New energy consumption monitoring method and system in electricity market environment

Abstract

The invention relates to a new energy consumption monitoring method and system in an electricity market environment. The method comprises the following steps: collecting historical data of a new energy power station and a power grid; predicting the new energy output and load demand of the new energy power station and the power grid according to the historical data; establishing a consumption model according to the new energy output and the load demand, and obtaining a consumption threshold by solving the consumption model; collecting real-time data of the new energy power station and the power grid, and predicting real-time new energy output and real-time load demand of the real-time data; according to the consumption threshold value, the real-time load demand and the real-time new energy output, new energy consumption of the new energy power station and the power grid is monitored, the method mainly depends on historical data and real-time data of the new energy power station and the power grid, and the data are usually easy to obtain and process.

Description

Technical Field

[0001] The present invention relates to a new energy consumption monitoring method and system in an electric power market environment, and belongs to the field of electrical engineering and energy management. Background Art

[0002] In the power market environment, the new energy consumption monitoring method aims to improve the utilization rate of new energy power generation, ensure the stable operation of the power system, and optimize the resource allocation of the power market. With the global attention to environmental protection and sustainable development, the installed capacity of new energy power generation (such as wind power, solar energy, etc.) has continued to increase. However, the intermittent and volatile nature of new energy power generation has brought challenges to the stable operation of the power system. The intermittent and volatile nature of new energy power generation makes it difficult to accurately predict its output. The traditional new energy consumption monitoring method has the problem of low accuracy in predicting the output of new energy power generation, which makes it difficult to formulate effective scheduling strategies during actual operation, thus affecting the effective consumption of new energy. Traditional new energy consumption monitoring methods often adopt a single scheduling strategy and lack the ability to flexibly select and combine multiple scheduling strategies. This makes it difficult to adjust the scheduling strategy in time according to the changes in the power market and the actual situation of new energy power generation during actual operation, thus affecting the stability and economy of the power system.

[0003] The patent document with the patent publication number "CN118232527A" has developed a distributed new energy system security monitoring method and system based on digital twins. The problem with this method is that it is highly dependent on real-time monitoring data, including state parameters of new energy power generation equipment, energy storage equipment, and the power grid. If the data quality is not high or there are missing data, it may affect the accuracy and reliability of the digital twin model. The digital twin system needs to process a large amount of real-time monitoring data, which requires high-performance computing and data processing capabilities. If the computing resources are insufficient or the data processing efficiency is not high, it may affect the real-time and accuracy of the monitoring. Summary of the invention

[0004] In order to solve the above problems existing in the prior art, the present invention proposes a new energy consumption monitoring method and system in an electricity market environment.

[0005] The technical solution of the present invention is as follows:

[0006] On the one hand, the present invention provides a method for monitoring the consumption of new energy in an electric power market environment, comprising the following steps:

[0007] Collect historical data of renewable energy power stations and power grids;

[0008] Forecast the new energy output and load demand of new energy power stations and power grids based on historical data;

[0009] Establish a consumption model based on the output of new energy and load demand, and obtain the consumption threshold by solving the consumption model;

[0010] Collect real-time data of renewable energy power stations and power grids, and predict real-time renewable energy output and real-time load demand based on real-time data;

[0011] Monitor the new energy consumption of new energy power stations and power grids based on the consumption threshold, real-time load demand and real-time new energy output.

[0012] As a preferred implementation, the prediction method of the new energy output and load demand is:

[0013] The dataset D is represented as:

[0014] D={d1...d t ...d n};

[0015] Among them, d t Represents real-time data or historical data at time t;

[0016] The prediction method is expressed as:

[0017] P t =α·P ARIMA (t)+(1-α)·P LSTM (t);

[0018] Among them, P t represents the final prediction result at time t, α represents the preset proportional coefficient, P ARIMA (t) represents the ARIMA model prediction result at time t, P LSTM (t) represents the prediction result of the LSTM model at the tth moment;

[0019] ARIMA model prediction results P ARIMA The prediction method of (t) is expressed as:

[0020]

[0021] Among them, δ represents the preset adjustment coefficient, represents the autoregressive term coefficient, ω j represents the moving average coefficient, ρ(ti) and ε(tj) represent the real-time data or historical data at the tth moment. t The lag value of , t represents time, Q represents the preset autoregressive term order, and P represents the preset moving average term order;

[0022] LSTM model prediction result P LSTM The prediction method of (t) is expressed as:

[0023] PLSTM (t) = f LSTM (X (t) ,θ LSTM );

[0024] Among them, f LSTM () represents the mapping function of the LSTM model, X (t) Indicates the real-time data or historical data at time t t The eigenvector of LSTM Represents the built-in parameters of the LSTM model.

[0025] As a preferred implementation, the consumption model is expressed as:

[0026]

[0027] Among them, min represents the minimum function, C t represents the cost coefficient of new energy at time t, D t represents the cost coefficient of the load at time t, P c (t) represents the amount of new energy abandoned at the tth moment, L c (t) represents the abandoned load at the tth moment, and γ represents the preset coefficient;

[0028] V t =P ARIMA (t)-P c (t);

[0029] Z t =P LSTM (t)+L c (t);

[0030] Among them, V t represents the constraints of the new energy at time t, Z t Represents the load constraint at time t.

[0031] As a preferred implementation, the solution method of the absorption model is:

[0032] SL=SOL(Q,Y);

[0033] Among them, SL represents the absorption threshold, Q represents the absorption model, Y represents the solution strategy, and the mathematical optimization solver Gurobi is used for solution. SOL() represents the solution function.

[0034] As a preferred implementation, the method for monitoring the consumption of new energy is:

[0035] W=(|XY|)>SL? 1:0;

[0036] Among them, W represents the alarm signal. If the W value is 1, an alarm is triggered, and if the W value is 0, no alarm is triggered; X represents the real-time new energy output, and Y represents the real-time load demand.

[0037] On the other hand, the present invention also provides a new energy consumption monitoring system in an electric power market environment, comprising:

[0038] Historical data collection module: collects historical data of new energy power stations and power grids;

[0039] Model prediction module: predicts the new energy output and load demand of new energy power stations and power grids based on historical data;

[0040] Consumption threshold solution module: establish a consumption model based on the output of new energy and load demand, and obtain the consumption threshold by solving the consumption model;

[0041] Real-time data collection module: collects real-time data of renewable energy power stations and power grids, and predicts real-time renewable energy output and real-time load demand of real-time data;

[0042] Monitoring module: monitors the new energy consumption of new energy power stations and power grids based on the consumption threshold, real-time load demand and real-time new energy output.

[0043] The present invention has the following beneficial effects:

[0044] The present invention collects historical data of new energy power stations and power grids, establishes a consumption model and solves the consumption threshold, thereby realizing the monitoring of new energy consumption. The method is simpler, easy to implement and promote. Not only the historical data of new energy power stations and power grids are collected, but also the collection and prediction of real-time data are considered. This method can fully reflect the actual situation of new energy power generation and power grid load, and provide more accurate data support for consumption monitoring. At the same time, through in-depth analysis of historical data, the changing laws of new energy power generation and power grid load can be revealed, providing a more reliable basis for prediction and monitoring. A prediction method based on historical data is adopted. This method can fully consider the intermittent and volatility of new energy power generation, as well as the changing laws of power grid load, thereby improving the accuracy of prediction. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] Figure 1 The present invention is a flowchart for implementing the method. DETAILED DESCRIPTION

[0046] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0047] It should be understood that the step numbers used in this document are only for convenience of description and are not intended to limit the order in which the steps are executed.

[0048] It should be understood that the terms used in the present specification are only for the purpose of describing specific embodiments and are not intended to limit the present invention. As used in the present specification and the appended claims, unless the context clearly indicates otherwise, the singular forms "a", "an" and "the" are intended to include plural forms.

[0049] The terms “include” and “comprising” indicate the presence of described features, integers, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or combinations thereof.

[0050] The term "and / or" means and includes any and all possible combinations of one or more of the associated listed items.

[0051] In the power market environment, the main goal of the new energy consumption monitoring method is to ensure that new energy (such as wind power and solar power) can be effectively integrated into the power grid, while reducing the phenomenon of wind and solar power abandonment and optimizing the operating efficiency of the power system.

[0052] Embodiment 1:

[0053] See also Figure 1 The present invention provides a new energy consumption monitoring method in an electric power market environment, comprising the following steps:

[0054] Collect historical data of renewable energy power stations and power grids (including power generation, load demand, weather forecast, electricity price, power market demand data, etc.);

[0055] Forecast the new energy output and load demand of new energy power stations and power grids based on historical data;

[0056] Establish a consumption model based on the output of new energy and load demand, and obtain the consumption threshold by solving the consumption model;

[0057] Collect real-time data of renewable energy power stations and power grids, and predict real-time renewable energy output and real-time load demand based on real-time data;

[0058] Monitor the new energy consumption of new energy power stations and power grids based on the consumption threshold, real-time load demand and real-time new energy output.

[0059] As a preferred implementation, the prediction method of the new energy output and load demand is:

[0060] The dataset D is represented as:

[0061] D={d1...d t ...d n};

[0062] Among them, d t Represents real-time data or historical data at time t;

[0063] The prediction method is expressed as:

[0064] P t =α·P ARIMA (t)+(1-α)·P LSTM (t);

[0065] Among them, P t represents the final prediction result at time t, α represents the preset proportional coefficient, P ARIMA (t) represents the ARIMA model prediction result at time t, P LSTM (t) represents the prediction result of the LSTM model at the tth moment;

[0066] ARIMA model prediction results P ARIMA The prediction method of (t) is expressed as:

[0067]

[0068] Among them, δ represents the preset adjustment coefficient, represents the autoregressive term coefficient, ω j represents the moving average coefficient, ρ(ti) and ε(tj) represent the real-time data or historical data at the tth moment. t The lag value of , t represents time, Q represents the preset autoregressive term order, and P represents the preset moving average term order;

[0069] LSTM model prediction result P LSTM The prediction method of (t) is expressed as:

[0070] P LSTM (t) = f LSTM (X (t) ,θ LSTM );

[0071] Among them, f LSTM () represents the mapping function of the LSTM model, X(t) Indicates the real-time data or historical data at time t t The eigenvector of LSTM Represents the built-in parameters of the LSTM model.

[0072] The ARIMA model is a classic statistical model that is particularly suitable for processing data with linear relationships and seasonality. It makes non-stationary series stationary through differences, and then uses components such as autoregression, moving average, and integration for prediction.

[0073] The LSTM model is a variant of RNN (recurrent neural network) and is good at handling long-term dependency problems. The LSTM unit contains an input gate, an output gate, and a forget gate. These structures enable it to remember information over a long span of time and have good adaptability to time series data.

[0074] Combining the two, the ARIMA model can capture the linear trend and periodicity of the data, while the LSTM model is used to extract complex nonlinear features. By combining the outputs of the two, the advantages of both can be combined to reduce the prediction error and thus improve the prediction accuracy.

[0075] As a preferred implementation, the consumption model is expressed as:

[0076]

[0077] Among them, min represents the minimum function, C t represents the cost coefficient of new energy at time t, D t represents the cost coefficient of the load at time t, P c (t) represents the amount of new energy abandoned at the tth moment, L c (t) represents the abandoned load at the tth moment, and γ represents the preset coefficient;

[0078] V t =P ARIMA (t)-P c (t);

[0079] Z t =P LSTM (t)+L c (t);

[0080] Among them, V t represents the constraints of the new energy at time t, Z t Represents the load constraint at time t.

[0081] As a preferred implementation, the solution method of the absorption model is:

[0082] SL=SOL(Q,Y);

[0083] Among them, SL represents the absorption threshold, Q represents the absorption model, Y represents the solution strategy, and the mathematical optimization solver Gurobi is used for solution. SOL() represents the solution function.

[0084] As a preferred implementation, the method for monitoring the consumption of new energy is:

[0085] W=(|XY|)>SL? 1:0;

[0086] Among them, W represents the alarm signal. If the W value is 1, an alarm is triggered, and if the W value is 0, no alarm is triggered; X represents the real-time new energy output, and Y represents the real-time load demand.

[0087] Embodiment 2:

[0088] The present invention also provides a new energy consumption monitoring system in an electric power market environment, comprising:

[0089] Historical data collection module: collects historical data of new energy power stations and power grids;

[0090] Model prediction module: predicts the new energy output and load demand of new energy power stations and power grids based on historical data;

[0091] Consumption threshold solution module: establish a consumption model based on the output of new energy and load demand, and obtain the consumption threshold by solving the consumption model;

[0092] Real-time data collection module: collects real-time data of renewable energy power stations and power grids, and predicts real-time renewable energy output and real-time load demand of real-time data;

[0093] Monitoring module: monitors the new energy consumption of new energy power stations and power grids based on the consumption threshold, real-time load demand and real-time new energy output.

[0094] In the embodiments of the present application, "at least one" refers to one or more, and "more than one" refers to two or more. "And / or" describes the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B can represent the existence of A alone, the existence of A and B at the same time, and the existence of B alone. Among them, A and B can be singular or plural. The character " / " generally indicates that the previous and next associated objects are in an "or" relationship. "At least one of the following" and similar expressions refer to any combination of these items, including any combination of single or plural items. For example, at least one of a, b and c can be represented by: a, b, c, a and b, a and c, b and c, or a and b and c, where a, b, c can be single or multiple.

[0095] Those of ordinary skill in the art will appreciate that the various units and algorithm steps described in the embodiments disclosed herein can be implemented in a combination of electronic hardware, computer software, and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0096] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0097] In several embodiments provided in the present application, if any function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (Read-Only Memory; hereinafter referred to as: ROM), random access memory (Random Access Memory; hereinafter referred to as: RAM), disk or optical disk, and other media that can store program codes.

[0098] The above descriptions are merely embodiments of the present invention and are not intended to limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made using the contents of the present invention specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.

Claims

1. A method for monitoring the consumption of new energy in an electric power market environment, characterized in that: The following steps are involved: Collect historical data of renewable energy power stations and power grids; Forecast the new energy output and load demand of new energy power stations and power grids based on historical data; Establish a consumption model based on the output of new energy and load demand, and obtain the consumption threshold by solving the consumption model; Collect real-time data of renewable energy power stations and power grids, and predict real-time renewable energy output and real-time load demand based on real-time data; Monitor the new energy consumption of new energy power stations and power grids based on the consumption threshold, real-time load demand and real-time new energy output.

2. The method for monitoring new energy consumption in the power market environment according to claim 1 is characterized in that: The prediction method of the new energy output and load demand is: The dataset D is represented as: D={d1...d t ...d n }; Among them, d t Represents real-time data or historical data at time t; The prediction method is expressed as: P t =α·P ARIMA (t)+(1-α)·P LSTM (t); Among them, P t represents the final prediction result at time t, α represents the preset proportional coefficient, P ARIMA (t) represents the ARIMA model prediction result at time t, P LSTM (t) represents the prediction result of the LSTM model at the tth moment; ARIMA model prediction results P ARIMA The prediction method of (t) is expressed as: Among them, δ represents the preset adjustment coefficient, represents the autoregressive term coefficient, ω j represents the moving average coefficient, ρ(ti) and ε(tj) represent the real-time data or historical data at the tth moment. t The lag value of , t represents time, Q represents the preset autoregressive term order, and P represents the preset moving average term order; LSTM model prediction result P LSTM The prediction method of (t) is expressed as: P LSTM (t)=f LSTM (X (t) ,θ LSTM ); Among them, f LSTM () represents the mapping function of the LSTM model, X (t) Indicates the real-time data or historical data at time t t The eigenvector of LSTM Represents the built-in parameters of the LSTM model.

3. The method for monitoring new energy consumption in the power market environment according to claim 2 is characterized in that: The consumption model is expressed as: Among them, min represents the minimum function, C t represents the cost coefficient of new energy at time t, D t represents the cost coefficient of the load at time t, P c (t) represents the amount of new energy abandoned at the tth moment, L c (t) represents the abandoned load at the tth moment, and γ represents the preset coefficient; V t =P ARIMA (t)-P c (t); Z t =P LSTM (t)+L c (t); Among them, V t represents the constraints of the new energy at time t, Z t Represents the load constraint at time t.

4. The method for monitoring new energy consumption in the power market environment according to claim 3 is characterized in that: The solution method of the absorption model is: SL=SOL(Q,Y); Among them, SL represents the absorption threshold, Q represents the absorption model, Y represents the solution strategy, and the mathematical optimization solver Gurobi is used for solution. SOL() represents the solution function.

5. The method for monitoring new energy consumption in the power market environment according to claim 4 is characterized in that: The methods for monitoring the consumption of new energy are: W=(|XY|)>SL? 1:0; Among them, W represents the alarm signal. If the W value is 1, an alarm is triggered, and if the W value is 0, no alarm is triggered; X represents the real-time new energy output, and Y represents the real-time load demand.

6. A new energy consumption monitoring system in the power market environment, characterized in that: include: Historical data collection module: collects historical data of new energy power stations and power grids; Model prediction module: predicts the new energy output and load demand of new energy power stations and power grids based on historical data; Consumption threshold solution module: establish a consumption model based on the output of new energy and load demand, and obtain the consumption threshold by solving the consumption model; Real-time data collection module: collects real-time data of renewable energy power stations and power grids, and predicts real-time renewable energy output and real-time load demand of real-time data; Monitoring module: monitors the new energy consumption of new energy power stations and power grids based on the consumption threshold, real-time load demand and real-time new energy output.

7. The new energy consumption monitoring system in the power market environment according to claim 6 is characterized in that: The model prediction module predicts the output of new energy and load demand using the following method: The dataset D is represented as: D={d1...d t ...d n }; Among them, d t Represents real-time data or historical data at time t; The prediction method is expressed as: P t =α·P ARIMA (t)+(1-α)·P LSTM (t); Among them, P t represents the final prediction result at time t, α represents the preset proportional coefficient, P ARIMA (t) represents the ARIMA model prediction result at time t, P LSTM (t) represents the prediction result of the LSTM model at the tth moment; ARIMA model prediction results P ARIMA The prediction method of (t) is expressed as: Among them, δ represents the preset adjustment coefficient, represents the autoregressive term coefficient, ω j represents the moving average coefficient, ρ(ti) and ε(tj) represent the real-time data or historical data at the tth moment. t The lag value of , t represents time, Q represents the preset autoregressive term order, and P represents the preset moving average term order; LSTM model prediction result P LSTM The prediction method of (t) is expressed as: P LSTM (t)=f LSTM (X (t) ,θ LSTM ); Among them, f LSTM () represents the mapping function of the LSTM model, X (t) Indicates the real-time data or historical data at time t t The eigenvector of LSTM Represents the built-in parameters of the LSTM model.

8. The new energy consumption monitoring system in the power market environment according to claim 7 is characterized in that: The absorption threshold solution module, the absorption model is expressed as: Among them, min represents the minimum function, C t represents the cost coefficient of new energy at time t, D t represents the cost coefficient of the load at time t, P c (t) represents the amount of new energy abandoned at the tth moment, L c (t) represents the abandoned load at the tth moment, and γ represents the preset coefficient; V t =P ARIMA (t)-P c (t); Z t =P LSTM (t)+L c (t); Among them, V t represents the constraints of the new energy at time t, Z t Represents the load constraint at time t.

9. The new energy consumption monitoring system in the power market environment according to claim 8 is characterized in that: The solution method of the absorption threshold solution module and the absorption model is as follows: SL=SOL(Q,Y); Among them, SL represents the absorption threshold, Q represents the absorption model, Y represents the solution strategy, and the mathematical optimization solver Gurobi is used for solution. SOL() represents the solution function.

10. The new energy consumption monitoring system in the power market environment according to claim 9 is characterized in that: The monitoring module and the method for monitoring the consumption of new energy are as follows: W=(|XY|)>SL? 1:0; Among them, W represents the alarm signal. If the W value is 1, an alarm is triggered, and if the W value is 0, no alarm is triggered; X represents the real-time new energy output, and Y represents the real-time load demand.

Images