Construction method, application method and system of water-light output prediction model

Abstract

The invention provides a construction method, an application method and a system for a water-light output prediction model, and the construction method comprises the steps: carrying out the construction of a seasonal autoregression comprehensive moving average model and an exponential smoothing trigonometric function model through the collected water-power output data of a historical time interval and the collected photovoltaic output data of the historical time interval; calculating respective weight coefficients corresponding to the seasonal autoregression comprehensive moving average model and the exponential smoothing trigonometric function model by adopting a least square method; and constructing a water-light combined output model based on the seasonal autoregression comprehensive moving average model, the exponential smoothing trigonometric function model and respective corresponding weight coefficients, thereby further improving the accuracy and efficiency of the water-light combined output model in water-light output prediction.

Description

Technical Field

[0001] The present invention relates to the field of power systems, and particularly to a method, an application method and a system for constructing a water-light output prediction model. Background Art

[0002] The output of distributed photovoltaic power fluctuates greatly, and the reliable power supply capacity and power supply quality level are poor; the water and photovoltaic power generations have certain complementarity. Taking China as an example, small hydropower resources are rich in the remote areas in the central and western regions of China, and at the same time, a large number of small hydropower resources highly coincide with the light resources in terms of geographical distribution. Therefore, it is very necessary to jointly model and predict water and light, and construct a combined output model to provide a theoretical basis for system optimal dispatching and resource allocation.

[0003] The current research mainly focuses on separately dealing with the uncertainty modeling of small hydropower and distributed photovoltaic power, ignoring the significant differences in the output characteristics of the two resources and the potential of the synergistic effect in the actual situation. And the method of constructing a combined output model by weighted combination can more accurately predict the combined output and improve the adaptability and flexibility of the model.

[0004] Therefore, how to construct a water-light combined output model and further improve the accuracy of model prediction is of great significance. Summary of the Invention

[0005] In order to solve the problem that the existing technology mainly focuses on static analysis in the aggregation modeling and often ignores the relationship between seasonal characteristics and daily power generation patterns, the present invention provides a method, an application method and a system for constructing a water-light output prediction model.

[0006] In the first aspect, a method for constructing a water-light output prediction model is provided, including:

[0007] Constructing a seasonal autoregressive integrated moving average model with the collected historical time interval of hydropower output data as the input and the predicted future time interval of hydropower output data as the output;

[0008] Constructing an exponential smoothing trigonometric function model with the collected historical time interval of photovoltaic output data as the input and the predicted future time interval of photovoltaic output data as the output;

[0009] Calculating the respective weight coefficients of the seasonal autoregressive integrated moving average model and the exponential smoothing trigonometric function model by using the least square method;

[0010] Constructing a water-light combined output model based on the seasonal autoregressive integrated moving average model, the exponential smoothing trigonometric function model and their respective weight coefficients.

[0011] Preferably, calculating the weight coefficients corresponding to the seasonal autoregressive integrated moving average model and the exponential smoothing trigonometric function model by using the least squares method includes:

[0012] Collect the hydropower output data and photovoltaic output data at the current moment;

[0013] Input the hydropower output data at the current moment into the seasonal autoregressive integrated moving average model to obtain the predicted hydropower output data in the future time interval;

[0014] Input the photovoltaic output data at the current moment into the exponential smoothing trigonometric function model to obtain the predicted photovoltaic output data in the future time interval;

[0015] Construct an objective function with the minimum square error between the actual power generation and the predicted power generation as the goal, where the predicted power generation is the weighted sum of the predicted hydropower output data and photovoltaic output data in the future time interval;

[0016] Take the partial derivatives of the weight coefficients in the objective function respectively, set the partial derivatives to zero to solve the optimal solutions of the weight coefficients in the objective function, and use the obtained optimal solutions of the weight coefficients in the objective function as the weight coefficients corresponding to the seasonal autoregressive integrated moving average model and the exponential smoothing trigonometric function model respectively.

[0017] Preferably, the calculation formula of the objective function is as follows:

[0018]

[0019] where, P h (t) represents the predicted hydropower output data at time t output by the seasonal autoregressive integrated moving average model, P v (t) represents the predicted photovoltaic output data at time t output by the exponential smoothing trigonometric function model, P0(t) represents the actual power generation at time t, J(α,β) is the objective function with the minimum square error between the actual power generation and the predicted hydropower output data and photovoltaic output data in the future time interval as the goal, α represents the weight coefficient of the hydropower output data, β represents the weight coefficient of the photovoltaic output data, and T is the length of the time series.

[0020] Preferably, the calculation formula for taking the partial derivatives of the weight coefficients in the objective function respectively and setting the partial derivatives to zero is as follows:

[0021]

[0022] where, the P0(t) represents the actual power generation at time t.

[0023] Preferably, the construction of the seasonal autoregressive integrated moving average model includes:

[0024] Preprocess the hydropower output data in the obtained historical time interval to obtain the processed hydropower output time series data;

[0025] Determine the parameter values of each parameter in the seasonal autoregressive integrated moving average model based on the seasonal characteristic information of the processed hydropower output data, and generate a seasonal autoregressive integrated moving average model based on the parameter values of each parameter, where the input of the seasonal autoregressive integrated moving average model is the hydropower output time series data in the historical time interval, and the output is the predicted hydropower output data in the future time interval.

[0026] Preferably, the construction of the exponential smoothing trigonometric function model includes:

[0027] Preprocess the photovoltaic data in the obtained historical time interval to obtain the processed photovoltaic output data;

[0028] Use the processed photovoltaic output data as the input and the predicted photovoltaic output data in the future time interval as the output to construct an exponential smoothing trigonometric function model.

[0029] Preferably, the hydropower output data includes at least one of the daily flow, power generation, and regulating reservoir water level in the small hydropower current domain;

[0030] The photovoltaic output data includes the power generation of the photovoltaic system and / or meteorological conditions.

[0031] In a second aspect, the present application provides a system for constructing a water-light output prediction model, including:

[0032] The first construction module is used to construct a seasonal autoregressive integrated moving average model with the hydropower output data in the collected historical time interval as the input and the predicted hydropower output data in the future time interval as the output;

[0033] The second construction module is used to construct an exponential smoothing trigonometric function model with the photovoltaic output data in the collected historical time interval as the input and the predicted photovoltaic output data in the future time interval as the output;

[0034] The calculation module is used to calculate the respective weight coefficients of the seasonal autoregressive integrated moving average model and the exponential smoothing trigonometric function model by using the least squares method;

[0035] The third construction module is used to construct a water-light combined output model based on the seasonal autoregressive integrated moving average model, the exponential smoothing trigonometric function model, and their respective weight coefficients.

[0036] Preferably, the calculation module is further configured to:

[0037] Collect the hydropower output data and photovoltaic output data at the current moment;

[0038] Input the hydropower output data at the current moment into the seasonal autoregressive integrated moving average model to obtain the predicted hydropower output data for the future time interval;

[0039] Input the photovoltaic output data at the current moment into the exponential smoothing trigonometric function model to obtain the predicted photovoltaic output data for the future time interval;

[0040] Construct an objective function with the minimum square error between the actual power generation and the predicted power generation as the goal, where the predicted power generation is the weighted sum of the predicted hydropower output data and photovoltaic output data for the future time interval;

[0041] Take the partial derivatives of the weight coefficients in the objective function respectively, set the partial derivatives to zero to solve the optimal solutions of the weight coefficients in the objective function, and use the obtained optimal solutions of the weight coefficients in the objective function as the weight coefficients corresponding to the seasonal autoregressive integrated moving average model and the exponential smoothing trigonometric function model respectively.

[0042] Preferably, the calculation formula of the objective function in the calculation module is as follows:

[0043]

[0044] Where, P h (t) represents the predicted hydropower output data at time t output by the seasonal autoregressive integrated moving average model, P v (t) represents the predicted photovoltaic output data at time t output by the exponential smoothing trigonometric function model, P0(t) represents the actual power generation at time t, J(α, β) is an objective function with the minimum square error between the actual power generation and the predicted hydropower output data and photovoltaic output data for the future time interval as the goal, α represents the weight coefficient of the hydropower output data, β represents the weight coefficient of the photovoltaic output data, and T is the length of the time series.

[0045] Preferably, the calculation formula for taking the partial derivatives of the weight coefficients in the objective function respectively and setting the partial derivatives to zero is as follows:

[0046]

[0047] Where, the P0(t) represents the actual power generation at time t.

[0048] Preferably, the construction of the seasonal autoregressive integrated moving average model in the first construction module includes:

[0049] Preprocess the hydropower output data in the obtained historical time interval to obtain processed hydropower output time series data;

[0050] Determine the parameter values of each parameter in the seasonal autoregressive integrated moving average model based on the seasonal characteristic information of the processed hydropower output data, and generate a seasonal autoregressive integrated moving average model based on the parameter values of each parameter. Among them, the input of the seasonal autoregressive integrated moving average model is the hydropower output time series data in the historical time interval, and the output is the predicted hydropower output data in the future time interval.

[0051] Preferably, the construction of the exponential smoothing trigonometric function model in the second construction module includes:

[0052] Preprocess the photovoltaic data in the obtained historical time interval to obtain processed photovoltaic output data;

[0053] Use the processed photovoltaic output data as the input and the predicted photovoltaic output data in the future time interval as the output to construct an exponential smoothing trigonometric function model.

[0054] Preferably, the hydropower output data includes at least one of the daily flow, power generation, and regulating reservoir water level in the small hydropower current domain;

[0055] The photovoltaic output data includes the power generation of the photovoltaic system and / or meteorological conditions.

[0056] In a third aspect, the present application provides a method for applying a water-light output prediction model, including:

[0057] Collect hydropower output data and photovoltaic output data in the target time interval;

[0058] Input the hydropower output data and photovoltaic output data in the target time interval into a pre-constructed water-light combined output model to obtain predicted water-light combined output data in the future time interval;

[0059] Among them, the water-light combined output model is constructed by a water-light output prediction model construction method as described above.

[0060] In a fourth aspect, the present application provides a water-light output prediction model application system, including:

[0061] A collection module for collecting hydropower output data and photovoltaic output data in the target time interval;

[0062] A prediction module for inputting the hydropower output data and photovoltaic output data in the target time interval into a pre-constructed water-light combined output model to obtain predicted water-light combined output data in the future time interval;

[0063] Among them, the water-light combined output model is constructed by using a water-light output prediction model construction method as described in any one of the foregoing.

[0064] On the other hand, the present application also provides an electronic device, including: at least one processor and a memory; the memory and the processor are connected by a bus;

[0065] The memory is used to store one or more programs;

[0066] When the one or more programs are executed by the at least one processor, a water-light output prediction model construction method and an application method as described above are implemented.

[0067] On the other hand, the present application also provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed, a water-light output prediction model construction method and an application method as described above are implemented.

[0068] Compared with the prior art, the beneficial effects of the present invention are:

[0069] The present invention provides a water-light output prediction model construction method, an application method and a system. The construction method constructs a seasonal autoregressive integrated moving average model and an exponential smoothing trigonometric function model respectively through the hydropower output data in the collected historical time interval and the photovoltaic output data in the historical time interval, and calculates the respective weight coefficients corresponding to the seasonal autoregressive integrated moving average model and the exponential smoothing trigonometric function model by using the least square method. Furthermore, a water-light combined output model is constructed based on the seasonal autoregressive integrated moving average model, the exponential smoothing trigonometric function model and their respective weight coefficients, further improving the accuracy and efficiency of the water-light combined output model for predicting water-light output. BRIEF DESCRIPTION OF THE DRAWINGS

[0070] Figure 1 is a flowchart of the water-light output prediction model construction method of the present invention;

[0071] Figure 2 is a schematic structural diagram of the water-light output prediction model construction system of the present invention;

[0072] Figure 3 is a flowchart of the water-light output prediction model application method of the present invention;

[0073] Figure 4 is a schematic structural diagram of the water-light output prediction model application system of the present invention;

[0074] Figure 5 is a schematic structural diagram of an electronic device of the present invention. Specific implementation manner

[0075] The present invention proposes a method, application method and system for constructing a water-light output prediction model, which systematically analyzes the seasonal fluctuations of small hydropower and the intra-day fluctuations of distributed photovoltaic, and reveals the significant differences in their power generation characteristics. This differential understanding provides a basis for data preprocessing, including missing value filling and standardization processing, ensuring the reliability and comparability of data. Secondly, the SARIMA and TBATS models are used to model the output of small hydropower and distributed photovoltaic respectively, effectively capturing the characteristics of their time series, thereby significantly improving the accuracy of prediction. In addition, through the joint modeling and weighted combination of the two models, the research realizes the synergy effect between different power sources, and further enhances the accuracy of the overall power generation capacity prediction. This method not only optimizes resource planning and management, but also provides a scientific basis for the rational allocation of renewable energy, and has broad application prospects.

[0076] To better understand the present invention, the content of the present invention will be further described below in conjunction with the accompanying drawings of the specification and embodiments.

[0077] Embodiment 1:

[0078] A method for constructing a water-light output prediction model, as Figure 1 shown, includes:

[0079] Step 1: Construct a seasonal autoregressive integrated moving average model with the hydropower output data in the collected historical time interval as the input and the hydropower output data in the predicted future time interval as the output;

[0080] Step 2: Construct an exponential smoothing trigonometric function model with the photovoltaic output data in the collected historical time interval as the input and the photovoltaic output data in the predicted future time interval as the output;

[0081] Step 3: Calculate the respective weight coefficients of the seasonal autoregressive integrated moving average model and the exponential smoothing trigonometric function model by using the least square method;

[0082] Step 4: Construct a water-light combined output model based on the seasonal autoregressive integrated moving average model, the exponential smoothing trigonometric function model and their respective weight coefficients.

[0083] In this embodiment, the hydropower output data includes at least one of the daily flow, power generation amount, and regulating reservoir water level in the small hydropower current domain; the photovoltaic output data includes the power generation amount of the photovoltaic system and / or meteorological conditions.

[0084] In this embodiment, in the process of calculating the weight coefficients corresponding to the seasonal autoregressive integrated moving average model and the exponential smoothing trigonometric function model by using the least squares method in step 2, it includes:

[0085] Collect the hydropower output data and photovoltaic output data at the current moment;

[0086] Input the hydropower output data at the current moment into the seasonal autoregressive integrated moving average model to obtain the predicted hydropower output data for the future time interval;

[0087] Input the photovoltaic output data at the current moment into the exponential smoothing trigonometric function model to obtain the predicted photovoltaic output data for the future time interval;

[0088] Construct an objective function with the goal of minimizing the squared error between the actual power generation and the predicted power generation, where the predicted power generation is the weighted sum of the predicted hydropower output data and photovoltaic output data for the future time interval;

[0089] Take the partial derivatives of the weight coefficients in the objective function respectively, set the partial derivatives to zero to solve the optimal solutions of the weight coefficients in the objective function, and use the obtained optimal solutions of the weight coefficients in the objective function as the weight coefficients corresponding to the seasonal autoregressive integrated moving average model and the exponential smoothing trigonometric function model respectively.

[0090] In this embodiment, the calculation formula of the constructed objective function is as follows:

[0091]

[0092] Where, P h (t) represents the predicted hydropower output data at time t output by the seasonal autoregressive integrated moving average model, P v (t) represents the predicted photovoltaic output data at time t output by the exponential smoothing trigonometric function model, P0(t) represents the actual power generation at time t, J(α,β) is the objective function with the goal of minimizing the squared error between the actual power generation and the predicted hydropower output data and photovoltaic output data for the future time interval, α represents the weight coefficient of the hydropower output data, β represents the weight coefficient of the photovoltaic output data, and T is the length of the time series.

[0093] In this embodiment, the calculation formulas for taking the partial derivatives of the weight coefficients in the objective function respectively and setting the partial derivatives to zero are as follows:

[0094]

[0095] Where, the P0(t) represents the actual power generation at time t.

[0096] In this embodiment, in the process of constructing the seasonal autoregressive integrated moving average model in step 1, it includes:

[0097] Preprocess the hydropower output data of the obtained historical time interval to obtain the processed hydropower output time series data;

[0098] Determine the parameter values of each parameter in the seasonal autoregressive integrated moving average model based on the seasonal characteristic information of the processed hydropower output data, and generate the seasonal autoregressive integrated moving average model based on the parameter values of each parameter. Among them, the input of the seasonal autoregressive integrated moving average model is the hydropower output time series data of the historical time interval, and the output is the predicted hydropower output data of the future time interval.

[0099] Specifically, the seasonal autoregressive integrated moving average model understands the basic structure of the hydropower output time series data, observes its overall trend, seasonal fluctuations, and outliers, and uses differences or deletes missing points to ensure time continuity. Then, it conducts a stationarity test on the data, and performs differencing processing when the stationarity test is passed. Next, it determines the orders of the autoregressive and moving average terms, and verifies whether the model adequately captures the data characteristics through model fitting. Furthermore, it conducts model prediction and evaluation to generate the hydropower output prediction data of the future time interval and verifies the accuracy of the model based on this hydropower output prediction data.

[0100] In this embodiment, in the process of constructing the exponential smoothing trigonometric function model in step 2, it includes:

[0101] Preprocess the photovoltaic data of the obtained historical time interval to obtain the processed photovoltaic output data;

[0102] Use the processed photovoltaic output data as the input and the predicted photovoltaic output data of the future time interval as the output to construct the exponential smoothing trigonometric function model.

[0103] Embodiment 2:

[0104] This embodiment details the foregoing method for constructing the water and light output prediction model.

[0105] First, process and standardize the data of small hydropower and photovoltaic, including but not limited to the daily flow, power generation, regulated reservoir water level in the small hydropower catchment area, power generation of the photovoltaic system, meteorological conditions (such as sunshine hours, light intensity), etc.

[0106] Then, based on the time series analysis method, aiming at the obvious seasonal fluctuation characteristics of small hydropower, its SARIMA model (i.e., the aforementioned seasonal autoregressive integrated moving average model) is constructed and the TBATS model (i.e., the aforementioned trigonometric function model of exponential smoothing) is constructed to accurately capture the intraday and seasonal characteristics of the photovoltaic system.

[0107] After constructing the water-light power prediction model, fully considering the contribution ratio and characteristics of water and light power, a combined water-light power output model is constructed by using the weighted combination method, and the least squares method (OLS) is used to estimate the optimal values of the weight coefficients α and β, so that the combined output data predicted by the combined water-light power output model is as close as possible to the actual output.

[0108] Assume that the power outputs of small hydropower and photovoltaic are P h (t) and P v (t) respectively, then the combined output can be expressed as:

[0109] P all (t) = αP h (t) + βP v (t) (1)

[0110] Where: α and β are weighted coefficients.

[0111] In order to make the combined water-light power output model more accurate, it is necessary to estimate and optimize the weight coefficients α and β in the model. The least squares method (OLS) is used to estimate the optimal values of α and β, mainly by minimizing the square error between the actual power generation and the model prediction value. The objective function is:

[0112]

[0113] Where, P0(t) is the actual power generation at time t, and T is the length of the time series.

[0114] The least squares method can obtain the analytical solutions of α and β by taking the partial derivatives of the objective function and making them zero.

[0115] First, rewrite the objective function as:

[0116]

[0117] To minimize J(α, β), take the partial derivatives of α and β respectively and set them to zero:

[0118]

[0119] By arranging these equations, a system of linear equations can be obtained:

[0120]

[0121] Write it in matrix form:

[0122]

[0123] It is represented by matrix notation as:

[0124]

[0125] Where:

[0126]

[0127] Finally, α and β can be solved by matrix inversion:

[0128]

[0129] The constraint conditions are:

[0130] α + β = 1, α ≥ 0, β ≥ 0 (11)

[0131] Through the least squares method, the weight coefficients α and β in the water-light combined output model can be effectively estimated, making the combined output predicted by the model as close as possible to the actual output. This method relies on the observed data and can provide the optimal coefficient estimation by minimizing the squared error.

[0132] Embodiment 3:

[0133] Based on the same inventive concept, the present invention also provides a water-light output prediction model construction system, as Figure 2 shown, including:

[0134] A first construction module, configured to construct a seasonal autoregressive integrated moving average model with the hydropower output data in the collected historical time interval as the input and the hydropower output data in the predicted future time interval as the output;

[0135] A second construction module, configured to construct an exponentially smoothed trigonometric function model with the photovoltaic output data in the collected historical time interval as the input and the photovoltaic output data in the predicted future time interval as the output;

[0136] A calculation module, configured to calculate the respective weight coefficients of the seasonal autoregressive integrated moving average model and the exponentially smoothed trigonometric function model by using the least squares method;

[0137] A third construction module, configured to construct a water-light combined output model based on the seasonal autoregressive integrated moving average model, the exponentially smoothed trigonometric function model, and their respective weight coefficients.

[0138] Preferably, the calculation module is further configured to:

[0139] Collect the hydropower output data and photovoltaic output data at the current moment;

[0140] Input the hydropower output data at the current moment into the seasonal autoregressive integrated moving average model to obtain the predicted hydropower output data for the future time interval;

[0141] Input the photovoltaic output data at the current moment into the trigonometric function model of exponential smoothing to obtain the predicted photovoltaic output data for the future time interval;

[0142] Construct an objective function with the goal of minimizing the squared error between the actual power generation and the predicted power generation, where the predicted power generation is the weighted sum of the predicted hydropower output data and photovoltaic output data for the future time interval;

[0143] Take the partial derivatives of the weight coefficients in the objective function respectively, set the partial derivatives to zero to solve the optimal solutions of the weight coefficients in the objective function, and use the obtained optimal solutions of the weight coefficients in the objective function as the corresponding weight coefficients of the seasonal autoregressive integrated moving average model and the trigonometric function model of exponential smoothing respectively.

[0144] Preferably, the calculation formula of the objective function in the calculation module is as follows:

[0145]

[0146] Among them, P h (t) represents the predicted hydropower output data at time t output by the seasonal autoregressive integrated moving average model, P v (t) represents the predicted photovoltaic output data at time t output by the trigonometric function model of exponential smoothing, P0(t) represents the actual power generation at time t, J(α,β) is the objective function with the goal of minimizing the squared error between the actual power generation and the predicted hydropower output data and photovoltaic output data for the future time interval, α represents the weight coefficient of the hydropower output data, β represents the weight coefficient of the photovoltaic output data, and T is the length of the time series.

[0147] Preferably, the calculation formula for taking the partial derivatives of the weight coefficients in the objective function respectively and setting the partial derivatives to zero in the calculation module is as follows:

[0148]

[0149] Among them, the P0(t) represents the actual power generation at time t.

[0150] Preferably, the construction of the seasonal autoregressive integrated moving average model in the first construction module includes:

[0151] Preprocess the hydropower output data in the obtained historical time interval to obtain the processed hydropower output time series data;

[0152] Determine the parameter values of each parameter in the seasonal autoregressive integrated moving average model based on the seasonal characteristic information of the processed hydropower output data, and generate a seasonal autoregressive integrated moving average model based on the parameter values of each parameter. Among them, the input of the seasonal autoregressive integrated moving average model is the hydropower output time series data in the historical time interval, and the output is the predicted hydropower output data in the future time interval.

[0153] Preferably, the construction of the exponential smoothing trigonometric function model in the second construction module includes:

[0154] Preprocess the photovoltaic data in the obtained historical time interval to obtain the processed photovoltaic output data;

[0155] Use the processed photovoltaic output data as the input and the predicted photovoltaic output data in the future time interval as the output to construct an exponential smoothing trigonometric function model.

[0156] Preferably, the hydropower output data includes at least one of the daily flow, power generation, and regulating reservoir water level in the small hydropower current domain;

[0157] The photovoltaic output data includes the power generation of the photovoltaic system and meteorological conditions / or.

[0158] Embodiment 4:

[0159] Based on the same inventive concept, the present invention also provides a method for applying a water-light output prediction model, as Figure 3 shown, including:

[0160] Step S1: Collect hydropower output data and photovoltaic output data in the target time interval;

[0161] Step S2: Input the hydropower output data and photovoltaic output data in the target time interval into the pre-constructed water-light combined output model to obtain the predicted water-light combined output data in the future time interval;

[0162] Among them, the water-light combined output model is constructed by a water-light output prediction model construction method as described above.

[0163] Embodiment 5:

[0164] Based on the same inventive concept, the present invention also provides a water-light output prediction model application system, as Figure 4 shown, including:

[0165] A collection module for collecting hydropower output data and photovoltaic output data in the target time interval;

[0166] A prediction module, configured to input the hydropower output data and photovoltaic output data in the target time interval into a pre-constructed combined water and light output model, and obtain the predicted combined water and light output data in a future time interval;

[0167] Wherein, the combined water and light output model is constructed by using a combined water and light output prediction model construction method as described in any one of the foregoing.

[0168] Embodiment 6

[0169] As Figure 5 shown, the present invention further provides an electronic device, which may be a computer device, a single-chip microcomputer device, a smart mobile device, etc. The electronic device in this embodiment may include a processor, a memory, a transceiver component, etc. The memory, the processor and the transceiver component are connected through a bus; the memory can be used to store an execution program, and an exemplary execution program may include instructions; the processor is used to execute the instructions stored in the memory. The memory can also be used to store data, and the data can be called and / or modified when the instructions are executed.

[0170] The processor may be a Central Processing Unit (CPU), or may also be other general-purpose processors, Digital Signal Processors (DSPs), Application Specific Integrated Circuits (ASICs), Field-Programmable Gate Arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. It is the computing core and control core of the terminal, and is adapted to implement one or more instructions, specifically adapted to load and execute one or more instructions in a storage medium to implement the corresponding method flow or corresponding function, so as to implement the steps of a combined water and light output prediction model construction method and an application method in the foregoing embodiment.

[0171] Embodiment 7

[0172] Based on the same inventive concept, the present invention also provides a readable storage medium, specifically an electronic device-readable storage medium (Memory). The electronic device-readable storage medium is a memory device in the electronic device, used to store programs and data. It can be understood that the storage medium here can include both the built-in storage medium in the electronic device and, of course, the extended storage medium supported by the electronic device. The storage medium provides a storage space, and this storage space stores the operating system of the terminal. Moreover, in this storage space, there is also stored one or more instructions suitable for being loaded and executed by the processor. These instructions can be one or more execution programs (including program codes). It should be noted that the storage medium here can be a high-speed RAM memory or a non-volatile memory, such as at least one disk memory. By the processor loading and executing one or more instructions stored in the storage medium, the steps of a method for constructing a water-light output prediction model and an application method in the above embodiments can be implemented.

[0173] Those skilled in the art should understand that the embodiments of the present invention can be provided as a method, a system, or a computer program product. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present invention can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk memories, CD-ROMs, optical memories, etc.) containing computer-usable program codes.

[0174] The present invention is described with reference to the flowcharts and / or block diagrams of methods, apparatuses (systems), and computer program products according to the embodiments of the present invention. It should be understood that each flow and / or block in the flowcharts and / or block diagrams, as well as the combination of flows and / or blocks in the flowcharts and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to generate a machine, such that the instructions executed by the processor of the computer or other programmable data processing devices generate a device for implementing the specified functions in Figure 1 one flow or multiple flows and / or blocks Figure 1 one block or multiple blocks.

[0175] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, such that the instructions stored in the computer-readable memory generate a manufactured article including an instruction device, and the instruction device implements the specified functions in Figure 1 one flow or multiple flows and / or blocks Figure 1The functions specified in one or more boxes.

[0176] These computer program instructions can also be loaded onto a computer or other programmable data processing device, so that a series of operation steps are executed on the computer or other programmable device to generate a computer-implemented process. Thus, the instructions executed on the computer or other programmable device provide for implementing the steps of the functions specified in one Figure 1 one process or more processes and / or boxes Figure 1 step of the functions specified in one or more boxes.

[0177] The above are only embodiments of the present invention and are not used to limit the present invention. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present invention are included within the scope of the claims of the present invention pending approval.

Claims

1. A method for constructing a water-light output prediction model, characterized in that Including: Construct a seasonal autoregressive integrated moving average model with the hydropower output data in the collected historical time interval as the input and the predicted hydropower output data in the future time interval as the output; Construct an exponential smoothing trigonometric function model with the photovoltaic output data in the collected historical time interval as the input and the predicted photovoltaic output data in the future time interval as the output; Calculate the respective weight coefficients corresponding to the seasonal autoregressive integrated moving average model and the exponential smoothing trigonometric function model by using the least squares method; Construct a combined hydropower and photovoltaic output model based on the seasonal autoregressive integrated moving average model, the exponential smoothing trigonometric function model and their respective corresponding weight coefficients.

2. The method according to claim 1, characterized in that, The calculating the respective weight coefficients corresponding to the seasonal autoregressive integrated moving average model and the exponential smoothing trigonometric function model by using the least squares method includes: Collect the hydropower output data and photovoltaic output data at the current moment; Input the hydropower output data at the current moment into the seasonal autoregressive integrated moving average model to obtain the predicted hydropower output data in the future time interval; Input the photovoltaic output data at the current moment into the exponential smoothing trigonometric function model to obtain the predicted photovoltaic output data in the future time interval; Construct an objective function with the goal of minimizing the squared error between the actual power generation and the predicted power generation, where the predicted power generation is the weighted sum of the predicted hydropower output data and photovoltaic output data in the future time interval; Take the partial derivatives of the weight coefficients in the objective function respectively, set the partial derivatives to zero to solve the optimal solutions of the weight coefficients in the objective function, and use the obtained optimal solutions of the weight coefficients in the objective function as the respective corresponding weight coefficients of the seasonal autoregressive integrated moving average model and the exponential smoothing trigonometric function model.

3. The method according to claim 2, characterized in that, The calculation formula of the objective function is as follows: Among them, P h (t) represents the hydropower output data at time t of the prediction output by the seasonal autoregressive integrated moving average model, P v (t) represents the photovoltaic output data at time t of the prediction output by the exponential smoothing trigonometric function model, P0(t) represents the actual power generation at time t, J(α, β) is the objective function with the goal of minimizing the squared error between the actual power generation and the hydropower output data and the photovoltaic output data in the predicted future time interval, α represents the weight coefficient of the hydropower output data, β represents the weight coefficient of the photovoltaic output data, and T is the length of the time series.

4. The method according to claim 3, characterized in that, The calculation formulas for taking the partial derivatives of the weight coefficients in the objective function respectively and setting the partial derivatives to zero are as follows: Where, P0(t) represents the actual power generation at time t.

5. The method according to claim 1, wherein The construction of the seasonal autoregressive integrated moving average model includes: Preprocess the hydropower output data in the obtained historical time interval to obtain the processed hydropower output time series data; Determine the parameter values of each parameter in the seasonal autoregressive integrated moving average model based on the seasonal characteristic information of the processed hydropower output data, and generate a seasonal autoregressive integrated moving average model based on the parameter values of each parameter, where the input of the seasonal autoregressive integrated moving average model is the hydropower output time series data in the historical time interval and the output is the predicted hydropower output data in the future time interval.

6. The method according to claim 1, characterized in that, The construction of the exponential smoothing trigonometric function model includes: Preprocess the photovoltaic data in the obtained historical time interval to obtain the processed photovoltaic output data; Use the processed photovoltaic output data as the input and the predicted photovoltaic output data in the future time interval as the output to construct an exponential smoothing trigonometric function model.

7. The method according to claim 1, characterized in that The hydropower output data includes at least one of the daily flow, power generation, and regulating reservoir water level in the small hydropower current domain; The photovoltaic output data includes the power generation of the photovoltaic system and / or meteorological conditions.

8. A system for constructing a water-light output prediction model, characterized in that Comprising: A first construction module for constructing a seasonal autoregressive integrated moving average model with the collected hydropower output data in the historical time interval as the input and the predicted hydropower output data in the future time interval as the output; A second construction module for constructing an exponentially smoothed trigonometric function model with the collected photovoltaic output data in the historical time interval as the input and the predicted photovoltaic output data in the future time interval as the output; A calculation module for calculating the respective weight coefficients of the seasonal autoregressive integrated moving average model and the exponentially smoothed trigonometric function model by using the least squares method; A third construction module for constructing a combined hydropower and photovoltaic output model based on the seasonal autoregressive integrated moving average model, the exponentially smoothed trigonometric function model and their respective weight coefficients.

9. The system according to claim 8, wherein The calculation module is further configured to: Collect the hydropower output data and the photovoltaic output data at the current moment; Input the hydropower output data at the current moment into the seasonal autoregressive integrated moving average model to obtain the predicted hydropower output data in the future time interval; Input the photovoltaic output data at the current moment into the exponentially smoothed trigonometric function model to obtain the predicted photovoltaic output data in the future time interval; Construct an objective function with the goal of minimizing the squared error between the actual power generation and the predicted power generation, wherein the predicted power generation is the weighted sum of the predicted hydropower output data and the photovoltaic output data in the future time interval; Respectively take partial derivatives of the weight coefficients in the objective function, set the partial derivatives to zero to solve the optimal solutions of the weight coefficients in the objective function, and respectively use the obtained optimal solutions of the weight coefficients in the objective function as the weight coefficients corresponding to the seasonal autoregressive integrated moving average model and the exponentially smoothed trigonometric function model.

10. The system according to claim 9, wherein, The calculation formula of the objective function in the calculation module is as follows: Among them, P h (t) represents the hydropower output data at time t of the prediction output by the seasonal autoregressive integrated moving average model, P v (t) represents the photovoltaic output data at time t of the prediction output by the exponential smoothing trigonometric function model, P0(t) represents the actual power generation at time t, J(α,β) is the objective function with the minimum square error between the actual power generation and the hydropower output data and the photovoltaic output data in the predicted future time interval as the goal, α represents the weight coefficient of the hydropower output data, β represents the weight coefficient of the photovoltaic output data, and T is the length of the time series.

11. The system according to claim 10, wherein The calculation formulas for respectively taking partial derivatives of the weight coefficients in the objective function in the calculation module and setting the partial derivatives to zero are as follows: Wherein, the P0(t) represents the actual power generation at time t.

12. The system according to claim 8, wherein The construction of the seasonal autoregressive integrated moving average model in the first construction module includes: Preprocess the collected hydropower output data in the historical time interval to obtain the processed hydropower output time series data; Determine the parameter values of each parameter in the seasonal autoregressive integrated moving average model based on the seasonal characteristic information of the processed hydropower output data, and generate a seasonal autoregressive integrated moving average model based on the parameter values of each parameter, wherein the input of the seasonal autoregressive integrated moving average model is the processed hydropower output time series data in the historical time interval, and the output is the predicted hydropower output data in the future time interval.

13. The system according to claim 8, wherein The construction of the exponentially smoothed trigonometric function model in the second construction module includes: Preprocess the collected photovoltaic data in the historical time interval to obtain the processed photovoltaic output data; Use the processed photovoltaic output data as the input and the predicted photovoltaic output data in the future time interval as the output to construct an exponentially smoothed trigonometric function model.

14. The system according to claim 8, wherein The hydropower output data includes at least one of the daily flow, power generation, and regulating reservoir water level in a small hydropower area; The photovoltaic output data includes the power generation of the photovoltaic system and / or meteorological conditions.

15. A method for applying a water-light output prediction model, characterized in that, It includes: Collecting the hydropower output data and photovoltaic output data in a target time interval; Inputting the hydropower output data and photovoltaic output data in the target time interval into a pre-constructed combined water and light output model to obtain the predicted combined water and light output data in a future time interval; Wherein, the combined water and light output model is constructed by a method for constructing a combined water and light output prediction model as described in any one of claims 1 to 7.

16. A system for applying a water-light output prediction model, characterized in that, It includes: A collection module for collecting the hydropower output data and photovoltaic output data in a target time interval; A prediction module for inputting the hydropower output data and photovoltaic output data in the target time interval into a pre-constructed combined water and light output model to obtain the predicted combined water and light output data in a future time interval; Wherein, the combined water and light output model is constructed by a method for constructing a combined water and light output prediction model as described in any one of claims 1 to 7.

17. An electronic device, characterized in that, It includes: At least one processor and a memory; The memory and the processor are connected by a bus; The memory is used to store one or more programs; When the one or more programs are executed by the at least one processor, the method for constructing a combined water and light output prediction model as described in any one of claims 1 to 7 and the method for applying the combined water and light output prediction model as described in claim 15 are implemented.

18. A readable storage medium, characterized in that, There is an execution program stored thereon, and when the execution program is executed, the method for constructing a combined water and light output prediction model as described in any one of claims 1 to 7 and the method for applying the combined water and light output prediction model as described in claim 15 are implemented.

Images