A method and device for controlling an energy storage system applied to a substation

Abstract

The present invention discloses a control method and device for an energy storage system applied to a substation, the method comprising: detecting the real-time load data of the substation transformer, calculating the overload degree score value of the substation transformer according to the real-time load data of the substation transformer; obtaining the substation load forecast value of a preset time in the future in combination with historical load data based on the substation load forecast model; obtaining the current state of the energy storage system, obtaining the energy forecast value that the energy storage system can provide in the preset time in the future based on the current state; calculating the overload risk forecast value of the substation transformer in combination with the overload degree score value, the substation load forecast value and the energy forecast value based on the overload risk forecast model, and determining the energy storage system control strategy according to the corresponding overload risk forecast level. Real-time monitoring and prediction of the overload state of the transformer is achieved, potential overload risks are identified in advance, and the charging and discharging plan of the energy storage system is optimized through accurate prediction of load and energy, thereby improving the regulation capability and response speed of the power grid.

Description

Technical Field

[0001] The present invention relates to the field of energy storage control technology, and in particular to an energy storage system control method and device applied to a substation. Background Art

[0002] Substation transformers are key equipment in the distribution network, mainly used to reduce the high-voltage transmission voltage to a low voltage level suitable for home and commercial use. They are usually installed near residential, industrial or commercial areas to meet the electricity needs of users in these areas. Substation transformers usually have a specific rated capacity, which determines the maximum amount of power they can provide. In daily operation, the load on the transformer fluctuates according to changes in user demand. Ideally, the transformer should operate within a certain percentage of its rated capacity to ensure efficiency and safety.

[0003] The overload degree of the transformer in the substation refers to the proportional relationship between the electrical load borne by the transformer during operation and its rated capacity. This concept involves the safe operation and efficiency of the transformer. The overload degree is usually expressed as the ratio of the actual operating load of the transformer to its rated load. For example, if the rated capacity of a transformer is 500 kilovolt-amperes (kVA) and the actual operating load reaches 600kVA, its overload degree is 120%. The high overload degree of the transformer in the substation may be caused by increased electricity demand, insufficient transformer capacity, unreasonable grid planning, or inaccurate power demand forecasting. At present, in order to adjust the overload degree of the transformer in the substation, measures such as adjusting the grid operation mode, increasing transformer capacity, optimizing load distribution, or using energy storage systems may be needed.

[0004] Although the above-mentioned adjustment methods can alleviate the overload problem to a certain extent, they also have some disadvantages and shortcomings. For example, adjusting the operation mode of the power grid may require complex coordination and control strategies, and have high requirements for the stability and reliability of the power grid; increasing the capacity of the transformer involves a large initial investment cost and may be subject to on-site space constraints; optimizing the load distribution requires accurate load forecasting and dynamic adjustment mechanisms, which may be more complicated to implement; and the use of energy storage systems may provide flexible adjustment capabilities, but their efficiency, cost and life are also factors that need to be considered. In addition, these measures may take a long time to plan and implement, and may not be immediately effective for short-term overload problems. Summary of the invention

[0005] The purpose of the embodiments of the present invention is to provide a method and device for controlling an energy storage system applied to a substation. By obtaining the overload degree score value, the substation load forecast value, and the energy forecast value of the substation transformer, the overload risk forecast value is calculated, and the control mode of the substation energy storage system is determined according to the corresponding level. This truly reflects the overload condition of the transformer and highlights the impact of certain extreme conditions, thereby improving the regulation effect of the substation transformer.

[0006] In order to solve the above technical problems, an embodiment of the present invention provides a method for controlling an energy storage system applied to a substation, comprising the following steps:

[0007] Detecting real-time load data of the transformer in the substation area, and calculating a heavy load degree score value of the transformer in the substation area according to the real-time load data of the transformer in the substation area;

[0008] Based on the load forecasting model of the substation, the load forecast value of the substation at a preset time in the future is obtained in combination with historical load data;

[0009] Acquire a current state of the energy storage system, and based on the current state, acquire a predicted value of energy that the energy storage system can provide at a preset time in the future;

[0010] Based on the overload risk prediction model, combined with the overload degree score, the substation load prediction value and the energy prediction value, the overload risk prediction value of the substation transformer is calculated, and the control strategy of the energy storage system is determined according to the overload risk prediction level corresponding to the overload risk prediction value.

[0011] Furthermore, the real-time load data includes: real-time active power, operating temperature and power factor;

[0012] The overload rating value F of the transformer in the substation area 重载 The calculation formula is:

[0013] F 重载 =ω1×φ 功率 (P 实 , P 额定 )+ω2×φ 温度 (T 实 , T 额定 )+ω3×φ 功率因数 (COS(φ 实 ), COS(φ 额定 ))+ε;

[0014] Among them, F 重载 is the overload degree score, ω1 is the weight coefficient of the real-time active power, φ 功率 (P 实 , P 额定 ) is the power conversion function, P 实is the real-time active power, P 额定 is the rated active power, ω2 is the weight coefficient of the operating temperature, φ 温度 (T 实 , T 额定 ) is the temperature conversion function, T 实 is the real-time operating temperature, T 额定 is the rated operating temperature, ω3 is the weight coefficient of the power factor, φ 功率因数 (COS(φ 实 ), COS(φ 额定 )) is the power factor conversion function, COS(φ 实 ) is the real-time power factor, COS(φ 额定 ) is the rated power factor, and ε is the random disturbance term.

[0015] Furthermore, the power conversion function φ 功率 (P 实 , P 额定 )for:

[0016]

[0017] The temperature conversion function φ 温度 (T 实 , T 额定 )for:

[0018]

[0019] The power factor conversion function φ 功率因数 (COS(φ 实 ), COS(φ 额定 ))for:

[0020] φ 功率因数 (COS(φ 实 ), COS(φ 额定 ))=-(COS(φ 实 )-COS(φ 额定 )) 2 ;

[0021] The random disturbance term ε is:

[0022] ε~N(0,σ 2 );

[0023] Among them, ε has a mean of 0 and a variance of σ 2 The normal distribution of .

[0024] Furthermore, the calculation formula of the load forecast value of the substation is:

[0025] P(t)=f(P hist,t,T(t),M(t),E(t),R(t));

[0026] Among them, P(t) is the load forecast value of the substation, f is the load forecast model of the substation, P hist,t is the historical load data, T(t) is the time characteristic vector, M(t) is the meteorological data vector at time t, E(t) is the economic activity data vector at time t, and R(t) is the electricity price data vector at time t.

[0027] Furthermore, the types of the substation load forecasting model include: linear regression model, decision tree model, random forest model, gradient boosting machine model, support vector machine model or deep learning model.

[0028] Furthermore, when the load prediction model of the substation is a linear regression model, the calculation formula of the load prediction value of the substation is:

[0029] P(t)=β0+β1×P hist,t +β2×T(t)+β3×M(t)+β4×E(t)+β5×R(t)+θ(t);

[0030] Among them, β0 is the intercept term, β1, β2, β3, β4 and β5 are the parameters of the substation load prediction model, and θ(t) is the error term.

[0031] Furthermore, the calculation formula of the energy prediction value E(t) is:

[0032]

[0033] Wherein, E(t) is the energy prediction value, E current is the current total energy of the energy storage system, r discharge is the discharge rate of the energy storage system, E min is the minimum energy of the energy storage system, Δt is the time interval, r charge is the charging rate of the energy storage system, E max is the maximum energy of the energy storage system.

[0034] Furthermore, when the overload risk prediction model is a logistic regression classifier, the calculation formula of the overload risk prediction value W(t) of the transformer in the substation is:

[0035] W(t)=Logistic(δ0+δ1P(t)+δ2E(t)+δ3F 重载 );

[0036] Wherein, Logistic is the conversion function that maps the linear combination to the probability interval, δ0, δ1, δ2, δ3 are the parameter values ​​of the conversion function, P(t) is the load prediction value of the substation, E(t) is the energy prediction value, F 重载 is the overload degree score, and t is a preset time in the future.

[0037] Further, the determining of the control strategy of the energy storage system based on the overload risk prediction level includes:

[0038] If the overload risk prediction level is high risk, controlling the energy storage system to only discharge at the future preset time;

[0039] If the predicted level of overload risk is medium risk, controlling the energy storage system to maintain the current state;

[0040] If the overload risk prediction level is low risk, the energy storage system is only charged.

[0041] Accordingly, a second aspect of an embodiment of the present invention provides an energy storage system control device applied to a substation, comprising:

[0042] A heavy load degree calculation module, which is used to detect the real-time load data of the transformer in the substation area, and calculate the heavy load degree score value of the transformer in the substation area according to the real-time load data of the transformer in the substation area;

[0043] The load forecasting module is used to obtain the load forecast value of the area at a preset time in the future based on the load forecasting model of the area and in combination with the historical load data;

[0044] An energy prediction calculation module, which is used to obtain the current state of the energy storage system, and obtain the energy prediction value that the energy storage system can provide at a preset time in the future based on the current state;

[0045] An overload risk calculation module is used to calculate the overload risk prediction value of the substation transformer based on an overload risk prediction model in combination with the overload degree score, the substation load prediction value and the energy prediction value, and determine the control strategy of the energy storage system according to the overload risk prediction level corresponding to the overload risk prediction value.

[0046] Accordingly, a third aspect of an embodiment of the present invention provides an electronic device, comprising: at least one processor; and a memory connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor executes the above-mentioned energy storage system control method applied to the substation.

[0047] Accordingly, a fourth aspect of an embodiment of the present invention provides a computer-readable storage medium having computer instructions stored thereon, which, when executed by a processor, implement the above-mentioned energy storage system control method applied to a substation.

[0048] The above technical solution of the embodiment of the present invention has the following beneficial technical effects:

[0049] 1. It can realize real-time monitoring and prediction of transformer overload status, so as to identify potential overload risks in advance;

[0050] 2. Through accurate prediction of load and energy, optimize the charging and discharging plan of the energy storage system and improve the regulation capability and response speed of the power grid;

[0051] 3. The control strategy can be dynamically adjusted according to real-time data to achieve load balance and reasonable allocation of energy, reduce the operating cost of the power grid, and effectively extend the service life of transformers and other power equipment and reduce maintenance costs by predicting and avoiding overload conditions. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] Figure 1 is a flow chart of a method for controlling an energy storage system applied to a substation provided by an embodiment of the present invention;

[0053] Figure 2 It is a block diagram of a module of an energy storage system control device applied to a substation provided by an embodiment of the present invention.

[0054] Reference numerals:

[0055] 1. Overload degree calculation module, 2. Substation load prediction module, 3. Energy prediction calculation module, 4. Overload risk calculation module. DETAILED DESCRIPTION

[0056] In order to make the purpose, technical scheme and advantages of the present invention clearer, the present invention is further described in detail below in conjunction with specific embodiments and with reference to the accompanying drawings. It should be understood that these descriptions are only exemplary and are not intended to limit the scope of the present invention. In addition, in the following description, the description of well-known structures and technologies is omitted to avoid unnecessary confusion of the concept of the present invention.

[0057] Please refer to Figure 1 The embodiment of the present invention provides a method for controlling an energy storage system applied to a substation, comprising the following steps:

[0058] Step S100, detecting the real-time load data of the transformer in the substation area, and calculating the heavy load degree score of the transformer in the substation area according to the real-time load data of the transformer in the substation area.

[0059] Step S200, based on the substation load prediction model, combined with historical load data, obtain the substation load prediction value for a preset time in the future.

[0060] Step S300, obtaining the current state of the energy storage system, and obtaining a predicted value of energy that can be provided by the energy storage system at a preset time in the future based on the current state.

[0061] Step S400, based on the overload risk prediction model, combined with the overload degree score, the area load prediction value and the energy prediction value, calculate the overload risk prediction value of the area transformer, and determine the control strategy of the energy storage system according to the overload risk prediction level corresponding to the overload risk prediction value.

[0062] The overload risk prediction value is calculated based on the overload degree score of the substation transformer, the substation load prediction value, and the energy prediction value, and the control method of the substation energy storage system is determined accordingly. This can achieve real-time monitoring and prediction of the transformer overload status, thereby identifying potential overload risks in advance. Through accurate prediction of load and energy, the charging and discharging plan of the energy storage system is optimized, thereby improving the regulation ability and response speed of the power grid.

[0063] Specifically, the real-time load data includes: real-time active power, operating temperature and power factor.

[0064] Furthermore, based on the three specific parameter types of the load data implemented above, the heavy load rating value F of the transformer in the substation area is 重载 The calculation formula is:

[0065] F 重载 =ω1×φ 功率 (P 实 , P 额定 )+ω2×φ 温度 (T 实 , T 额定 )+ω3×φ 功率因数 (COS(φ 实 ), COS(φ 额定 ))+ε;

[0066] Among them, F 重载 is the overload degree score, ω1 is the weight coefficient of real-time active power, φ 功率 (P 实 , P 额定 ) is the power conversion function, P 实 is the real-time active power, P 额定 is the rated active power, ω2 is the weight coefficient of the operating temperature, φ 温度 (T 实 , T 额定 ) is the temperature conversion function, T 实 is the real-time operating temperature, T 额定is the rated operating temperature, ω3 is the weight coefficient of the power factor, φ 功率因数 (COS(φ 实 ), COS(φ 额定 )) is the power factor conversion function, COS(φ 实 ) is the real-time power factor, COS(φ 额定 ) is the rated power factor and ε is the random disturbance term, which is used to simulate the uncertainty and random fluctuations in actual operation.

[0067] Furthermore, the power conversion function φ 功率 (P 实 , P 额定 )for:

[0068]

[0069] Power conversion function φ 功率 (P 实 , P 额定 ) in real-time active power P 实 Greater than the rated active power P 额定 It increases rapidly when the load is too high, corresponding to the nonlinear increase in the degree of transformer overloading.

[0070] Temperature conversion function φ 温度 (T 实 , T 额定 )for:

[0071]

[0072] Temperature conversion function φ 温度 (T 实 , T 额定 ) uses the natural logarithmic function to simulate the nonlinear effect of temperature on the transformer overload degree.

[0073] Power factor conversion function φ 功率因数 (COS(φ 实 ), COS(φ 额定 ))for:

[0074] φ 功率因数 (COS(φ 实 ), COS(φ 额定 ))=-(COS(φ 实 )-COS(φ 额定 )) 2 ;

[0075] Power factor conversion function φ 功率因数 (COS(φ 实 ), COS(φ 额定)) will increase when the power factor decreases, and the square term is used to represent the nonlinear effect of the power factor on the degree of transformer overload.

[0076] The random disturbance term ε is:

[0077] ε~N(0,σ 2 );

[0078] Among them, ε has a mean of 0 and a variance of σ 2 The normal distribution of .

[0079] The above heavy load rating value F 重载 The calculation method not only takes into account the different nonlinear effects of various factors on the overload degree of the transformer, but also introduces the above-mentioned random disturbance term ε to simulate the uncertain factors in the actual operation process. The corresponding weight coefficients can also be adjusted according to the actual operating conditions and importance. Through the above calculation process, the overload degree of the transformer in the substation can be comprehensively reflected based on the various reference factors of the real-time load data. Based on the preset threshold, it is determined whether the transformer in the substation is in an overload state.

[0080] The above preset thresholds are dynamically adjusted by comprehensively considering transformer design standards, safety margins, operating environment, historical data and other factors. For example, if the threshold is set to 95%, then when the real-time load of the transformer reaches 95% of the rated load, it may trigger early warning or control measures, such as starting the energy storage system for load adjustment.

[0081] In actual operation, multiple indicators may be combined, such as load duration, load volatility, etc., to comprehensively judge whether measures need to be taken. By combining more parameter indicators, the overload condition of the transformer can be more realistically reflected and the impact of certain extreme conditions can be highlighted. For example, when the transformer is close to its rated capacity, its temperature rise, efficiency decrease and other phenomena are often nonlinear. The nonlinear formula can give a larger weight coefficient value to extreme conditions. When the load power far exceeds the rated power, the nonlinear formula can give a higher overload score, thereby prompting potential risks more quickly.

[0082] Furthermore, the calculation formula of the load forecast value of the substation is:

[0083] P(t)=f(P hist,t ,T(t),M(t),E(t),R(t));

[0084] Among them, P(t) is the load forecast value of the substation, f is the load forecast model of the substation, P hist,t is the historical load data, T(t) is the time characteristic vector, M(t) is the meteorological data vector at time t, E(t) is the economic activity data vector at time t, and R(t) is the electricity price data vector at time t.

[0085] The above historical load data P hist,t The daily load curve and / or weekly load curve of the same time period in the previous month may be used; the above-mentioned time characteristic vector T(t) may be in the form of year, month or day of the week.

[0086] Furthermore, the types of substation load forecasting models include: linear regression model, decision tree model, random forest model, gradient boosting machine model, support vector machine model or deep learning model.

[0087] Furthermore, when the load forecasting model of the substation is a linear regression model, the calculation formula of the load forecast value of the substation is:

[0088] P(t)=β0+β1×P hist,t +β2×T(t)+β3×M(t)+β4×E(t)+β5×R(t)+θ(t);

[0089] Among them, β0 is the intercept term, β1, β2, β3, β4 and β5 are the parameters of the load forecasting model of the substation, and θ(t) is the error term.

[0090] Optionally, a relatively complex model, such as a deep learning model, can be used to build a neural network. The input layer contains all the features of historical load, time characteristics, meteorological data, economic activity data and electricity price data. The hidden layer can contain multiple nodes to extract the complex relationship between the features. The output layer outputs the predicted load.

[0091] At this time, the calculation formula for the predicted load value of the substation is:

[0092] P(t)=NN(P hist,t ,T(t),M(t),E(t),R(t));

[0093] Among them, NN is the function of the neural network model.

[0094] Furthermore, the calculation formula of the energy prediction value E(t) is:

[0095]

[0096] Among them, E(t) is the energy prediction value, E current is the current total energy of the energy storage system, r discharge is the discharge rate of the energy storage system, E min is the minimum energy of the energy storage system to prevent over-discharge of the energy storage system, Δt is the time interval, t is the time, which can be a specific number of hours or days, r chargeThe charging rate of the energy storage system, which represents the amount of electrical energy that the energy storage system can receive per unit time, is usually measured in kW or W, denoted as E. max E is the maximum energy of the energy storage system.

[0097] The predicted energy value E(t) takes into account the following factors: starting from the current state E of the energy storage system, as time increases, the energy will decrease according to the discharge rate r current until it reaches E discharge ; at the same time, the energy storage system will also increase energy according to the charging rate r min but not exceeding its maximum capacity E charge 。 max .

[0098] Normalize the above-mentioned predicted values of the substation area load, predicted energy value, and overloading degree score value, and adjust the values of the three parameters to the same scale before calculating the predicted value of the overloading risk. The prediction function of the predicted value W(t) of the overloading risk of the above-mentioned substation area transformer selects a model suitable for classification tasks, such as logistic regression, support vector machine (SVM), random forest, or gradient boosting tree. Use the historical data set, including the past predicted values of the substation area load, predicted energy value of the energy storage system, overloading degree score value, and known risk prediction values, to train the model.

[0099] Furthermore, when the overloading risk prediction model is a logistic regression classifier, the calculation formula for the predicted value W(t) of the overloading risk of the substation area transformer is:

[0100] W(t) = Logistic(δ0 + δ1P(t) + δ2E(t) + δ3F 重载 );

[0101] where Logistic is a conversion function that maps the linear combination to the probability interval, δ0, δ1, δ2, δ3 are the parameter values of the conversion function, P(t) is the predicted value of the substation area load, E(t) is the predicted energy value, F 重载 is the overloading degree score value, and t is the preset future time.

[0102] In a specific implementation manner of the embodiment of the present invention, the respective risk levels corresponding to the predicted value of the overloading risk can be defined as follows:

[0103] When 0 < W(t) < 0.33, the overloading risk level is a low risk level;

[0104] When 0.33 < W(t) < 0.66, the overloading risk level is a medium risk level;

[0105] When 0.66 < W(t) < 1, the overloading risk level is a high risk level.

[0106] Furthermore, the control strategy of the energy storage system determined based on the overload risk prediction level in step S400 can be refined into the following steps:

[0107] Step S401: If the overload risk prediction level is high risk, the energy storage system is controlled to only discharge at a preset time in the future.

[0108] Step S402: If the overload risk prediction level is medium risk, the energy storage system is controlled to maintain the current state.

[0109] Step S403: If the overload risk prediction level is low risk, the energy storage system is only charged.

[0110] In the above process, if the overload risk prediction level is high risk, the discharge program of the energy storage system is started at the corresponding time to reduce the load on the power grid; if the overload risk prediction level is medium risk, the energy storage system can be kept in its current state; if the overload risk prediction level is low risk, it indicates that the overload degree of the transformer in the substation is relatively low, and no intervention through the energy storage system is required.

[0111] Accordingly, please refer to Figure 2 A second aspect of an embodiment of the present invention provides an energy storage system control device applied to a substation, comprising:

[0112] The overload degree calculation module 1 is used to detect the real-time load data of the transformer in the substation area, and calculate the overload degree score value of the transformer in the substation area according to the real-time load data of the transformer in the substation area;

[0113] The load prediction module 2 is used to obtain the load prediction value of the area at a preset time in the future based on the load prediction model of the area and in combination with the historical load data;

[0114] Energy prediction calculation module 3, which is used to obtain the current state of the energy storage system, and obtain the energy prediction value that the energy storage system can provide at a preset time in the future based on the current state;

[0115] The overload risk calculation module 4 is used to calculate the overload risk prediction value of the transformer in the substation based on the overload risk prediction model, combined with the overload degree score value, the substation load prediction value and the energy prediction value, and determine the control strategy of the energy storage system according to the overload risk prediction level corresponding to the overload risk prediction value.

[0116] The functional modules of the energy storage system control device described above correspond to the steps in the energy storage system control method applied to the substation, and may also further include functional units corresponding to the detailed process based on the detailed process of the control method, which will not be repeated here.

[0117] Accordingly, a third aspect of an embodiment of the present invention provides an electronic device, comprising: at least one processor; and a memory connected to the at least one processor; wherein the memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor executes the above-mentioned energy storage system control method applied to the substation.

[0118] Accordingly, a fourth aspect of an embodiment of the present invention provides a computer-readable storage medium having computer instructions stored thereon, which, when executed by a processor, implement the above-mentioned energy storage system control method applied to a substation.

[0119] The embodiment of the present invention aims to protect a method and device for controlling an energy storage system applied to a substation, wherein the method includes: detecting the real-time load data of the substation transformer, and calculating the overload degree score of the substation transformer based on the real-time load data of the substation transformer; based on the substation load prediction model, combining historical load data to obtain the substation load prediction value for a preset time in the future; obtaining the current state of the energy storage system, and based on the current state, obtaining the energy prediction value that the energy storage system can provide at a preset time in the future; based on the overload risk prediction model, combining the overload degree score, the substation load prediction value and the energy prediction value, calculating the overload risk prediction value of the substation transformer, and determining the control strategy of the energy storage system according to the overload risk prediction level corresponding to the overload risk prediction value. The above technical scheme has the following effects:

[0120] 1. It can realize real-time monitoring and prediction of transformer overload status, so as to identify potential overload risks in advance;

[0121] 2. Through accurate prediction of load and energy, optimize the charging and discharging plan of the energy storage system and improve the regulation capability and response speed of the power grid;

[0122] 3. The control strategy can be dynamically adjusted according to real-time data to achieve load balance and reasonable allocation of energy, reduce the operating cost of the power grid, and effectively extend the service life of transformers and other power equipment and reduce maintenance costs by predicting and avoiding overload conditions.

[0123] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that include computer-usable program code.

[0124] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0125] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0126] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0127] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the above embodiments, ordinary technicians in the relevant field should understand that the specific implementation methods of the present invention can still be modified or replaced by equivalents. Any modification or equivalent replacement that does not depart from the spirit and scope of the present invention should be covered within the scope of protection of the claims of the present invention.

Claims

1. A method for controlling an energy storage system applied to a substation, characterized in that: The steps include: Detecting real-time load data of the transformer in the substation area, and calculating a heavy load degree score value of the transformer in the substation area according to the real-time load data of the transformer in the substation area; Based on the load forecasting model of the substation, the load forecast value of the substation at a preset time in the future is obtained in combination with historical load data; Acquire a current state of the energy storage system, and based on the current state, acquire a predicted value of energy that the energy storage system can provide at a preset time in the future; Based on the overload risk prediction model, in combination with the overload degree score, the area load prediction value and the energy prediction value, the overload risk prediction value of the area transformer is calculated, and the control strategy of the energy storage system is determined according to the overload risk prediction level corresponding to the overload risk prediction value; The real-time load data includes: real-time active power, operating temperature and power factor; The overload rating value F of the transformer in the substation area 重载 The calculation formula is: F 重载 =ω1×φ 功率 (P 实 ,P 额定 )+ω2×φ 温度 (T 实 ,T 额定 )+ω3×φ 功率因数 (COS(φ 实 ), COS(φ 额定 ))+e; Among them, F 重载 is the overload degree score, ω1 is the weight coefficient of the real-time active power, φ 功率 (P 实 , P 额定 ) is the power conversion function, P 实 is the real-time active power, P 额定 is the rated active power, ω2 is the weight coefficient of the operating temperature, φ 温度 (T 实 , T 额定 ) is the temperature conversion function, T 实 is the real-time operating temperature, T 额定 is the rated operating temperature, ω3 is the weight coefficient of the power factor, φ 功率因数 (COS(φ 实 ), COS(φ 额定 )) is the power factor conversion function, COS(φ 实 ) is the real-time power factor, COS(φ 额定 ) is the rated power factor, ε is the random disturbance term; When the overload risk prediction model is a logistic regression classifier, the calculation formula of the overload risk prediction value W(t) of the transformer in the substation is: W(t)=Logistic(δ0+δ1P(t)+δ2E(t)+δ3F 重载 ); Wherein, Logistic is the conversion function that maps the linear combination to the probability interval, δ0, δ1, δ2, δ3 are the parameter values ​​of the conversion function, P(t) is the load prediction value of the substation, E(t) is the energy prediction value, F 重载 is the overload degree score, and t is a preset time in the future.

2. The energy storage system control method applied to a substation according to claim 1, characterized in that: The power conversion function φ 功率 (P 实 , P 额定 )for: The temperature conversion function φ 温度 (T 实 , T 额定 )for: The power factor conversion function φ 功率因数 (COS(φ 实 ), COS(φ 额定 ))for: f 功率因数 (COS(φ 实 ), COS(φ 额定 ))=-(COS(φ 实 )-COS(φ 额定 )) 2 ; The random disturbance term ε is: ε~N(0,σ 2 ); Among them, ε has a mean of 0 and a variance of σ 2 The normal distribution of .

3. The energy storage system control method applied to a substation according to claim 1, characterized in that: The calculation formula of the load forecast value of the substation is: P(t)=f(P hist,t ,T(t),M(t),E(t),R(t)); Among them, P(t) is the load forecast value of the substation, f is the load forecast model of the substation, P hist,t is the historical load data, T(t) is the time characteristic vector, M(t) is the meteorological data vector at time t, E(t) is the economic activity data vector at time t, and R(t) is the electricity price data vector at time t.

4. The energy storage system control method applied to a substation according to claim 3 is characterized in that: The types of the substation load prediction model include: linear regression model, decision tree model, random forest model, gradient boosting machine model, support vector machine model or deep learning model.

5. The energy storage system control method applied to a substation according to claim 4, characterized in that: When the load prediction model of the substation is a linear regression model, the calculation formula of the load prediction value of the substation is: P(t)=β0+β1×P hist,t +β2×T(t)+β3×M(t)+β4×E(t)+β5×R(t)+θ(t); Among them, β0 is the intercept term, β1, β2, β3, β4 and β5 are the parameters of the substation load prediction model, and θ(t) is the error term.

6. The energy storage system control method applied to a substation according to claim 1, characterized in that: The calculation formula of the energy prediction value E(t) is: Wherein, E(t) is the energy prediction value, E current is the current total energy of the energy storage system, r discharge is the discharge rate of the energy storage system, E min is the minimum energy of the energy storage system, Δt is the time interval, r charge is the charging rate of the energy storage system, E max is the maximum energy of the energy storage system.

7. The energy storage system control method applied to a substation according to any one of claims 1 to 6, characterized in that: The determining of the control strategy of the energy storage system based on the overload risk prediction level includes: If the overload risk prediction level is high risk, controlling the energy storage system to only discharge at the future preset time; If the predicted level of overload risk is medium risk, controlling the energy storage system to maintain the current state; If the overload risk prediction level is low risk, the energy storage system is only charged.

8. An energy storage system control device applied to a substation, characterized in that: The energy storage system is controlled by the energy storage system control method applied to a substation as claimed in any one of claims 1 to 7, comprising: A heavy load degree calculation module, which is used to detect the real-time load data of the transformer in the substation area, and calculate the heavy load degree score value of the transformer in the substation area according to the real-time load data of the transformer in the substation area; The load forecasting module is used to obtain the load forecast value of the area at a preset time in the future based on the load forecasting model of the area and in combination with the historical load data; An energy prediction calculation module, which is used to obtain the current state of the energy storage system, and obtain the energy prediction value that the energy storage system can provide at a preset time in the future based on the current state; An overload risk calculation module is used to calculate the overload risk prediction value of the substation transformer based on an overload risk prediction model in combination with the overload degree score, the substation load prediction value and the energy prediction value, and determine the control strategy of the energy storage system according to the overload risk prediction level corresponding to the overload risk prediction value.

Images