A power system regulation device configuration method and device, terminal equipment and storage medium

Abstract

The application discloses a power system regulation device configuration method and device, terminal equipment and storage medium, which can take the device regulation potential value and the demand response regulation potential value as parameters of a regulation device configuration model, and then can obtain target configuration variables conforming to actual regulation conditions and user actual response characteristics after solving the regulation device configuration model. When obtaining the configuration scheme of each regulation device of the power system, the application can comprehensively consider the device regulation potential value and the demand response regulation potential value, so that the finally obtained target configuration variables not only conform to the actual regulation capacity of the device, but also make the power system conform to the actual response characteristics of the user. Through solving of the configuration variables and configuration of the power system based on the configuration variables, the performance advantages of each regulation device can be fully brought into play, the stable operation of the power system is ensured, and the supply and demand relationship of the power system is effectively balanced.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of power system regulation, and particularly relates to a power system regulation device configuration method and device, a terminal device and a storage medium. BACKGROUND

[0002] The operation efficiency and quality of a power system directly affect the power demand and life quality of people. By optimizing the configuration of regulation devices, power resources can be reasonably allocated, energy utilization efficiency can be improved, and energy consumption can be reduced, thereby improving the operation efficiency and quality of the power system and providing better protection for people's life.

[0003] However, the existing configuration optimization method often directly obtains a configuration optimization scheme of each regulation device by fixed rules or empirical formulas, or by simple calculation with reference to historical load data, device capacity and other factors. For example, according to historical load data of the power system, a relatively stable load range is determined, and then a suitable device capacity is selected according to the load range to ensure that the device can normally operate at peak load. Therefore, the existing configuration optimization method does not fully consider the actual regulation capacity of the device, nor does it consider the influence of user load adjustment capacity on the power system. Because the device regulation potential value and the demand response regulation potential value are not fully considered, the configuration scheme is often too rigid to fully utilize the performance advantages of the device. Moreover, because the user load adjustment capacity is not fully considered, the obtained configuration scheme may not effectively balance the supply and demand relationship of the power system, such as power supply shortage at peak period or power resource waste at low valley period, thereby failing to guarantee the stable operation of the power system. SUMMARY

[0004] The present application provides a power system regulation device configuration method, device, terminal device and storage medium, which can comprehensively consider the device regulation potential value and the demand response regulation potential value, so that the finally obtained target configuration variable can not only meet the actual regulation capacity of the device, but also make the power system meet the actual response characteristics of users, thereby effectively solving the problem that the performance advantages of the device cannot be fully utilized and the supply and demand relationship of the power system cannot be effectively balanced due to the failure to fully consider the device regulation potential value and the demand response regulation potential value in the prior art.

[0005] An embodiment of the present application provides a power system regulation device configuration method, comprising:

[0006] Based on the performance parameters and power data of the control equipment, a control potential value is generated to characterize the control equipment's ability to regulate the power system; wherein, the control equipment includes: generator sets and energy storage devices; the control potential value includes: available capacity, response rate, and probability of active support occurring;

[0007] Based on user electricity load data and demand response event data, a demand response regulation potential value is generated to characterize the user's ability to adjust load when participating in demand response; wherein, the demand response regulation potential value includes: capacity range, response accuracy, and capacity adjustment cost.

[0008] Based on the cost data of control equipment, the compensation cost data of demand response, the control potential value of equipment, and the control potential value of demand response, a control equipment configuration model is constructed with the goal of minimizing the operating cost of the power system. The constraints corresponding to the control equipment configuration model include: the output constraints of generator sets, the charging and discharging constraints of energy storage devices, and the capacity constraints of energy storage devices.

[0009] Under the constraints, the configuration model of the control equipment is solved to generate target configuration variables when the operating cost of the power system is minimized; wherein, the target configuration variables include: the output power of the generator set, the charging and discharging power of the energy storage device, and the capacity of the energy storage device;

[0010] Configure the control equipment in the power system according to the target configuration variables.

[0011] Preferably, the performance parameters of the control equipment include: the performance parameters of the generator set and the performance parameters of the energy storage device;

[0012] The performance parameters of the generator set include: rated power, ramp rate, output power regulation rate, load regulation rate, primary frequency regulation response time, and generator set response time.

[0013] The performance parameters of the energy storage device include: charging response time, discharging response time, and state of charge;

[0014] The step of generating a device control potential value, which characterizes the control device's ability to regulate the power system, based on the performance parameters and power data of the control device includes:

[0015] The available capacity of the generator set is generated based on the generator set's rated power, ramp rate, and output power.

[0016] The response rate of the generator set is generated based on the primary frequency regulation response time and the response time of the generator set.

[0017] generate a probability of active support of the power generator set according to an output power adjustment rate of the power generator set and a load adjustment rate;

[0018] generate an available capacity of the energy storage device according to a charging power, a discharging power and a state of charge of the energy storage device;

[0019] generate a response rate of the energy storage device according to a charging response time and a discharging response time of the energy storage device;

[0020] generate a probability of active support of the energy storage device according to a state of charge of the energy storage device.

[0021] Preferably, the demand response event data comprises: a first response time corresponding to a peak shaving demand response event, a first adjustment cost corresponding to the peak shaving demand response event, a second response time corresponding to a valley filling demand response event, and a second adjustment cost corresponding to the valley filling demand response event; the first response time is used to represent the time from receiving the peak shaving demand response instruction to starting to adjust the load; the second response time is used to represent the time from receiving the valley filling demand response instruction to starting to adjust the load;

[0022] The power consumption load data of the user comprises: a first load adjustment amount corresponding to a peak shaving demand response event and a second load adjustment amount corresponding to a valley filling demand response event;

[0023] The demand response regulation potential value for representing the ability of the user to adjust the load when participating in the demand response is generated according to the power consumption load data of the user and the demand response event data, comprising:

[0024] The first response time, the first adjustment cost, the second response time, the second adjustment cost, the first load adjustment amount and the second load adjustment amount are input into the regulation potential prediction model, so that the regulation potential prediction model extracts a load adjustment feature for representing the sustainable adjustment capacity of the user in different types of demand response events according to the first load adjustment amount, the second load adjustment amount, the first adjustment cost and the second adjustment cost; extracts a response feature for representing the response ability of the user in different types of demand response events according to the first response time, the second response time, the first load adjustment amount and the second load adjustment amount; extracts an adjustment cost feature for representing the cost bearing ability of the user in different types of demand response events according to the first adjustment cost, the second adjustment cost, the first load adjustment amount and the second load adjustment amount; generates a capacity interval, a response accuracy rate and a capacity adjustment cost according to the load adjustment feature, the response feature and the adjustment cost feature;

[0025] The training process of the regulation potential prediction model comprises:

[0026] The power consumption load data sample and the demand response event data sample are used as training samples; wherein, the power consumption load data sample comprises: load adjustment amount samples corresponding to peak shaving demand response events and load adjustment amount samples corresponding to valley filling demand response events; the demand response event data sample comprises: response time samples corresponding to peak shaving demand response events, adjustment cost samples corresponding to peak shaving demand response events, response time samples corresponding to valley filling demand response events, and adjustment cost samples corresponding to valley filling demand response events;

[0027] With the plurality of training samples and the actual capacity interval, the actual response accuracy and the actual capacity adjustment cost corresponding to each training sample as inputs, and with the predicted capacity interval, the predicted response accuracy and the predicted capacity adjustment cost of each training sample as outputs, the training of the to-be-trained regulation and control potential prediction model is iteratively performed until the model converges, and a preset regulation and control potential prediction model is generated.

[0028] Preferably, in each iteration training, a training sample is input into the regulation and control potential prediction model, so that the regulation and control potential prediction model generates the capacity interval prediction result, the response accuracy prediction result and the capacity adjustment cost prediction result corresponding to the training sample according to the load adjustment feature, the response feature and the adjustment cost feature in the training sample;

[0029] The capacity interval prediction result, the response accuracy prediction result and the capacity adjustment cost prediction result are compared with the actual capacity interval result, the actual response accuracy result and the actual capacity adjustment cost result, and the network parameters of the regulation and control potential prediction model are adjusted according to the comparison result.

[0030] Preferably, the regulation and control device configuration model comprises:

[0031] min F=ω1·C cost +ω2·S stability +ω3·P potential +ω4·D response ;

[0032]

[0033] C gen (t)=c i *P i,t ;

[0034]

[0035] Wherein, F is the operation cost of the power system, C cost is the regulation and control cost, S stability is a preset voltage stability index, P potentialD represents the equipment's controllability potential value. response For the demand response regulation potential value, ω1, ω2, ω3, and ω4 are different weighting coefficients; C gen (t) represents the power generation cost of the generator set at time t, C storage (t) represents the operating cost of the energy storage device at time t, C demand (t) represents the demand response compensation cost at time t, where T is the preset time period; c i P represents the unit output power cost of the generator set. i,t Let be the output power of the i-th generator set at time t, and di be the unit power cost of the energy storage device. Let be the discharge power of the i-th energy storage device at time t. c is the charging power of the i-th energy storage device at time t; e Q represents the unit capacity cost of energy storage equipment. i,t Let be the capacity of the i-th energy storage device at time t.

[0036] Preferably, the output constraint of the generator set includes:

[0037] P i,min ≤Pi,t≤P i,max ;

[0038] Among them, P i,min P represents the minimum output power corresponding to the i-th generator set. i,max This represents the maximum output power corresponding to the i-th generator set.

[0039] Preferably, the charge and discharge constraints of the energy storage device include:

[0040]

[0041] in, Let be the minimum discharge power of the i-th energy storage device. Let be the maximum discharge power of the i-th energy storage device; Let i be the minimum charging power of the i-th energy storage device. The maximum charging power of the i-th energy storage device;

[0042] The capacity constraints of the energy storage device include:

[0043] Q i,min ≤Q i,t ≤Q i,max ;

[0044] Among them, Q i,min Q is the minimum capacity limit for the i-th energy storage device. i,max This represents the maximum capacity limit for the i-th energy storage device.

[0045] Based on the above method embodiments, the present invention provides corresponding apparatus embodiments.

[0046] One embodiment of the present invention provides a power system control equipment configuration device, including: an equipment control potential generation module, a demand response control potential generation module, a model building module, a model solving module, and a control equipment configuration module;

[0047] The equipment regulation potential generation module is used to generate an equipment regulation potential value, which characterizes the regulation capability of the equipment to regulate the power system, based on the performance parameters and power data of the regulation equipment; wherein, the regulation equipment includes: generator sets and energy storage devices; the equipment regulation potential value includes: available capacity, response rate, and probability of active support occurring;

[0048] The demand response regulation potential generation module is used to generate a demand response regulation potential value, which characterizes the user's ability to adjust load when participating in demand response, based on the user's electricity load data and demand response event data; wherein, the demand response regulation potential value includes: capacity range, response accuracy, and capacity adjustment cost.

[0049] The model building module is used to construct a control equipment configuration model with the goal of minimizing the operating cost of the power system, based on the cost data of the control equipment, the compensation cost data of the demand response, the control potential value of the equipment, and the control potential value of the demand response. The constraints corresponding to the control equipment configuration model include: the output constraints of the generator set, the charging and discharging constraints of the energy storage device, and the capacity constraints of the energy storage device.

[0050] The model solving module is used to solve the configuration model of the control equipment under the constraints, and generate target configuration variables when the operating cost of the power system is minimized; wherein, the target configuration variables include: the output power of the generator set, the charging and discharging power of the energy storage device, and the capacity of the energy storage device;

[0051] The control equipment configuration module is used to configure the control equipment in the power system according to the target configuration variables.

[0052] Based on the above method embodiments, the present invention provides corresponding terminal device embodiments.

[0053] Another embodiment of the present invention provides a terminal device, including a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor. When the processor executes the computer program, it implements a power system control device configuration method as described in the above-described embodiment of the invention.

[0054] Based on the above method embodiments, the present invention provides corresponding storage medium embodiments.

[0055] Another embodiment of the present invention provides a storage medium, the computer-readable storage medium including a stored computer program, wherein, when the computer program is executed, it controls the device where the computer-readable storage medium is located to execute the power system control equipment configuration method described in the above-described embodiment of the invention.

[0056] The following benefits can be obtained by implementing the present invention:

[0057] This invention provides a method, apparatus, terminal equipment, and storage medium for configuring control equipment in a power system. It generates control potential values ​​for the control capabilities of the control equipment based on performance parameters and power data; and generates demand response control potential values ​​based on user load data and demand response event data. These control potential values ​​and demand response control potential values ​​are then used as parameters to construct a control equipment configuration model. After solving this model, target configuration variables that conform to both actual control conditions and user response characteristics are obtained. Since the control potential values ​​comprehensively reflect the control capabilities of the control equipment in the power system, ensuring that the model fully considers the actual control capabilities of the equipment during the solution process, target configuration variables that better reflect the actual control conditions of the power system can be derived. The demand response control potential values ​​characterize the user's ability to adjust load when participating in demand response. Introducing these values ​​ensures that the model fully considers the user's load adjustment capabilities during the solution process, resulting in target configuration variables that better reflect the user's actual response characteristics, ultimately achieving the optimal configuration of various control devices in the power system. Compared with existing technologies, this invention, when deriving the configuration scheme of various control devices in a power system, can comprehensively consider the control potential value of the devices and the control potential value of demand response. This ensures that the final target configuration variables not only conform to the actual control capabilities of the devices but also make the power system conform to the actual response characteristics of users. Therefore, by solving the configuration variables of this invention and configuring and scheduling the power system based on the configuration variables, the performance advantages of each control device can be fully utilized, ensuring the stable operation of the power system and effectively balancing the supply and demand relationship of the power system. Attached Figure Description

[0058] Figure 1 This is a flowchart illustrating a method for configuring control equipment in a power system according to an embodiment of the present invention.

[0059] Figure 2 This is a schematic diagram of the structure of a power system control equipment configuration device provided in an embodiment of the present invention. Detailed Implementation

[0060] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0061] like Figure 1 The diagram shown is a flowchart illustrating a method for configuring control equipment in a power system according to an embodiment of the present invention. The method includes:

[0062] Step S1: Based on the performance parameters and power data of the control equipment, generate equipment control potential values ​​to characterize the control equipment's ability to regulate the power system; wherein, the control equipment includes: generator sets and energy storage devices; the equipment control potential values ​​include: available capacity, response rate, and probability of active support occurring;

[0063] Step S2: Based on the user's electricity load data and demand response event data, generate a demand response regulation potential value to characterize the user's ability to adjust load when participating in demand response; wherein, the demand response regulation potential value includes: capacity range, response accuracy, and capacity adjustment cost.

[0064] Step S3: Based on the cost data of the control equipment, the compensation cost data of demand response, the control potential value of the equipment, and the control potential value of demand response, construct a control equipment configuration model with the goal of minimizing the operating cost of the power system; wherein, the constraints corresponding to the control equipment configuration model include: the output constraints of the generator set, the charging and discharging constraints of the energy storage device, and the capacity constraints of the energy storage device.

[0065] Step S4: Under the constraints, solve the configuration model of the control equipment and generate target configuration variables when the operating cost of the power system is minimized; wherein, the target configuration variables include: the output power of the generator set, the charging and discharging power of the energy storage device, and the capacity of the energy storage device;

[0066] Step S5: Configure the control equipment in the power system according to the target configuration variables.

[0067] In a preferred embodiment, for step S1, when determining the equipment control potential value of the control equipment's ability to regulate the power system, the present invention can separately determine the equipment control potential value of the generator set and the equipment control potential value of the energy storage device. The equipment control potential value is then: the available capacity, response rate, and probability of active support of the generator set, and the available capacity, response rate, and probability of active support of the energy storage device.

[0068] The performance parameters of the control equipment may include: the performance parameters of the generator set and the performance parameters of the energy storage equipment;

[0069] The performance parameters of the generator set include: rated power, ramp rate, output power regulation rate, load regulation rate, primary frequency regulation response time, and generator set response time.

[0070] The performance parameters of the energy storage device include: charging response time, discharging response time, and state of charge.

[0071] Therefore, when calculating the equipment control potential value of a generator set, the specific steps include:

[0072] The available capacity of the generator set is generated based on the generator set's rated power, ramp rate, and output power.

[0073] The response rate of the generator set is generated based on the primary frequency regulation response time and the response time of the generator set.

[0074] The probability of active support for the generator set is generated based on the generator set's output power regulation rate and load regulation rate.

[0075] When calculating the equipment regulation potential value of energy storage devices, the specific steps include:

[0076] The available capacity of the energy storage device is generated based on its charging power, discharging power, and state of charge.

[0077] The response rate of the energy storage device is generated based on its charging response time and discharging response time.

[0078] The probability of active support for the energy storage device is generated based on the state of charge of the energy storage device.

[0079] In illustrative terms, by calculating the regulation potential values ​​of generator sets and energy storage devices separately, the regulation capabilities of each type of regulation device can be evaluated more precisely. This allows for a more accurate understanding of the actual role of various devices in the power system, enabling reasonable allocation of regulation devices based on their regulation potential during configuration, thereby maximizing resource utilization.

[0080] Generator sets and energy storage devices play different roles in the power system. By calculating their regulation potential values ​​separately, we can better understand their regulation capabilities in the power system, thereby enabling more precise control of the power system's stability during regulation.

[0081] In a preferred embodiment, the present invention can acquire the generator set type, rated power, ramp rate, frequency regulation capability, voltage regulation capability, primary frequency regulation response time, and AGC response time as physical control characteristic parameters; and further acquire the energy storage device's charging and discharging power, response time, and state of charge as auxiliary control characteristic parameters.

[0082] The analytic hierarchy process (AHP) can be used to construct a parameter weight evaluation system. Weight coefficients are set according to the contribution of each parameter to the regulation of the power system. The physical regulation characteristic parameters and auxiliary regulation parameters are weighted and calculated with their corresponding weight coefficients to obtain the final physical regulation potential index.

[0083] Specifically, firstly, physical regulation characteristic parameters can be divided into primary indicators, including basic regulation capacity (i.e., available capacity), dynamic response characteristics (i.e., response rate), and stability support capacity (i.e., the probability of active support occurring).

[0084] The basic regulation capability includes rated power and ramp rate; the dynamic response characteristics cover primary frequency regulation response time and AGC response time; and the stability support capability includes frequency regulation capability and voltage regulation capability. The relative importance of each level of indicator is determined through expert scoring, and a judgment matrix is ​​established.

[0085] Since the rated power in the basic regulation capacity reflects the size of the unit's capacity, it can directly determine the adjustable range, and the weighting coefficient can be set to 0.3; the ramp rate characterizes the speed of change of output power and affects the flexibility of regulation, and the weighting coefficient is 0.25.

[0086] In the dynamic response characteristics, the primary frequency modulation response time represents the system's rapid response capability after disturbance, with a weighting coefficient of 0.15; the AGC response time reflects the secondary frequency modulation effect, with a weighting coefficient of 0.1.

[0087] The frequency regulation capability in the stability support capability reflects the frequency adjustment range, and the weighting coefficient is set to 0.12; the voltage regulation capability is related to voltage control, and the weighting coefficient is set to 0.08.

[0088] Secondly, the auxiliary regulation characteristic parameters are divided into secondary indicators. Since the charging and discharging power determines the range of energy storage's ability to participate in regulation, the weighting coefficient is 0.4; the response time reflects the timeliness of regulation, and the weighting coefficient is 0.35; the state of charge reflects the availability of energy storage equipment, and the weighting coefficient is 0.25.

[0089] Then, after determining the weighting coefficients, each parameter needs to be standardized. For positive indicators (such as rated power and frequency regulation capability), the maximum value standardization method is used; for negative indicators (such as response time), the minimum value standardization method is used. The standardized values ​​are unified to the [0,1] interval.

[0090] Finally, the standardized parameter values ​​are multiplied by the corresponding weight coefficients to obtain the score for each individual indicator.

[0091] Therefore, the formula for calculating the comprehensive score of the physical regulation potential index is:

[0092]

[0093] Among them, I p w represents an indicator of physical control potential. i Let X′ represent the weight coefficient of the i-th parameter. i Let represent the standardized value of the i-th parameter, and n represent the total number of parameters.

[0094] Indicatively, the comprehensive score of the physical control potential index is the sum of the available capacity, response rate, and probability of active support of the generator set, as well as the available capacity, response rate, and probability of active support of the energy storage device. Based on this comprehensive score, the control capability of the control device on the power system can be quantified, thus clearly understanding the actual contribution and potential of each device in the power system, so as to achieve reasonable resource allocation.

[0095] In a preferred embodiment, for step S2, in addition to introducing the evaluation and calculation process of equipment control potential value, the present invention also introduces the factor of demand response control potential value, thereby achieving optimal configuration of control equipment in the power system.

[0096] When determining the demand response control potential value, this invention can use a trained control potential prediction model to predict the demand response control potential value based on the user's electricity load data and demand response event data.

[0097] Specifically, the demand response event data includes: a first response time corresponding to a peak shaving demand response event, a first adjustment cost corresponding to a peak shaving demand response event, a second response time corresponding to a valley filling demand response event, and a second adjustment cost corresponding to a valley filling demand response event; the first response time is used to characterize the time from when the user receives the peak shaving demand response instruction to when the user begins to adjust the load; the second response time is used to characterize the time from when the user receives the valley filling demand response instruction to when the user begins to adjust the load.

[0098] The process of generating a demand response regulation potential value, which characterizes a user's ability to adjust load when participating in demand response, based on user electricity load data and demand response event data, is as follows:

[0099] The first response time, first adjustment cost, second response time, second adjustment cost, first load adjustment amount, and second load adjustment amount are input into the regulation potential prediction model. This allows the model to extract load adjustment features characterizing a user's sustainable regulation capacity in different types of demand response events, based on the first load adjustment amount, second load adjustment amount, first adjustment cost, and second adjustment cost. It also extracts response features characterizing a user's responsiveness in different types of demand response events, based on the first response time, second response time, first load adjustment amount, and second load adjustment amount. Furthermore, it extracts adjustment cost features characterizing a user's cost-bearing capacity in different types of demand response events, based on the first adjustment cost, second adjustment cost, first load adjustment amount, and second load adjustment amount. Finally, based on the load adjustment features, response features, and adjustment cost features, the model generates a capacity range, response accuracy, and capacity regulation cost.

[0100] The training process of the regulation potential prediction model includes:

[0101] Electricity load data samples and demand response event data samples are used as training samples; wherein, the electricity load data samples include: load adjustment amount samples corresponding to peak shaving demand response events and load adjustment amount samples corresponding to valley filling demand response events; the demand response event data samples include: response time samples corresponding to peak shaving demand response events, adjustment cost samples corresponding to peak shaving demand response events, response time samples corresponding to valley filling demand response events, and adjustment cost samples corresponding to valley filling demand response events.

[0102] The model is iteratively trained using several training samples and the actual capacity range, actual response accuracy, and actual capacity adjustment cost corresponding to each training sample as inputs, and the predicted capacity range, predicted response accuracy, and predicted capacity adjustment cost of each training sample as outputs, until the model converges, thus generating the preset regulatory potential prediction model.

[0103] During each iteration of training, a training sample is input into the regulation potential prediction model, so that the regulation potential prediction model generates the capacity range prediction result, response accuracy prediction result, and capacity regulation cost prediction result corresponding to the training sample based on the load adjustment characteristics, response characteristics, and regulation cost characteristics in the training sample.

[0104] The predicted results of capacity range, response accuracy, and capacity regulation cost are compared with the actual results of capacity range, response accuracy, and capacity regulation cost. The network parameters of the regulation potential prediction model are then adjusted based on the comparison results.

[0105] Specifically, historical electricity load data can be collected, including load adjustments corresponding to peak shaving and valley filling demand response events. Historical demand response event data, including response time and adjustment costs, can also be collected. This data can then be used as training samples to train a predictive model for control potential.

[0106] Machine learning algorithms (such as neural networks and support vector machines) are used to build a model for predicting regulatory potential. Training samples are input into the model for iterative training until convergence. During training, the model learns how to predict capacity ranges, response accuracy, and capacity regulation costs based on load adjustment characteristics, response characteristics, and regulation cost characteristics.

[0107] Therefore, when it is necessary to predict the potential value of demand response regulation in the current or future period, the current electricity load data and demand response event data are input into the trained model. The model will then output the predicted potential value of demand response regulation based on the input data, including the capacity range, response accuracy and capacity regulation cost.

[0108] It can be understood that, in this embodiment of the invention, a control potential prediction model can be trained based on historical demand response event data and user electricity load data. After the model is deployed, the current electricity load data and demand response event data are input into the control potential prediction model, and the predicted value of the demand response control potential is output, that is, the potential for load adjustment by users when participating in demand response, such as the capacity range when users participate in demand response, the response accuracy when users participate in demand response, and the capacity adjustment cost when users participate in demand response.

[0109] To improve the model's adaptability, embodiments of this invention can also introduce an online learning mechanism, updating the model parameters weekly by adding new response event data to the training set and updating the model using incremental learning. Simultaneously, a feature importance evaluation mechanism is established, analyzing the contribution of each feature to the prediction results using SHAP (SHapley Additive exPlanations) values.

[0110] In the forecasting process, a sliding time window method can also be used, setting the forecast window to 24 hours and the step size to 1 hour. For each time window, combining electricity consumption characteristic data and the characteristics of demand response events, the trained demand response forecasting model is used to derive the potential value of each demand response regulation.

[0111] For step S3, based on the equipment control potential value and demand response control potential value obtained from the previous steps, the two can be used as the basic parameters for constructing the control equipment configuration model. In this way, a control equipment configuration model that can generate the optimal configuration scheme of the power system can be constructed. This control equipment configuration model can comprehensively consider the equipment control potential value and the demand response control potential value, so that the final target configuration variable can not only conform to the actual control capability of the equipment, but also make the power system conform to the actual response characteristics of the users.

[0112] In a preferred embodiment, the control device configuration model includes:

[0113] min F=ω1·C cost +ω2·S stability +ω3·P potential +ω4·D response ;

[0114]

[0115] C gen (t)=c i *P i,t ;

[0116]

[0117] Where F is the operating cost of the power system, and C cost In order to control costs, S stability P is the preset voltage stability index. potential D represents the equipment's controllability potential value. response For the demand response regulation potential value, ω1, ω2, ω3, and ω4 are different weighting coefficients; C gen (t) represents the power generation cost of the generator set at time t, C storage (t) represents the operating cost of the energy storage device at time t, C demand (t) represents the demand response compensation cost at time t, where T is the preset time period; c i P represents the unit output power cost of the generator set. i,t Let be the output power of the i-th generator set at time t, and di be the unit power cost of the energy storage device. Let be the discharge power of the i-th energy storage device at time t. c is the charging power of the i-th energy storage device at time t; e Q represents the unit capacity cost of energy storage equipment. i,t Let be the capacity of the i-th energy storage device at time t.

[0118] Furthermore, the output constraint of the generator set includes:

[0119] P i,min ≤P i,t ≤P i,max ;

[0120] Among them, P i,min P represents the minimum output power corresponding to the i-th generator set. i,max This represents the maximum output power corresponding to the i-th generator set.

[0121] The charge and discharge constraints of the energy storage device include:

[0122]

[0123]

[0124] in, Let be the minimum discharge power of the i-th energy storage device. Let be the maximum discharge power of the i-th energy storage device; Let i be the minimum charging power of the i-th energy storage device. Let be the maximum charging power of the i-th energy storage device.

[0125] The capacity constraints of the energy storage device include:

[0126] Q i,min ≤Q i,t ≤Q i,max ;

[0127] Among them, Q i,min Q is the minimum capacity limit for the i-th energy storage device. i,max This represents the maximum capacity limit for the i-th energy storage device.

[0128] In illustrative terms, the control equipment configuration model of the present invention comprehensively considers multiple factors such as power system operating costs, control costs, voltage stability indicators, equipment control potential values, and demand response control potential values, thereby enabling it to more comprehensively reflect the actual situation of the power system and generate a better configuration scheme.

[0129] It is understood that the equipment configuration model of this invention uses the equipment control potential value as one of the basic parameters, which can ensure that the final configuration scheme can fully utilize the equipment's control potential and improve equipment utilization. Furthermore, by considering the demand response control potential value, it can more accurately predict user response characteristics, thereby formulating response strategies that better meet actual user needs and obtaining configuration schemes that conform to actual user response characteristics.

[0130] Furthermore, by considering preset voltage stability indicators, it can be ensured that the final configuration scheme meets the voltage stability requirements of the power system. Moreover, by considering the output and capacity constraints of generator sets and energy storage devices, equipment overload can be avoided, thereby ensuring the stable operation of the power system.

[0131] In summary, the construction of the control equipment configuration model and constraints can improve the optimization of power system operation, cost control, equipment utilization, response characteristic matching, and system stability by ultimately solving the configuration variables (i.e., configuration schemes).

[0132] In a preferred embodiment, steps S4 and S5 can be solved by inputting the objective function and constraints of the control equipment configuration model into a selected optimization algorithm (such as linear programming, nonlinear programming, dynamic programming, genetic algorithm, particle swarm optimization, etc.). During the solution process, variables such as the generator output power, the charging and discharging power, and the capacity of the energy storage device are continuously adjusted based on the objective function and constraints to find the optimal solution. This yields target configuration variables that not only meet the actual control capabilities of the equipment but also ensure the power system meets the actual response characteristics of the user.

[0133] Therefore, by solving the configuration variables of this invention and configuring and scheduling the power system based on the configuration variables, the performance advantages of each control device can be fully utilized, ensuring the stable operation of the power system and effectively balancing the supply and demand relationship of the power system.

[0134] In a preferred embodiment, the present invention can also solve for the optimal control configuration scheme at different time scales based on the established control equipment configuration model.

[0135] Based on the cost data of the control equipment, the compensation cost data of demand response, the control potential value of the equipment, and the control potential value of demand response, after constructing the control equipment configuration model, the output plan of each unit can be accurately planned to meet the control needs at different time granularities, and the output power of the generator units, the charging and discharging power of the energy storage equipment, and the capacity of the energy storage equipment can be allocated at different time scales.

[0136] Furthermore, embodiments of the present invention can also clarify the response scale, call sequence, and duration of various types of users, thereby deriving compensation prices and incentive mechanisms to encourage users to participate in demand response, so as to improve the demand response regulation potential value, and thus more accurately derive the final configuration scheme.

[0137] like Figure 2 As shown, based on the embodiments of the above-mentioned power system control equipment configuration methods, the present invention provides corresponding device embodiments;

[0138] One embodiment of the present invention provides a power system control equipment configuration device, including: an equipment control potential generation module, a demand response control potential generation module, a model building module, a model solving module, and a control equipment configuration module;

[0139] The equipment regulation potential generation module is used to generate an equipment regulation potential value, which characterizes the regulation capability of the equipment to regulate the power system, based on the performance parameters and power data of the regulation equipment; wherein, the regulation equipment includes: generator sets and energy storage devices; the equipment regulation potential value includes: available capacity, response rate, and probability of active support occurring;

[0140] The demand response regulation potential generation module is used to generate a demand response regulation potential value, which characterizes the user's ability to adjust load when participating in demand response, based on the user's electricity load data and demand response event data; wherein, the demand response regulation potential value includes: capacity range, response accuracy, and capacity adjustment cost.

[0141] The model building module is used to construct a control equipment configuration model with the goal of minimizing the operating cost of the power system, based on the cost data of the control equipment, the compensation cost data of the demand response, the control potential value of the equipment, and the control potential value of the demand response. The constraints corresponding to the control equipment configuration model include: the output constraints of the generator set, the charging and discharging constraints of the energy storage device, and the capacity constraints of the energy storage device.

[0142] The model solving module is used to solve the configuration model of the control equipment under the constraints, and generate target configuration variables when the operating cost of the power system is minimized; wherein, the target configuration variables include: the output power of the generator set, the charging and discharging power of the energy storage device, and the capacity of the energy storage device;

[0143] The control equipment configuration module is used to configure the control equipment in the power system according to the target configuration variables.

[0144] It should be noted that the device embodiments described above are merely illustrative. The modules described as separate components may or may not be physically separate, and the components shown as modules may or may not be physical modules; they may be located in one place or distributed across multiple network modules. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Furthermore, in the accompanying drawings of the device embodiments provided by this invention, the connection relationships between modules indicate that they have communication connections, which can be specifically implemented as one or more communication buses or signal lines. Those skilled in the art can understand and implement this without any creative effort.

[0145] Those skilled in the art will clearly understand that, for convenience and simplicity, the specific working process of the device described above can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0146] Based on the above embodiments of various power system control equipment configuration methods, the present invention provides corresponding embodiments of terminal equipment.

[0147] One embodiment of the present invention provides a terminal device, including a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor. When the processor executes the computer program, it implements a power system control device configuration method according to any one of the method embodiments of the present invention.

[0148] The terminal device may be a desktop computer, laptop, handheld computer, or cloud server, etc. The terminal device may include, but is not limited to, a processor and a memory.

[0149] The processor can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor can be a microprocessor or any conventional processor. The processor is the control center of the terminal device, connecting all parts of the terminal device via various interfaces and lines.

[0150] The memory can be used to store the computer program. The processor implements various functions of the terminal device by running or executing the computer program stored in the memory and calling data stored in the memory. The memory may mainly include a program storage area and a data storage area. The program storage area may store the operating system, at least one application program required for a function, etc.; the data storage area may store data created based on the use of the mobile phone, etc. In addition, the memory may include high-speed random access memory, and may also include non-volatile memory, such as hard disk, RAM, plug-in hard disk, smart media card (SMC), secure digital (SD) card, flash card, at least one disk storage device, flash memory device, or other volatile solid-state storage device.

[0151] Based on the above embodiments of various power system control equipment configuration methods, the present invention provides corresponding embodiments of storage media.

[0152] One embodiment of the present invention provides a storage medium including a stored computer program, wherein, when the computer program is executed, it controls the device where the computer-readable storage medium is located to execute a power system control equipment configuration method according to any one of the method embodiments of the present invention.

[0153] The storage medium is a computer-readable storage medium, and the computer program is stored in the computer-readable storage medium. When executed by a processor, the computer program can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable file, or some intermediate form. The computer-readable medium can include: any entity or device capable of carrying the computer program code, recording media, USB flash drive, portable hard drive, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signals, telecommunication signals, and software distribution media, etc. It should be noted that the content included in the computer-readable medium can be appropriately added or removed according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, the computer-readable medium does not include electrical carrier signals and telecommunication signals.

[0154] The above description represents the preferred embodiments of the present invention. It should be noted that those skilled in the art can make various improvements and modifications without departing from the principles of the present invention, and these improvements and modifications are also considered to be within the scope of protection of the present invention.

Claims

1. A method of configuring a regulating device of a power system, characterized by, The method comprises the following steps: According to the performance parameters of the regulating device and the power data, a device regulation potential value is generated to represent the regulation capability of the regulating device to the power system; wherein, the regulating device comprises a generator set and an energy storage device; the device regulation potential value comprises available capacity, response rate and probability of active support; According to the user's electricity load data and demand response event data, a demand response regulation potential value is generated to represent the user's ability to adjust the load when participating in demand response; wherein, the demand response regulation potential value comprises capacity interval, response accuracy rate and capacity adjustment cost; According to the cost data of the regulating device, the compensation cost data of demand response, the device regulation potential value and the demand response regulation potential value, a regulating device configuration model is constructed with the objective of minimizing the operation cost of the power system; wherein, the constraint conditions corresponding to the regulating device configuration model comprise the output constraint of the generator set, the charge and discharge constraint of the energy storage device and the capacity constraint of the energy storage device; Under the constraint conditions, the regulating device configuration model is solved to generate target configuration variables at the minimum operation cost of the power system; wherein, the target configuration variables comprise the output power of the generator set, the charge and discharge power of the energy storage device and the capacity of the energy storage device; According to the target configuration variables, the regulating devices in the power system are configured; The regulating device configuration model comprises: ； ； ； ； in, For the operating costs of the power system, In order to control costs, This is a preset voltage stability index. This represents the potential value for equipment regulation. This represents the potential value for demand response regulation. , , , These are different weighting coefficients; For generator sets in The cost of generating electricity at any given time For energy storage devices in The operating cost at any given time for Real-time demand response compensation costs The preset time period; Cost per unit output power of generator set, For the first One generator set Output power at any moment The unit power cost of energy storage devices, For the j-th energy storage device in Discharge power at any given time For the j-th energy storage device in The charging power at any given time; The unit capacity cost of energy storage equipment, For the j-th energy storage device in The capacity of a moment.

2. The method of claim 1, wherein the power system control device configuration method is characterized by, The performance parameters of the regulating device comprise the performance parameters of the generator set and the performance parameters of the energy storage device; The performance parameters of the generator set comprise rated power, climbing rate, output power adjustment rate, load adjustment rate, primary frequency modulation response time and response time of the unit; The performance parameters of the energy storage device comprise charge response time, discharge response time and state of charge; According to the performance parameters of the regulating device and the power data, the device regulation potential value is generated to represent the regulation capability of the regulating device to the power system, which comprises: According to the rated power of the generator set, the climbing rate and the output power of the generator set, the available capacity of the generator set is generated; According to the primary frequency modulation response time and the response time of the unit, the response rate of the generator set is generated; According to the output power adjustment rate and the load adjustment rate of the generator set, the probability of active support of the generator set is generated; According to the charge power, discharge power and state of charge of the energy storage device, the available capacity of the energy storage device is generated; According to the charge response time and the discharge response time of the energy storage device, the response rate of the energy storage device is generated; According to the state of charge of the energy storage device, the probability of active support of the energy storage device is generated.

3. The method of claim 2, wherein the power system control device configuration method is characterized by, The demand response event data comprises: a first response time corresponding to the peak-cut demand response event, a first adjustment cost corresponding to the peak-cut demand response event, a second response time corresponding to the valley-fill demand response event, and a second adjustment cost corresponding to the valley-fill demand response event; the first response time is used to represent the time from when the user receives the peak-cut demand response instruction to when the user starts to adjust the load; the second response time is used to represent the time from when the user receives the valley-fill demand response instruction to when the user starts to adjust the load; The user's power consumption load data comprises: a first load adjustment amount corresponding to the peak-cut demand response event, and a second load adjustment amount corresponding to the valley-fill demand response event; The demand response regulation potential value generated according to the user's power consumption load data and the demand response event data comprises: The first response time, the first adjustment cost, the second response time, the second adjustment cost, the first load adjustment amount, and the second load adjustment amount are input into the regulation potential prediction model, so that the regulation potential prediction model extracts a load adjustment feature used to represent the sustainable adjustment capacity of the user in different types of demand response events according to the first load adjustment amount, the second load adjustment amount, the first adjustment cost, and the second adjustment cost; extracts a response feature used to represent the response ability of the user in different types of demand response events according to the first response time, the second response time, the first load adjustment amount, and the second load adjustment amount; extracts an adjustment cost feature used to represent the cost bearing capacity of the user in different types of demand response events according to the first adjustment cost, the second adjustment cost, the first load adjustment amount, and the second load adjustment amount; and generates a capacity interval, a response accuracy, and a capacity adjustment cost according to the load adjustment feature, the response feature, and the adjustment cost feature. The training process of the regulation potential prediction model comprises: The power consumption load data sample and the demand response event data sample are used as training samples; the power consumption load data sample comprises: a load adjustment amount sample corresponding to the peak-cut demand response event and a load adjustment amount sample corresponding to the valley-fill demand response event; and the demand response event data sample comprises: a response time sample corresponding to the peak-cut demand response event, an adjustment cost sample corresponding to the peak-cut demand response event, a response time sample corresponding to the valley-fill demand response event, and an adjustment cost sample corresponding to the valley-fill demand response event; The training process of the regulation potential prediction model comprises: The training process of the regulation potential prediction model comprises:

4. The method of claim 3, wherein the power system control device configuration method is characterized by, In each iteration of the training, a training sample is input into the regulation potential prediction model, so that the regulation potential prediction model generates a capacity interval prediction result, a response accuracy prediction result and a capacity adjustment cost prediction result corresponding to the training sample according to the load adjustment feature, the response feature and the adjustment cost feature in the training sample; The capacity interval prediction result, the response accuracy prediction result and the capacity adjustment cost prediction result are compared with actual capacity interval results, actual response accuracy results and actual capacity adjustment cost results, and the network parameters of the regulation potential prediction model are adjusted according to the comparison results.

5. The method of claim 4, wherein the power system control device configuration method is characterized by, The output constraint of the generator set includes: ； in, For the first The minimum output power corresponding to each generator set For the first The maximum output power corresponding to each generator set.

6. The method of claim 5, wherein the output constraint of the generator set includes: The charge and discharge constraint of the energy storage device includes: ； ； wherein, Pmin,j is the minimum discharging power of the jth energy storage device, Pmax,j is the maximum discharging power of the jth energy storage device; Pmin,j is the minimum discharging power of the jth energy storage device, Pmax,j is the maximum discharging power of the jth energy storage device; The capacity constraint of the energy storage device includes: ； wherein, is a minimum capacity limit value for the jth energy storage device, is a maximum capacity limit value for the jth energy storage device.

7. A device configuration apparatus for a power system control, characterized by comprising: The method includes: The device regulation potential generation module, the demand response regulation potential generation module, the model construction module, the model solving module and the regulation device configuration module; The device regulation potential generation module is configured to generate a device regulation potential value for representing the regulation capability of a regulation device on a power system according to performance parameters of the regulation device and power data; the regulation device includes a generator set and an energy storage device; the device regulation potential value includes available capacity, response rate and probability of active support; The demand response regulation potential generation module is configured to generate a demand response regulation potential value for representing the capability of a user to adjust load when participating in demand response according to user power consumption load data and demand response event data; the demand response regulation potential value includes a capacity interval, a response accuracy and a capacity adjustment cost; The model construction module is configured to construct a regulation device configuration model with the minimum power system operation cost as the target according to cost data of the regulation device, compensation cost data of demand response, the device regulation potential value and the demand response regulation potential value; the constraint conditions corresponding to the regulation device configuration model include output constraints of the generator set, charge and discharge constraints of the energy storage device and capacity constraints of the energy storage device; The regulation device configuration model includes: ； ； ； ； in, For the operating costs of the power system, In order to control costs, This is a preset voltage stability index. This represents the potential value for equipment regulation. This represents the potential value for demand response regulation. , , , These are different weighting coefficients; For generator sets in The cost of generating electricity at any given time For energy storage devices in The operating cost at any given time for Real-time demand response compensation costs The preset time period; Cost per unit output power of generator set, For the first One generator set Output power at any moment The unit power cost of energy storage devices, For the j-th energy storage device in Discharge power at any given time For the j-th energy storage device in The charging power at any given time; The unit capacity cost of energy storage equipment, For the j-th energy storage device in The capacity of a given moment; The model solving module is configured to solve the regulation device configuration model under the constraint conditions to generate target configuration variables at the minimum power system operation cost; the target configuration variables include output power of the generator set, charge and discharge power of the energy storage device and capacity of the energy storage device; The regulation device configuration module is configured to configure the regulation device in the power system according to the target configuration variables.

8. A terminal device, comprising: The computer program is configured to be executed by the processor, and the processor implements the method of claim 1-6 when executing the computer program.

9. A storage medium, characterized by The storage medium comprises a stored computer program, wherein the computer program controls a device where the storage medium is located to perform the configuration method of the power system regulating device according to any one of claims 1 to 6 when the computer program is running.

Images