment amount in the objective game function and constraints are dynamically adjusted values, while the other parameters are input values ​​obtained directly from external sources.

[0034] This includes obtaining the objective game function and constraints that maximize economic benefits, specifically: Obtain the objective game function that maximizes economic benefits: ; ; in, Indicates the incentive coefficient. This represents the day-ahead market electricity sales volume during time period t. This represents the market electricity price for the day before time period t. This represents the real-time market power purchase volume during time period t. This represents the real-time market electricity price during time period t. Indicates the total number of time periods. Indicates the stability weight factor. This represents the net power of the system during time period t. This represents the net average power. Indicates the maximum allowable power fluctuation; This represents the photovoltaic power generation during time period t. This represents the photovoltaic curtailment rate during time period t. This represents the amount of energy storage charging during time period t. This represents the amount of energy stored and discharged during time period t. This represents the load adjustment amount during time period t. This represents the load power during time period t; Obtaining constraints: SOC_min ≤ SOC(t) ≤ SOC_max; where

[0035] ; When P_PV(t) > P_curtail_thres * rated capacity = min(Bat_cap, P_PV(t) -P_curtail_thres*rated capacity); Pload(t) > ΔPDR(t) > 0; Where SOC_min represents the preset minimum value of SOC, and SOC_max represents the preset maximum value of SOC. , , All are configured with preset initial values, t∈[1,T], Indicates charging efficiency. Indicates discharge efficiency. Indicates the preset time difference. Indicates the rated capacity of energy storage. Indicates the number of cycles allowed per day. This represents the light rejection rate threshold, and Bat_cap represents the battery capacity.

[0036] in, , The standard deviation of scheduling command fluctuations is represented by the larger value, indicating a greater emphasis on stability. This represents the standard deviation of the real-time to day-ahead price difference; the larger the deviation, the more emphasis is placed on economic efficiency.

[0037] Based on the above description, this paper directly links policy incentives (incentive coefficients) with electricity market transaction parameters (day-ahead / real-time electricity prices, power purchase and sale) without constructing a multi-dimensional objective game function, enabling economic benefit calculations to respond synchronously to policy changes and market fluctuations. Parameters dynamically adjusted in the function (such as energy storage charging and discharging capacity, and photovoltaic curtailment rate) can optimize resource allocation based on real-time operating conditions. For example, increasing energy storage charging capacity during off-peak electricity price periods can reduce electricity purchase costs, or triggering energy storage consumption through a curtailment rate threshold when photovoltaic output is excessive.

[0038] Constraints ensure system operational safety through boundary limits (such as upper and lower limits of SOC and daily cycle count) and dynamic rules (such as triggering energy storage charging based on curtailment rate thresholds). For example, hard constraints on SOC prevent battery overcharging / over-discharging, extending equipment lifespan; the linkage mechanism between curtailment rate thresholds and battery capacity (triggering charging when P_PV(t) > P_curtail_thres * rated capacity) reduces renewable energy waste. Dynamic range limits on load regulation (Pload(t) > ΔPDR(t) > 0) prevent load fluctuations from impacting the grid. These constraints, working synergistically with the objective function, maximize economic benefits while ensuring technical feasibility, policy compliance, and equipment safety.

[0039] Step 130: Using the objective game function and constraints, obtain the specific energy storage charging amount, energy storage discharging amount, photovoltaic curtailment rate, and load adjustment amount corresponding to the maximum economic benefit in each time period, and then generate adjustment instructions for energy storage, photovoltaics, and load.

[0040] It should be noted that this step dynamically generates specific operational instructions (energy storage charging / discharging, photovoltaic curtailment rate, and load regulation) to maximize economic benefits in each time period by jointly solving the objective game function and constraints. Its direct effects are reflected in three aspects: First, the charging / discharging behavior of the energy storage system is directly related to electricity price fluctuations, such as charging during low-price periods and discharging during high-price periods, thereby reducing electricity purchase costs or increasing electricity sales revenue; second, the photovoltaic curtailment rate is dynamically adjusted based on real-time power generation and absorption capacity, reducing renewable energy waste while avoiding grid overload; third, load regulation instructions are generated based on system net power and stability requirements (such as power fluctuation constraints), ensuring that user-side load changes remain within a safe range. All instructions are generated strictly according to preset constraints (such as SOC range and cycle count limits), improving economic efficiency while ensuring equipment lifespan and grid stability.

[0041] This includes generating regulation commands for energy storage, photovoltaics, and loads, specifically including: Based on the specific energy storage charging amount, energy storage discharging amount, photovoltaic curtailment rate, and load adjustment amount, generate energy storage charging amount adjustment instructions, energy storage discharging amount adjustment instructions, photovoltaic curtailment rate adjustment instructions, and load adjustment amount adjustment instructions.

[0042] Understandably, the system achieves optimized control by precisely generating various adjustment commands. Based on the calculated energy storage charging and discharging amounts, photovoltaic curtailment rate, and load regulation, the system can generate corresponding adjustment commands: energy storage charging command ensures reasonable charging during off-peak electricity price periods to reduce electricity purchase costs; energy storage discharging command ensures orderly discharging during peak electricity price periods to increase revenue; photovoltaic curtailment rate command dynamically adjusts the curtailment ratio according to the grid's absorption capacity, reducing renewable energy waste and avoiding grid overload; and load regulation command smoothly adjusts the load based on the system's supply and demand balance requirements without affecting users' normal electricity consumption. The generation of these commands strictly adheres to pre-set constraints, including the energy storage SOC safety range and charge / discharge cycle limits, ensuring equipment safety and stable grid operation while maximizing economic benefits.

[0043] Step 140: Obtain the 24-hour forecast electricity price; calculate the system net power for each time period as the bidding electricity amount using energy storage charging amount, energy storage discharging amount, photovoltaic curtailment rate, and load adjustment amount; generate the day-ahead bidding strategy using the 24-hour forecast electricity price and the bidding electricity amount.

[0044] The day-ahead bidding strategy includes the predicted electricity price and the amount of electricity to be bid for each time period.

[0045] In some embodiments, the net system power for each time period is calculated as the bidding power using energy storage charging capacity, energy storage discharging capacity, photovoltaic curtailment rate, and load regulation capacity. Specifically, this includes: Through the formula: ; Calculate the net power of the system ; in, This represents the photovoltaic power generation during time period t. This represents the photovoltaic curtailment rate during time period t. This represents the amount of energy storage charging during time period t. This represents the amount of energy stored and discharged during time period t. This represents the load adjustment amount during time period t. This represents the load power during time period t.

[0046] Understandably, by acquiring 24-hour forecast electricity prices and combining them with real-time data such as energy storage charging and discharging, photovoltaic curtailment rate, and load regulation, the system's net power for each time period can be accurately calculated and used as the bidding volume. This, in turn, generates a day-ahead bidding strategy that includes the forecast electricity price and the bidding volume. This strategy directly reflects the system's supply-demand balance capability and economic efficiency at different times, enabling operators to rationally plan energy storage charging and discharging, photovoltaic power generation utilization, and load regulation based on electricity price fluctuations and actual system operation. This ensures that the bidding volume meets the grid's acceptance capacity, maximizes the utilization of energy storage during low-price periods, reduces electricity purchases during high-price periods, and lowers the photovoltaic curtailment rate. The entire process is based on real-time parameters and precise calculations, eliminating the need for subjective judgment or historical experience, effectively improving the scientific nature of bidding decisions and the economic efficiency of system operation.

[0047] Additionally, this application may also include: a real-time market adjuster that adjusts the output of physical energy storage based on ultra-short-term load forecasts (Pload(t) within a preset short-term time period); Ancillary Service Compensator: Obtains adjustment capability score, when adjustment capability score (obtained directly). > At that time, the bidding for frequency modulation ancillary services is triggered.

[0048] in, The minimum regulation capacity scoring threshold for triggering frequency regulation ancillary service bidding is dynamically set based on the frequency regulation resource response rate threshold in the latest regulations for the target power grid area.

[0049] By adding two functional modules—a real-time market corrector and an ancillary service compensator—the system's responsiveness has been further improved. The real-time market corrector dynamically adjusts energy storage output based on ultra-short-term load forecast data (Pload(t)), correcting deviations in day-ahead plans on a minute-level timescale and improving the system's tracking accuracy of load fluctuations. The ancillary service compensator monitors regulation capacity scores in real time. When the score exceeds a dynamically set threshold (determined based on the grid area frequency regulation resource response rate threshold), it automatically triggers frequency regulation ancillary service bidding, allowing the system to flexibly participate in the ancillary service market to obtain additional revenue while meeting basic operational needs. The two modules work together, enhancing the system's adaptability to real-time market conditions and expanding commercial opportunities for participating in grid ancillary services. All functions are implemented based on actually available operating parameters and grid regulations, without relying on predicted data.

[0050] As described above, this embodiment extracts rule keywords and calculates incentive coefficients by parsing the announcement text in real time, directly integrating policy guidance into the objective game function, thus enabling the photovoltaic-storage system to respond agilely to dynamic incentive policies. Traditional methods often lag behind policy update cycles due to the lack of a policy parameter quantification mechanism. However, this application, through the automatic calculation of incentive coefficients and the embedding of the objective function, allows core parameters such as energy storage charging and discharging and photovoltaic curtailment rates to follow policy adjustments in real time. This mechanism not only avoids the time cost and bias risk of manual policy interpretation but also transforms policy incentives into quantifiable optimization variables through algorithms, making the current-day bidding strategy inherently policy compliant and significantly improving the probability of winning bids and the ability to obtain subsidies.

[0051] By constructing a target game function incorporating multiple parameters such as incentive coefficients, curtailment rate, and load regulation, the limitations of traditional single-economic-objective game models are overcome. The constraints simultaneously consider the physical limits of energy storage charging and discharging, the photovoltaic absorption rate threshold, and load regulation requirements, ensuring that the generated regulation commands always operate within the technically feasible domain. Specifically, in calculating the system's net power, the linkage optimization of energy storage charging and discharging with the curtailment rate reduces ineffective photovoltaic power reduction, while the addition of load regulation makes the bid electricity volume closer to the actual supply-demand balance point. The binding output of 24-hour forecasted electricity prices and bid electricity volume further transmits the policy incentive effect to the electricity market trading process, forming a closed-loop optimization chain from policy interpretation to market bidding. This collaborative decision-making under a multi-dimensional constraint framework not only ensures the safe operation boundary of the photovoltaic-energy storage system but also maximizes the capture of economic benefits and policy dividends.

[0052] In addition, this application Figure 2 This application provides a policy-incentive-driven collaborative bidding management system for photovoltaic and energy storage resources. For example... Figure 2 As shown in the embodiments of this application, the system mainly includes: The policy analysis module 210 is used to obtain rule keywords in the announcement text and calculate incentive coefficients.

[0053] Policy analysis module 210 includes a coefficient calculation unit. This is used to extract specific content corresponding to rule keywords from announcement text using a keyword extraction algorithm; the rule keywords include at least: quantitative keywords and long subsidy validity period. Maximum number of days for subsidies ; Obtain the preset base coefficients corresponding to the quantitative keywords ; Through the formula: Calculate the excitation coefficient ; in, Indicates the time normalization factor, Indicates effectiveness indicators.

[0054] The photovoltaic-storage collaborative optimization module 220 is used to obtain the objective game function and constraints that maximize economic benefits. The calculation parameters involved in the objective game function and constraints include energy storage charging amount, energy storage discharging amount, photovoltaic curtailment rate, and load adjustment amount. The calculation parameters of the objective game function also include incentive coefficients. Using the objective game function and constraints, the specific energy storage charging amount, energy storage discharging amount, photovoltaic curtailment rate, and load adjustment amount corresponding to the maximum economic benefits in each time period are obtained, and then adjustment instructions for energy storage, photovoltaics, and load are generated.

[0055] The photovoltaic-storage collaborative optimization module 220 includes a function acquisition unit. Used to obtain the objective game function that maximizes economic benefits: ; ; in, Indicates the incentive coefficient. This represents the day-ahead market electricity sales volume during time period t. This represents the market electricity price for the day before time period t. This represents the real-time market power purchase volume during time period t. This represents the real-time market electricity price during time period t. Indicates the total number of time periods. Indicates the stability weight factor. This represents the net power of the system during time period t. This represents the net average power. Indicates the maximum allowable power fluctuation; This represents the photovoltaic power generation during time period t. This represents the photovoltaic curtailment rate during time period t. This represents the amount of energy storage charging during time period t. This represents the amount of energy stored and discharged during time period t. This represents the load adjustment amount during time period t. This represents the load power during time period t; Obtaining constraints: SOC_min ≤ SOC(t) ≤ SOC_max; where

[0056] ; When P_PV(t) > P_curtail_thres * rated capacity = min(Bat_cap, P_PV(t) -P_curtail_thres*rated capacity); Pload(t) > ΔPDR(t) > 0; Where SOC_min represents the preset minimum value of SOC, and SOC_max represents the preset maximum value of SOC. , , All are configured with preset initial values, t∈[1,T], Indicates charging efficiency. Indicates discharge efficiency. Indicates the preset time difference. Indicates the rated capacity of energy storage. Indicates the number of cycles allowed per day. This represents the light rejection rate threshold, and Bat_cap represents the battery capacity.

[0057] The closed-loop decision management module 230 is used to obtain the 24-hour forecast electricity price; calculate the system net power for each time period as the bidding electricity amount using energy storage charging amount, energy storage discharging amount, photovoltaic curtailment rate, and load adjustment amount; and generate the day-ahead bidding strategy using the 24-hour forecast electricity price and the bidding electricity amount; wherein, the day-ahead bidding strategy includes the forecast electricity price and the bidding electricity amount for each time period.

[0058] Additionally, this application may also include: a real-time market adjuster that adjusts the output of physical energy storage based on ultra-short-term load forecasts (Pload(t) within a preset short-term time period); Ancillary Service Compensator: Obtains adjustment capability score, when adjustment capability score (obtained directly). > At that time, the bidding for frequency modulation ancillary services is triggered.

[0059] in, The minimum regulation capacity scoring threshold for triggering frequency regulation ancillary service bidding is dynamically set based on the frequency regulation resource response rate threshold in the latest regulations for the target power grid area.

[0060] As described above, this embodiment extracts rule keywords and calculates incentive coefficients by parsing the announcement text in real time, directly integrating policy guidance into the objective game function, thus enabling the photovoltaic-storage system to respond agilely to dynamic incentive policies. Traditional methods often lag behind policy update cycles due to the lack of a policy parameter quantification mechanism. However, this application, through the automatic calculation of incentive coefficients and the embedding of the objective function, allows core parameters such as energy storage charging and discharging and photovoltaic curtailment rates to follow policy adjustments in real time. This mechanism not only avoids the time cost and bias risk of manual policy interpretation but also transforms policy incentives into quantifiable optimization variables through algorithms, making the current-day bidding strategy inherently policy compliant and significantly improving the probability of winning bids and the ability to obtain subsidies.

[0061] By constructing a target game function incorporating multiple parameters such as incentive coefficients, curtailment rate, and load regulation, the limitations of traditional single-economic-objective game models are overcome. The constraints simultaneously consider the physical limits of energy storage charging and discharging, the photovoltaic absorption rate threshold, and load regulation requirements, ensuring that the generated regulation commands always operate within the technically feasible domain. Specifically, in calculating the system's net power, the linkage optimization of energy storage charging and discharging with the curtailment rate reduces ineffective photovoltaic power reduction, while the addition of load regulation makes the bid electricity volume closer to the actual supply-demand balance point. The binding output of 24-hour forecasted electricity prices and bid electricity volume further transmits the policy incentive effect to the electricity market trading process, forming a closed-loop optimization chain from policy interpretation to market bidding. This collaborative decision-making under a multi-dimensional constraint framework not only ensures the safe operation boundary of the photovoltaic-energy storage system but also maximizes the capture of economic benefits and policy dividends.

[0062] The above are method embodiments of this application. Based on the same inventive concept, this application also provides a policy incentive-driven collaborative bidding management device for photovoltaic and energy storage resources. Figure 3 As shown, the device includes: a processor; and a memory storing executable code thereon, which, when executed, causes the processor to perform a policy incentive-driven collaborative bidding management method for photovoltaic and energy storage resources as described in the above embodiment.

[0063] Specifically, the server retrieves rule keywords from the announcement text and calculates incentive coefficients; it obtains the objective game function and constraints for maximizing economic benefits; the calculation parameters involved in the objective game function and constraints include energy storage charging, energy storage discharging, photovoltaic curtailment rate, and load regulation, and the calculation parameters of the objective game function also include incentive coefficients; using the objective game function and constraints, it obtains the specific energy storage charging, energy storage discharging, photovoltaic curtailment rate, and load regulation corresponding to maximizing economic benefits in each time period, and then generates regulation instructions for energy storage, photovoltaics, and load; it obtains the 24-hour forecast electricity price; using the energy storage charging, energy storage discharging, photovoltaic curtailment rate, and load regulation, it calculates the system net power for each time period as the bidding electricity volume; and it generates a day-ahead bidding strategy using the 24-hour forecast electricity price and the bidding electricity volume; the day-ahead bidding strategy includes the forecast electricity price and the bidding electricity volume for each time period.

[0064] In addition, this application embodiment also provides a non-volatile computer storage medium storing executable instructions, which, when executed, implement a policy incentive-driven collaborative bidding management method for photovoltaic and energy storage resources as described above.

[0065] The above description of the disclosed embodiments enables those skilled in the art to make or use the invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the invention. Therefore, the invention is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A policy incentive driven photovoltaic storage resource collaborative bidding management method, characterized in that, The method comprises: Obtaining a rule keyword in the announcement text and calculating an incentive coefficient; Obtaining a target game function and a constraint condition for maximum economic benefit; wherein the calculation parameters involved in the target game function and the constraint condition include energy storage charging capacity, energy storage discharging capacity, photovoltaic light abandonment rate and load adjustment amount, and the calculation parameters of the target game function further include the incentive coefficient; Using the target game function and the constraint condition, obtaining specific energy storage charging capacity, energy storage discharging capacity, photovoltaic light abandonment rate and load adjustment amount corresponding to maximum economic benefit in each time period, and then generating an adjustment instruction for energy storage, photovoltaic and load; Obtaining a 24-hour predicted electricity price; using the energy storage charging capacity, the energy storage discharging capacity, the photovoltaic light abandonment rate and the load adjustment amount to calculate the system net power in each time period as a bidding electricity amount; using the 24-hour predicted electricity price and the bidding electricity amount to generate a day-ahead bidding strategy; wherein the day-ahead bidding strategy includes the predicted electricity price and the bidding electricity amount in each time period.

2. The policy incentive-driven optical storage resource collaborative bidding management method according to claim 1, characterized in that, Obtaining a rule keyword in the announcement text and calculating an incentive coefficient, specifically comprising: The specific content corresponding to the rule keywords is extracted from the announcement text by a keyword extraction algorithm, wherein the rule keywords at least include: a quantitative keyword, a subsidy effective period , a subsidy upper limit day ; a preset basic coefficient corresponding to the quantitative keyword is acquired ; Obtaining a target game function and a constraint condition for maximum economic benefit, specifically comprising: , calculating the excitation coefficient ; wherein, denotes a time normalization factor, denotes an effectiveness indicator.

3. The policy incentive-driven optical storage resource collaborative bidding management method according to claim 1, characterized in that, Obtaining a target game function for maximum economic benefit: Obtaining a constraint condition: ； ； wherein, represents an incentive coefficient, represents the day-ahead market sold power at time period t, represents the day-ahead market price at time period t, represents the real-time market bought power at time period t, represents the real-time market price at time period t, represents the total number of time periods, represents a stability weight factor, represents the system net power at time period t, represents the net power mean value, represents the allowed maximum power fluctuation; represents the photovoltaic power generation at time period t, represents the photovoltaic light rejection rate at time period t, represents the energy storage charging amount at time period t, represents the energy storage discharging amount at time period t, represents the load adjustment amount at time period t, represents the load power at time period t, SOC_min ≤ SOC(t) ≤ SOC_max; Pload(t)>ΔPDR(t)>0; ； When P_PV(t) > P_curtail_thres*rated capacity, = min(Bat_cap, P_PV(t) - P_curtail_thres*rated capacity); Generating an adjustment instruction for energy storage, photovoltaic and load, specifically comprising: wherein SOC_min represents a preset minimum value of SOC, SOC_max represents a preset maximum value of SOC, , , are each configured with a preset initial value, t ∈ [1, T], represents a charging efficiency, represents a discharging efficiency, represents a preset time difference, represents a rated capacity of energy storage, represents a daily allowable cycle number, represents a light rejection rate threshold, and Bat_cap represents a battery capacity.

4. The policy incentive-driven optical storage resource collaborative bidding management method according to claim 1, characterized in that, Generating an energy storage charging capacity adjustment instruction, an energy storage discharging capacity adjustment instruction, a photovoltaic light abandonment rate adjustment instruction and a load adjustment amount adjustment instruction according to the specific energy storage charging capacity, the energy storage discharging capacity, the photovoltaic light abandonment rate and the load adjustment amount. Using the energy storage charging capacity, the energy storage discharging capacity, the photovoltaic light abandonment rate and the load adjustment amount to calculate the system net power in each time period as a bidding electricity amount, specifically comprising:

5. The policy incentive-driven optical storage resource collaborative bidding management method according to claim 1, characterized in that, Using the 24-hour predicted electricity price and the bidding electricity amount to generate a day-ahead bidding strategy; wherein the day-ahead bidding strategy includes the predicted electricity price and the bidding electricity amount in each time period. The system comprises: ； Computing system net power ; wherein, represents the photovoltaic power generation amount at time t, represents the photovoltaic light rejection rate at time t, represents the energy storage charging amount at time t, represents the energy storage discharging amount at time t, represents the load adjustment amount at time t, represents the load power at time t.

6. A policy incentive driven photovoltaic storage resource collaborative bidding management system, characterized in that, A policy analysis module for obtaining a rule keyword in the announcement text and calculating an incentive coefficient; A light-storage collaborative optimization module for obtaining a target game function and a constraint condition for maximum economic benefit; wherein the calculation parameters involved in the target game function and the constraint condition include energy storage charging capacity, energy storage discharging capacity, photovoltaic light abandonment rate and load adjustment amount, and the calculation parameters of the target game function further include the incentive coefficient; using the target game function and the constraint condition, obtaining specific energy storage charging capacity, energy storage discharging capacity, photovoltaic light abandonment rate and load adjustment amount corresponding to maximum economic benefit in each time period, and then generating an adjustment instruction for energy storage, photovoltaic and load; A closed-loop decision management module for obtaining a 24-hour predicted electricity price; using the energy storage charging capacity, the energy storage discharging capacity, the photovoltaic light abandonment rate and the load adjustment amount to calculate the system net power in each time period as a bidding electricity amount; using the 24-hour predicted electricity price and the bidding electricity amount to generate a day-ahead bidding strategy; wherein the day-ahead bidding strategy includes the predicted electricity price and the bidding electricity amount in each time period. The policy analysis module comprises a coefficient calculation unit, 7. The policy incentive-driven optical storage resource collaborative bidding management system according to claim 6, wherein, Using the 24-hour predicted electricity price and the bidding electricity amount to generate a day-ahead bidding strategy; wherein the day-ahead bidding strategy includes the predicted electricity price and the bidding electricity amount in each time period. The specific content corresponding to the rule keyword is extracted from the announcement text by a keyword extraction algorithm, wherein the rule keyword at least includes: a quantitative keyword, a subsidy effective period , a subsidy upper limit day ; a preset basic coefficient corresponding to the quantitative keyword is obtained ; The light-storage collaborative optimization module comprises a function acquisition unit, , calculating the excitation coefficient ; wherein, denotes a time normalization factor, denotes an effectiveness indicator. 8.The policy incentive-driven optical storage resource collaborative bidding management system according to claim 6, characterized in that, for obtaining a target game function for maximum economic benefit: Obtaining a constraint condition: ； ； wherein, represents an incentive coefficient, represents the day-ahead market selling power of the t period, represents the day-ahead market price of the t period, represents the real-time market buying power of the t period, represents the real-time market price of the t period, represents the total number of periods, represents a stability weight factor, represents the system net power of the t period, represents the mean value of the net power, represents the maximum power fluctuation allowed; represents the photovoltaic power generation of the t period, represents the photovoltaic light rejection rate of the t period, represents the energy storage charging amount of the t period, represents the energy storage discharging amount of the t period, represents the load adjustment amount of the t period, represents the load power of the t period; ​ SOC_min < SOC(t) < SOC_max; ； When P_PV(t) > P_curtail_thres*rated capacity, = min(Bat_cap, P_PV(t) - P_curtail_thres*rated capacity); Pload(t) > ΔPDR(t) > 0; wherein SOC_min represents a preset minimum value of SOC, SOC_max represents a preset maximum value of SOC, , , are each configured with a preset initial value, t ∈ [1, T], represents a charging efficiency, represents a discharging efficiency, represents a preset time difference, represents a rated capacity of energy storage, represents a daily allowable cycle number, represents a light rejection rate threshold, and Bat_cap represents a battery capacity.

9. A fast face recognition device based on multi-stage convolutional network, characterized in that, The device comprises: a processor; and a memory having stored thereon executable code that, when executed, is to cause the processor to perform a method of fast face recognition based on a multi-stage convolutional network as claimed in any of claims 1-5.

10. A non-transitory computer storage medium, comprising, a computer program product having stored thereon computer instructions that, when executed, implement a method of policy incentive driven co-bidding management of optical storage resources as claimed in any of claims 1-5.

Images