Automatic dispatching method and system for smart power grid

Abstract

The invention discloses an automatic scheduling method and system for a smart power grid, relates to the technical field of power transmission and distribution, and solves the technical problems that the accuracy of prediction data is affected, prediction models are repeatedly deployed at different levels and the development cost is increased due to the fact that data of all levels are independently analyzed in most power grid automatic scheduling schemes. Constructing a wind-light-storage collaborative layer, a thermoelectric coupling management layer and a regional power grid dispatching layer to carry out joint optimization dispatching on the power grid; the edge nodes are directly deployed in a thermal power plant or a heat supply center, time delay of data uploading to the cloud is avoided, and thermoelectric load fluctuation can be quickly responded. Dynamic coordination is carried out on the nodes of the wind-light-storage coordination layer and the thermoelectric coupling management layer through the nodes of the wind-light-storage coordination layer and the thermoelectric coupling management layer according to the prediction data and in combination with the coordination strategies corresponding to the nodes; and predicting optimal thermoelectric unit output data and wind and light output data of a next period through rolling optimization by taking a preset time period as a period through a regional power grid dispatching layer.

Description

Technical Field

[0001] The present invention belongs to the field of power transmission and distribution, and specifically relates to an intelligent power grid automatic dispatching method and system. Background Art

[0002] Modern power grids have evolved from a single power source structure to a "wind-solar-storage-heat-hydrogen" multi-energy coupling system. The intermittency and volatility of wind and solar power fundamentally conflict with the requirements of the safe and stable operation of the power grid. Traditional dispatching systems cannot respond in real time to sudden changes in wind and solar power output, resulting in a high rate of wind and solar curtailment. There is a need for an intelligent power grid automatic dispatching solution. The power grid dispatching automation system is an intelligent management system based on computer technology and communication technology, aiming to achieve the efficient operation and safe and stable operation of the power system. The system improves the operation efficiency and reliability of the power grid by real-time monitoring, controlling, and managing all aspects of the power system.

[0003] Most power grid automatic dispatching solutions only separately analyze the data at each level between power plants based on the detection data of thermal power plants and wind-solar power plants, which affects the accuracy of the prediction data. Repeatedly deploying prediction models at different levels increases the development cost. Summary of the Invention

[0004] The present invention aims to solve at least one of the technical problems existing in the prior art; for this purpose, the present invention proposes an intelligent power grid automatic dispatching method and system, which are used to solve the technical problems that most power grid automatic dispatching solutions separately analyze the data at each level, affecting the accuracy of the prediction data, and repeatedly deploying prediction models at different levels, increasing the development cost.

[0005] To solve the above problems, the first aspect of the present invention provides an intelligent power grid automatic dispatching method, including the following steps: Construct a wind-solar-storage collaborative layer, a thermal-electricity coupling management layer, and a regional power grid dispatching layer to jointly optimize the dispatching of the power grid; Set up edge management nodes in the thermal-electricity coupling management layer. Based on the output and heating status of thermal power units and the current reference value of the thermal-electricity ratio at the edge management nodes, construct a thermal-electricity dynamic regulation model, analyze the optimal output data of thermal power units in real time, and set the collaborative strategy of the thermal-electricity coupling management layer to the wind-solar-storage collaborative layer; Periodically upload the thermal-electricity ratio adjustment range of thermal power units and the output data of thermal power units to the regional power grid dispatching layer; Set up edge management nodes in the wind-solar-storage collaborative layer. Based on the wind-solar output and power supply status at the edge management nodes, construct a wind-solar-storage joint optimization model, set constraint conditions, analyze the optimal wind-solar output data, and set the collaborative strategy of the wind-solar-storage collaborative layer to the thermal-electricity coupling management layer; Periodically upload the wind-solar output data and the state of charge (SOC) of energy storage to the regional power grid dispatching layer; Establish a regional power grid dispatching layer in the cloud. Based on the data uploaded by the wind-solar-storage coordination layer and the thermoelectric coupling management layer, construct a joint optimization model to predict the optimal thermal power generation unit output data and wind-solar output data of the wind-solar-storage coordination layer and the thermoelectric coupling management layer nodes in the next cycle, and send the results to the corresponding nodes.

[0006] Optionally, in an example of the above aspect, at the edge management node, based on the thermal power generation unit output and the heating status, and based on the current thermoelectric ratio reference value, construct a thermoelectric dynamic regulation model to perform real-time thermoelectric regulation on the thermoelectric coupling management layer devices, including the following steps: Based on the thermal power generation unit output and the heating status, and based on the current thermoelectric ratio reference value, construct a thermoelectric dynamic regulation model by constructing a dynamic thermal balance optimization charge-discharge equation set and constraint conditions; The dynamic thermal balance optimization charge-discharge equation set includes: a thermoelectric conversion equation, a phase change heat storage equation, a coupling relationship equation, and a thermoelectric ratio dynamic regulation equation; The constraint conditions include: setting constraint conditions according to the temperature range, power limit, and energy storage capacity; Solve the dynamic thermal balance optimization charge-discharge equation set through the particle swarm optimization algorithm to obtain the optimal solutions of the thermoelectric ratio of the motor unit and the output of the thermal power generation unit.

[0007] Optionally, in an example of the above aspect, constructing a dynamic thermal balance optimization charge-discharge equation set and constraint conditions includes:

[0008] Among them, Qth is thermal energy, ηth is the thermoelectric conversion efficiency, Pelec is the input electric energy, Rth and Cth are the thermal resistance and heat capacity respectively, Qpcm is the thermoelectric material energy storage, Tpcm is the thermal energy consumed by the thermoelectric material, Tin is the input thermal energy of the thermoelectric material, Tout is the output thermal energy of the thermoelectric material, α and β are the charge-discharge rate coefficients, m is the mass of the thermoelectric material, and c is the specific heat capacity of the thermoelectric material.

[0009] Optionally, in an example of the above aspect, the cooperation strategy of the thermoelectric coupling management layer to the wind-solar-storage coordination layer includes: Periodically analyze the optimal solutions of the thermoelectric ratio of the thermal power generation unit and the output of the thermal power generation unit of the node. According to the degree of deviation of the thermoelectric ratio of the thermal power generation unit of the node from the optimal solution of the thermoelectric ratio of the motor unit, and the degree of deviation of the output of the thermal power generation unit of the node from the optimal solution of the output of the thermal power generation unit, analyze the output redundancy degree of the corresponding thermoelectric coupling management layer node; Screen the wind-solar-storage coordination layer nodes with a distance less than the threshold, obtain the wind-solar output data of the screened nodes, analyze whether the wind-solar output data reaches the predicted optimal wind-solar output data of the corresponding nodes, and mark the nodes that do not reach as priority supplementary nodes; When the redundancy degree of the node output in the thermoelectric coupling management layer is greater than the threshold, power is transmitted to the power grid in the direction of the node with priority supplement annotation.

[0010] Optionally, in an example of the above aspect, the edge management node constructs a combined optimization model of wind-solar-storage according to the wind-solar output and the power supply status, sets constraint conditions, and analyzes the optimal wind-solar output data, including the following steps: Taking the minimization of the power deviation between the wind-solar output and the load and the minimization of the deviation between the energy storage SOC and the target value as the principle, through the wind-solar output and the power supply status, by constructing an objective function and constraint conditions, a combined optimization model of wind-solar-storage is constructed; The constraint conditions include: energy storage charge and discharge power limit, uncontrollable constraint of wind-solar output, power balance of wind-solar-storage system and dynamic constraint of energy storage SOC; By using the particle swarm optimization algorithm, the dynamic objective function is solved to obtain the optimal solution of the wind-solar output data.

[0011] Optionally, in an example of the above aspect, by constructing an objective function and constraint conditions, a combined optimization model of wind-solar-storage is constructed, including: Set the detection interval, and divide the detection time interval into T time periods, and construct the objective function:

[0012] Wherein, Pwind(i)+Psolar(i) is the average value of the wind-solar output power in the i-th time period, Pload(i) is the average value of the wind-solar system load power in the i-th time period, SOC(i) is the energy storage SOC in the i-th time period, SOCtarget(i) is the target energy storage SOC in the i-th time period, and a1 and a2 are the weights of the power deviation between the wind-solar output and the load and the deviation between the energy storage SOC and the target value respectively; Optionally, in an example of the above aspect, the cooperation strategy between the wind-solar-storage coordination layer and the thermoelectric coupling management layer includes: obtaining the wind-solar output data and the optimal solution data of the wind-solar output data of the nodes in the wind-solar-storage coordination layer in real time; Screen the nodes in the thermoelectric coupling management layer with a distance less than the threshold, obtain the output data of the thermal power units of the selected nodes, analyze the degree of deviation of the output data of the thermal power units from the predicted optimal output data of the corresponding nodes, and label the nodes with a deviation degree greater than the threshold; if the real-time monitored wind-solar output data exceeds the optimal solution of the wind-solar output data, send a "request for increasing the thermoelectric ratio" to the labeled nodes in the thermoelectric coupling management layer, and consume the excess power through thermoelectric equipment, otherwise, do not send a request. Use electric boilers and heat pumps to consume the excess power.

[0013] Optionally, in an example of the above aspect, a regional power grid dispatching layer is established in the cloud. According to the data uploaded by the wind-solar-storage coordination layer and the thermoelectric coupling management layer, a joint optimization model is constructed to predict the optimal thermal power unit output data and wind-solar output data of the wind-solar-storage coordination layer and the thermoelectric coupling management layer nodes in the next cycle, including the following steps: Obtain the historical data of the thermoelectric ratio adjustment range, thermal power unit output data, wind-solar output data, and energy storage SOC status of each node periodically uploaded by the wind-solar-storage coordination layer and the thermoelectric coupling management layer, as well as the optimal solution data calculated by the corresponding node through the thermoelectric dynamic adjustment model or the wind-solar-storage joint optimization model; Mark the historical data with a cycle, and add the optimal solution data of the next cycle as a label to the historical data of the thermoelectric ratio adjustment range, thermal power unit output data, wind-solar output data, and energy storage SOC status of the node thermal power unit; Train the LSTM model with the historical data after adding the label as the joint optimization model; Predict the optimal thermal power unit output data and wind-solar output data of the wind-solar-storage coordination layer and the thermoelectric coupling management layer nodes in the next cycle through the trained model.

[0014] According to another aspect of the present disclosure, an intelligent power grid automatic dispatching system is provided. This system realizes the intelligent power grid automatic dispatching by adopting an intelligent power grid automatic dispatching method as described above.

[0015] Compared with the prior art, the beneficial effects of the present invention are: The edge nodes of the present invention are directly deployed in the thermal power plant or the heating center, avoiding the time delay of uploading data to the cloud and enabling rapid response to the fluctuations of thermoelectric loads.

[0016] The present invention dynamically coordinates the wind-solar-storage coordination layer and the thermoelectric coupling management layer nodes through the wind-solar-storage coordination layer and the thermoelectric coupling management layer nodes according to the prediction data and in combination with the corresponding coordination strategies of the nodes.

[0017] The present invention predicts the optimal thermal power unit output data and wind-solar output data of the next cycle through the regional power grid dispatching layer with a preset time period as a cycle for rolling optimization. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0019] Figure 1Schematic diagram of the method flow of the present invention; Figure 2 Schematic diagram of the architecture of the intelligent power grid automatic dispatching system of the present invention; Figure 3 Schematic diagram of the method flow for constructing the thermoelectric dynamic regulation model of the present invention. Specific implementation manners

[0020] Next, the technical solutions of the present invention will be clearly and completely described in conjunction with the embodiments. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0021] Please refer to Figure 1-Figure 3 , an embodiment of the first aspect of the present invention provides an intelligent power grid automatic dispatching method, including the following steps: Construct a coordinated layer of wind power, photovoltaics and energy storage, a thermoelectric coupling management layer and a regional power grid dispatching layer to perform joint optimal dispatching on the power grid; Set edge management nodes in the thermoelectric coupling management layer. At the edge management nodes, based on the current thermoelectric ratio reference value through the output and heating status of the thermal power units, construct a thermoelectric dynamic regulation model, analyze the optimal thermal power unit output data in real time, and set the coordination strategy of the thermoelectric coupling management layer to the wind power, photovoltaics and energy storage coordinated layer; Periodically upload the thermoelectric ratio adjustment range and thermal power unit output data of the thermal power units to the regional power grid dispatching layer; Set edge management nodes in the wind power, photovoltaics and energy storage coordinated layer. At the edge management nodes, construct a joint optimization model of wind power, photovoltaics and energy storage according to the wind and photovoltaic power output and power supply status, set constraint conditions, analyze the optimal wind and photovoltaic power output data, and set the coordination strategy of the wind power, photovoltaics and energy storage coordinated layer to the thermoelectric coupling management layer; Periodically upload the wind and photovoltaic power output data and the energy storage SOC status to the regional power grid dispatching layer; Establish a regional power grid dispatching layer in the cloud. According to the data uploaded by the wind power, photovoltaics and energy storage coordinated layer and the thermoelectric coupling management layer, construct a joint optimization model, predict the optimal thermal power unit output data and wind and photovoltaic power output data of the nodes in the wind power, photovoltaics and energy storage coordinated layer and the thermoelectric coupling management layer in the next cycle, and send the results to the corresponding nodes.

[0022] Specifically, in this embodiment, a coordinated layer of wind power, photovoltaics and energy storage, a thermoelectric coupling management layer and a regional power grid dispatching layer are constructed; Set edge management nodes in the thermoelectric coupling management layer. At the edge management nodes, based on the current thermoelectric ratio reference value through the output and heating status of the thermal power units, construct a thermoelectric dynamic regulation model, analyze the optimal thermal power unit output data in real time, and set the coordination strategy of the thermoelectric coupling management layer to the wind power, photovoltaics and energy storage coordinated layer; Based on the real-time output and heating status of thermal power units (such as the temperature and pressure of the heating pipe network), the edge node dynamically adjusts the power distribution between power generation and heating of thermal power units in combination with the current reference value of the thermoelectric ratio. For example, during the peak heating period in winter, the heating demand is prioritized, and more power generation capacity is released in summer.

[0023] The edge node is directly deployed in the thermal power plant or heating center, avoiding the time delay of uploading data to the cloud, and can quickly respond to the fluctuations of thermoelectric loads, such as the sudden drop in heating demand caused by the sudden shutdown of industrial users.

[0024] The nodes of the wind-solar-storage coordination layer and the thermoelectric coupling management layer dynamically coordinate the nodes of the wind-solar-storage coordination layer and the thermoelectric coupling management layer according to the prediction data and in combination with the corresponding coordination strategies of the nodes.

[0025] A regional power grid dispatching layer is established in the cloud. According to the data uploaded by the wind-solar-storage coordination layer and the thermoelectric coupling management layer, a joint optimization model is constructed to predict the optimal thermal power unit output data and wind-solar output data of the nodes of the wind-solar-storage coordination layer and the thermoelectric coupling management layer in the next cycle, and the results are sent to the corresponding nodes.

[0026] The cloud dispatching layer uses deep learning models such as LSTM and Transformer, combined with historical output data, historical optimal solution data, and equipment status, to predict the wind-solar output curve.

[0027] The regional power grid dispatching layer established in the cloud performs rolling optimization in a preset time period to predict the optimal thermal power unit output data and wind-solar output data in the next cycle; the nodes of the wind-solar-storage coordination layer and the thermoelectric coupling management layer dynamically coordinate the nodes of the wind-solar-storage coordination layer and the thermoelectric coupling management layer according to the prediction data and in combination with the corresponding coordination strategies of the nodes.

[0028] In one embodiment of the present invention, in the edge management node, based on the output and heating status of the thermal power unit and the current reference value of the thermoelectric ratio, a thermoelectric dynamic regulation model is constructed to perform thermoelectric regulation on the equipment of the thermoelectric coupling management layer in real time, including the following steps: Based on the output and heating status of the thermal power unit and the current reference value of the thermoelectric ratio, a thermoelectric dynamic regulation model is constructed by constructing a dynamic heat balance optimization charging and discharging equation set and constraint conditions. The dynamic heat balance optimization charging and discharging equation set includes: a thermoelectric conversion equation, a phase change heat storage equation, a coupling relationship equation, and a thermoelectric ratio dynamic regulation equation. The constraint conditions include: setting constraint conditions according to the temperature range, power limit, and energy storage capacity. By using the particle swarm optimization algorithm, the dynamic heat balance optimization charging and discharging equation set is solved to obtain the optimal solutions of the thermoelectric ratio of the motor unit and the output of the thermal power unit.

[0029] In one embodiment of the present invention, a dynamic thermal balance optimization charging and discharging equation set and constraint conditions are constructed, including:

[0030] Among them, Qth is thermal energy, ηth is the thermoelectric conversion efficiency, Pelec is the input electric energy, Rth and Cth are the thermal resistance and heat capacity respectively, Qpcm is the energy storage of the thermoelectric material, Tpcm is the thermal energy consumed by the thermoelectric material, Tin is the thermal energy input to the thermoelectric material, Tout is the thermal energy output from the thermoelectric material, α and β are the charging and discharging rate coefficients, m is the mass of the thermoelectric material, and c is the specific heat capacity of the thermoelectric material; Constraint conditions are set, including: Temperature range: Tpcm,min ≤ Tpcm ≤ Tpcm,max; to avoid thermal decomposition or phase change failure.

[0031] Power limit: 0 ≤ Pelec ≤ Prated, where Prated is the rated power of the device; the thermoelectric conversion power Pelec is constrained by the rated power Prated of the device; Energy storage capacity: the energy storage of the phase change material Qpcm is less than or equal to its maximum capacity threshold Qpcm,max.

[0032] In one embodiment of the present invention, the cooperation strategy of the thermoelectric coupling management layer with the wind-solar-storage cooperation layer includes: Periodically analyze the thermoelectric ratio of the thermal power unit and the optimal solution of the output of the thermal power unit at the node. According to the degree of deviation of the thermoelectric ratio of the thermal power unit at the node from the optimal solution of the thermoelectric ratio of the thermal power unit, and the degree of deviation of the output of the thermal power unit at the node from the optimal solution of the output of the thermal power unit, analyze the redundancy degree of the output of the corresponding thermoelectric coupling management layer node; Redundancy degree of the output of the thermoelectric coupling management layer node = w1 (thermoelectric ratio of the thermal power unit at the node - optimal solution of the thermoelectric ratio of the thermal power unit) / optimal solution of the thermoelectric ratio of the thermal power unit + w2 (output of the thermal power unit at the node - optimal solution of the output of the thermal power unit) / optimal solution of the output of the thermal power unit; Screen the wind-solar-storage cooperation layer nodes with a distance less than the threshold, obtain the wind-solar output data of the screened nodes, analyze whether the wind-solar output data reaches the predicted optimal wind-solar output data of the corresponding node, and mark the nodes that do not reach as priority supplement nodes; If the redundancy degree of the output of the node in the thermoelectric coupling management layer is greater than the threshold, power is transmitted to the power grid in the direction of the marked priority supplement nodes.

[0033] In this embodiment, the redundancy degree threshold of the output of the thermoelectric coupling management layer node is set to 0.5, and w1 and w2 are the corresponding weights, set to 0.2 and 0.8 respectively, to achieve that when the wind-solar output is excessive, the electric boiler / heat pump is preferentially started to absorb power; when the wind-solar output is insufficient, more power is released to the power grid.

[0034] In one embodiment of the present invention, the edge management node constructs a combined optimization model of wind-solar energy storage according to the wind-solar power output and power supply status, sets constraint conditions, and analyzes the optimal wind-solar power output data, including the following steps: Taking the minimization of the power deviation between the wind-solar power output and the load and the minimization of the deviation between the energy storage SOC and the target value as the principles, through the wind-solar power output and power supply status, by constructing an objective function and constraint conditions, a combined optimization model of wind-solar energy storage is constructed; The constraint conditions include: energy storage charge and discharge power limits, uncontrollable constraints of wind-solar power output, power balance of the wind-solar energy storage system, and dynamic constraints of energy storage SOC; By using the particle swarm optimization algorithm, the dynamic objective function is solved to obtain the optimal solution of the wind-solar power output data.

[0035] In one embodiment of the present invention, by constructing an objective function and constraint conditions, a combined optimization model of wind-solar energy storage is constructed, including: Set the detection time interval, divide the detection time interval into T time periods, and construct the objective function:

[0036] Wherein, Pwind(i)+Psolar(i) is the average value of the wind-solar power output in the i-th time period, Pload(i) is the average value of the wind-solar system load power in the i-th time period, SOC(i) is the energy storage SOC in the i-th time period, SOCtarget(i) is the target energy storage SOC in the i-th time period, and a1 and a2 are the weights of the power deviation between the wind-solar power output and the load and the deviation between the energy storage SOC and the target value respectively; The first item: Minimize the power deviation between the wind-solar power output and the load (smooth fluctuations).

[0037] The second item: Minimize the deviation between the energy storage SOC and the target value (avoid overcharging and over-discharging).

[0038] The constraint conditions are: Energy storage charge and discharge power limits: Pchargemin≤Pcharge(i)≤Pchargemax, Pdischargemin≤Pdischarge(i)≤Pdischargemax, where Pchargemin and Pchargemax are the minimum and maximum charging powers, Pdischargemin and Pdischargemax are the minimum and maximum discharging powers, and Pcharge(i) and Pdischarge(i) are the average values of the charging and discharging powers in the i-th time period respectively; Uncontrollable constraints on wind and solar power output: Pwindmin ≤ Pwind(i) ≤ Pwindmax, Psolarmin ≤ Psolar(i) ≤ Psolarmax, where Pwindmin and Pwindmax are the minimum and maximum wind power generation respectively, and Psolarmin and Psolarmax are the minimum and maximum solar power generation respectively; Power balance of wind-solar-storage system: Pload(i) = Pwind(i) + Psolar(i) + Pstorage(i) + Pgrid(i), where Pload(i) is the load power in the i-th time period, Pstorage(i) is the storage power in the i-th time period, and Pgrid(i) is the grid power in the i-th time period; Dynamic constraints on energy storage SOC: SOC(i + 1) = SOC(i) + (ηcharge * Pcharge(i) * Δt) / Estorage - (Pdischarge(i) * Δt) / (ηdischarge * Estorage), where ηcharge and ηdischarge are the charging and discharging efficiencies respectively, Estorage is the stored electricity, and Δt is the time interval between the midpoints of different time periods.

[0039] In one embodiment of the present invention, the cooperation strategy between the wind-solar-storage cooperation layer and the thermoelectric coupling management layer includes: Obtain the wind and solar power output data and the optimal solution data of the wind and solar power output data of the nodes in the wind-solar-storage cooperation layer in real time; Screen the nodes in the thermoelectric coupling management layer with a distance less than the threshold, obtain the output data of the thermal power units of the screened nodes, analyze the degree to which the output data of the thermal power units deviates from the predicted optimal output data of the thermal power units of the corresponding nodes, and label the nodes with a deviation degree greater than the threshold; Degree of deviation of the output data of the thermal power unit from the predicted optimal output data of the thermal power unit of the corresponding node = (Actual output of the thermal power unit of the node - Predicted optimal output of the thermal power unit) / Predicted optimal output of the thermal power unit; Sort the calculation results from high to low, screen the top 10% of the nodes for labeling, and set the threshold to the minimum deviation degree of the top 10% of the nodes; If the real-time monitored wind and solar power output data exceeds the optimal solution of the wind and solar power output data, send a "request for increasing the thermoelectric ratio" to the labeled nodes in the thermoelectric coupling management layer to consume the excess power through thermoelectric equipment, otherwise, do not send the request. Use electric boilers and heat pumps to consume the excess power.

[0040] In one embodiment of the present invention, a regional power grid dispatching layer is established in the cloud. According to the data uploaded by the wind-solar-storage coordination layer and the thermoelectric coupling management layer, a joint optimization model is constructed to predict the optimal thermal power generation unit output data and wind-solar output data of the nodes in the wind-solar-storage coordination layer and the thermoelectric coupling management layer in the next cycle, including the following steps: Obtain the historical data of the thermoelectric ratio adjustment range, thermal power generation unit output data, wind-solar output data, and energy storage SOC status of each node periodically uploaded by the wind-solar-storage coordination layer and the thermoelectric coupling management layer, as well as the optimal solution data calculated by the corresponding node through the thermoelectric dynamic adjustment model or the wind-solar-storage joint optimization model; Mark the historical data with a cycle, and add the optimal solution data of the next cycle as a label to the historical data of the thermoelectric ratio adjustment range, thermal power generation unit output data, wind-solar output data, and energy storage SOC status of the node thermal power generation unit; Train the LSTM model with the historical data after adding the label as the joint optimization model; Predict the optimal thermal power generation unit output data and wind-solar output data of the nodes in the wind-solar-storage coordination layer and the thermoelectric coupling management layer in the next cycle through the trained model.

[0041] In another embodiment of the present invention, an intelligent power grid automatic dispatching system is provided, which is characterized in that the system realizes the intelligent power grid automatic dispatching by using an intelligent power grid automatic dispatching method as described above, including: a wind-solar-storage coordination layer, a thermoelectric coupling management layer, and a regional power grid dispatching layer; Thermoelectric coupling management layer: Set an edge management node in the thermoelectric coupling management layer. Based on the current thermoelectric ratio reference value through the thermal power generation unit output and heating status at the edge management node, construct a thermoelectric dynamic adjustment model, analyze the optimal thermal power generation unit output data in real time, and set the coordination strategy of the thermoelectric coupling management layer to the wind-solar-storage coordination layer; Periodically upload the thermoelectric ratio adjustment range of the thermal power generation unit and the available capacity of the electrothermal conversion equipment to the regional power grid dispatching layer; Wind-solar-storage coordination layer: Set an edge management node in the wind-solar-storage coordination layer. According to the wind-solar output and power supply status at the edge management node, construct a wind-solar-storage joint optimization model, set constraint conditions, analyze the optimal wind-solar output data, and set the coordination strategy of the wind-solar-storage coordination layer to the thermoelectric coupling management layer; Periodically upload the wind-solar output prediction data and the energy storage SOC status to the regional power grid dispatching layer; Power grid dispatching layer: Establish a regional power grid dispatching layer in the cloud. According to the data uploaded by the wind-solar-storage coordination layer and the thermoelectric coupling management layer, construct a joint optimization model, predict the optimal thermal power generation unit output data and wind-solar output data of the nodes in the wind-solar-storage coordination layer and the thermoelectric coupling management layer in the next cycle, and send the results to the corresponding nodes.

[0042] The above embodiments are only used to illustrate the technical method of the present invention and not to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that the technical method of the present invention can be modified or equivalently replaced without departing from the spirit and scope of the technical method of the present invention.

Claims

1. An intelligent power grid automatic dispatching method, characterized in that, Including the following steps: Construct a joint optimal dispatching for the power grid by building a wind-solar-storage collaborative layer, a thermoelectric coupling management layer, and a regional power grid dispatching layer; Set up edge management nodes in the thermoelectric coupling management layer. Based on the current thermoelectric ratio reference value and the heat output and heating status of the thermal power units at the edge management nodes, construct a thermoelectric dynamic regulation model, analyze the optimal thermal power unit output data in real time, and set the collaborative strategy from the thermoelectric coupling management layer to the wind-solar-storage collaborative layer; Periodically upload the thermoelectric ratio adjustment range and the thermal power unit output data of the thermal power units to the regional power grid dispatching layer; Set up edge management nodes in the wind-solar-storage collaborative layer. Based on the wind-solar output and power supply status at the edge management nodes, construct a wind-solar-storage joint optimization model, set constraint conditions, analyze the optimal wind-solar output data, and set the collaborative strategy from the wind-solar-storage collaborative layer to the thermoelectric coupling management layer; Periodically upload the wind-solar output data and the energy storage SOC status to the regional power grid dispatching layer; Establish a regional power grid dispatching layer in the cloud. Based on the data uploaded by the wind-solar-storage collaborative layer and the thermoelectric coupling management layer, construct a joint optimization model, predict the optimal thermal power unit output data and wind-solar output data of the wind-solar-storage collaborative layer and the thermoelectric coupling management layer nodes in the next cycle, and send the results to the corresponding nodes.

2. The intelligent power grid automatic scheduling method according to claim 1, characterized in that Based on the heat output and heating status of the thermal power units at the edge management nodes and the current thermoelectric ratio reference value, construct a thermoelectric dynamic regulation model at the edge management nodes to perform real-time thermoelectric regulation on the equipment in the thermoelectric coupling management layer, including the following steps: Based on the heat output and heating status of the thermal power units and the current thermoelectric ratio reference value, construct a thermoelectric dynamic regulation model by building a dynamic heat balance optimization charge-discharge equation set and constraint conditions; The dynamic heat balance optimization charge-discharge equation set includes: a thermoelectric conversion equation, a phase change heat storage equation, a coupling relationship equation, and a thermoelectric ratio dynamic regulation equation; The constraint conditions include: setting constraint conditions according to the temperature range, power limit, and energy storage capacity; Solve the dynamic heat balance optimization charge-discharge equation set through the particle swarm optimization algorithm to obtain the optimal solutions of the thermoelectric ratio of the motor units and the heat output of the thermal power units.

3. An intelligent power grid automatic dispatching method according to claim 2, characterized in that, Construct a dynamic heat balance optimization charge-discharge equation set and constraint conditions, including: Where, Qth is the thermal energy, ηth is the thermoelectric conversion efficiency, Pelec is the input electric energy, Rth and Cth are the thermal resistance and heat capacity respectively, Qpcm is the thermoelectric material energy storage, Tpcm is the thermal energy consumed by the thermoelectric material, Tin is the thermal energy input to the thermoelectric material, Tout is the thermal energy output from the thermoelectric material, α and β are the charge-discharge rate coefficients, m is the mass of the thermoelectric material, and c is the specific heat capacity of the thermoelectric material; Set constraint conditions, including: Temperature range: Tpcm,min ≤ Tpcm ≤ Tpcm,max; Power limit: 0 ≤ Pelec ≤ Prated, where Prated is the rated power of the equipment; Energy storage capacity: The phase change material energy storage Qpcm is less than or equal to its maximum capacity threshold Qpcm,max.

4. An intelligent power grid automatic dispatching method according to claim 1, characterized in that, The collaborative strategy from the thermoelectric coupling management layer to the wind-solar-storage collaborative layer includes: Periodically analyze the optimal solutions of the thermoelectric ratio of thermal power units at the analysis node and the output of thermal power units. According to the degree of deviation of the thermoelectric ratio of thermal power units at the node from the optimal solution of the thermoelectric ratio of the thermal power unit, and the degree of deviation of the output of thermal power units at the node from the optimal solution of the output of the thermal power unit, analyze the output redundancy degree of the corresponding thermoelectric coupling management layer node; Screen the wind-solar-storage collaborative layer nodes with a distance less than the threshold, obtain the wind-solar output data of the selected nodes, analyze whether the wind-solar output data reaches the predicted optimal wind-solar output data of the corresponding nodes, and mark the nodes that do not reach as priority replenishment nodes; When the output redundancy degree of the nodes in the thermoelectric coupling management layer is greater than the threshold, conduct power transmission to the power grid in the direction of the marked priority replenishment nodes.

5. An intelligent power grid automatic dispatching method according to claim 1, characterized in that, At the edge management node, construct a wind-solar-storage joint optimization model based on the wind-solar output and power supply status, set constraint conditions, and analyze the optimal wind-solar output data, including the following steps: Taking the minimization of the power deviation between the wind-solar output and the load and the minimization of the deviation between the energy storage SOC and the target value as the principles, construct a wind-solar-storage joint optimization model through the wind-solar output and power supply status, by constructing an objective function and constraint conditions; The constraint conditions include: energy storage charge and discharge power limits, uncontrollable constraints of wind-solar output, power balance of the wind-solar-storage system, and dynamic constraints of energy storage SOC; Solve the dynamic objective function through the particle swarm optimization algorithm to obtain the optimal solution of the wind-solar output data.

6. The intelligent power grid automatic dispatching method according to claim 5, characterized in that Construct a wind-solar-storage joint optimization model by constructing an objective function and constraint conditions, including: Set the detection time interval and divide the detection time interval into T time periods, and construct the objective function: Among them, Pwind(i)+Psolar(i) is the average value of the wind-solar output power in the i-th time period, Pload(i) is the average value of the wind-solar system load power in the i-th time period, SOC(i) is the energy storage SOC in the i-th time period, SOCtarget(i) is the target energy storage SOC in the i-th time period, and a1 and a2 are the weights of the power deviation between the wind-solar output and the load and the deviation between the energy storage SOC and the target value respectively; The constraint conditions are: Energy storage charge and discharge power limits: Pchargemin≤Pcharge(i)≤Pchargemax, Pdischargemin≤Pdischarge(i)≤Pdischargemax, where Pchargemin and Pchargemax are the minimum and maximum charging powers, Pdischargemin and Pdischargemax are the minimum and maximum discharge powers, and Pcharge(i) and Pdischarge(i) are the average values of the charging and discharging powers in the i-th time period respectively; Uncontrollable constraints of wind-solar output: Pwindmin≤Pwind(i)≤Pwindmax, Psolarmin≤Psolar(i)≤Psolarmax, where Pwindmin and Pwindmax are the minimum and maximum wind power generation respectively, and Psolarmin and ≤Psolarmax are the minimum and maximum solar power generation respectively; Power balance of the wind-solar-storage system: Pload(i) = Pwind(i) + Psolar(i) + Pstorage(i) + Pgrid(i), where Pload(i) is the load power in the i-th time period, Pstorage(i) is the storage power in the i-th time period, and Pgrid(i) is the grid power in the i-th time period; Dynamic constraint of energy storage SOC: SOC(i + 1) = SOC(i) + (ηcharge * Pcharge(i) * Δt) / Estorage - (Pdischarge(i) * Δt) / (ηdischarge * Estorage), where ηcharge and ηdischarge are the charging and discharging efficiencies respectively, Estorage is the stored electricity, and Δt is the time interval between the midpoints of different time periods.

7. An intelligent power grid automatic dispatching method according to claim 1, characterized in that, The cooperation strategy between the wind-solar-storage cooperation layer and the thermoelectric coupling management layer includes: Obtain the wind-solar output data and the optimal solution data of the wind-solar output data of the nodes in the wind-solar-storage cooperation layer in real time; Screen the nodes in the thermoelectric coupling management layer with a distance less than the threshold, obtain the output data of the thermal power units of the screened nodes, analyze the degree to which the output data of the thermal power units deviates from the predicted optimal output data of the thermal power units of the corresponding nodes, and mark the nodes with a deviation degree greater than the threshold; If the real-time monitored wind-solar output data exceeds the optimal solution of the wind-solar output data, send a "request for increasing the thermoelectric ratio" to the marked nodes in the thermoelectric coupling management layer, and consume the excess power through thermoelectric equipment; otherwise, do not send a request.

8. An intelligent power grid automatic dispatching method according to claim 1, characterized in that Establish a regional grid scheduling layer in the cloud. According to the data uploaded by the wind-solar-storage cooperation layer and the thermoelectric coupling management layer, construct a joint optimization model to predict the optimal output data of the thermal power units and the wind-solar output data of the nodes in the wind-solar-storage cooperation layer and the thermoelectric coupling management layer in the next cycle, including the following steps: Obtain the historical data of the thermoelectric ratio adjustment range, the output data of the thermal power units, the wind-solar output data, and the energy storage SOC status of each node periodically uploaded by the wind-solar-storage cooperation layer and the thermoelectric coupling management layer, as well as the optimal solution data calculated by the corresponding nodes through the thermoelectric dynamic adjustment model or the wind-solar-storage joint optimization model; Mark the historical data with a cycle, and add the optimal solution data of the next cycle as a label to the historical data of the thermoelectric ratio adjustment range, the output data of the thermal power units, the wind-solar output data, and the energy storage SOC status of the nodes; Train the LSTM model with the historical data after adding the label as the joint optimization model; Predict the optimal output data of the thermal power units and the wind-solar output data of the nodes in the wind-solar-storage cooperation layer and the thermoelectric coupling management layer in the next cycle through the trained model.

9. An intelligent power grid automatic dispatching system, characterized in that This system realizes the automatic scheduling of the smart grid by using an automatic scheduling method for the smart grid described in any one of claims 1-8, including: a wind-solar-storage cooperation layer, a thermoelectric coupling management layer, and a regional grid scheduling layer; Thermoelectric coupling management layer: Edge management nodes are set in the thermoelectric coupling management layer. Based on the output of thermal power units and the heating status at the edge management nodes and the current thermoelectric ratio reference value, a thermoelectric dynamic regulation model is constructed to analyze the optimal thermal power unit output data in real time, and the cooperation strategy from the thermoelectric coupling management layer to the wind-solar-storage coordination layer is set; The thermoelectric ratio adjustment range of thermal power units and the available capacity of electro-thermal conversion equipment are periodically uploaded to the regional power grid dispatching layer; Wind-solar-storage coordination layer: Edge management nodes are set in the wind-solar-storage coordination layer. Based on the wind-solar output and power supply status at the edge management nodes, a wind-solar-storage joint optimization model is constructed, constraints are set, the optimal wind-solar output data is analyzed, and the cooperation strategy from the wind-solar-storage coordination layer to the thermoelectric coupling management layer is set; The wind-solar output prediction data and the energy storage SOC status are periodically uploaded to the regional power grid dispatching layer; Power grid dispatching layer: The regional power grid dispatching layer is established in the cloud. According to the data uploaded by the wind-solar-storage coordination layer and the thermoelectric coupling management layer, a joint optimization model is constructed to predict the optimal thermal power unit output data and wind-solar output data of the wind-solar-storage coordination layer and the thermoelectric coupling management layer nodes in the next cycle, and the results are sent to the corresponding nodes.

Images