Virtual power plant adjustable capacity calculation method and system considering sewage treatment plant

Abstract

The invention discloses a virtual power plant adjustable capacity calculation method and system considering a sewage treatment plant. Acquiring power market side data, demand side response data and other source data, and preprocessing the data to construct a clearing price prediction model for predicting a power spot market clearing price and a demand side response market clearing price; establishing a multi-level market joint optimization scheduling model by taking minimization of the total cost of the electric power spot market and the electric power demand side response market as a target; solving the multi-level market joint optimization scheduling model under the production operation constraint condition of a sewage treatment plant; and calculating the adjustable capability of the virtual power plant according to the solved optimal lift pump power. By accurately predicting the market price and optimizing the lift pump scheduling, the sewage treatment plant provides reliable virtual power plant adjustable capability on the premise of guaranteeing the process safety, and the market income and scheduling efficiency are improved.

Description

Technical Field

[0001] This invention relates to the field of virtual power plant optimization scheduling technology, specifically to a method and system for calculating the adjustable capacity of a virtual power plant that includes a wastewater treatment plant. Background Technology

[0002] As electricity market reforms deepen, the electricity spot market is gradually developing into a two-sided market, with both the generation and load sides participating in the market and competing for prices. As a key part of the construction of the new power system, virtual power plants cannot only consider responding to a single market on the demand side, but also need to optimize their regulation capabilities across multiple markets.

[0003] However, in existing integrated dispatch optimization methods, the dispatch efficiency and flexibility of wastewater treatment plants in the electricity market still need improvement. Specifically, the fusion processing of multi-source data from the generation and load sides and the methods for calculating electricity market costs are not yet perfect, which affects the accuracy of market price forecasts and consequently the optimization of dispatch decisions. Furthermore, existing technologies do not fully consider the production constraints of wastewater treatment plants in electricity market dispatch (such as booster pump power, equipment load, water level, etc.) and their impact on adjustable capacity calculation, lacking an accurate virtual power plant adjustable capacity calculation model, thus limiting the responsiveness and economic efficiency of wastewater treatment plants in the electricity market. (Summary of the Invention)

[0004] To address the shortcomings of existing technologies, this invention provides a method and system for calculating the adjustable capacity of a virtual power plant considering a wastewater treatment plant. The method involves acquiring data from the electricity spot market, the electricity demand-side response market, and weather forecasts; using a deep neural network model to predict the clearing prices of the electricity spot market and the electricity demand-side response market; acquiring operational data from the wastewater treatment plant and establishing operational constraints for the plant under electricity market participation conditions; establishing a multi-level market joint optimization scheduling mathematical model with the objective function of minimizing the total cost of participating in the electricity spot market and the electricity demand-side response market; and solving the model using a mathematical solver to obtain the adjustable capacity of the virtual power plant considering the wastewater treatment plant. This solves the problems existing in the prior art.

[0005] The first aspect of this application discloses a method for calculating the adjustable capacity of a virtual power plant that takes into account a wastewater treatment plant, using the following technical solution:

[0006] Continuous multi-source data is extracted from historical data, including electricity market data, demand-side response data, weather forecast data, load forecast data, and the baseline load for the trading day calculated based on the historical operating load of the wastewater treatment plant.

[0007] The preprocessed multi-source data is divided into main sequence data and covariate data, which are used as training data for constructing a clearing price prediction model. The clearing price prediction model is used to predict the clearing price of the electricity spot market and the clearing price of the demand-side response market.

[0008] Based on the operating data of the wastewater treatment plant, establish production and operation constraints for the wastewater treatment plant under the conditions of participating in the electricity market, including establishing effective response constraints for trading days based on the power of the booster pumps and equipment load, and setting safe water level constraints for the wastewater treatment plant's reservoir.

[0009] To minimize the total cost of the electricity spot market and the electricity demand-side response market, a multi-level market joint optimization scheduling model is established. The electricity spot market cost is calculated based on the booster pump power of the wastewater treatment plant and the predicted value of the electricity spot market clearing price, while the electricity demand-side response market cost is calculated based on the booster pump power, baseline load, and the predicted value of the demand-side response market clearing price.

[0010] Under the constraints of wastewater treatment plant production and operation, the multi-level market joint optimization scheduling model is solved; based on the solved optimal booster pump power, the adjustable capacity of the virtual power plant is calculated.

[0011] Furthermore, the construction steps of the clearing price prediction model include:

[0012] The main sequence data includes the preprocessed electricity spot market clearing price sequence P. t spot And demand-side response market clearing price series P t DR ;

[0013] From P t spot and P t DR Extracting time series features of the main sequence of the spot market respectively and demand-side response main sequence characteristics Will The data are fused and concatenated with the covariate data to generate a multidimensional feature tensor of the spot market and a multidimensional feature tensor of the demand-side response.

[0014] The multidimensional feature tensor of the spot market and the multidimensional feature tensor of the demand-side response are used to output the predicted values ​​of the electricity spot market clearing price and the predicted values ​​of the demand-side response market clearing price for each period of the trading day through a time series prediction model.

[0015] Furthermore, the effective response constraint for the trading day includes two sub-constraints;

[0016] The first sub-constraint is that, within any time period t, the sum of the loads of all booster pumps and the load of the second equipment in the wastewater treatment plant must be less than or equal to the baseline maximum load of the wastewater treatment plant on the trading day; wherein, the second equipment is the equipment used in the subsequent stages of the wastewater treatment plant, and the subsequent stages include aeration, sedimentation and sludge treatment.

[0017] The second sub-constraint is that the sum of the average power of all booster pumps in the wastewater treatment plant and the average power of the second equipment must be less than or equal to the baseline average load of the wastewater treatment plant on the trading day.

[0018] Furthermore, the safety water level constraint condition describes that, within any time period t, the water level of the reservoir is between the upper limit and the lower limit of the safety water level; the water level in time period t is the sum of the water level on the trading day and the actual rise in water level in time period t.

[0019] Furthermore, the total cost of the electricity spot market and the electricity demand-side response market is expressed as the difference between the spot market cost and the demand-side response result, which includes revenue and cost.

[0020] The spot market cost represents the total electricity cost consumed by operating all N booster pumps over the T time periods of a trading day.

[0021] The calculation method is as follows: within the calculation period t*, where t*∈T, the power of a single booster pump is multiplied by the predicted value of the electricity spot market clearing price to obtain the electricity cost of a single booster pump in a single time period; the electricity costs of all booster pumps in all time periods are summed to obtain the spot market cost.

[0022] Furthermore, the demand-side response result represents the result obtained by adjusting the power load of the booster pump to participate in the response-side project within T time periods of the trading day;

[0023] The calculation method is as follows: within the calculation period t*, t*∈T, the power deviation of a single booster pump is calculated based on the difference between the baseline load and the booster pump power;

[0024] The power deviation value is multiplied by the market-clearing price forecast of the demand-side response to calculate the response result of a single booster pump; the response results of all booster pumps in all time periods are summed to obtain the demand-side response result of the wastewater treatment plant.

[0025] Furthermore, under the constraints of effective response on the trading day and safe water level, a mathematical solver is used to solve for the optimal booster pump power P' of the nth booster pump within time period t*. n,t* ;

[0026] The adjustable capability of a virtual power plant is defined as follows: in, P represents the adjustable capacity of a wastewater treatment plant during the trading day period t*.b,t* and P n,t* These represent the baseline load and optimal power for the trading day period t*, respectively, where n is the booster pump number and N is the total number of booster pumps;

[0027] Adjustable capabilities for all T time periods This forms the virtual power plant adjustable capacity curve of the wastewater treatment plant on the trading day.

[0028] The second aspect of this application discloses a virtual power plant adjustable capacity calculation system considering a wastewater treatment plant, employing the virtual power plant adjustable capacity calculation method described in the first aspect of this application. The system includes:

[0029] The multi-source data acquisition module is used to extract continuous multi-source data from historical data, including electricity market data, demand-side response data, weather forecast data, load forecast data, and the baseline load for the trading day calculated based on the historical operating load of the wastewater treatment plant.

[0030] The price prediction model construction module is used to divide the preprocessed multi-source data into main sequence data and covariate data as training data for building the clearing price prediction model; the clearing price prediction model is used to predict the clearing price of the electricity spot market and the clearing price of the demand-side response market.

[0031] The constraint establishment module is used to establish production and operation constraints of the wastewater treatment plant under the condition of participating in the electricity market based on the operation data of the wastewater treatment plant. This includes establishing effective response constraints for trading days based on the booster pump power and equipment load, and setting safe water level constraints for the wastewater treatment plant's reservoir.

[0032] The objective function establishment module is used to establish a multi-level market joint optimization scheduling model with the goal of minimizing the total cost of the electricity spot market and the electricity demand-side response market. The electricity spot market cost is calculated based on the booster pump power of the sewage treatment plant and the predicted value of the electricity spot market clearing price, while the electricity demand-side response market cost is calculated based on the booster pump power, baseline load, and the predicted value of the demand-side response market clearing price.

[0033] The adjustable capacity calculation module is used to solve the multi-level market joint optimization scheduling model under the production and operation constraints of the sewage treatment plant; and to calculate the adjustable capacity of the virtual power plant based on the solved optimal power of the booster pump.

[0034] The beneficial effects of this invention are that, compared with the prior art,

[0035] 1. This application utilizes a systematic extraction and preprocessing of historical electricity market data, demand-side response data, weather forecast data, and load forecast data. By combining this data with the historical operating load of wastewater treatment plants to calculate the baseline load for trading days, this invention can construct a high-precision clearing price prediction model. This model can not only predict prices in the electricity spot market and demand-side response market but also provide baseline load references for each time period, thereby enabling precise scheduling of booster pump power in multi-level market joint optimization scheduling. This method reduces electricity procurement costs and improves the economic viability of wastewater treatment plants participating in the market as virtual power plants.

[0036] 2. This invention introduces operational constraints on wastewater treatment plants during the scheduling optimization process, including effective response constraints on trading days and safe water level constraints in reservoirs. This ensures that the power scheduling of booster pumps meets both the adjustable capacity requirements of the electricity market and guarantees the continuity of the wastewater treatment process and water level safety. By calculating the optimal power of the booster pumps for each time period and generating an adjustable capacity curve, wastewater treatment plants can maintain safe operation and stable treatment capacity while participating in the market, achieving a balance between load adjustability and process safety. Attached Figure Description

[0037] Figure 1 This is a flowchart illustrating a method for calculating the adjustable capacity of a virtual power plant, taking into account a wastewater treatment plant, according to an embodiment of the present invention. Detailed Implementation

[0038] To make the objectives, technical solutions, and advantages of this invention clearer, the technical solutions of this invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of this invention. The embodiments described in this application are merely some embodiments of this invention, and not all embodiments. Based on the spirit of this invention, all other embodiments obtained by those skilled in the art without creative effort are within the protection scope of this invention.

[0039] The load regulation capacity of wastewater treatment plants provides a unique type of "rigidly adjustable" resource for virtual power plants. The regulation of booster pumps possesses a dual nature: firstly, their load changes directly impact electricity consumption, allowing for rapid response to market price signals; secondly, their flow regulation forms "implicit energy storage" through changes in reservoir water levels, such as raising the water level to the upper limit during off-peak electricity periods and lowering it during peak periods to reduce energy consumption. This type of regulation requires no additional energy storage equipment investment and is deeply coupled with the wastewater treatment process, offering high operational safety. Compared to traditional adjustable loads (such as interruptible industrial and commercial loads), the regulation behavior of wastewater treatment plants is less constrained by production plans, enabling continuous daily regulation, making it particularly suitable as a fundamental regulation resource for virtual power plants participating in the day-ahead market. By incorporating the adjustable capacity of booster pumps into the joint optimization model of the virtual power plant, reliance on high-cost energy storage resources can be reduced, increasing the profitability of the virtual power plant.

[0040] Wastewater treatment plants, as energy-intensive industries, have booster pumps and aeration blowers accounting for 70% of their total energy consumption, demonstrating significant load regulation potential. Therefore, the load regulation capacity of wastewater treatment plants can be considered as part of virtual power plant scheduling. This application presents a method for calculating the adjustable capacity of a virtual power plant that takes into account wastewater treatment plants, enabling the acquisition of adjustable capacity that considers multiple market levels, further improving the operational benefits of virtual power plants.

[0041] Considering the high safety requirements for equipment operation in the aeration process, this application focuses only on improving the pump's adjustment capability, which has greater adjustment potential.

[0042] Example 1

[0043] As one embodiment of this application, this embodiment provides a specific implementation method for calculating the adjustable capacity of a virtual power plant that takes into account a wastewater treatment plant, such as... Figure 1 As shown, Figure 1 This is a flowchart illustrating a method for calculating the adjustable capacity of a virtual power plant, taking into account a wastewater treatment plant, according to an embodiment of the present invention.

[0044] S1. Obtain electricity market data, electricity demand-side response data, and weather forecast data; specifically:

[0045] (1) Obtain electricity market-side data through national or regional power trading centers, including:

[0046] The market clearing price for each trading session, i.e. the trading price of electrical energy in the electricity spot market, is expressed in yuan per megawatt-hour.

[0047] The measured load at the system level is the measured load value released by the power grid dispatch center on the system trading day. The sampling period is 15 minutes, and the unit is megawatts.

[0048] User-side actual load, i.e., the actual electricity load data of users in the target area, with a sampling period of 15 minutes, and the unit is megawatts;

[0049] The tie-line plan, namely the inter-regional tie-line (inter-regional transmission line) power transmission plan, has a sampling period of 15 minutes and is measured in megawatts.

[0050] (2) Obtain demand-side response data through the power demand-side management platform, including:

[0051] Demand-side response capacity refers to the total capacity that needs to be adjusted, as announced by the provincial company based on the power generation balance situation of the following day. The unit is megawatts, and the sampling period is 15 minutes.

[0052] Demand-side response period, i.e. the specific time period during which load adjustment is required;

[0053] Demand-side response clearing price is the transaction price after the demand-side response market clears according to market rules, and the unit is yuan / megawatt-hour.

[0054] (3) Obtain meteorological forecast data through official meteorological forecasts released by meteorological departments, including:

[0055] Temperature (in degrees Celsius), humidity (in %), air pressure (in hectopascals), wind speed (in meters per second), wind direction (in azimuth), and rainfall (in millimeters).

[0056] (4) Obtain system load forecast data and trading day baseline load data through the power dispatch center;

[0057] System load forecast data refers to the load forecast values ​​for the entire power system in various future time periods, in megawatts, with a forecast time interval of 15 minutes;

[0058] The baseline load data for the trading day refers to the benchmark load value of a wastewater treatment plant under normal operating conditions, without participating in electricity market regulation. The unit is kilowatt-hours, and the sampling period is 15 minutes. Furthermore, the calculation rules for the baseline load data for the trading day are as follows:

[0059] If trading day D is a working day, look back to the previous 5 normal working days before D-1 (these 5 working days are not involved in the corresponding load management). For each 15-minute sampling point corresponding to day D, take the load data at the same time point of these 5 working days and calculate the average to obtain the "baseline load" of that 15-minute sampling point.

[0060] The baseline average load for the hour is determined by the average baseline load at four sampling time points within the hour t, and the maximum baseline load at the four sampling time points within the hour is determined by the maximum baseline load.

[0061] If the load value of a certain sampling point is lower than 25% of the 5-day average or higher than 200% of the 5-day average, the sampling point is considered abnormal and removed, and the workday with the required load is pushed back to make up for it.

[0062] If trading day D is a non-working day, the calculation method is similar to that for working days, except that three consecutive non-working days are counted backward from D-1 as typical days for calculation.

[0063] S2. Construct a time-series forecasting model for predicting the clearing price of the electricity spot market and the clearing price of the electricity demand-side response market;

[0064] 2.1: Data preprocessing;

[0065] The demand response period indicates which time periods within a day need to participate in load regulation. In this embodiment, a 15-minute sampling interval is used, so the 24 hours of a day are divided into 96 time points (periods). The demand response period is encoded with 0-1. If the period is a demand response period, it is marked as 1, otherwise it is marked as 0.

[0066] Holidays are encoded using 0-1, with 0 representing holidays and 1 representing non-holidays.

[0067] The time-series data obtained from S1, such as the electricity spot market clearing price, demand-side response market clearing price, system-level measured load, user-side actual load, connection plan, system load forecast data, trading day baseline load data, and meteorological data, can be normalized or standardized by calling the StandardScaler() standardization toolkit in Python.

[0068] 2.2: Construct the main sequence P using the pre-processed spot market clearing price and the demand-side response market clearing price. t spot and P t DR Each main sequence has a dimension of seq_len; seq_len is the length of the historical time step. For example, in this embodiment, 15-minute sampling points from the past 7 days are used, so seq_len is 7×96, which is 672.

[0069] 2.3: The main sequence P t spot and P t DR The input is fed into the Chronos model, and the temporal features of the main sequence are extracted, denoted as follows: and

[0070] The other preprocessed data are used as covariates [f] t 1 ,f t 2 ,...,f t s ], where s is the number of covariates and the temporal characteristics of the main sequence. and The data is then merged and input into TS-Mixer, which outputs the predicted market clearing prices for each time period of the trading day. And predicting demand-side response prices for different time periods of the trading day

[0071] S3. Obtain wastewater treatment plant operation data and establish production and operation constraints for wastewater treatment plants under the conditions of participating in the electricity market, including effective response constraints and safe water level constraints on trading days.

[0072] 3.1: Obtain operational data from the wastewater treatment plant, primarily including the booster pump power P. n,t This indicates the power of pump n during trading day period t; other equipment load P e,t This indicates the electrical load of equipment in other stages besides the booster pump (such as aeration, sedimentation, sludge treatment, etc.).

[0073] Based on the wastewater treatment plant's operational data and the baseline maximum and average loads obtained from S1, effective response constraints for trading days are established, expressed as follows:

[0074]

[0075] Where N is the total number of booster pumps in the wastewater treatment plant. and These represent the baseline maximum load and baseline average load of the wastewater treatment plant on the trading day, respectively. The average power of all booster pumps; This represents the average electrical load of equipment in other stages of the wastewater treatment plant.

[0076] In the effective response constraints for trading days, the first constraint means that within any time period t, the electrical load of all equipment in the wastewater treatment process of the wastewater treatment plant shall not exceed the baseline maximum load of the wastewater treatment plant on the trading day in order to ensure effective response.

[0077] The second constraint means that the average power of all equipment in the wastewater treatment process shall not exceed the baseline average load of the wastewater treatment plant on the trading day.

[0078] 3.2: Set the upper and lower limits H of the safe water level in the sewage treatment plant's storage tank. max and H min Establish safe water level constraints for the reservoir. This is represented as:

[0079] H min ≤H t ≤H max ;

[0080] H t The water level in the reservoir during time period t is calculated as follows:

[0081]

[0082] Where H0 represents the initial water level, Q represents the initial water level at 00:00 on the trading day, and Q represents the initial water level at 00:00 on the trading day. in,k and Q out,k Let represent the inflow direction and outflow rate of the reservoir at each time k within the time period t; S is the bottom area of ​​the reservoir.

[0083] Furthermore, the inflow rate is controlled by a booster pump, as expressed as:

[0084]

[0085] In the formula, Q in,n,t The single-pump outflow rate (m³) of booster pump n within time period t. 3 / h); H pump The design head (m) of the pump is determined by the elevation difference of the sewage treatment plant's pipelines; ρ is the density of the sewage (kg / m³). 3 In this embodiment, 1000 kg / m³ is used. 3 g (gravitational acceleration) (m / s²) 2 );η pump To improve pump efficiency (%), the value is determined based on the parameters on the pump nameplate.

[0086] The outflow rate is determined by the subsequent wastewater treatment process and is usually a preset value that is not subject to scheduling optimization.

[0087] S4. Taking the minimum total cost of participating in the electricity spot market and the electricity demand-side response market as the objective function, a multi-level market joint optimization scheduling mathematical model is established. The objective function is expressed as:

[0088]

[0089] in, Indicates the cost in the spot market. This is the predicted clearing price for the spot market in time period t*, output by the time series forecasting model. Indicates the benefits / costs of demand-side response. P is the predicted clearing price of the demand-side response market in time period t*, output by the time series forecasting model. b,t P represents the baseline load for time period t*. n,t* This represents the power of the booster pump n during time period t*.

[0090] The spot market cost represents the total electricity cost consumed by operating all N booster pumps over the T time periods of a trading day. It is the sum of the products of the power of all booster pumps in all time periods and the spot market clearing price, representing the cost of purchasing electricity in the spot electricity market.

[0091] Demand-side response revenue / cost represents the total revenue or cost incurred by participating in a demand-side response project within T time periods on a trading day by adjusting the power load of booster pumps. The demand-side response revenue / cost is the sum of the products of (the difference between the baseline load and the total power of the booster pumps) and the demand-side response market clearing price. When the booster pump power is lower than the baseline load, this portion represents the revenue gained from participating in demand-side response; when the booster pump power is higher than the baseline load, this portion represents additional costs, reflecting the overall cost or revenue in the demand-side response market.

[0092] Among them, P n,t* It satisfies the effective response constraint for the trading day established in step 3.1 and the safety water level constraint established in step 2.

[0093] This step establishes a multi-level market joint optimization scheduling mathematical model, comprehensively considering the costs and benefits of the electricity spot market and the demand-side response market, to find the optimal booster pump power adjustment strategy, so as to minimize the total cost of the sewage treatment plant when participating in the two markets, and at the same time provide a basis for calculating the adjustability of the virtual power plant.

[0094] S5. Use a mathematical solver to solve the multi-level market joint optimization scheduling mathematical model to obtain the virtual power plant adjustable capacity of the sewage treatment plant on the trading day.

[0095] 5.1: The adjustable capacity of a virtual power plant is defined as follows:

[0096]

[0097] Among them, P t adj P' represents the adjustable capacity of the virtual power plant during time period t*, in megawatts. n,t* To obtain the optimal power of booster pump n in time period t* by solving the objective function.

[0098] Adjustable capacity is the difference between the booster pump power and the baseline load, reflecting the load regulation that the wastewater treatment plant can provide during the specified period. When the booster pump power is lower than the baseline load, the difference is positive, representing the amount of load that can be reduced, i.e., the downward regulation capacity provided, which can be used as the amount to be declared in the demand-side response market. When the booster pump power is higher than the baseline load, the difference is negative, indicating that downward regulation capacity cannot be provided in the current period. Summing up the adjustable capacities of all booster pumps yields the total adjustable capacity, which comprehensively reflects the regulation capacity provided by the wastewater treatment plant to the virtual power plant throughout the entire trading day.

[0099] As one implementation method of this embodiment, a hybrid solution strategy combining an improved genetic algorithm and the MOSEK interior point method is adopted to optimize and solve the mathematical model of joint optimization scheduling of multi-level markets, and output the virtual power plant adjustable capacity curves for each time period of the trading day.

[0100] This embodiment first uses an improved genetic algorithm to perform a global search of the solution space to obtain a better initial solution, so as to avoid getting trapped in local optima under the complex scheduling problem involving multiple booster pumps, nonlinear start-stop constraints and cross-time coupling constraints.

[0101] The initial solution is then input into the MOSEK commercial mathematical solver, which uses the interior point method to refine the optimization of the linear objective function and linear constraints, achieving rapid convergence and improving the accuracy of the solution.

[0102] Wastewater treatment plant loads are discrete and subject to rigid constraints. The start-up and shutdown of booster pumps exhibit discontinuous characteristics. Relying solely on mathematical solvers is insufficient to guarantee the global optimum for jump loads, while the global search capability of genetic algorithms can better cover the feasible solution space.

[0103] Furthermore, in virtual power plant dispatching, it is necessary not only to meet the constraints of adjustable capacity declaration in the electricity market, but also to consider the continuity of wastewater treatment processes and energy consumption limitations. Genetic algorithms can provide global multi-objective trade-offs, while MOSEK can further achieve high-precision optimization within the feasible region.

[0104] The calculated adjustable capacity data is fed back to the virtual power plant's dispatch center, serving as an important basis for the virtual power plant to participate in the electricity market's bidding for quantity and price and for dispatch decisions. This helps the virtual power plant to formulate better market strategies and improve its profitability.

[0105] Example 2

[0106] As an embodiment of this application, this embodiment is based on the same inventive concept, a virtual power plant adjustable capacity calculation system considering a sewage treatment plant, and adopts the specific implementation method as in Embodiment 1, including:

[0107] The multi-source data acquisition module is used to extract continuous multi-source data from historical data, including electricity market data, demand-side response data, weather forecast data, load forecast data, and the baseline load for the trading day calculated based on the historical operating load of the wastewater treatment plant.

[0108] The price prediction model construction module is used to divide the preprocessed multi-source data into main sequence data and covariate data as training data for building the clearing price prediction model; the clearing price prediction model is used to predict the clearing price of the electricity spot market and the clearing price of the demand-side response market.

[0109] The constraint establishment module is used to establish production and operation constraints of the wastewater treatment plant under the condition of participating in the electricity market based on the operation data of the wastewater treatment plant. This includes establishing effective response constraints for trading days based on the booster pump power and equipment load, and setting safe water level constraints for the wastewater treatment plant's reservoir.

[0110] The objective function establishment module is used to establish a multi-level market joint optimization scheduling model with the goal of minimizing the total cost of the electricity spot market and the electricity demand-side response market. The electricity spot market cost is calculated based on the booster pump power of the sewage treatment plant and the predicted value of the electricity spot market clearing price, while the electricity demand-side response market cost is calculated based on the booster pump power, baseline load, and the predicted value of the demand-side response market clearing price.

[0111] The adjustable capacity calculation module is used to solve the multi-level market joint optimization scheduling model under the production and operation constraints of the sewage treatment plant; and to calculate the adjustable capacity of the virtual power plant based on the solved optimal power of the booster pump.

[0112] Example 3

[0113] Embodiment 3 of this application provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the computer program is loaded onto the processor, it implements the virtual power plant adjustable capacity calculation method according to Embodiment 1.

[0114] Example 4

[0115] Embodiment 4 of this application provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the virtual power plant adjustable capacity calculation method according to Embodiment 1. Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit it. Although the present invention has been described in detail with reference to the above embodiments, those skilled in the art should understand that modifications or equivalent substitutions can still be made to the specific embodiments of the present invention. Any modifications or equivalent substitutions that do not depart from the spirit and scope of the present invention should be covered within the scope of protection of the claims of the present invention.

Claims

1. A method for calculating the adjustable capacity of a virtual power plant considering a wastewater treatment plant, characterized in that, include: Continuous multi-source data is extracted from historical data, including electricity market data, demand-side response data, weather forecast data, load forecast data, and the baseline load for the trading day calculated based on the historical operating load of the wastewater treatment plant. The preprocessed multi-source data is divided into main sequence data and covariate data, which are used as training data for constructing a clearing price prediction model. The clearing price prediction model is used to predict the clearing price of the electricity spot market and the clearing price of the demand-side response market. Based on the operating data of the wastewater treatment plant, establish production and operation constraints for the wastewater treatment plant under the conditions of participating in the electricity market, including establishing effective response constraints for trading days based on the power of the booster pumps and equipment load, and setting safe water level constraints for the wastewater treatment plant's reservoir. To minimize the total cost of the electricity spot market and the electricity demand-side response market, a multi-level market joint optimization scheduling model is established. The electricity spot market cost is calculated based on the booster pump power of the wastewater treatment plant and the predicted value of the electricity spot market clearing price, while the electricity demand-side response market cost is calculated based on the booster pump power, baseline load, and the predicted value of the demand-side response market clearing price. Under the constraints of wastewater treatment plant production and operation, the multi-level market joint optimization scheduling model is solved; based on the solved optimal booster pump power, the adjustable capacity of the virtual power plant is calculated.

2. The method for calculating the adjustable capacity of a virtual power plant considering a wastewater treatment plant according to claim 1, characterized in that, The steps for constructing the clearing price prediction model include: The main sequence data includes the preprocessed electricity spot market clearing price sequence P. t spot And demand-side response market clearing price series P t DR ; From P t spot and P t DR Extracting time series features of the main sequence of the spot market respectively and demand-side response main sequence characteristics Will The data are fused and concatenated with the covariate data to generate a multidimensional feature tensor of the spot market and a multidimensional feature tensor of the demand-side response. The multidimensional feature tensor of the spot market and the multidimensional feature tensor of the demand-side response are used to output the predicted values ​​of the electricity spot market clearing price and the predicted values ​​of the demand-side response market clearing price for each period of the trading day through a time series prediction model.

3. The method for calculating the adjustable capacity of a virtual power plant considering a wastewater treatment plant according to claim 1, characterized in that, The effective response constraint for the trading day includes two sub-constraints; The first sub-constraint is that, within any time period t, the sum of the loads of all booster pumps and the load of the second equipment in the wastewater treatment plant must be less than or equal to the baseline maximum load of the wastewater treatment plant on the trading day; wherein, the second equipment is the equipment used in the subsequent stages of the wastewater treatment plant, and the subsequent stages include aeration, sedimentation and sludge treatment. The second sub-constraint is that the sum of the average power of all booster pumps in the wastewater treatment plant and the average power of the second equipment must be less than or equal to the baseline average load of the wastewater treatment plant on the trading day.

4. The method for calculating the adjustable capacity of a virtual power plant considering a wastewater treatment plant according to claim 1, characterized in that, The safety water level constraint condition describes that, within any time period t, the water level of the reservoir is between the upper and lower limits of the safety water level; the water level in time period t is the sum of the water level on the trading day and the actual rise in water level during time period t.

5. The method for calculating the adjustable capacity of a virtual power plant considering a wastewater treatment plant according to claim 1, characterized in that, The total cost of the electricity spot market and the electricity demand-side response market is expressed as the difference between the spot market cost and the demand-side response result, which includes revenue and cost. The spot market cost represents the total electricity cost consumed by operating all N booster pumps over the T time periods of a trading day. The calculation method is as follows: within the calculation period t*, where t*∈T, the power of a single booster pump is multiplied by the predicted value of the electricity spot market clearing price to obtain the electricity cost of a single booster pump in a single time period; the electricity costs of all booster pumps in all time periods are summed to obtain the spot market cost.

6. The method for calculating the adjustable capacity of a virtual power plant considering a wastewater treatment plant according to claim 5, characterized in that, The demand-side response result refers to the result obtained by adjusting the power load of the booster pump to participate in the response-side project within T time periods of the trading day; The calculation method is as follows: within the calculation period t*, t*∈T, the power deviation of a single booster pump is calculated based on the difference between the baseline load and the booster pump power; The power deviation value is multiplied by the market-clearing price forecast of the demand-side response to calculate the response result of a single booster pump; the response results of all booster pumps in all time periods are summed to obtain the demand-side response result of the wastewater treatment plant.

7. The method for calculating the adjustable capacity of a virtual power plant considering a wastewater treatment plant according to claim 1, characterized in that, Under the constraints of effective response on the trading day and safe water level, the optimal booster pump power P' of the nth booster pump within time period t* is solved using a mathematical solver. n,t* ; The adjustable capability of a virtual power plant is defined as follows: in, P represents the adjustable capacity of a wastewater treatment plant during the trading day period t*. b,t* and P n,t* These represent the baseline load and optimal power for the trading day period t*, respectively, where n is the booster pump number and N is the total number of booster pumps; Adjustable capabilities for all T time periods This forms the virtual power plant adjustable capacity curve of the wastewater treatment plant on the trading day.

8. A virtual power plant adjustable capacity calculation system considering a wastewater treatment plant, employing the virtual power plant adjustable capacity calculation method as described in any one of claims 1-7, characterized in that, The system includes: The multi-source data acquisition module is used to extract continuous multi-source data from historical data, including electricity market data, demand-side response data, weather forecast data, load forecast data, and the baseline load for the trading day calculated based on the historical operating load of the wastewater treatment plant. The price prediction model construction module is used to divide the preprocessed multi-source data into main sequence data and covariate data as training data for building the clearing price prediction model; the clearing price prediction model is used to predict the clearing price of the electricity spot market and the clearing price of the demand-side response market. The constraint establishment module is used to establish production and operation constraints of the wastewater treatment plant under the condition of participating in the electricity market based on the operation data of the wastewater treatment plant. This includes establishing effective response constraints for trading days based on the booster pump power and equipment load, and setting safe water level constraints for the wastewater treatment plant's reservoir. The objective function establishment module is used to establish a multi-level market joint optimization scheduling model with the goal of minimizing the total cost of the electricity spot market and the electricity demand-side response market. The electricity spot market cost is calculated based on the booster pump power of the sewage treatment plant and the predicted value of the electricity spot market clearing price, while the electricity demand-side response market cost is calculated based on the booster pump power, baseline load, and the predicted value of the demand-side response market clearing price. The adjustable capacity calculation module is used to solve the multi-level market joint optimization scheduling model under the production and operation constraints of the sewage treatment plant; and to calculate the adjustable capacity of the virtual power plant based on the solved optimal power of the booster pump.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the computer program is loaded into the processor, it implements the virtual power plant adjustable capacity calculation method according to any one of claims 1-7.

10. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, it implements the virtual power plant adjustable capacity calculation method according to any one of claims 1-7.

Images