Microgrid demand response scheduling method and device based on aggregation temperature control load, terminal equipment and computer readable storage medium

Abstract

The invention discloses a micro-grid demand response scheduling method and device based on an aggregation temperature control load, terminal equipment and a computer readable storage medium, and the method comprises the steps: obtaining a rigid load prediction value, a photovoltaic output prediction value, a fan output prediction value and a power grid electricity price of a to-be-scheduled time period, and taking the minimum scheduling cost as a target; constructing a micro-grid demand side response model; solving the model, and generating the response power of the aggregation temperature control load in the to-be-scheduled time period when the scheduling cost objective function is minimum; substituting the response power of the aggregation temperature control load in the to-be-scheduled time period into the aggregation temperature control load model, and updating the virtual charge state of the aggregation temperature control load; wherein the aggregation temperature control load model is constructed based on the number of single temperature control loads and parameters of each virtual battery in each temperature control load; and according to the virtual charge state of the aggregation temperature control load, adjusting power generation of the demand response side of the micro-grid. According to the invention, the flexibility and stability of micro-grid scheduling can be improved.

Description

Technical Field

[0001] The present invention relates to the field of power system control technology, and in particular to a microgrid demand response scheduling method, device, terminal equipment and computer-readable storage medium based on aggregated temperature control loads. Background Art

[0002] With the continuous growth of global energy demand and the enhancement of environmental protection awareness, traditional energy systems are facing huge challenges. The widespread application of renewable energy sources such as solar and wind energy provides new opportunities for the sustainable development of power systems. However, the output of these renewable energy sources is intermittent and unstable, which brings difficulties to the dispatching and management of power systems. Therefore, how to effectively integrate renewable energy and improve the flexibility and reliability of power systems has become a hot topic in current research. In this context, microgrids, as a new type of power system architecture, have gradually received attention. Microgrids can integrate multiple distributed energy resources in a local area and achieve efficient energy management through intelligent dispatching.

[0003] In the dispatching strategy of microgrids, the application of demand-side response is becoming more and more widespread. Existing studies have shown that by adjusting the user's load, especially the temperature control load, the economy and flexibility of the microgrid can be significantly improved. In the prior art, many studies focus on how to model the temperature control load as a virtual battery to enhance the dispatching capability of the microgrid. However, the existing technical solutions usually face the problem of insufficient adjustable capacity of a single temperature control load, which limits its application in dynamic energy management. Summary of the invention

[0004] The embodiments of the present invention provide a method, an apparatus, a terminal device and a computer-readable storage medium for demand response scheduling of a microgrid based on aggregated temperature control loads, which can improve the flexibility and stability of microgrid scheduling.

[0005] An embodiment of the present invention provides a microgrid demand response scheduling method based on aggregated temperature control loads, including:

[0006] Obtain the rigid load forecast value, photovoltaic output forecast value, wind turbine output forecast value and grid electricity price for the period to be scheduled;

[0007] According to the rigid load forecast value, photovoltaic output forecast value, wind turbine output forecast value and grid electricity price in the dispatching period, a microgrid demand side response model is constructed with the goal of minimizing the dispatching cost.

[0008] Solve the microgrid demand side response model to generate the response power of the aggregated temperature control load in the scheduling period when the scheduling cost objective function is minimized;

[0009] Substitute the response power of the aggregated temperature control load in the time period to be scheduled into the aggregated temperature control load model, and update the virtual charge state of the aggregated temperature control load; wherein the aggregated temperature control load model is constructed based on the number of single temperature control loads and the parameters of each virtual battery inside each temperature control load;

[0010] Adjust the power generation on the demand response side of the microgrid according to the virtual state of charge of the aggregated temperature control load.

[0011] Furthermore, the aggregate temperature control load model is as follows:

[0012] SOC agg (k+1)=λ agg1 ·SOC agg (k)+P agg (k)+λ agg2 ;

[0013]

[0014]

[0015] Among them, SOC agg (k) represents the virtual state of charge of the aggregated temperature control load at time k, SOC agg (k+1) represents the virtual charge state of the aggregated temperature control load at time k+1, P agg (k) represents the response power of the aggregate temperature control load, λ agg1 The weight coefficient of the virtual state of charge of the aggregated temperature control load at time k, λ agg2 represents the error parameter of the aggregated temperature control load, n represents the number of individual temperature control loads in the aggregated temperature control load, and λ 1i represents the weight coefficient of the virtual state of charge of the ith temperature control load in the aggregated temperature control load, λ 2i represents the weight coefficient of the response power of the i-th temperature control load in the aggregated temperature control load, λ 3i Represents the error parameter of the i-th temperature control load in the aggregated temperature control load.

[0016] Furthermore, the rigid load forecast value, photovoltaic output forecast value, wind turbine output forecast value and grid electricity price of the scheduled period are obtained, including:

[0017] Obtain the rigid load value, photovoltaic output value, wind turbine output value, first historical grid electricity price, meteorological data and periodic demand parameters within the preset historical period at the current moment;

[0018] The rigid load value, photovoltaic output value, wind turbine output value, the first historical grid electricity price, meteorological data and periodic demand parameters in the preset historical time period at the current moment are input into the trained prediction model, so that the prediction model generates the rigid load prediction value, photovoltaic output prediction value, wind turbine output prediction value and grid electricity price for the scheduling period according to the rigid load value, photovoltaic output value, wind turbine output value, the first historical grid electricity price, meteorological data and periodic demand parameters in the preset historical time period at the current moment.

[0019] Furthermore, the prediction model is determined in the following way:

[0020] Acquire a number of training data and their corresponding training labels; the training data include: rigid load value, photovoltaic output value, wind turbine output value, second historical grid electricity price, meteorological data and periodic demand parameters within a preset historical period; the training labels include: rigid load value, photovoltaic output value, wind turbine output value and third historical grid electricity price within a preset time after the preset historical period;

[0021] Each training data and its corresponding training label are input into the prediction model to be trained for iterative training until the loss function converges to obtain a trained prediction model.

[0022] Furthermore, the microgrid demand side response model is as follows:

[0023]

[0024] Among them, P load (k) represents the predicted value of rigid load in the kth time period, P PV (k) represents the predicted photovoltaic output value in the kth time period, P WT (k) represents the predicted value of the fan output in the kth time period, P agg (k) represents the response power of the aggregate temperature control load in the kth time period, I price (k) represents the real-time grid electricity price in the kth time period, and T represents the dispatch time.

[0025] Furthermore, according to the virtual state of charge of the aggregated temperature control load, the power generation on the demand response side of the microgrid is adjusted, including:

[0026] comparing the virtual state of charge of the aggregated temperature-controlled load with a preset threshold;

[0027] When the virtual state of charge of the aggregated temperature control load does not exceed a first preset threshold, reducing power generation on the demand response side of the microgrid by a first preset proportion;

[0028] When the virtual state of charge of the aggregated temperature control load exceeds the first preset threshold, and the virtual state of charge of the aggregated temperature control load does not exceed the second preset threshold, the power generation on the demand response side of the microgrid is not adjusted;

[0029] When the virtual state of charge of the aggregated temperature-controlled load exceeds a second preset threshold, the power generation on the demand response side of the microgrid is increased by a second preset proportion.

[0030] Based on the above method embodiment, the present invention provides a corresponding device embodiment, including: a prediction data acquisition module, a microgrid demand side response model construction module, a microgrid demand side response model solution module, an aggregated virtual charge state update module, and a demand response side scheduling module;

[0031] The forecast data acquisition module is used to obtain the rigid load forecast value, photovoltaic output forecast value, wind turbine output forecast value and grid electricity price during the scheduling period;

[0032] The microgrid demand side response model construction module is used to construct the microgrid demand side response model based on the rigid load forecast value, photovoltaic output forecast value, wind turbine output forecast value and grid electricity price in the scheduling period with the goal of minimizing the scheduling cost;

[0033] A microgrid demand side response model solving module is used to solve the microgrid demand side response model and generate the response power of the aggregated temperature control load in the scheduling period when the scheduling cost objective function is minimized;

[0034] An aggregated virtual state of charge update module is used to substitute the response power of the aggregated temperature control load in the scheduling period into the aggregated temperature control load model to update the virtual state of charge of the aggregated temperature control load; wherein the aggregated temperature control load model is constructed based on the number of single temperature control loads and the parameters of each virtual battery inside each temperature control load;

[0035] The demand response side scheduling module is used to adjust the power generation on the demand response side of the microgrid according to the virtual charge state of the aggregated temperature control load.

[0036] Furthermore, the aggregate temperature control load model is as follows:

[0037] SOC agg (k+1)=λ agg1 ·SOC agg (k)+P agg (k)+λ agg2 ;

[0038]

[0039]

[0040] Among them, SOCagg (k) represents the virtual state of charge of the aggregated temperature control load at time k, SOC agg (k+1) represents the virtual charge state of the aggregated temperature control load at time k+1, P agg (k) represents the response power of the aggregate temperature control load, λ agg1 The weight coefficient of the virtual state of charge of the aggregated temperature control load at time k, λ agg2 represents the error parameter of the aggregated temperature control load, n represents the number of individual temperature control loads in the aggregated temperature control load, and λ 1i represents the weight coefficient of the virtual state of charge of the ith temperature control load in the aggregated temperature control load, λ 2i represents the weight coefficient of the response power of the i-th temperature control load in the aggregated temperature control load, λ 3i Represents the error parameter of the i-th temperature control load in the aggregated temperature control load.

[0041] Based on the above-mentioned method embodiment, the present invention provides a corresponding terminal device embodiment, 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, the steps of the microgrid demand response scheduling method based on aggregated temperature control loads as described in the present invention are implemented.

[0042] Based on the above-mentioned method embodiment, the present invention provides a corresponding computer-readable storage medium embodiment, including: a stored computer program, which controls the device where the computer-readable storage medium is located to execute the steps of the microgrid demand response scheduling method based on aggregated temperature control loads as described in the present invention when the computer program is running.

[0043] Compared with the prior art, the beneficial effects of the embodiment of this solution are:

[0044] The present invention constructs a microgrid demand-side response model with the goal of minimizing the dispatching cost through the rigid load forecast value, photovoltaic output forecast value, wind turbine output forecast value and grid electricity price in the time period to be dispatched. The model itself takes into account the complementarity and adjustability of multiple energy resources, and provides a larger adjustment space for the aggregated temperature-controlled load. Then, the microgrid demand-side response model is solved to generate the response power of the aggregated temperature-controlled load in the time period to be dispatched when the dispatching cost objective function is minimized. The response power of the aggregated temperature-controlled load in the time period to be dispatched is substituted into the aggregated temperature-controlled load model to update the virtual state of charge of the aggregated temperature-controlled load. The aggregated temperature-controlled load model is constructed based on the number of single temperature-controlled loads and the parameters of each virtual battery inside each temperature-controlled load. By aggregating multiple single temperature-controlled loads for overall management and dispatching, the adjustment capacity of each temperature-controlled load is fully utilized to form a larger adjustment capacity and a faster response speed, thereby making it easier to affect the supply and demand balance of the power grid. Finally, by monitoring the virtual charge state of the aggregated temperature control loads, the microgrid can flexibly adjust its power generation plan on the demand response side. The aggregated temperature control loads can be dispatched in a unified manner to reduce unnecessary energy waste, maximize the absorption of renewable energy, and reduce dependence on traditional power sources.

[0045] In summary, the present invention improves the flexibility and stability of microgrid scheduling by aggregating temperature control loads as virtual batteries for demand-side response. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] Figure 1 It is a flow chart of a microgrid demand response scheduling method based on aggregated temperature control loads provided by an embodiment of the present invention;

[0047] Figure 2 It is a flowchart of a prediction model training process provided by an embodiment of the present invention;

[0048] Figure 3 It is a structural schematic diagram of a microgrid demand response scheduling device based on aggregated temperature control loads provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0049] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0050] In the description of the present invention, it should be understood that the terms "first" and "second" are only used for descriptive purposes and cannot be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features.

[0051] like Figure 1 As shown, an embodiment of the present invention provides a microgrid demand response scheduling method based on aggregated temperature control loads, the method comprising at least the following steps:

[0052] Step S1: Obtain the rigid load forecast value, photovoltaic output forecast value, wind turbine output forecast value and grid electricity price for the time period to be scheduled;

[0053] In a preferred embodiment, obtaining the rigid load forecast value, photovoltaic output forecast value, wind turbine output forecast value and grid electricity price in the time period to be scheduled includes:

[0054] Obtain the rigid load value, photovoltaic output value, wind turbine output value, first historical grid electricity price, meteorological data and periodic demand parameters within the preset historical period at the current moment;

[0055] The rigid load value, photovoltaic output value, wind turbine output value, the first historical grid electricity price, meteorological data and periodic demand parameters in the preset historical time period at the current moment are input into the trained prediction model, so that the prediction model generates the rigid load prediction value, photovoltaic output prediction value, wind turbine output prediction value and grid electricity price for the scheduling period according to the rigid load value, photovoltaic output value, wind turbine output value, the first historical grid electricity price, meteorological data and periodic demand parameters in the preset historical time period at the current moment.

[0056] For step S1, assuming that the microgrid demand response for the next day needs to be scheduled, the rigid load value, photovoltaic output value, wind turbine output value, first historical grid electricity price, meteorological data and periodic demand parameters of the day before the current time point are first obtained from the microgrid system. Among them, meteorological data include temperature, wind speed and sunshine duration, etc. These meteorological data have a direct and significant impact on the power generation efficiency of photovoltaic and wind power; periodic demand parameters include seasonal changes, differences between weekdays and weekends, and holiday effects, etc. These periodic demand parameters reflect the periodic changes of load and renewable energy output.

[0057] The collected data is input into a trained prediction model, which is a machine learning model (such as a neural network, support vector machine or random forest, etc.) or a statistical model (such as time series analysis or regression analysis, etc.), which has been trained to capture the complex relationship between the above variables. The prediction model is run to generate the rigid load forecast value, photovoltaic output forecast value, wind turbine output forecast value and grid electricity price forecast value for the next day.

[0058] It should be noted that, assuming that the microgrid demand response needs to be scheduled for the next three days, it is necessary to obtain data from the three days before the current time point in order to obtain sufficient information for longer-term predictions.

[0059] The following is a detailed description of the training process of the prediction model:

[0060] like Figure 2 As shown in Figure 1, the training process of the prediction model includes the following steps:

[0061] Step S101: Acquire a number of training data and their corresponding training labels; the training data include: rigid load values, photovoltaic output values, wind turbine output values, second historical grid electricity prices, meteorological data, and periodic demand parameters within a preset historical period; the training labels include: rigid load values, photovoltaic output values, wind turbine output values, and third historical grid electricity prices within a preset time after the preset historical period;

[0062] For step S101, in order to train the prediction model, first obtain multiple groups of training data and corresponding training labels. The training data include rigid load values, photovoltaic output values, wind turbine output values, the second historical grid electricity price, meteorological data and periodic demand parameters within a preset historical period. These data are used as inputs to the prediction model to help the model learn the relationship between input data and output data; the training labels are rigid load values, photovoltaic output values, wind turbine output values ​​and the third historical grid electricity price within a preset time after the preset historical period. These labels are the targets of the prediction model.

[0063] It should be noted that the preset historical time periods in each set of training data can be different. For example, the first set of training data can contain data from one historical day, while the second set of training data can contain data from five historical days. This allows the model to learn data patterns and trends within different time ranges, thereby improving the model's generalization ability and prediction accuracy.

[0064] Step S102: input each training data and its corresponding training label into the prediction model to be trained for iterative training until the loss function converges to obtain a trained prediction model.

[0065] For step S102, each set of training data and its corresponding training labels are input into the prediction model for iterative training. During the training process, the model will extract features related to load, photovoltaic, and wind power output from the training data, such as time features (hours, days, weeks, etc.), meteorological features (temperature, humidity, wind speed, light, etc.), and user behavior features (holidays, seasonality, etc.), and then adjust the weights and biases according to the relationship between the extracted feature data and the labels to minimize the difference between the prediction results and the actual labels. Through multiple iterative training, the model is gradually optimized to obtain a trained prediction model. The model has acquired a certain prediction ability by learning the relationship between the training data and the labels, and can be used to predict new input data and generate prediction results.

[0066] Step S2: According to the rigid load forecast value, photovoltaic output forecast value, wind turbine output forecast value and grid electricity price in the time period to be dispatched, a microgrid demand side response model is constructed with the goal of minimizing the dispatching cost;

[0067] In a preferred embodiment, the microgrid demand side response model is specifically:

[0068]

[0069] Among them, P load (k) represents the predicted value of rigid load in the kth time period, P PV (k) represents the predicted photovoltaic output value in the kth time period, P WT (k) represents the predicted value of the fan output in the kth time period, P agg (k) represents the response power of the aggregate temperature control load in the kth time period, I price (k) represents the real-time grid electricity price in the kth time period, and T represents the dispatch time.

[0070] For step S2, in order to schedule the microgrid demand side response for the next day, the scheduling time T=24 is set, which means that in the next 24 hours, with the minimum scheduling cost F as the goal, the following microgrid demand side response model is constructed:

[0071]

[0072] Among them, P load (k) represents the predicted value of rigid load in the kth time period, P PV (k) represents the predicted photovoltaic output value in the kth time period, P WT (k) represents the predicted value of the fan output in the kth time period, P agg (k) represents the response power of the aggregate temperature control load in the kth time period, I price (k) represents the real-time grid electricity price in the kth time period.

[0073] The microgrid demand-side response model provides a quantitative analysis method for the demand-side response of the microgrid. Specifically, in each time period k, the difference between the rigid load forecast value and the renewable energy output forecast value (photovoltaic and wind power) is calculated, and then the response power of the aggregated temperature control load is subtracted from this difference to obtain the net load demand for the time period. Next, this net load demand is multiplied by the real-time grid electricity price to obtain the cost of the time period. Finally, the costs of all time periods are summed to obtain the total dispatch cost F. By optimizing the parameters in the model, that is, the response power of the aggregated temperature control load, the total dispatch cost can be minimized.

[0074] Step S3: solving the microgrid demand side response model to generate the response power of the aggregated temperature control load in the scheduling period when the scheduling cost objective function is minimized;

[0075] For step S3, by solving the microgrid demand-side response model of step S2, and combining the rigid load forecast value, photovoltaic output forecast value, wind turbine output forecast value and grid electricity price of the scheduled period obtained in step S1, the response power of the aggregated temperature control load when the dispatch cost objective function is minimized can be determined. The response power of this aggregated temperature control load not only reflects the response of the temperature control load to the grid electricity price and the demand-side response signal, but also reflects the flexible adjustment of power demand under the premise of meeting the user comfort and power system stability requirements.

[0076] Step S4: Substitute the response power of the aggregated temperature control load in the time period to be scheduled into the aggregated temperature control load model to update the virtual charge state of the aggregated temperature control load; wherein the aggregated temperature control load model is constructed based on the number of single temperature control loads and the parameters of each virtual battery inside each temperature control load;

[0077] In a preferred embodiment, the aggregate temperature control load model is specifically:

[0078] SOC agg (k+1)=λ agg1 ·SOC agg (k)+P agg (k)+λ agg2 ;

[0079]

[0080]

[0081] Among them, SOC agg (k) represents the virtual state of charge of the aggregated temperature control load at time k, SOC agg (k+1) represents the virtual charge state of the aggregated temperature control load at time k+1, P agg(k) represents the response power of the aggregate temperature control load, λ agg1 The weight coefficient of the virtual state of charge of the aggregated temperature control load at time k, λ agg2 represents the error parameter of the aggregated temperature control load, n represents the number of individual temperature control loads in the aggregated temperature control load, and λ 1i represents the weight coefficient of the virtual state of charge of the ith temperature control load in the aggregated temperature control load, λ 2i represents the weight coefficient of the response power of the i-th temperature control load in the aggregated temperature control load, λ 3i Represents the error parameter of the i-th temperature control load in the aggregated temperature control load.

[0082] For step S4, a large number of individual temperature control loads are considered as a whole to build an aggregate temperature control load model, which means that we no longer focus on each individual temperature control load, but consider them as a collection to better understand and manage the overall power consumption and response characteristics. Before building an aggregate temperature control load model, it is necessary to build a model for a single temperature control load:

[0083] For a single temperature control load, its equivalent thermal parameter model is as follows:

[0084]

[0085] Where C represents the equivalent heat capacity of the temperature control load, R represents the equivalent thermal resistance of the temperature control load, T out Indicates the outdoor temperature, T in Indicates the indoor temperature that changes over time. Q indicates the cooling capacity of the temperature control load. In the cooling scenario, Q is a positive number, and in the heating scenario, Q is a negative number.

[0086] For variable frequency air conditioners, the power and cooling capacity are calculated by the following formula:

[0087] P = a 1 f+b 1 ;

[0088] Q = a 2 f+b 2 ;

[0089] According to the above formula, the temperature control load cooling capacity Q can be expressed as:

[0090]

[0091] Where P represents the rated power of the temperature control load, a 1 、a 2 、b 1 and b 2 Represents different correlation constant coefficients.

[0092] Due to the similarity between temperature control load and traditional battery, a single temperature control load can be encapsulated as a virtual battery. The virtual battery model is as follows:

[0093]

[0094]

[0095] P cd (k)=P(k)-P baseline ;

[0096] Among them, Q baseline represents the baseline cooling capacity, P baseline represents the baseline power, P cd It represents the charge and discharge power of the virtual battery, that is, when there is a control signal, the baseline power and the temperature control load power P cd The difference.

[0097] The state of charge of the virtual battery is similar to the definition of a traditional battery. The state of charge of the virtual battery can be expressed as:

[0098]

[0099] Where soc(k) represents the state of charge of the virtual battery in the kth time period, U(k) represents the capacity of the virtual battery in the kth time period, and U max It represents the maximum value of the virtual battery capacity, that is, the capacity of the virtual battery when the indoor temperature reaches the minimum temperature allowed by the end user, T max and T min They respectively represent the maximum and minimum indoor temperatures allowed by the end user.

[0100] Similar to the update of the state of charge of a traditional load, the update rule of the state of charge of a single virtual battery is:

[0101] soc(k+1)=λ 1 soc(k)+λ 2 P cd (k)+λ 3 ;

[0102]

[0103]

[0104] λ 3 =(1-λ 1 )·soc(0);

[0105] Among them, λ 1 The weight coefficient of the state of charge of a single virtual battery reflects the influence of the battery power at the previous moment on the battery power at the current moment.2 The weight coefficient of the response power of a single virtual battery represents the discharge rate or load condition of the battery at the current moment, λ 3 It represents the error parameter of a single virtual battery, which is a constant term and represents other unknown factors or error terms in the battery power change. When the time interval is constant, λ 1 , 2 and λ 3 Also a constant.

[0106] Since the regulation capability of a single temperature control load is limited, the response time and the adjustment range are constrained by the equipment and user comfort, the present invention aggregates multiple temperature control loads with similar physical properties (such as air conditioners, water heaters, etc.) and dispatches the aggregated temperature control loads in a unified manner, which can reduce unnecessary energy waste, maximize the absorption of renewable energy, and reduce dependence on traditional power sources. The charge state update model of the aggregated temperature control load is shown as follows:

[0107] SOC agg (k+1)=λ agg1 ·SOC agg (k)+P agg (k)+λ agg2 ;

[0108]

[0109]

[0110]

[0111] Among them, SOC agg (k) represents the virtual state of charge of the aggregated temperature control load at time k, SOC agg (k+1) represents the virtual charge state of the aggregated temperature control load at time k+1, P agg (k) represents the response power of the aggregate temperature control load, λ agg1 The weight coefficient of the virtual state of charge of the aggregated temperature control load at time k, λ agg2 represents the error parameter of the aggregated temperature control load, n represents the number of individual temperature control loads in the aggregated temperature control load, and λ 1i represents the weight coefficient of the virtual state of charge of the ith temperature control load in the aggregated temperature control load, λ 2i represents the weight coefficient of the response power of the i-th temperature control load in the aggregated temperature control load, λ 3i represents the error parameter of the ith temperature control load in the aggregated temperature control load, P cd,i (k) represents the response power of the i-th temperature control load in the aggregate temperature control load, and the initial value of the charge state of the aggregate temperature control load is half of the maximum limit.

[0112] Next, the response power P of the aggregated temperature control load in the scheduled period obtained in step S3 is agg (k) Substitute into the aggregate temperature control load model to update the virtual state of charge SOC of the aggregate temperature control load agg (k+1).

[0113] It should be noted that It explains the response power P of the aggregate temperature control load agg (k) and the response power P of a single temperature control load cd (k), that is, the response power of the aggregated temperature control load is limited by the response power of the single temperature control load.

[0114] Step S5: adjusting the power generation on the demand response side of the microgrid according to the virtual state of charge of the aggregated temperature control load.

[0115] In a preferred embodiment, adjusting the power generation on the demand response side of the microgrid according to the virtual state of charge of the aggregated temperature control load includes:

[0116] comparing the virtual state of charge of the aggregated temperature-controlled load with a preset threshold;

[0117] When the virtual state of charge of the aggregated temperature control load does not exceed a first preset threshold, reducing power generation on the demand response side of the microgrid by a first preset proportion;

[0118] When the virtual state of charge of the aggregated temperature control load exceeds the first preset threshold, and the virtual state of charge of the aggregated temperature control load does not exceed the second preset threshold, the power generation on the demand response side of the microgrid is not adjusted;

[0119] When the virtual state of charge of the aggregated temperature-controlled load exceeds a second preset threshold, the power generation on the demand response side of the microgrid is increased by a second preset proportion.

[0120] For step S5, in order to achieve effective management of the aggregated temperature control load, two preset thresholds are set in the microgrid system: a first preset threshold and a second preset threshold, wherein the first preset threshold is less than the second preset threshold. The two thresholds divide the virtual charge state of the aggregated temperature control load into three intervals, each of which corresponds to a different microgrid demand response side power generation adjustment strategy.

[0121] When the virtual state of charge of the aggregated temperature control load does not exceed the first preset threshold, it indicates that the current regulation capability or remaining regulation potential of the aggregated temperature control load is low and may not be able to meet further load regulation requirements. In this case, the microgrid system will reduce the power generation on the microgrid demand response side by the first preset proportion to reduce the power supply pressure of the microgrid, while avoiding excessive calls to the aggregated temperature control load to ensure that it can maintain a basic operating state.

[0122] When the virtual state of charge of the aggregated temperature-controlled load exceeds the first preset threshold and does not exceed the second preset threshold, it indicates that the current regulation capacity or remaining regulation potential of the aggregated temperature-controlled load is moderate, which can meet certain load regulation requirements without over-consuming its regulation potential. Therefore, the microgrid system does not adjust the power generation on the demand response side of the microgrid within this range to maintain the current supply and demand balance.

[0123] When the virtual state of charge of the aggregated temperature control load exceeds the second preset threshold, it indicates that the current regulation capability or remaining regulation potential of the aggregated temperature control load is high and has a larger load regulation space. Therefore, the microgrid system will increase the power generation on the microgrid demand response side by a second preset proportion to make full use of the regulation capability of the aggregated temperature control load, further balance the supply and demand relationship, or meet other possible power needs.

[0124] Through the above scheduling method, the microgrid system can achieve effective management of the aggregated temperature control load, ensuring that it can reasonably participate in the demand response of the microgrid under different virtual charge states, thereby achieving supply and demand balance and stable operation of the microgrid.

[0125] like Figure 3 As shown, based on the above method embodiment, a corresponding device embodiment is provided;

[0126] An embodiment of the present invention provides a microgrid demand response scheduling device based on aggregated temperature control loads, comprising: a prediction data acquisition module, a microgrid demand side response model construction module, a microgrid demand side response model solution module, an aggregated virtual state of charge update module, and a demand response side scheduling module;

[0127] The forecast data acquisition module is used to obtain the rigid load forecast value, photovoltaic output forecast value, wind turbine output forecast value and grid electricity price during the scheduling period;

[0128] The microgrid demand side response model construction module is used to construct the microgrid demand side response model based on the rigid load forecast value, photovoltaic output forecast value, wind turbine output forecast value and grid electricity price in the scheduling period with the goal of minimizing the scheduling cost;

[0129] A microgrid demand side response model solving module is used to solve the microgrid demand side response model and generate the response power of the aggregated temperature control load in the scheduling period when the scheduling cost objective function is minimized;

[0130] An aggregated virtual state of charge update module is used to substitute the response power of the aggregated temperature control load in the scheduling period into the aggregated temperature control load model to update the virtual state of charge of the aggregated temperature control load; wherein the aggregated temperature control load model is constructed based on the number of single temperature control loads and the parameters of each virtual battery inside each temperature control load;

[0131] The demand response side scheduling module is used to adjust the power generation on the demand response side of the microgrid according to the virtual charge state of the aggregated temperature control load.

[0132] In a preferred embodiment, the aggregate temperature control load model is specifically:

[0133] SOC agg (k+1)=λ agg1 ·SOC agg (k)+P agg (k)+λ agg2 ;

[0134]

[0135]

[0136] Among them, SOC agg (k) represents the virtual state of charge of the aggregated temperature control load at time k, SOC agg (k+1) represents the virtual charge state of the aggregated temperature control load at time k+1, P agg (k) represents the response power of the aggregate temperature control load, λ agg1 The weight coefficient of the virtual state of charge of the aggregated temperature control load at time k, λ agg2 represents the error parameter of the aggregated temperature control load, n represents the number of individual temperature control loads in the aggregated temperature control load, and λ 1i represents the weight coefficient of the virtual state of charge of the ith temperature control load in the aggregated temperature control load, λ 2i represents the weight coefficient of the response power of the i-th temperature control load in the aggregated temperature control load, λ 3i Represents the error parameter of the i-th temperature control load in the aggregated temperature control load.

[0137] It can be understood that the above-mentioned device item embodiments correspond to the method item embodiments of the present invention, which can implement the microgrid demand response scheduling method based on aggregated temperature control load provided by any of the above-mentioned method item embodiments of the present invention.

[0138] It should be noted that the device embodiments described above are merely illustrative, and some or all of the modules may be selected according to actual needs to achieve the purpose of the present embodiment. In addition, in the accompanying drawings of the device embodiments provided by the present invention, the connection relationship between the modules indicates that there is a communication connection between them, which may be specifically implemented as one or more communication buses or signal lines. Those of ordinary skill in the art may understand and implement the present invention without creative work.

[0139] Based on the above-mentioned embodiment of the microgrid demand response scheduling method based on aggregated temperature control loads, another embodiment of the present invention provides a terminal device, which includes 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, the microgrid demand response scheduling method based on aggregated temperature control loads according to any embodiment of the present invention is implemented.

[0140] Exemplarily, in this embodiment, the computer program may be divided into one or more modules, which are stored in the memory and executed by the processor to implement the present invention. The one or more module elements may be a series of computer program instruction segments capable of implementing specific functions, which are used to describe the execution process of the computer program in the terminal device.

[0141] The terminal device may be a computing device such as a desktop computer, a notebook, a PDA, a cloud server, etc. The terminal device may include, but is not limited to, a processor and a memory.

[0142] The processor may be a central processing unit (CPU), other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor, etc. The processor is the control center of the terminal device, and uses various interfaces and lines to connect various parts of the entire terminal device.

[0143] Based on the above method embodiment, another embodiment is provided: another embodiment of the present invention provides a computer-readable storage medium, including a stored computer program, wherein when the computer program is running, the device where the computer-readable storage medium is located is controlled to execute the microgrid demand response scheduling method based on aggregated temperature control loads described in any one of the above method embodiments of the present invention.

[0144] Wherein, the module / unit integrated with the microgrid demand response dispatching device / terminal device based on the aggregated temperature control load can be stored in a computer-readable storage medium if it is implemented in the form of a software functional unit and sold or used as an independent product. Based on such an understanding, the present invention implements all or part of the processes in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of the above-mentioned various method embodiments when executed by the processor. Wherein, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form, etc. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, U disk, mobile hard disk, disk, optical disk, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electric carrier signal, telecommunication signal and software distribution medium, etc.

[0145] The above is a preferred embodiment of the present invention. It should be pointed out that a person skilled in the art can make several improvements and modifications without departing from the principle of the present invention. These improvements and modifications are also considered to be within the scope of protection of the present invention.

Claims

1. A microgrid demand response scheduling method based on aggregated temperature control loads, characterized in that: include: Obtain the rigid load forecast value, photovoltaic output forecast value, wind turbine output forecast value and grid electricity price for the period to be dispatched; According to the rigid load forecast value, photovoltaic output forecast value, wind turbine output forecast value and grid electricity price in the time period to be dispatched, a microgrid demand side response model is constructed with the goal of minimizing the dispatching cost; Solve the microgrid demand-side response model to generate the response power of the aggregated temperature control load in the scheduling period when the scheduling cost objective function is minimized; Substituting the response power of the aggregated temperature control load in the time period to be scheduled into the aggregated temperature control load model, and updating the virtual charge state of the aggregated temperature control load; wherein the aggregated temperature control load model is constructed based on the number of single temperature control loads and the parameters of each virtual battery inside each temperature control load; Adjust the power generation on the demand response side of the microgrid according to the virtual state of charge of the aggregated temperature control load.

2. The microgrid demand response scheduling method based on aggregated temperature control load according to claim 1 is characterized in that: The polymerization temperature control load model is specifically: SOCIETY agg (k+1)=λ agg1 ·SOC agg (k)+P agg (k)+λ agg2 ; Among them, SOC agg (k) represents the virtual state of charge of the aggregated temperature control load at time k, SOC agg (k+1) represents the virtual charge state of the aggregated temperature control load at time k+1, P agg (k) represents the response power of the aggregate temperature control load, λ agg1 The weight coefficient of the virtual state of charge of the aggregated temperature control load at time k, λ agg2 represents the error parameter of the aggregated temperature control load, n represents the number of individual temperature control loads in the aggregated temperature control load, and λ 1i represents the weight coefficient of the virtual state of charge of the ith temperature control load in the aggregated temperature control load, λ 2i represents the weight coefficient of the response power of the i-th temperature control load in the aggregated temperature control load, λ 3i Represents the error parameter of the i-th temperature control load in the aggregated temperature control load.

3. The microgrid demand response scheduling method based on aggregated temperature control load according to claim 2 is characterized in that: Obtain the rigid load forecast value, photovoltaic output forecast value, wind turbine output forecast value and grid electricity price for the scheduled period, including: Obtain the rigid load value, photovoltaic output value, wind turbine output value, first historical grid electricity price, meteorological data and periodic demand parameters within the preset historical period at the current moment; The rigid load value, photovoltaic output value, wind turbine output value, the first historical grid electricity price, meteorological data and periodic demand parameters in the preset historical time period at the current moment are input into the trained prediction model, so that the prediction model generates the rigid load prediction value, photovoltaic output prediction value, wind turbine output prediction value and grid electricity price for the scheduling period according to the rigid load value, photovoltaic output value, wind turbine output value, the first historical grid electricity price, meteorological data and periodic demand parameters in the preset historical time period at the current moment.

4. The microgrid demand response scheduling method based on aggregated temperature control load according to claim 3 is characterized in that: The prediction model is determined by: Acquire a number of training data and their corresponding training labels; the training data include: rigid load value, photovoltaic output value, wind turbine output value, second historical grid electricity price, meteorological data and periodic demand parameters within a preset historical period; the training labels include: rigid load value, photovoltaic output value, wind turbine output value and third historical grid electricity price within a preset time after the preset historical period; Each training data and its corresponding training label are input into the prediction model to be trained for iterative training until the loss function converges to obtain a trained prediction model.

5. The microgrid demand response scheduling method based on aggregated temperature control load according to claim 4 is characterized in that: The microgrid demand side response model is specifically: Among them, P load (k) represents the predicted value of rigid load in the kth time period, P PV (k) represents the predicted photovoltaic output value in the kth time period, P WT (k) represents the predicted value of the fan output in the kth time period, P agg (k) represents the response power of the aggregate temperature control load in the kth time period, I price (k) represents the real-time grid electricity price in the kth time period, and T represents the dispatch time.

6. The microgrid demand response scheduling method based on aggregated temperature control load according to claim 5 is characterized in that: According to the virtual state of charge of the aggregated temperature control load, the power generation on the demand response side of the microgrid is adjusted, including: comparing the virtual state of charge of the aggregated temperature-controlled load with a preset threshold; When the virtual state of charge of the aggregated temperature control load does not exceed a first preset threshold, reducing power generation on the demand response side of the microgrid by a first preset proportion; When the virtual state of charge of the aggregated temperature control load exceeds the first preset threshold, and the virtual state of charge of the aggregated temperature control load does not exceed the second preset threshold, the power generation on the demand response side of the microgrid is not adjusted; When the virtual state of charge of the aggregated temperature-controlled load exceeds a second preset threshold, the power generation on the demand response side of the microgrid is increased by a second preset proportion.

7. A microgrid demand response dispatching device based on aggregated temperature control load, characterized in that: include: Prediction data acquisition module, microgrid demand side response model construction module, microgrid demand side response model solution module, aggregated virtual charge state update module, and demand response side scheduling module; The forecast data acquisition module is used to obtain the rigid load forecast value, photovoltaic output forecast value, wind turbine output forecast value and grid electricity price in the scheduling period; The microgrid demand side response model construction module is used to construct a microgrid demand side response model based on the rigid load prediction value, photovoltaic output prediction value, wind turbine output prediction value and grid electricity price in the to-be-scheduled period with the goal of minimizing the scheduling cost; The microgrid demand side response model solving module is used to solve the microgrid demand side response model to generate the response power of the aggregated temperature control load in the scheduling period when the scheduling cost objective function is minimized; The aggregated virtual state of charge update module is used to substitute the response power of the aggregated temperature control load in the to-be-scheduled period into the aggregated temperature control load model to update the virtual state of charge of the aggregated temperature control load; wherein the aggregated temperature control load model is constructed based on the number of single temperature control loads and the parameters of each virtual battery inside each temperature control load; The demand response side scheduling module is used to adjust the power generation on the demand response side of the microgrid according to the virtual charge state of the aggregated temperature control load.

8. The microgrid demand response dispatching device based on aggregated temperature control load according to claim 7 is characterized in that: The polymerization temperature control load model is specifically: SOCIETY agg (k+1)=λ agg1 ·SOC agg (k)+P agg (k)+λ agg2 ; Among them, SOC agg (k) represents the virtual state of charge of the aggregated temperature control load at time k, SOC agg (k+1) represents the virtual charge state of the aggregated temperature control load at time k+1, P agg (k) represents the response power of the aggregate temperature control load, λ agg1 The weight coefficient of the virtual state of charge of the aggregated temperature control load at time k, λ agg2 represents the error parameter of the aggregated temperature control load, n represents the number of individual temperature control loads in the aggregated temperature control load, and λ 1i represents the weight coefficient of the virtual state of charge of the ith temperature control load in the aggregated temperature control load, λ 2i represents the weight coefficient of the response power of the i-th temperature control load in the aggregated temperature control load, λ 3i Represents the error parameter of the i-th temperature control load in the aggregated temperature control load.

9. A terminal device, characterized in that: include: 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, the microgrid demand response scheduling method based on aggregated temperature control loads as described in any one of claims 1 to 6 is implemented.

10. A computer-readable storage medium, characterized in that: include: A stored computer program, wherein when the computer program is running, the device where the computer-readable storage medium is located is controlled to execute the microgrid demand response scheduling method based on aggregated temperature control loads as described in any one of claims 1-6.

Images