Coordination control method of distributed energy system and related equipment

Abstract

The invention provides a coordination control method of a distributed energy system and related equipment, and the method comprises the steps: obtaining the production modes and basic data of a plurality of energy supply units, classifying the plurality of energy supply units according to the production modes, and determining the main environment parameters of any type of energy supply units; determining first data corresponding to the main environmental parameters at different energy supply powers, constructing a first influence function, determining a time sequence for the energy supply powers, and forming a power model in combination with the first influence function; load requirements in different time periods are determined, and a load model is formed; determining the cost under unit power, and generating a second influence function in combination with second data corresponding to the main environmental parameters; performing power prediction and load prediction by using a power model and a load model according to the real-time data, and performing first adjustment by using a prediction result; and inputting the real-time data into a second influence function, performing prediction in combination with the power after the first adjustment, and performing second adjustment according to a prediction result.

Description

Technical Field

[0001] The present application relates to the technical field of data processing, and particularly to a coordinated control method for a distributed energy system and related devices. Background Art

[0002] The traditional energy system highly depends on fossil fuels and faces many challenges such as resource depletion, environmental pollution, and climate change. The new energy system, relying on renewable and clean energies such as solar energy, wind energy, water energy, and biomass energy, has become a key force in promoting the transformation of the energy structure towards low-carbon and sustainable development.

[0003] However, most of the new energy systems are distributed energy systems, and these distributed energies have characteristics such as intermittency, volatility, and low energy density. There is an urgent need for intelligent coordinated control optimization technology to ensure the stable and efficient operation of the system.

[0004] It should be noted that the information disclosed in the above background art section is only used to enhance the understanding of the background of the present disclosure, and thus may include information that does not constitute the prior art known to those skilled in the art. Summary of the Invention

[0005] In view of this, the present application provides a coordinated control method for a distributed energy system and related devices to solve or partially solve the above problems.

[0006] Based on the above purpose, the present application provides a coordinated control method for a distributed energy system, where the distributed energy system includes multiple energy supply units, and the method includes:

[0007] Obtain the production methods and basic data of the multiple energy supply units, classify the multiple energy supply units according to the production methods, and determine the main environmental parameters of any type of energy supply unit according to the supply power and environmental parameters in the basic data;

[0008] According to the basic data, determine the first data corresponding to the main environmental parameters of any type of energy supply unit at different supply powers, construct a first influence function using a linear regression model, determine the time series of any type of energy supply unit for the supply power, and form a power model in combination with the first influence function;

[0009] According to the basic data, determine the load demands of the distributed energy system at different time periods, and form a load model according to the change law of the load demands;

[0010] According to the basic data, determine the cost of any type of energy supply unit under unit power, and generate a second influence function in combination with the second data corresponding to the main environmental parameters when the cost changes under the same power;

[0011] Obtain the real-time data corresponding to the main environmental parameters, perform power prediction and load prediction using the power model and the load model based on the real-time data, and perform a first adjustment on the power of the multiple energy supply units using the prediction results;

[0012] Input the real-time data into the second influence function, construct a cost model in combination with the power after the first adjustment, perform prediction using the cost model, and perform a second adjustment according to the prediction results.

[0013] In some exemplary embodiments, determining the main environmental parameters of any type of energy supply unit includes:

[0014] According to the basic data, determine the change rate of the energy supply power of any type of energy supply unit under the influence of different environmental parameters, and select the environmental parameters whose change rate meets the set conditions as the main environmental parameters.

[0015] In some exemplary embodiments, constructing the first influence function using a linear regression model includes:

[0016] Taking the first data as the independent variable and the energy supply power as the dependent variable to form a first curve graph, using the linear regression model to fit the first curve graph, and then obtaining the first influence function in combination with the least squares method.

[0017] In some exemplary embodiments, forming the power model in combination with the first influence function includes:

[0018] Analyze the energy supply power of the time series using an autoregressive moving average model to form an autoregressive moving average model of any type of energy supply unit;

[0019] Substitute the autoregressive moving average model of any type of energy supply unit into the first influence function to obtain the power model of any type of energy supply unit.

[0020] In some exemplary embodiments, forming the load model according to the change law of the load demand includes:

[0021] Form a second curve graph according to the load demand of the distributed energy system at different time periods;

[0022] Determine the initial point and the initial load demand of the initial point in the second curve graph, determine the first point position where the initial load demand is reached in the second curve graph, take the curve from the initial point to the adjacent first point position as the first curve, and take the curves between other adjacent first point positions as the second curves;

[0023] Determine the similarity between the second curve and the first curve in sequence, take the previous first point position in the first completely similar second curve as the target point position, and take the curve between the initial point and the target point position as the target curve;

[0024] Form the load model according to the target curve.

[0025] In some exemplary embodiments, the constructing the cost model by combining the power after the first adjustment includes:

[0026] On the premise of ensuring that the total power after the first adjustment remains unchanged, construct the cost model by comparing the result obtained by inputting the real-time data into the second influence function with the power of the multiple energy supply units.

[0027] Based on the same concept, the present application also provides a coordinated control device for a distributed energy system. The distributed energy system includes multiple energy supply units, and the device includes:

[0028] A first module, configured to obtain the production methods and basic data of the multiple energy supply units, classify the multiple energy supply units according to the production methods, and determine the main environmental parameters of any type of energy supply unit according to the supply power and environmental parameters in the basic data;

[0029] A second module, configured to determine the first data corresponding to the main environmental parameters of any type of energy supply unit at different supply powers according to the basic data, construct a first influence function by using a linear regression model, determine the time series of the supply power of any type of energy supply unit, and form a power model by combining the first influence function;

[0030] A third module, configured to determine the load demand of the distributed energy system at different time periods according to the basic data, and form a load model according to the change rule of the load demand;

[0031] A fourth module, configured to determine the cost of any type of energy supply unit under unit power according to the basic data, and generate a second influence function by combining the second data corresponding to the main environmental parameters when the cost changes under the same power;

[0032] A fifth module, configured to obtain the real-time data corresponding to the main environmental parameters, perform power prediction and load prediction according to the real-time data by using the power model and the load model, and perform a first adjustment on the power of the multiple energy supply units by using the prediction results;

[0033] The sixth module is configured to input the real-time data into the second influence function, construct a cost model by combining the first adjusted power, perform prediction using the cost model, and perform a second adjustment according to the prediction result.

[0034] Based on the same concept, the present application further provides an electronic device, including a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the program, the method described in any one of the above is implemented.

[0035] Based on the same concept, the present application further provides a non-transitory computer-readable storage medium storing computer instructions for causing a computer to implement the method described in any one of the above.

[0036] Based on the same concept, the present application further provides a computer program product including computer program instructions that, when run on a computer, cause the computer to execute the method described in any one of the above.

[0037] As can be seen from the above, the present application provides a coordinated control method and related devices for a distributed energy system. The method includes: obtaining the production methods and basic data of multiple energy supply units, classifying the multiple energy supply units according to the production methods, and determining the main environmental parameters of any type of energy supply unit; determining the first data corresponding to the main environmental parameters at different energy supply powers, constructing a first influence function, determining the time series of the energy supply power, and forming a power model in combination with the first influence function; determining the load demands in different time periods to form a load model; determining the cost per unit power and generating a second influence function in combination with the second data corresponding to the main environmental parameters; performing power prediction and load prediction using the power model and the load model according to the real-time data, and performing a first adjustment using the prediction result; inputting the real-time data into the second influence function, performing prediction in combination with the power after the first adjustment, and performing a second adjustment according to the prediction result. Through the classification and analysis of the energy supply units, the present application can clearly distinguish the geographical distribution characteristics of different energy sources through classification, which helps to formulate exclusive production management strategies for different energy sources. After classification, targeted adjustments can be made according to various types to ensure stable energy output. At the same time, the response speed and adjustability of various types of energy supply units can be determined more accurately. Then, different main environmental parameters are obtained for different types of energy supply units, and the first influence function and the second influence function are calculated, so as to analyze the power, cost, etc. of different energy supply units respectively, optimize energy scheduling, and enhance energy storage planning. Description of the Drawings

[0038] To more clearly illustrate the technical solutions in the embodiments of the present application or in the related art, the following will briefly introduce the drawings required for use in the description of the embodiments or the related art. Obviously, the drawings in the following description are only the embodiments of the present application. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0039] Figure 1 It is a schematic flowchart of an exemplary method provided by an embodiment of the present application.

[0040] Figure 2 It is a schematic structural diagram of an exemplary device provided by an embodiment of the present application.

[0041] Figure 3 It is a schematic structural diagram of an electronic device provided by an embodiment of the present application. Detailed implementation manners

[0042] To make the purpose, technical solutions, and advantages of this specification clearer, the following will further describe this specification in detail with reference to specific embodiments and the accompanying drawings.

[0043] It should be noted that unless otherwise defined, the technical terms or scientific terms used in the embodiments of the present application should have the ordinary meaning understood by those of ordinary skill in the field to which the present application belongs. The "first", "second", and similar terms used in the embodiments of the present application do not indicate any order, quantity, or importance, but are only used to distinguish different components. The terms such as "including" or "comprising" mean that the elements, objects, or method steps appearing before this word cover the elements, objects, or method steps listed after this word and their equivalents, without excluding other elements, objects, or method steps. The terms such as "connected" or "coupled" are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. The terms such as "upper", "lower", "left", "right", etc. are only used to represent relative positional relationships, and when the absolute position of the object being described changes, the relative positional relationship may also change accordingly.

[0044] As described in the background art section, modern users have higher requirements for energy quality, reliability, and flexibility. They not only expect stable power supply and heating, but also pursue energy autonomy and controllability, and can customize energy services on demand, such as real-time regulation of electrical appliance power consumption in a smart home scenario. The distributed energy system is close to the user side. With the help of intelligent coordinated control optimization, it can integrate the scattered energy resources on the user side to meet diverse needs. However, the existing intelligent coordination of distributed energy systems analyzes different energy supply units uniformly, but the influence of some environmental parameters on different energy supply units is different, and the same analysis will lead to large errors, resulting in unnecessary energy waste.

[0045] In combination with the above actual situation, the embodiments of the present application provide a coordinated control method for a distributed energy system. By classifying and analyzing energy supply units, the geographical distribution characteristics of different energy sources can be clearly distinguished through classification; it helps to formulate exclusive production management strategies for different energy sources. After classification, targeted adjustments can be made according to each category to ensure stable energy output, and at the same time, the response speed and adjustability of each type of energy supply unit can be determined more accurately. Then, different main environmental parameters are obtained for different types of energy supply units, and the first influence function and the second influence function are calculated, so as to separately analyze the power, cost, etc. of different energy supply units, optimize energy scheduling, and enhance energy storage planning.

[0046] Figure 1 The flowchart of an exemplary method provided by the embodiments of the present application is shown.

[0047] As Figure 1 shown, the coordinated control method for a distributed energy system exemplarily proposed by the embodiments of the present application, where the distributed energy system may include multiple energy supply units, and the method specifically includes the following steps.

[0048] Step 102, obtain the production methods and basic data of the multiple energy supply units, classify the multiple energy supply units according to the production methods, and determine the main environmental parameters of any type of energy supply unit according to the supply power and environmental parameters in the basic data.

[0049] In this step, first, an energy supply unit can be understood as a unit that provides energy. In this scenario, specifically, it can be a new energy supply unit such as a wind energy supply unit, a solar energy supply unit, a water energy supply unit, a biomass energy supply unit, etc. Then, the production method is the specific energy production method of the energy supply unit, and the basic data can be the basic attribute data of an energy supply unit, such as power supply quantity data, or the historical data of the power supply data related to the energy supply unit. As long as it is data related to the energy supply unit and related to power supply or historical statistical data, it can be considered as the basic data of an energy supply unit.

[0050] In some embodiments, first, the energy supply units can be classified according to different production methods, and the energy supply units with the same production method are grouped together to form a type of energy supply unit. Then, by querying or collecting the supply power of all types of energy supply units under different environmental parameters in history through the basic data, the main environmental parameters affecting the power of each type of energy supply unit are extracted.

[0051] Specifically, the energy supply methods of each energy supply unit can be extracted first. The energy supply units with the same energy supply method are classified into the same type of energy supply unit. After classification, the number of types of energy supply units in the distributed energy system is N. Based on the basic data, all environmental parameters during the energy supply of all types of energy supply units in history are collected. The environmental parameters and the energy supply power of the energy supply unit are corresponding to form an energy supply point. The energy supply power curve is drawn with the change of the environmental parameters, and the speed of the change of the energy supply power affected by each environmental parameter is calculated. The specific formula can be:

[0052]

[0053] Among them, F represents the change speed of the power of the energy supply unit caused by each environmental parameter; G(h + Δh) represents the energy supply power after the environmental parameter h increases by Δh, G(h) represents the energy supply power when the environmental parameter is h, and Δh represents the change amount of the environmental parameter; the change speed of the energy supply power affected by each environmental parameter is repeatedly calculated in an energy supply unit.

[0054] After that, after calculating the change speeds of the energy supply power affected by all environmental parameters, compare their magnitudes, and select the one with the largest change speed as the main environmental parameter affecting the power of the corresponding energy supply unit. Then, repeat the above method to calculate the main environmental data of all types of energy supply units in the distributed energy system as {Hz 1 、Hz 2 、Hz 3 、…、Hz N}, Hz 1 、Hz 2 、Hz 3 、…、Hz N represents the main environmental parameters of the 1st, 2nd, 3rd, ……, Nth types of energy supply units in the calculated distributed energy system, and N is a positive integer. That is, in some embodiments, determining the main environmental parameter of any type of energy supply unit includes: determining the change speed of the energy supply power of the any type of energy supply unit under the influence of different environmental parameters according to the basic data, and selecting the environmental parameter whose change speed meets the set condition as the main environmental parameter. Among them, the set condition can be the largest change speed in the foregoing embodiments, and of course, in other scenarios, it can also be other specific conditions.

[0055] Classify and analyze the energy supply units in the distributed energy system. Through classification, the geographical distribution characteristics of different energies can be clearly distinguished; it helps to formulate exclusive production management strategies for different energies, and the equipment failure modes and operation and maintenance cycles of different energies are very different. After classification, inspections can be carried out according to their respective operation and maintenance cycles to extend the equipment life and ensure stable energy output; the classification of multiple energies enables dispatchers to clearly understand the response speed and adjustability of each energy.

[0056] Step 104: According to the basic data, determine the first data corresponding to the main environmental parameters of any type of energy supply unit at different energy supply powers, use a linear regression model to construct a first influence function, determine the time series of the energy supply power for any type of energy supply unit, and form a power model in combination with the first influence function.

[0057] In this step, first, it is possible to continue to follow up the data (i.e., the first data) corresponding to the main environmental parameters of all types of energy supply units at different energy supply powers in the basic data collection history, draw a curve graph using the data corresponding to the energy supply power and the main environmental parameters for each type of energy supply unit, and use a linear regression model to construct an environment-power influence function (i.e., the first influence function) for each type of energy supply unit. After that, it is possible to continue to collect the time series of the energy supply power of each type of energy supply unit in history, and generate a power model for each type of energy supply unit in combination with the constructed environment-power influence function.

[0058] In this embodiment, first, according to the basic data, it is possible to collect the first data corresponding to the main environmental parameters of all types of energy supply units at different energy supply powers in history. Let the collected energy supply power be G, and the first data corresponding to the main environmental parameters be Hz. Use the collected first data as the independent variable and the energy supply power G as the dependent variable to draw a curve graph, and use a linear regression model to fit the drawn curve graph to obtain the environment-power influence function as G = a×Hz + b. In the function, G represents the energy supply power of the energy supply unit, Hz represents the data corresponding to the main environmental parameters, which is the first data here, a represents the slope of the environment-power influence function, and b represents the intercept of the environment-power influence function. After calculating the environment-power influence function, use the least squares method to calculate the values of the slope a and the intercept b in the function respectively, and repeat the steps to calculate the environment-power influence function of each type of energy supply unit. Here, linear regression is a statistical analysis method that uses regression analysis in mathematical statistics to determine the quantitative relationship of mutual dependence between two or more variables; the least squares method is a mathematical optimization technique that finds the best function matching for a set of data by minimizing the sum of the squares of the errors. That is, in some embodiments, the constructing the first influence function using the linear regression model includes: using the first data as the independent variable and the energy supply power as the dependent variable to form a first curve graph, using the linear regression model to fit the first curve graph, and then obtaining the first influence function in combination with the least squares method. Among them, the first curve graph can be the curve graph drawn using the data corresponding to the energy supply power and the main environmental parameters as described above.

[0059] After that, it is possible to obtain the first data corresponding to different main environmental parameters for different types of energy supply units, calculate the environment-power influence function, and can specifically analyze the power of different types of energy supply units respectively to optimize energy scheduling and enhance energy storage planning.

[0060] In some embodiments, based on the basic data, the power supply power time series of each type of energy supply unit in history can be collected, and the autoregressive moving average model can be used to analyze the power supply power of the collected historical time series, and the autoregressive moving average model of each type of energy supply unit can be constructed. Specifically, it can be GY = ARMA(GL); in the model, GY represents the predicted power supply power of a certain type of energy supply unit, ARMA represents the autoregressive moving average model, and GL represents the power supply power time series in the collected history. Extract the environment-power influence function of each type of energy supply unit and construct the power model of each type of energy supply unit in combination with the autoregressive moving average model. Its formula can be:

[0061] P t = a × GY t + b

[0062] Wherein, GY t represents the power supply power at time t predicted by the autoregressive moving average model; P t represents the power supply power at time t predicted by the power prediction model combined with the environment-power influence function; since this formula is combined with the environment-power influence function, a and b are the same as or approximate to the definitions in the environment-power influence function. The power models are constructed by calculating each type of energy supply unit in the distributed energy system. Among them, the autoregressive moving average model (Autoregressive Moving Average Model, ARMA) is a time series prediction model that combines the characteristics of two models: autoregressive (AR) and moving average (MA). That is, in some embodiments, forming the power model by combining the first influence function includes: analyzing the power supply power of the time series by using the autoregressive moving average model to form the autoregressive moving average model of any type of energy supply unit; substituting the autoregressive moving average model of any type of energy supply unit into the first influence function to obtain the power model of any type of energy supply unit.

[0063] Step 106, according to the basic data, determine the load demand of the distributed energy system in different time periods, and form a load model according to the change law of the load demand.

[0064] In this step, based on the basic data, the load demands of the distributed energy system in different time periods can be collected, and a model corresponding to the load demand, that is, a load model, can be generated.

[0065] In some embodiments, through the basic data, the load demands of the distributed energy system in different time periods in history can be collected, and a curve graph can be drawn using the load demands that change with time in the collected distributed energy system. Then, for the initial point J in the curve graph0 Record the load demand, and then start traversing in the curve graph. When finding the point where the load demand in the curve is equal to the load demand at the initial point, mark it as J 1 , tentatively mark J 0 -J 1 as a curve segment, and record the time interval as t 0 . Continue to search for the next time period of t 0 length, and judge whether a second point J equal to the load demand at the initial point is obtained at 2t 0 ; Judge the similarity between the curve segments J 2 -J 0 -J 1 and J 1 -J 2 . Fit the curve segment J 0 -J 1 to obtain the fitting function f(t). Substitute the data points in the curve segment J 1 -J 2 into the fitting function f(t) to calculate the residual. The formula is: e i =Q i -f(t i ); In the formula, E i represents the residual of the curve segment J 1 -J 2 at t i , Q i represents the load demand of the curve segment J 1 -J 2 at t i , and f(t i ) represents the calculated value of the curve segment J 1 -J 2 at t i ; After calculating the residuals of all points, calculate the average residual. When the average residual is 0, judge that the curve segments J 0 -J 1 and J 1 -J 2 are the same; When the average residual is not 0, judge that the curve segments J 0 -J 1 and J 1 -J 2 are not the same. Then continue to search to obtain the curve segment judgment and the similarity of the curve segment J 0 -J 1 . When it is judged that the curve segment J j -J j+1 is the same as the curve segment J 0 -J 1 , judge that the curve segment J 0 -J jis a cycle of load demand; for the load demand cycle J 0 -J j The curve is fitted as a load model.

[0066] Thus, by using the power model to accurately predict the power of the energy supply unit, the power generation enterprise can know in advance the output of each energy unit. Based on the prediction of power and load by the power model and the load model, the energy supplier can arrange the start and stop of the unit more reasonably; predicting the power of different types of energy supply units and the load demand can enable the dispatching personnel to more scientifically match multiple types of energy. That is, in some embodiments, forming a load model according to the change rule of the load demand includes: forming a second curve graph according to the load demand of the distributed energy system at different time periods; determining an initial point and the initial load demand of the initial point in the second curve graph, determining a first point position where the initial load demand is reached in the second curve graph, taking the curve from the initial point to the adjacent first point position as the first curve, and taking the curves between other adjacent first point positions as the second curves; sequentially determining the similarity between the second curve and the first curve, taking the previous first point position in the first completely similar second curve as the target point position, and taking the curve from the initial point to the target point position as the target curve; forming the load model according to the target curve. Among them, the second curve graph can be the curve graph drawn by using the load demand changing with time in the collected distributed energy system; the first curve can be the aforementioned J 0 -J 1 curve segment, and the second curve can be the aforementioned J j -J j+1 curve segment.

[0067] Step 108, according to the basic data, determine the cost of any type of energy supply unit under unit power, and combine the second data corresponding to the main environmental parameters when the cost changes under the same power to generate a second influence function.

[0068] In this step, by collecting the power values and costs when each type of energy supply unit supplies energy in history, calculate the power and cost to obtain the cost of each type of energy supply unit under unit power; collect the data corresponding to the main environmental parameters when the cost of each type of energy supply unit changes under the same power in history (i.e., the second data), and construct an environment-cost influence function of the second data on the cost, that is, the second influence function.

[0069] In some embodiments, collect the power values and costs when each type of energy supply unit supplies energy in history, calculate the power and cost to obtain the cost of each type of energy supply unit under unit power, and the formula is: Ce = G / C; in the formula, Ce represents the calculated cost under unit power, G represents the power value when supplying energy in the collected history, and C represents the cost when supplying energy in history.

[0070] After that, collect the data corresponding to the main environmental parameters when the power cost of each type of energy supply unit in the history changes (i.e., the second data), draw a curve graph using the second data and the cost, and fit the curve graph through a linear regression model to obtain the environment-cost impact function as C = a 1 ×Hz + b 1 , in the function, C represents the cost, Hz represents the data corresponding to the main environmental parameters, here it is the second data, a 1 represents the slope of the environment-cost impact function, and b 1 represents the intercept of the environment-cost impact function. After that, substitute the environment-cost impact function here into the previous formula to obtain the environment-cost impact function under unit power, that is, the second impact function.

[0071] Step 110, obtain the real-time data corresponding to the main environmental parameters, perform power prediction and load prediction according to the real-time data using the power model and the load model, and perform a first adjustment on the power of the multiple energy supply units using the prediction results.

[0072] In this step, after obtaining the power model in step 104 and the load model in step 106, the load demand in the distributed energy system can be predicted using the load model; then, input the specific data of the real-time main environmental parameters into the power model, and use the power model to synchronously predict the power supply in the distributed energy system. After comparing the predicted load demand and power supply, a round of adjustment is performed on the power of each energy supply unit, that is, the first adjustment.

[0073] In some embodiments, the time period t to be predicted can be extracted y , use the load model to predict the load demand in the distributed energy system, and it can be predicted that the load demand at time t y is Q y . Input the real-time data corresponding to the real-time main environmental parameters into the power model, and use the power model to synchronously predict the power supply in the distributed energy system, and obtain the power of each type of energy supply unit at time t y as {Gy 1 , Gy 2 , Gy 3 , …, Gy N}, Gy 1 , Gy 2 , Gy 3 , …, Gy N represents the power of the 1st, 2nd, 3rd, …, Nth types of energy supply units at time t y .

[0074] After that, calculate the total power of all energy supply units predicted as G z , when G z <Q y , perform an adjustment round on all energy supply units. Specifically, the power of the energy supply units can be increased according to the prediction order. When the power of the first energy supply unit is increased to the maximum power, if the inequality still holds at this time (G z <Q y ), then continue to adjust the power of the second energy supply unit, and so on, until the inequality does not hold. The formula is: (Gy 1 +Gy 2 +Gy 3 +…+Gy N ) ↑ =Q y ; in the formula, () ↑ represents an increase in the power of the energy supply unit.

[0075] By predicting the energy generation and consumption trends in the future for a period of time, plan the operation plans of each energy supply unit in advance to ensure that the system can achieve efficient and stable operation under different working conditions, maximize the energy comprehensive utilization efficiency and system reliability, and effectively cope with the challenges of energy supply uncertainty and volatility.

[0076] Step 112: Input the real-time data into the second influence function, construct a cost model in combination with the power after the first adjustment, use the cost model for prediction, and perform a second adjustment according to the prediction results.

[0077] In this step, after obtaining the second influence function in step 108, the real-time data can be input into the second influence function. On the premise that the total power remains unchanged after one round of adjustment, construct a cost model using the real-time unit cost and the power after one round of adjustment, use the cost model for cost prediction, and then obtain the best optimization plan according to the prediction results, and use the best optimization plan for the second-round optimization adjustment, that is, the second adjustment.

[0078] In some embodiments, the total cost in the distributed energy system can be minimized by performing a second adjustment on the power of each energy supply unit. Specifically, input the real-time data into the second influence function, and use the real-time data to calculate the real-time unit cost of each energy supply unit as Ces; construct a cost model using the real-time unit cost and the energy supply unit after the first adjustment, and the model can be expressed as:

[0079] Ces 1 ×Gy 1 +Ces 2 ×Gy 2 +Ces 3 ×Gy 3 +…+CesN × Gy N = Cz

[0080] where Cz represents the cost model, and Ces 1 , Ces 2 , Ces 3 , …, Ces N represent the real-time unit costs of the 1st, 2nd, 3rd, ..., Nth energy supply units. The power of the N energy supply units is optimized in two rounds. During the optimization, the cost model is used for cost prediction, and the optimization scheme when Cz min is obtained is used as the optimal optimization scheme.

[0081] By performing the second adjustment after the first adjustment, not only can it be ensured that the adjusted power meets the load demand, but also the cost can be predicted through the cost model, greatly reducing the cost during distributed energy scheduling. That is, in some embodiments, constructing the cost model in combination with the power after the first adjustment includes: on the premise of ensuring that the total power after the first adjustment remains unchanged, constructing the cost model based on the result obtained by inputting the real-time data into the second influence function and the power of the multiple energy supply units.

[0082] As can be seen from the above embodiments, the coordinated control method for the distributed energy system provided by the embodiments of the present application includes: obtaining the production methods and basic data of multiple energy supply units, classifying the multiple energy supply units according to the production methods, and determining the main environmental parameters of any class of energy supply units; determining the first data corresponding to the main environmental parameters at different supply powers, constructing the first influence function, determining the time series for the supply power, and forming the power model in combination with the first influence function; determining the load demand in different time periods to form the load model; determining the cost per unit power and generating the second influence function in combination with the second data corresponding to the main environmental parameters; using the power model and the load model to perform power prediction and load prediction according to the real-time data, and performing the first adjustment using the prediction results; inputting the real-time data into the second influence function, combining the power after the first adjustment for prediction, and performing the second adjustment according to the prediction results. Through the classification and analysis of the energy supply units in the present application, through classification, the geographical distribution characteristics of different energies can be clearly distinguished; it helps to formulate exclusive production management strategies for different energies. After classification, targeted adjustments can be made according to various categories to ensure stable energy output, and at the same time, the response speed and adjustability of various types of energy supply units can be determined more accurately. Then, different main environmental parameters are obtained for different types of energy supply units, and the first influence function and the second influence function are calculated, so that the power, cost, etc. of different energy supply units can be analyzed separately, optimizing energy scheduling and enhancing energy storage planning.

[0083] It should be noted that the method of the embodiment of the present application can be executed by a single device, such as a computer or a server. The method of the embodiment of the present application can also be applied to a distributed scenario and completed by the cooperation of multiple devices. In this case of a distributed scenario, one of the multiple devices can only execute one or more steps of the method of the embodiment of the present application, and these multiple devices will interact with each other to complete the described method.

[0084] It should be noted that the above describes specific embodiments of the present application. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims can be performed in a different order than in the above embodiments and still achieve the desired result. Additionally, the processes depicted in the figures do not necessarily require the particular order or sequential order shown to achieve the desired result. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0085] Based on the same concept, corresponding to the method of any of the above embodiments, the present application further provides a coordinated control device for a distributed energy system.

[0086] Referring to Figure 2 , the coordinated control device for the distributed energy system includes:

[0087] The first module 210 is configured to obtain the production modes and basic data of the multiple energy supply units, classify the multiple energy supply units according to the production modes, and determine the main environmental parameters of any type of energy supply unit according to the energy supply power and environmental parameters in the basic data.

[0088] The second module 220 is configured to determine, according to the basic data, the first data corresponding to the main environmental parameters of any type of energy supply unit at different energy supply powers, construct a first influence function by using a linear regression model, determine the time series of any type of energy supply unit for the energy supply power, and form a power model in combination with the first influence function.

[0089] The third module 230 is configured to determine the load demand of the distributed energy system at different time periods according to the basic data, and form a load model according to the change rule of the load demand.

[0090] The fourth module 240 is configured to determine the cost of any type of energy supply unit under unit power according to the basic data, and generate a second influence function in combination with the second data corresponding to the main environmental parameters when the cost changes under the same power.

[0091] The fifth module 250 is configured to obtain real-time data corresponding to the main environmental parameters, perform power prediction and load prediction based on the real-time data by using the power model and the load model, and perform a first adjustment on the power of the multiple energy supply units by using the prediction results.

[0092] The sixth module 260 is configured to input the real-time data into the second influence function, construct a cost model by combining the power after the first adjustment, perform prediction by using the cost model, and perform a second adjustment according to the prediction results.

[0093] In some exemplary embodiments, the first module 210 is further configured to:

[0094] According to the basic data, determine the change rate of the energy supply power of any type of energy supply unit under the influence of different environmental parameters, and select the environmental parameters whose change rate meets the set conditions as the main environmental parameters.

[0095] In some exemplary embodiments, the second module 220 is further configured to:

[0096] Take the first data as the independent variable and the energy supply power as the dependent variable to form a first curve graph, fit the first curve graph by using the linear regression model, and then obtain the first influence function in combination with the least squares method.

[0097] In some exemplary embodiments, the second module 220 is further configured to:

[0098] Analyze the energy supply power of the time series by using the autoregressive moving average model, so as to form the autoregressive moving average model of any type of energy supply unit;

[0099] Substitute the autoregressive moving average model of any type of energy supply unit into the first influence function to obtain the power model of any type of energy supply unit.

[0100] In some exemplary embodiments, the third module 230 is further configured to:

[0101] Form a second curve graph according to the load demands of the distributed energy system at different time periods;

[0102] Determine an initial point and the initial load demand of the initial point in the second curve graph, determine a first point position where the initial load demand is reached in the second curve graph, take the curve from the initial point to the adjacent first point position as the first curve, and take the curves between other adjacent first point positions as the second curves;

[0103] Determine the similarity between the second curve and the first curve in sequence, take the previous first point position in the first completely similar second curve as the target point position, and take the curve between the initial point and the target point position as the target curve;

[0104] Form the load model according to the target curve.

[0105] In some exemplary embodiments, the sixth module 260 is further configured to:

[0106] On the premise of ensuring that the total power after the first adjustment remains unchanged, construct the cost model based on the result obtained by inputting the real-time data into the second influence function and the power of the multiple energy supply units.

[0107] For the convenience of description, when describing the above device, various modules are described separately according to their functions. Of course, when implementing the embodiments of the present application, the functions of each module can be implemented in the same or multiple software and / or hardware.

[0108] The device of the above embodiment is used to implement the corresponding coordinated control method of the distributed energy system in the foregoing embodiment, and has the beneficial effects of the corresponding method embodiment, which will not be elaborated here.

[0109] Based on the same concept, corresponding to the method of any of the above embodiments, the present application further provides an electronic device, including a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the program, it implements the coordinated control method of the distributed energy system as described in any of the above embodiments.

[0110] Figure 3 FIG. shows a more specific schematic diagram of the hardware structure of the electronic device provided in this embodiment. The device may include: a processor 1010, a memory 1020, an input / output interface 1030, a communication interface 1040, and a bus 1050. Among them, the processor 1010, the memory 1020, the input / output interface 1030, and the communication interface 1040 are communicatively connected to each other inside the device through the bus 1050.

[0111] The processor 1010 may be implemented in a general-purpose CPU (Central Processing Unit), a microprocessor, an application-specific integrated circuit (ASIC), or one or more integrated circuits, etc., and is used to execute relevant programs to implement the technical solutions provided in the embodiments of this specification.

[0112] The memory 1020 can be implemented in the form of ROM (Read Only Memory), RAM (Random Access Memory), static storage devices, dynamic storage devices, etc. The memory 1020 can store an operating system and other application programs. When implementing the technical solutions provided in the embodiments of this specification through software or firmware, the relevant program codes are stored in the memory 1020 and called and executed by the processor 1010.

[0113] The input / output interface 1030 is used to connect to the input / output module to achieve information input and output. The input / output module can be configured as a component in the device (not shown in the figure) or externally connected to the device to provide corresponding functions. Among them, the input devices can include keyboards, mice, touchscreens, microphones, various sensors, etc., and the output devices can include displays, speakers, vibrators, indicator lights, etc.

[0114] The communication interface 1040 is used to connect to the communication module (not shown in the figure) to achieve communication interaction between this device and other devices. Among them, the communication module can achieve communication through wired means (such as USB, network cable, etc.) or through wireless means (such as mobile network, WIFI, Bluetooth, etc.).

[0115] The bus 1050 includes a path for transmitting information between various components of the device (such as the processor 1010, the memory 1020, the input / output interface 1030, and the communication interface 1040).

[0116] It should be noted that although the above device only shows the processor 1010, the memory 1020, the input / output interface 1030, the communication interface 1040, and the bus 1050, in the specific implementation process, the device may also include other components necessary for normal operation. In addition, those skilled in the art can understand that the above device may also only include the components necessary to implement the solutions of the embodiments of this specification, and do not necessarily include all the components shown in the figure.

[0117] The electronic device in the above embodiment is used to implement the coordinated control method of the corresponding distributed energy system in any of the foregoing embodiments, and has the beneficial effects of the corresponding method embodiments, which will not be elaborated here.

[0118] Based on the same concept, corresponding to the method in any of the above embodiments, the present application also provides a non-transitory computer-readable storage medium storing computer instructions for causing the computer to execute the coordinated control method of the distributed energy system as described in any of the above embodiments.

[0119] The computer-readable medium of this embodiment includes permanent and non-permanent, removable and non-removable media, and information storage can be implemented by any method or technology. The information can be computer-readable instructions, data structures, program modules, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassette tapes, magnetic disk storage or other magnetic storage devices, or any other non-transmission media that can be used to store information accessible by a computing device.

[0120] The computer instructions stored in the storage medium of the above embodiment are used to cause the computer to execute the coordinated control method of the distributed energy system described in any of the above embodiments, and have the beneficial effects of the corresponding method embodiments, which will not be elaborated here.

[0121] Based on the same concept, corresponding to any of the above method embodiments, the present application also provides a computer program product, which includes computer program instructions. In some embodiments, the computer program instructions can be executed by one or more processors of the computer to cause the computer and / or the processor to execute the coordinated control method of the distributed energy system. Corresponding to the execution subjects corresponding to the steps in each of the embodiments of the coordinated control method of the distributed energy system, the processors that execute the corresponding steps can belong to the corresponding execution subjects.

[0122] The computer program product of the above embodiment is used to cause the computer and / or the processor to execute the coordinated control method of the distributed energy system described in any of the above embodiments, and has the beneficial effects of the corresponding method embodiments, which will not be elaborated here.

[0123] Those of ordinary skill in the art should understand that: the discussion of any of the above embodiments is only exemplary and is not intended to imply that the scope of the present application (including the claims) is limited to these examples; under the concept of the present application, the technical features in the above embodiments or different embodiments can also be combined, the steps can be implemented in any order, and there are many other variations in different aspects of the embodiments of the present application as described above, and they are not provided in detail for the sake of brevity.

[0124] In addition, for simplicity of explanation and discussion, and in order not to make the embodiments of the present application difficult to understand, known power / ground connections to integrated circuit (IC) chips and other components may or may not be shown in the provided drawings. Further, the devices may be shown in block diagram form in order to avoid making the embodiments of the present application difficult to understand, and this also takes into account the fact that details of the implementation of these block diagram devices are highly dependent on the platform on which the embodiments of the present application are to be implemented (i.e., these details should be fully within the understanding of those skilled in the art). In cases where specific details (such as circuits) are set forth to describe exemplary embodiments of the present application, it will be apparent to those skilled in the art that the embodiments of the present application may be practiced without these specific details or with variations of these specific details. Accordingly, these descriptions should be considered illustrative rather than restrictive.

[0125] Although the present application has been described in connection with specific embodiments thereof, many alternatives, modifications, and variations of these embodiments will be apparent to those of ordinary skill in the art in light of the foregoing description. For example, other memory architectures (such as dynamic RAM (DRAM)) may be used with the embodiments discussed.

[0126] Embodiments of the present application are intended to cover all such alternatives, modifications, and variations that fall within the broad scope of the appended claims. Therefore, any omissions, modifications, equivalent substitutions, improvements, etc., made within the spirit and principle of the embodiments of the present application shall be included within the protection scope of the present application.

Claims

1. A coordinated control method for a distributed energy system, characterized in that: The distributed energy system includes a plurality of energy supply units, and the method includes: Acquire the production methods and basic data of the multiple energy supply units, classify the multiple energy supply units according to the production methods, and determine the main environmental parameters of any type of energy supply unit according to the energy supply power and environmental parameters in the basic data; According to the basic data, first data corresponding to the main environmental parameters of any type of energy supply unit at different energy supply powers are determined, a first influence function is constructed using a linear regression model, a time series of any type of energy supply unit for energy supply power is determined, and a power model is formed in combination with the first influence function; Determine the load demand of the distributed energy system in different time periods according to the basic data, and form a load model according to the change law of the load demand; Determine the cost of any type of energy supply unit under unit power according to the basic data, and generate a second influence function by combining the second data corresponding to the main environmental parameters when the cost changes under the same power; Acquire real-time data corresponding to the main environmental parameters, perform power forecasting and load forecasting using the power model and the load model according to the real-time data, and make a first adjustment to the power of the multiple energy supply units using the forecast results; The real-time data is input into the second influence function, a cost model is constructed in combination with the power after the first adjustment, prediction is performed using the cost model, and a second adjustment is performed according to the prediction result.

2. The method according to claim 1, characterized in that The main environmental parameters for determining any type of energy supply unit include: According to the basic data, the change speed of the energy supply power of any type of energy supply unit under the influence of different environmental parameters is determined, and the environmental parameter whose change speed meets the set conditions is selected as the main environmental parameter.

3. The method according to claim 1, characterized in that The method of constructing the first influence function by using the linear regression model includes: The first data is used as an independent variable and the energy supply power is used as a dependent variable to form a first curve graph, the first curve graph is fitted using the linear regression model, and then the first influence function is obtained in combination with the least squares method.

4. The method according to claim 1, characterized in that: The forming a power model by combining the first influence function includes: Analyzing the energy supply power of the time series using an autoregressive moving average model, thereby forming an autoregressive moving average model of any type of energy supply unit; Substitute the autoregressive moving average model of any type of energy supply unit into the first influence function to obtain the power model of any type of energy supply unit.

5. The method according to claim 1, characterized in that The forming of a load model according to the change rule of the load demand includes: forming a second curve graph according to the load demand of the distributed energy system in different time periods; Determine an initial point and an initial load demand of the initial point in the second curve graph, determine a first point reaching the initial load demand in the second curve graph, use a curve from the initial point to an adjacent first point as a first curve, and use curves between other adjacent first points as second curves; Determine the similarity between the second curve and the first curve in sequence, take the previous first point in the first completely similar second curve as the target point, and take the curve between the initial point and the target point as the target curve; The load model is formed according to the target curve.

6. The method according to claim 1, characterized in that The step of constructing a cost model based on the power after the first adjustment includes: On the premise of ensuring that the total power after the first adjustment remains unchanged, the cost model is constructed based on the result obtained after the real-time data is input into the second influence function and the power of the multiple energy supply units.

7. A coordinated control device for a distributed energy system, characterized in that: The distributed energy system includes multiple energy supply units, and the device includes: The first module is used to obtain the production methods and basic data of the multiple energy supply units, classify the multiple energy supply units according to the production methods, and determine the main environmental parameters of any type of energy supply unit according to the energy supply power and environmental parameters in the basic data; The second module is used to determine the first data corresponding to the main environmental parameters of any type of energy supply unit at different energy supply powers based on the basic data, construct a first influence function using a linear regression model, determine the time series of any type of energy supply unit for energy supply power, and form a power model in combination with the first influence function; The third module is used to determine the load demand of the distributed energy system in different time periods according to the basic data, and form a load model according to the change law of the load demand; A fourth module is used to determine the cost of any type of energy supply unit under unit power according to the basic data, and generate a second influence function in combination with the second data corresponding to the main environmental parameters when the cost changes under the same power; A fifth module is used to obtain real-time data corresponding to the main environmental parameters, perform power forecasting and load forecasting using the power model and the load model according to the real-time data, and perform a first adjustment on the power of the multiple energy supply units using the forecast results; The sixth module is used to input the real-time data into the second influence function, build a cost model in combination with the power after the first adjustment, use the cost model to make a prediction, and make a second adjustment based on the prediction result.

8. An electronic device, characterized in that: The method comprises a memory, a processor and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the method according to any one of claims 1 to 6 is implemented.

9. A non-transitory computer-readable storage medium, characterized in that: The non-transitory computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a computer to implement the method according to any one of claims 1 to 6.

10. A computer program product, characterized in that The method comprises computer program instructions, which, when executed on a computer, cause the computer to execute the method according to any one of claims 1 to 6.

Images