An Optimization Scheduling Method for a Central Heating System with an Electric Heat Pump and Heat Storage

Abstract

The present invention discloses an optimized scheduling method for a centralized heating system including an electric heat pump and heat storage, which comprises: predicting the heat load demands of heat-consuming buildings and the heat supply amounts of new energy heating units for each scheduling period of the next day, and calculating the remaining heat supply amounts for each scheduling period of the next day; predicting the heat production amounts of the electric heat pumps for each scheduling period of the next day, and setting combination strategies for the remaining heat supply amounts by traditional heating units, electric heat pumps and heat storage devices; establishing a day-ahead optimized scheduling model with the objectives of minimizing the total operating cost and the deviation degree of the heat load of heat-consuming buildings for each scheduling period of the next day, and outputting the start-stop states and output magnitudes of the traditional heating units, electric heat pumps and heat storage devices for each scheduling period of the next day; at the current moment of the next day, according to the predicted values of the heat load demands of heat-consuming buildings and the heat supply amounts of new energy heating units under the future intraday rolling adjustment period, re-planning the start-stop states and output magnitudes of the traditional heating units, electric heat pumps and heat storage devices for the subsequent scheduling periods.

Description

Technical Field

[0001] The invention belongs to the technical field of heating system scheduling, and particularly relates to an optimized scheduling method for a centralized heating system with an electric heat pump and heat storage. Background Art

[0002] With the development of the economy and the improvement of people's living standards, the consumption of energy is increasing day by day. However, primary energy sources such as petroleum, coal, and natural gas are gradually decreasing or even running out, and the combustion of fossil energy emits a large amount of carbon dioxide into the atmosphere, exacerbating the greenhouse effect. In the general situation where environmental problems are becoming increasingly severe, other forms of new energy such as wind energy, water conservancy, nuclear energy, geothermal energy, and air thermal energy are gradually developed and utilized, forming a structural pattern in which traditional fossil fuel heating and new energy heating coexist, and there is a trend of centralized heating.

[0003] At present, in the general environment of advocating energy conservation and emission reduction and taking the path of sustainable development across the country, the energy-saving and consumption-reducing economic operation of the centralized heating system is the current main direction. Among them, electric heat pump units including air source heat pumps, water source heat pumps, and ground source heat pumps are introduced for heating. Using a small amount of electricity to do work can supply high-grade heat energy that can be utilized to heat users, becoming the main supply object for the heat demand of the heating system. However, in the face of traditional heating, new energy heating, and a new type of centralized heating system combined with electric heat pump heating, how to achieve the supply-demand coordination of the heating system, the comprehensive utilization of energy, and output a scientific, reasonable, and effective optimized scheduling plan for the heating system is an urgent problem to be solved at present.

[0004] Based on the above technical problems, it is necessary to design a new optimized scheduling method for a centralized heating system with an electric heat pump and heat storage. Summary of the Invention

[0005] The technical problem to be solved by the present invention is to overcome the deficiencies of the prior art and provide an optimized scheduling method for a centralized heating system with an electric heat pump and heat storage, which can introduce the electric heat pump and heat storage device into the centralized heating system for day-ahead optimization scheduling and intra-day optimization scheduling. The electric heat pump can convert a small amount of input electric energy into a large amount of high-grade heat energy to supply the load demand, and use time-of-use electricity prices to provide heat output, which can effectively reduce the fuel consumption of traditional heating units, improve the energy utilization rate. The energy storage device can effectively regulate the peak-valley difference of the heat load, reduce the operating cost of the centralized heating system, enhance the flexible regulation ability of the system, and achieve the supply-demand coordinated operation of the heating system, as well as output a day-ahead optimized scheduling plan and adjust the optimized scheduling plan intra-day, and plan the start-stop status and output of traditional heating units, electric heat pumps, and heat storage devices in each scheduling period to improve the accuracy of system scheduling operation.

[0006] To solve the above technical problems, the technical solution of the present invention is:

[0007] The present invention provides an optimized scheduling method for a centralized heating system with an electric heat pump and heat storage, which includes:

[0008] Step S1, constructing a digital twin model of a centralized heating system including heat production equipment, heat auxiliary equipment, heat storage equipment, and heat-consuming buildings; the heat production equipment includes a new energy heating unit and a traditional heating unit; the heat auxiliary equipment includes an electric heat pump; the heat storage equipment includes a heat storage device;

[0009] Step S2, respectively predicting the heat load demand of heat-consuming buildings and the heat supply of new energy heating units for each scheduling period of the next day;

[0010] Step S3, calculating the remaining heat supply for each scheduling period of the next day based on the predicted values of the heat load demand of heat-consuming buildings and the heat supply of new energy heating units for each scheduling period of the next day;

[0011] Step S4, predicting the heat production of the electric heat pump for each scheduling period of the next day under the conditions of maximizing the energy efficiency of the electric heat pump and storing the excess heat production of the electric heat pump through the heat storage device, and at the same time setting the combined strategies of the traditional heating unit, the electric heat pump, and the heat storage device for the remaining heat supply;

[0012] Step S5, taking the minimum total operating cost of the centralized heating system for each scheduling period of the next day and the minimum deviation of the heat load of heat-consuming buildings as the objective function, establishing a day-ahead optimized scheduling model for the centralized heating system, and outputting the start-stop states and output sizes of the traditional heating unit, the electric heat pump, and the heat storage device for each scheduling period of the next day;

[0013] Step S6, at the current moment of the next day, according to the predicted values of the heat load demand of heat-consuming buildings and the heat supply of new energy heating units in the future intraday rolling adjustment period, re-planning the start-stop states and output sizes of the traditional heating unit, the electric heat pump, and the heat storage device for each subsequent scheduling period, and obtaining the intraday scheduling plan for the centralized heating system.

[0014] Further, in the step S1, constructing a digital twin model of a centralized heating system including heat production equipment, heat auxiliary equipment, heat storage equipment, and heat-consuming buildings includes:

[0015] Establishing a three-dimensional physical model of the physical entity of the centralized heating system, and graphically and formally describing the constituent elements, constituent structure, and operating mechanism of the logical model corresponding to the physical model, and then feeding back the attributes and behaviors of each element to the physical model to perform the mapping from the physical model to the logical model; the physical entity of the centralized heating system includes heat production equipment, heat auxiliary equipment, heat storage equipment, and heat-consuming buildings; the heat production equipment includes a new energy heating unit and a traditional heating unit; the heat auxiliary equipment includes an electric heat pump; the heat storage equipment includes a heat storage device;

[0016] Build a visual simulation model of the central heating system. Based on the multi-source data collected from the central heating system, use intelligent optimization algorithms to train and optimize the simulation model of the central heating system, and then feedback the simulation results to the physical model.

[0017] Verify the consistency and reliability of the physical model and the simulation model of the central heating system.

[0018] For the multi-source data fusion of the central heating system and the use of machine learning algorithms, perform data cleaning and transformation, sharing and aggregation, fusion and iterative optimization of the information flow, control flow, data flow and decision flow from the physical space to the virtual space of the central heating system, and establish a data model of the central heating system.

[0019] After integrating the physical model, logical model, simulation model and data model of the central heating system, establish a digital twin of the physical entities in the physical space of the central heating system in the virtual space through mapping reconstruction and 1:1 mirroring.

[0020] Furthermore, the new energy heating unit includes a solar heating unit; the traditional heating unit includes a coal-fired boiler and a cogeneration unit; the heat pump includes an air source heat pump.

[0021] Furthermore, in step S2, predict the heat load demand of the heating buildings and the heat supply of the new energy heating units for each scheduling period of the next day, including:

[0022] Collect the secondary network supply and return water temperatures, secondary water supply flow rates, building room temperatures, and outdoor meteorological information of each historical scheduling period related to the heat load of the heating buildings; collect the operation data and external environment information of each historical scheduling period related to the heat supply of the new energy heating units.

[0023] After performing data preprocessing and wavelet transform decomposition on the data information of each historical scheduling period related to the heat load of the heating buildings and the data information of each historical scheduling period related to the heat supply of the new energy heating units collected respectively, input them into the dendritic neural network model for training, establish a prediction model for the heat load demand of the heating buildings and a prediction model for the heat supply of the new energy heating units for each scheduling period of the next day, and then perform wavelet reconstruction on the data output by the models respectively to obtain the final predicted values of the heat load demand of the heating buildings and the heat supply of the new energy heating units for each scheduling period of the next day.

[0024] Furthermore, in step S3, based on the predicted values of the heat load demand of the heating buildings and the heat supply of the new energy heating units for each scheduling period of the next day, calculate the remaining heat supply for each scheduling period of the next day, and at the same time set the combination strategies of the traditional heating units, heat pumps and heat storage devices for the remaining heat supply, including:

[0025] Based on the predicted values of the heating load demands of heating buildings for each scheduling period on the next day, considering the time delay and heat loss characteristics of heat transfer from the heat source to the heating buildings, the predicted values of the heating load demands of heating buildings for each scheduling period on the next day are corrected to obtain the predicted values of the total heat supply of the heat source for each scheduling period on the next day;

[0026] Based on the predicted values of the total heat supply of the heat source and the predicted values of the heat supply of new energy heating units for each scheduling period on the next day, calculate the remaining heat supply for each scheduling period on the next day; the remaining heat supply is coordinately supplied by traditional heating units, electric heat pumps, and heat storage devices.

[0027] Furthermore, in step S4, under the conditions of maximizing the energy efficiency of the electric heat pump and storing the excess heat generated by the electric heat pump through the heat storage device, predict the heat generation of the electric heat pump for each scheduling period on the next day, and at the same time set the combined strategies of traditional heating units, electric heat pumps, and heat storage devices for the remaining heat supply, including:

[0028] Under the conditions of maximizing the energy efficiency of the electric heat pump and storing the excess heat generated by the electric heat pump through the heat storage device, collect the data of each historical scheduling period related to the heat generation of the electric heat pump, including external environment data, historical heat generation, energy efficiency values of the electric heat pump, historical electricity prices, power consumption, and target values of the supply and return water temperatures of the heat network;

[0029] After preprocessing and wavelet transform decomposition of the collected data of each historical scheduling period related to the heat generation of the electric heat pump, input it into the dendritic neural network model for training, establish a prediction model for the heat generation of the electric heat pump for each scheduling period on the next day, and then perform wavelet reconstruction on the data output by the model to obtain the final predicted values of the heat generation of the electric heat pump for each scheduling period on the next day;

[0030] Set the combined strategies for the coordinated supply of the remaining heat supply by traditional heating units, electric heat pumps, and heat storage devices: when the remaining heat supply is less than a preset first threshold, supply heat solely by the traditional heating unit or solely by the electric heat pump, and when the heat generation of the electric heat pump is excessive and the electricity price is at a low valley period, store the excess heat in the heat storage device; when the remaining heat supply is greater than the preset first threshold and less than the preset second threshold, first supply heat in combination by the electric heat pump and the heat storage device during the electricity price low valley period, and then, under the condition of the same heat generation, set the electric heat pump and / or the traditional heating unit to supply heat during the electricity price flat period and peak period; when the remaining heat supply is greater than the second threshold, supply heat in combination by the traditional heating unit, the electric heat pump, and the heat storage device during each scheduling period on the next day.

[0031] Furthermore, the process of wavelet transform decomposition includes: using wavelet transform decomposition to decompose the preprocessed data to obtain low-frequency components and high-frequency components, and then decompose the low-frequency components, repeating until three-level decomposition is completed to obtain each component;

[0032] The dendritic neural network includes a synaptic layer, a branching layer, a cell membrane layer, and a cell body layer; the data after wavelet transform decomposition is input into the dendritic neural network model for training, including: after the data is input into the dendritic neural network, the synaptic layer performs non-linear calculation, and then the corresponding branching layer performs multiplication operation on the operation result and aggregates it to the cell membrane layer for summation processing. Finally, the processed data is transmitted to the cell body layer. If the output data exceeds the preset threshold, the working state of the neuron is triggered, and the operation result of the final cell body layer is output.

[0033] Further, in step S5, taking the minimum total operating cost of each scheduling period of the central heating system on the next day and the minimum deviation of the heating load of the heating buildings as the objective function, a day-ahead optimal scheduling model of the central heating system is established, and the start-stop states and output powers of the traditional heating units, electric heat pumps, and heat storage devices in each scheduling period of the next day are output, including:

[0034] Based on the set traditional heating units, electric heat pumps, and heat storage devices, a coordinated supply combination strategy for the remaining heating supply is carried out, and multiple heating combination schemes for each scheduling period of the next day are preset;

[0035] For multiple heating combination schemes in each scheduling period, taking the minimum total operating cost of each scheduling period of the central heating system on the next day and the minimum deviation of the heating load of the heating buildings as the objective function, they are respectively expressed as:

[0036]

[0037]

[0038] F1 is the total operating cost of each scheduling period of the central heating system on the next day; F rl,t is the fuel cost of the traditional heating unit; F yw,t is the operation and maintenance cost of the electric heat pump and the heat storage device; F st,t is the start-stop cost; F dj,t is the electric energy interaction cost; T is the cycle of the scheduling period; F2 is the deviation of the heating load of the heating buildings in the central heating system; and are respectively the actual heating supply, the ideal heating supply, and the minimum heating supply of the heating building k at time t;

[0039] F rl,t =r rl P ct,t Δt; r rl is the price of unit fuel; P ct,t is the output power of the traditional heating unit at time t;

[0040] F yw,t =P dr,t K drΔt + |P ES,t |K ES Δt; P dr,t is the output power of the heat pump at time t; K dr is the operation and maintenance cost per unit power of the heat pump; P ES,t is the output of the heat storage device at time t; K ES is the operation and maintenance cost per unit power of the heat storage device;

[0041] F st,t = max{0, U i (t) - U i (t - 1)}C ST Δt; U(t) is the start-stop state of unit i at time t; C ST is the start-up cost;

[0042] F dj,t = C rb,t max{P EX,t , 0}; C rb,t is the electricity purchase price of the power grid at time t; P EX,t is the interaction power of the power grid at time t;

[0043] Set the operation constraints of the central heating system, including heat power balance constraint, output constraint of traditional heating units, output constraint of heat pumps, and heat storage device constraint;

[0044] Based on the objective function of minimizing the total operation cost of each scheduling period of the central heating system the next day and the deviation degree of the heating building load, combined with the operation constraints of the central heating system, establish a day-ahead optimal scheduling model for the central heating system;

[0045] Use an intelligent optimization algorithm to solve the day-ahead optimal scheduling model of the central heating system, and output the start-stop state and output size of the traditional heating units, heat pumps and heat storage devices in each scheduling period the next day.

[0046] Furthermore, in step S6, at the current moment the next day, according to the predicted values of the heating building heat load demand and the heat supply of the new energy heating unit in the future intra-day rolling adjustment period, re-plan the start-stop state and output size of the traditional heating units, heat pumps and heat storage devices in each subsequent scheduling period to obtain the intra-day scheduling plan of the central heating system, including:

[0047] Due to the volatility and uncertainty of the output of new energy heating units and the heating building heat load demand, there are errors between the predicted values of the heating building heat load demand and the predicted values of the heat supply of new energy heating units and the corresponding actual values in each scheduling period of the day-ahead scheduling. Correct the day-ahead scheduling plan to make up for the errors;

[0048] At the current moment of the next day, according to the predicted values of the heating load demand of the heated buildings and the predicted heat supply of the new energy heating units under the future intraday rolling adjustment period, re-plan the start-stop states and output levels of the traditional heating units, electric heat pumps, and heat storage devices for intraday scheduling;

[0049] Set the intraday rolling adjustment period to 4 hours, with a 15-minute adjustment period step size, that is, the [t+1, t+16] period starting from the current period is the next adjustment period; the scheduling objective of the intraday scheduling plan is to minimize the cost brought by the change in the start-stop state of the central heating system, and set the constraint condition that the minimum start-stop time of the unit is less than or equal to 4 hours;

[0050] The scheduling objective of the intraday scheduling plan is expressed as: U i,t is the start-stop state of unit i at time t; U i,t ′ is the start-stop state of unit i at the day-ahead scheduling time corresponding to time t; S i is the start-stop penalty cost;

[0051] Use an intelligent optimization algorithm to solve the scheduling objective of the intraday scheduling plan to obtain the intraday scheduling plan for the central heating system, and output the start-stop states and output levels of the traditional heating units, electric heat pumps, and heat storage devices for each intraday scheduling period.

[0052] Further, after the step S6, it further includes: using the digital twin model of the central heating system to simulate and verify the intraday scheduling plan, judging whether the heat quantity of the heated buildings meets the standard after implementing the intraday scheduling plan, and issuing and executing the intraday scheduling plan after it meets the standard.

[0053] The beneficial effects of the present invention are:

[0054] The present invention constructs a digital twin model of a centralized heating system including a heat production device, a heat assistance device, a heat storage device, and a heat-using building; predicts the heat load demand of the heat-using building and the heat supply of the new energy heating unit for each scheduling period of the next day respectively; calculates the remaining heat supply for each scheduling period of the next day based on the predicted values of the heat load demand of the heat-using building and the heat supply of the new energy heating unit for each scheduling period of the next day; predicts the heat production of the heat pump for each scheduling period of the next day under the conditions of maximizing the energy efficiency of the heat pump and storing the excess heat production of the heat pump through the heat storage device, and at the same time sets the combined strategies of the traditional heating unit, the heat pump, and the heat storage device for the remaining heat supply; takes the minimum total operating cost and the minimum load deviation of the heat-using building for each scheduling period of the next day of the centralized heating system as the objective function, establishes a day-ahead optimal scheduling model of the centralized heating system, and outputs the start-stop states and output sizes of the traditional heating unit, the heat pump, and the heat storage device for each scheduling period of the next day; at the current moment of the next day, according to the predicted values of the heat load demand of the heat-using building and the heat supply of the new energy heating unit under the future intraday rolling adjustment period, re-plan the start-stop states and output sizes of the traditional heating unit, the heat pump, and the heat storage device for the subsequent scheduling periods to obtain the intraday scheduling plan of the centralized heating system; on the one hand, it can introduce the heat pump and the heat storage device into the centralized heating system for day-ahead optimal scheduling and intraday optimal scheduling. The heat pump can convert a small amount of input electric energy into a large amount of high-grade heat energy to supply the load demand, and use the time-of-use electricity price to provide heat production, which can effectively reduce the fuel consumption of the traditional heating unit and improve the energy utilization rate. The energy storage device can effectively regulate the peak-valley difference of the heat load, reduce the operating cost of the centralized heating system, and enhance the flexible regulation ability of the system; on the other hand, based on the supply-demand coordination of the centralized heating system, after predicting the heat load demand of the heat-using building to obtain the heating demand, and then based on the predicted heat supply of the new energy heating unit and the predicted heat production of the heat pump, combined with the heat storage characteristics of the heat storage device and the output of the additional traditional heating unit, supply the heat supply, give play to the energy advantage for heating, and realize the supply-demand coordinated operation; in addition, by setting the multi-time scale optimal operation plan of day-ahead optimal scheduling and intraday optimal scheduling, output the day-ahead optimal scheduling plan and adjust the optimal scheduling plan intraday, and plan the start-stop states and output sizes of the traditional heating unit, the heat pump, and the heat storage device for each scheduling period to improve the accuracy of the system scheduling operation.

[0055] Other features and advantages will be set forth in the following description, and in part will be obvious from the description, or may be learned by practice of the invention. The objectives and other advantages of the invention are realized and attained by the structure particularly pointed out in the specification and the drawings.

[0056] To make the above objects, features, and advantages of the present invention more comprehensible, the following preferred embodiments are specifically described in detail in conjunction with the accompanying drawings. Brief Description of the Drawings

[0057] In order to more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the following will briefly introduce the drawings required for the description of the specific embodiments or the prior art. Obviously, the drawings in the following description are some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0058] Figure 1 It is a flowchart of an optimal scheduling method for a centralized heating system with an electric heat pump and heat storage according to the present invention;

[0059] Figure 2 It is a schematic diagram of a centralized heating system with an electric heat pump and heat storage according to the present invention;

[0060] Figure 3 It is a schematic diagram of wavelet decomposition according to the present invention. Detailed Embodiments

[0061] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the following will clearly and completely describe the technical solutions of the present invention in conjunction with the drawings. Obviously, the described embodiments are some, but not all, of the embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts fall within the scope of protection of the present invention.

[0062] Embodiment 1

[0063] Figure 1 It is a flowchart of an optimal scheduling method for a centralized heating system with an electric heat pump and heat storage according to the present invention.

[0064] Figure 2 It is a schematic diagram of a centralized heating system with an electric heat pump and heat storage according to the present invention.

[0065] As Figure 1-2 shown, Embodiment 1 of the present invention provides an optimal scheduling method for a centralized heating system with an electric heat pump and heat storage, which includes:

[0066] Step S1: Construct a digital twin model of a centralized heating system including heat production equipment, heat auxiliary equipment, heat storage equipment, and heat-consuming buildings; the heat production equipment includes a new energy heating unit and a traditional heating unit; the heat auxiliary equipment includes an electric heat pump; the heat storage equipment includes a heat storage device;

[0067] Step S2: Predict the heat load demand of heat-consuming buildings and the heat supply of new energy heating units for each scheduling period of the next day respectively;

[0068] Step S3: Calculate the remaining heat supply for each scheduling period of the next day based on the predicted values of the heat load demand of heat-consuming buildings and the predicted heat supply of new energy heating units for each scheduling period of the next day.

[0069] Step S4: Under the conditions of maximizing the energy efficiency of the heat pump and storing the excess heat production of the heat pump through the heat storage device, predict the heat production of the heat pump for each scheduling period of the next day, and at the same time set the combined strategies of the traditional heating unit, the heat pump, and the heat storage device for the remaining heat supply.

[0070] Step S5: Establish a day-ahead optimal scheduling model for the centralized heating system with the minimum total operating cost and the minimum deviation of the heat load of heat-consuming buildings for each scheduling period of the centralized heating system as the objective function, and output the start-stop status and output size of the traditional heating unit, the heat pump, and the heat storage device for each scheduling period of the next day.

[0071] Step S6: At the current moment of the next day, according to the predicted values of the heat load demand of heat-consuming buildings and the heat supply of new energy heating units under the future intra-day rolling adjustment period, re-plan the start-stop status and output size of the traditional heating unit, the heat pump, and the heat storage device for each subsequent scheduling period to obtain the intra-day scheduling plan of the centralized heating system.

[0072] In this embodiment, in step S1, a digital twin model of the centralized heating system including heat production equipment, heat auxiliary equipment, heat storage equipment, and heat-consuming buildings is constructed, including:

[0073] Establish a three-dimensional physical model of the physical entity of the centralized heating system, and through graphical and formal descriptions of the constituent elements, constituent structures, and operating mechanisms of the logical model corresponding to the physical model, and then feedback the element attributes and behaviors to the physical model to perform the mapping from the physical model to the logical model; the physical entity of the centralized heating system includes heat production equipment, heat auxiliary equipment, heat storage equipment, and heat-consuming buildings; the heat production equipment includes new energy heating units and traditional heating units; the heat auxiliary equipment includes heat pumps; the heat storage equipment includes heat storage devices;

[0074] Establish a visual simulation model of the centralized heating system, and based on the collected multi-source data of the centralized heating system, use intelligent optimization algorithms to train and optimize the simulation model of the centralized heating system, and then feedback the simulation results to the physical model;

[0075] Verify the consistency and reliability of the physical model and the simulation model of the centralized heating system;

[0076] Perform data cleaning, transformation, sharing, aggregation, fusion, and iterative optimization on the multi-source data fusion of the centralized heating system and using machine learning algorithms for the information flow, control flow, data flow, and decision flow from the physical space to the virtual space of the centralized heating system to establish a data model of the centralized heating system.

[0077] After integrating the physical model, logical model, simulation model, and data model of the central heating system, a digital twin of the physical entities in the physical space of the central heating system is established in the virtual space through mapping reconstruction and 1:1 mirroring.

[0078] It should be noted that the established digital twin model of the central heating system can lay a foundation for subsequent load prediction, unit output prediction, heat pump heating capacity prediction, and the implementation of day-ahead optimal scheduling and intra-day optimal scheduling. Through the digital twin model, simulation operations, predictions, and the execution of scheduling can be carried out in the virtual space.

[0079] In this embodiment, the new energy heating unit includes a solar heating unit; the traditional heating unit includes a coal-fired boiler and a cogeneration unit; the heat pump includes an air source heat pump.

[0080] It should be noted that the types of the new energy heating unit, traditional heating unit, and heat pump are not limited to the above types and can also be other types.

[0081] In this embodiment, in step S2, the heat load demand of the heating buildings and the heat supply of the new energy heating units for each scheduling period of the next day are predicted respectively, including:

[0082] Collect the secondary network supply and return water temperatures, secondary water supply flow rates, building room temperatures, and outdoor meteorological information of each historical scheduling period related to the heat load of the heating buildings; collect the operation data and external environment information of each historical scheduling period related to the heat supply of the new energy heating units;

[0083] After respectively performing data preprocessing and wavelet transform decomposition on the data information of each historical scheduling period related to the heat load of the heating buildings and the data information of each historical scheduling period related to the heat supply of the new energy heating units collected, they are respectively input into the dendritic neural network model for training to establish a prediction model for the heat load demand of the heating buildings and a prediction model for the heat supply of the new energy heating units for each scheduling period of the next day. Then, the data output by the models are respectively subjected to wavelet reconstruction to obtain the final predicted values of the heat load demand of the heating buildings and the heat supply of the new energy heating units for each scheduling period of the next day.

[0084] In this embodiment, in step S3, based on the predicted values of the heat load demand of the heating buildings and the heat supply of the new energy heating units for each scheduling period of the next day, the remaining heat supply for each scheduling period of the next day is calculated, and at the same time, a combined strategy for the remaining heat supply is set for the traditional heating units, heat pumps, and heat storage devices, including:

[0085] Based on the predicted values of the heating load demands of heat-consuming buildings for each scheduling period of the next day, and combining the delay characteristics and heat loss characteristics of heat transfer from the heat source to the heat-consuming buildings, the predicted values of the heating load demands of heat-consuming buildings for each scheduling period of the next day are corrected to obtain the predicted values of the total heat supply of the heat source for each scheduling period of the next day;

[0086] Based on the predicted values of the total heat supply of the heat source and the predicted values of the heat supply of new energy heating units for each scheduling period of the next day, calculate the remaining heat supply for each scheduling period of the next day; the remaining heat supply is coordinately supplied by traditional heating units, electric heat pumps, and heat storage devices.

[0087] In this embodiment, in step S4, under the conditions of maximizing the energy efficiency of the electric heat pump and storing the excess heat generated by the electric heat pump through the heat storage device, predict the heat output of the electric heat pump for each scheduling period of the next day, and at the same time set the combined strategies of traditional heating units, electric heat pumps, and heat storage devices for the remaining heat supply, including:

[0088] Under the conditions of maximizing the energy efficiency of the electric heat pump and storing the excess heat generated by the electric heat pump through the heat storage device, collect the data of each historical scheduling period related to the heat output of the electric heat pump, including external environment data, historical heat output, energy efficiency value of the electric heat pump, historical electricity price, power consumption, and target values of the supply and return water temperatures of the heat network;

[0089] After preprocessing and wavelet transform decomposition of the collected data of each historical scheduling period related to the heat output of the electric heat pump, input it into the dendritic neural network model for training, establish a prediction model for the heat output of the electric heat pump for each scheduling period of the next day, and then perform wavelet reconstruction on the data output by the model to obtain the final predicted values of the heat output of the electric heat pump for each scheduling period of the next day;

[0090] Set the combined strategies for the coordinated supply of the remaining heat supply by traditional heating units, electric heat pumps, and heat storage devices: when the remaining heat supply is less than a preset first threshold, supply heat by the traditional heating unit alone or by the electric heat pump alone, and when the heat output of the electric heat pump is excessive and the electricity price is at a low valley period, store the excess heat in the heat storage device; when the remaining heat supply is greater than the preset first threshold and less than the preset second threshold, first supply heat in combination by the electric heat pump and the heat storage device during the electricity price low valley period, and then, under the condition of the same heat output, set the electric heat pump and / or the traditional heating unit to supply heat during the electricity price flat period and peak period; when the remaining heat supply is greater than the second threshold, supply heat in combination by the traditional heating unit, the electric heat pump, and the heat storage device during each scheduling period of the next day.

[0091] It should be noted that when setting the combined strategy for the coordinated supply of the remaining heating capacity using traditional heating units, heat pumps, and heat storage devices, the remaining heating capacity in each scheduling period of the next day is different, and it is necessary to divide the remaining heating capacity into intervals. When the remaining heating capacity in a scheduling period is less than a preset first threshold, it can be selected to supply heat by the traditional heating unit alone or by the heat pump alone. And when the heating capacity of the heat pump is excessive and the electricity price is in the low valley period, the excess heat is stored in the heat storage device. At this time, the heating capacity of the traditional heating unit or the heat pump alone for heating is completely greater than the remaining heating capacity. When the remaining heating capacity in a scheduling period is greater than the preset first threshold and less than the preset second threshold, first, the heat pump and the heat storage device supply heat in combination during the low electricity price period (the low electricity price period is usually the peak heating period), and then, under the condition of the same heating capacity, it is set that the heat pump and / or the traditional heating unit supply heat during the flat and peak electricity price periods. It can be selected to supply heat by the heat pump alone, the traditional heating unit alone, or the heat pump and the traditional heating unit jointly during the flat and peak electricity price periods. At this time, the heat pump alone for heating and the traditional heating unit alone for heating can meet the heating capacity requirements and the corresponding equipment constraint conditions, and the heating methods selected for each scheduling period are also different. The start-stop state and output size of the equipment still need to be optimized through dispatching calculations. When the remaining heating capacity is greater than the second threshold, the traditional heating unit, the heat pump, and the heat storage device supply heat in combination in each scheduling period of the next day. At this time, the demand for the remaining heating capacity is large, and it is necessary to supply heat by combining the traditional heating unit, the heat pump, and the heat storage device, and the output sizes of the traditional heating unit, the heat pump, and the heat storage device need to be optimized through dispatching calculations.

[0092] Figure 3 It is the schematic diagram of wavelet decomposition involved in the present invention.

[0093] As Figure 3 shown, in this embodiment, the process of wavelet transform decomposition includes: performing data decomposition on the preprocessed data by using wavelet transform decomposition to obtain low-frequency components and high-frequency components, and then decomposing the low-frequency components, repeating until the third-level decomposition is completed to obtain each component;

[0094] The dendritic neural network includes a synaptic layer, a branch layer, a cell membrane layer, and a cell body layer; the data after wavelet transform decomposition is input into the dendritic neural network model for training, including: after the data is input into the dendritic neural network, the synaptic layer performs non-linear calculation, and then the corresponding branch layer performs multiplication operation on the operation result and summarizes it to the cell membrane layer for summation processing. Finally, the processed data is transmitted to the cell body layer. If the output data exceeds the preset threshold, the working state of the neuron is triggered, and the operation result of the final cell body layer is output.

[0095] It should be noted that the dendritic neural network includes:

[0096] Synaptic layer: Synapses connect neurons from one dendrite to another dendrite or the cell body of another neuron, and information flows from the presynaptic neuron to the postsynaptic neuron in a feed - forward transmission mode. The calculation between the \(i\) - th synapse and the output of the \(m\) - th branch layer is expressed as:

[0097]

[0098] x i is the \(i\) - th input of the synapse, with a value range of \([0,1]\); \(Y\) im is the output from the \(i\) - th synapse input to the \(m\) - th branch layer; \(k\) is a network parameter defined by the user, usually taking a positive constant value; \(w\) im and \(\theta\) im are the parameters of the synapse; \(i = 1,2,3,\cdots,I\); \(m = 1,2,3,\cdots,M\);

[0099] Branch layer: Multiplication is used in the branch layer to achieve the non - linear operation of the synapse. The branch layer receives signals at the contact point with the synaptic layer and performs multiplication on these signals to generate a local potential. The calculation of the \(j\) - th branch is expressed as:

[0100] Cell membrane layer: The cell membrane layer aggregates the signals in each branch layer, that is, performs a linear summation operation on the product results of each branch layer at the branch nodes, expressed as:

[0101] Cell body layer: The summation result of the cell membrane layer is input into the cell body, and the sigmoid function is used to calculate the final output value. When the output result of the cell body layer exceeds the threshold, the neuron is activated and discharges. The calculation is expressed as: \(\theta\) soma is the set threshold.

[0102] It should be noted that as an effective means in data signal processing, the wavelet transform algorithm can make the time series exhibit more stable variance and fewer outliers through its filtering effect; the wavelet transform algorithm is divided into two stages: decomposition and reconstruction. In the decomposition stage, the initial time series is divided into two components by two complementary filters: the approximation component and the detail component. The approximation component corresponds to the contour of the signal, that is, the low-frequency part, and the detail component corresponds to the high-frequency part. The decomposition process can be iterated. The approximation component will be decomposed into more low-resolution components. For example, the process of iteratively decomposing the initial data signal three times: the initial signal f generates a low-frequency component A1 and a high-frequency component D1 after the first decomposition. Decomposing A1 yields a low-frequency component A2 and a high-frequency component D2, and decomposing A2 again can obtain a low-frequency component A3 and a high-frequency component D3. In the signal reconstruction stage, these components generated after decomposition can be recombined into the original signal.

[0103] The prediction method of the dendritic neural network has a fast convergence rate; therefore, combining the wavelet transform algorithm with the dendritic neural network model can further improve the prediction accuracy of the model.

[0104] In this embodiment, in step S5, taking the minimum total operating cost of each scheduling period of the central heating system on the next day and the minimum deviation of the heating load of the heat-consuming buildings as the objective functions, a day-ahead optimal scheduling model of the central heating system is established, and the start-stop states and output powers of the traditional heating units, electric heat pumps, and heat storage devices in each scheduling period of the next day are output, including:

[0105] Based on the set traditional heating units, electric heat pumps, and heat storage devices, a coordinated supply combination strategy for the remaining heat supply is carried out, and multiple heating combination schemes for each scheduling period of the next day are preset;

[0106] For multiple heating combination schemes in each scheduling period, taking the minimum total operating cost of each scheduling period of the central heating system on the next day and the minimum deviation of the heating load of the heat-consuming buildings as the objective functions, which are respectively expressed as:

[0107]

[0108]

[0109] F1 is the total operating cost of each scheduling period of the central heating system on the next day; F rl,t is the fuel cost of the traditional heating unit; F yw,t is the operation and maintenance cost of the electric heat pump and the heat storage device; F st,t is the start-stop cost; F dj,t is the electricity interaction cost; T is the cycle of the scheduling period; F2 is the deviation of the heating load of the heat-consuming buildings of the central heating system; and They are the actual heat supply, ideal heat supply, and minimum heat supply of the thermal building k within time t, respectively.

[0110] F rl,t = r rl P ct,t Δt; r rl is the price per unit of fuel; P ct,t is the output power of the traditional heating unit at time t;

[0111] F yw,t = P dr,t K dr Δt + |P ES,t |K ES Δt; P dr,t is the output power of the heat pump at time t; K dr is the operation and maintenance cost per unit power of the heat pump; P ES,t is the output of the heat storage device at time t; K ES is the operation and maintenance cost per unit power of the heat storage device;

[0112] F st,t = max{0, U i (t) - U i (t - 1)}C ST Δt; U(t) is the start-stop state of unit i at time t; C ST is the start-up cost;

[0113] F dj,t = C rb,t max{P EX,t , 0}; C rb,t is the electricity purchase price of the power grid at time t; P EX,t is the interactive power of the power grid at time t;

[0114] Set the operation constraint conditions of the centralized heating system, including heat power balance constraint, traditional heating unit output constraint, heat pump output constraint, and heat storage device constraint;

[0115] Based on the objective functions of minimizing the total operation cost of each scheduling period of the centralized heating system the next day and minimizing the deviation of the heating load of the heating building, combined with the operation constraint conditions of the centralized heating system, establish a day-ahead optimal scheduling model for the centralized heating system;

[0116] Use an intelligent optimization algorithm to solve the day-ahead optimal scheduling model of the centralized heating system, and output the start-stop states and output sizes of the traditional heating units, heat pumps, and heat storage devices in each scheduling period the next day.

[0117] In practical applications, heat supply does not need to meet the heat load demand of user buildings in real time. It only needs to keep the heat within a certain range. However, if the actual heat supply deviates too much from the ideal heat supply, it will also cause discomfort to heat users. Therefore, the degree of deviation of the actual heat supply from the ideal heat supply of users is called the heat load deviation degree. An optimal dispatching model for a centralized heating system is established by combining the economic operation of the heat source energy supply side with the heat consumption experience of the heat-using building side, minimizing the heat load deviation degree on the basis of saving economic costs.

[0118] In this embodiment, in step S6, at the current moment of the next day, according to the heat load demand of the heat-using building and the predicted value of the heat supply of the new energy heating unit under the future intra-day rolling adjustment period, the start-stop states and output powers of the traditional heating unit, the electric heat pump, and the heat storage device in each subsequent dispatching period are re-planned to obtain the intra-day dispatching plan of the centralized heating system, including:

[0119] Based on the volatility and uncertainty of the output of the new energy heating unit and the heat load demand of the heat-using building, there are errors between the predicted values of the heat load demand of the heat-using building and the predicted values of the heat supply of the new energy heating unit in each dispatching period in the day-ahead dispatching and the corresponding actual values. The errors are compensated by correcting the day-ahead dispatching plan.

[0120] At the current moment of the next day, according to the predicted value of the heat load demand of the heat-using building and the predicted value of the heat supply of the new energy heating unit under the future intra-day rolling adjustment period, the start-stop states and output powers of the traditional heating unit, the electric heat pump, and the heat storage device are re-planned for intra-day dispatching.

[0121] The intra-day rolling adjustment period is set to 4 hours, and the adjustment period step size is 15 minutes, that is, the time period from [t + 1, t + 16] starting from the current period is the next adjustment period; the dispatching goal of the intra-day dispatching plan is to minimize the cost brought by the change of the start-stop state of the centralized heating system, and a constraint condition that the minimum start-stop time of the unit is less than or equal to 4 hours is set.

[0122] The dispatching goal of the intra-day dispatching plan is expressed as: U i,t is the start-stop state of unit i at time t; U i,t ′ is the start-stop state of unit i at the day-ahead dispatching moment corresponding to time t; S i is the start-stop penalty cost;

[0123] An intelligent optimization algorithm is used to solve the dispatching goal of the intra-day dispatching plan to obtain the intra-day dispatching plan of the centralized heating system, and the start-stop states and output powers of the traditional heating unit, the electric heat pump, and the heat storage device in each intra-day dispatching period are output.

[0124] In this embodiment, after the step S6, the method further includes: using the digital twin model of the central heating system to simulate and verify the intraday scheduling plan, determining whether the heat quantity of the heated buildings after implementing the intraday scheduling plan meets the standard, and issuing and implementing the intraday scheduling plan after it meets the standard.

[0125] In several embodiments provided by the present application, it should be understood that the disclosed systems and methods can also be implemented in other ways. The system embodiments described above are merely illustrative. For example, the flowcharts and block diagrams in the accompanying drawings show the possible architectures, functions, and operations of systems, methods, and computer program products according to multiple embodiments of the present invention. In this regard, each block in the flowchart or block diagram may represent a module, a program segment, or a part of code, and the module, program segment, or part of code contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the blocks may occur in a different order than marked in the accompanying drawings. For example, two consecutive blocks may actually be executed substantially in parallel, and they may sometimes be executed in the reverse order, depending on the functions involved. It should also be noted that each block in the block diagram and / or flowchart, and the combination of blocks in the block diagram and / or flowchart, can be implemented by a dedicated hardware-based system for performing the specified functions or actions, or can be implemented by a combination of dedicated hardware and computer instructions.

[0126] In addition, in each embodiment of the present invention, the functional modules can be integrated together to form an independent part, or each module can exist separately, or two or more modules can be integrated to form an independent part. If the function is implemented in the form of a software functional module and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or a part of this technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods in each embodiment of the present invention. The aforementioned storage medium includes: various media such as USB flash drives, mobile hard disks, read-only memories (ROMs), random access memories (RAMs), magnetic disks, or optical discs that can store program codes.

[0127] Inspired by the above-described ideal embodiments of the present invention, through the above description, relevant staff can completely make various changes and modifications without departing from the technical idea of this invention. The technical scope of this invention is not limited to the content in the specification, and its technical scope must be determined according to the scope of the claims.

Claims

1. An optimized scheduling method for a central heating system with an electric heat pump and heat storage, characterized in that, It includes: Step S1: Construct a digital twin model of a centralized heating system including a heat production device, a heat assistance device, a heat storage device, and a heated building; the heat production device includes a new energy heating unit and a traditional heating unit; the heat assistance device includes an electric heat pump; the heat storage device includes a heat storage device; Step S2: Forecast the heat load demand of the heated building and the heat supply of the new energy heating unit for each scheduling period of the next day respectively; Step S3: Calculate the remaining heat supply for each scheduling period of the next day based on the predicted values of the heat load demand of the heated building and the heat supply of the new energy heating unit for each scheduling period of the next day; Step S4: Under the conditions of meeting the highest energy efficiency of the electric heat pump and storing the excess heat production of the electric heat pump through the heat storage device, forecast the heat production of the electric heat pump for each scheduling period of the next day, and at the same time set the combined strategies of the traditional heating unit, the electric heat pump, and the heat storage device for the remaining heat supply; Step S5: Take the minimum total operating cost and the minimum deviation of the heat load of the heated building for each scheduling period of the centralized heating system the next day as the objective function, establish a day-ahead optimal scheduling model for the centralized heating system, and output the start-stop status and output size of the traditional heating unit, the electric heat pump, and the heat storage device for each scheduling period of the next day, including: Based on the combined strategies for coordinating the supply of the remaining heat supply set for the traditional heating unit, the electric heat pump, and the heat storage device, preset multiple heating combination schemes for each scheduling period of the next day; For multiple heating combination schemes for each scheduling period, take the minimum total operating cost and the minimum deviation of the heat load of the heated building for each scheduling period of the centralized heating system the next day as the objective function, and are respectively expressed as: F1 is the total operating cost of the centralized heating system during each dispatching period of the next day; F rl,t is the fuel cost of the traditional heating unit; F yw,t is the operation and maintenance cost of the electric heat pump and the heat storage device; F st,t is the start-stop cost; F dj,t is the cost of electricity interaction; T is the cycle of the dispatching period; F2 is the deviation degree of the heating load of the heat-using building in the centralized heating system; and are respectively the actual heat supply, the ideal heat supply and the minimum heat supply of the heat-using building k at time t; F rl,t = r rl P ct,t Δt; r rl is the price of unit fuel; P ct,t is the output power of the traditional heating unit at time t; F yw,t = P dr,t K dr Δt + |P ES,t |K ES Δt; P dr,t is the output power of the heat pump at time t; K dr is the operation and maintenance cost per unit power of the heat pump; P ES,t is the output of the heat storage device at time t; K ES is the operation and maintenance cost per unit power of the heat storage device; F st,t = max{0, U i (t) - U i (t - 1)} C ST Δt; U i (t) is the start / stop state of unit i at time t; C ST is the start-up cost; F dj,t = C rb,t max{P EX,t , 0}; C rb,t is the electricity purchase price of the power grid at time t; P EX,t is the interactive power of the power grid at time t; Set the operating constraint conditions of the centralized heating system, including heat power balance constraint, traditional heating unit output constraint, electric heat pump output constraint, heat storage device constraint; Based on the objective function of the minimum total operating cost and the minimum deviation of the heat load of the heated building for each scheduling period of the centralized heating system the next day, combined with the operating constraint conditions of the centralized heating system, establish a day-ahead optimal scheduling model for the centralized heating system; Use an intelligent optimization algorithm to solve the day-ahead optimal scheduling model of the centralized heating system, and output the start-stop status and output size of the traditional heating unit, the electric heat pump, and the heat storage device for each scheduling period of the next day; Step S6: At the current moment of the next day, according to the predicted values of the heat load demand of the heated building and the heat supply of the new energy heating unit under the future intraday rolling adjustment period, re-plan the start-stop status and output size of the traditional heating unit, the electric heat pump, and the heat storage device for each subsequent scheduling period, and obtain the intraday scheduling plan of the centralized heating system.

2. The optimized scheduling method for a central heating system according to claim 1, characterized in that, In step S1, constructing a digital twin model of a centralized heating system including a heat production device, a heat assistance device, a heat storage device, and a heated building includes: Establish a three-dimensional physical model of the physical entity of the centralized heating system, and graphically and formally describe the constituent elements, constituent structure, and operating mechanism of the logical model corresponding to the physical model, and then feedback the element attributes and behaviors to the physical model to perform the mapping from the physical model to the logical model; the physical entity of the centralized heating system includes a heat production device, a heat assistance device, a heat storage device, and a heated building; Build a visual simulation model of the central heating system. Based on the multi-source data collected from the central heating system, after training and optimizing the simulation model of the central heating system using intelligent optimization algorithms, the simulation results are fed back to the physical model; Verify the consistency and reliability of the physical model and the simulation model of the central heating system; For the multi-source data fusion of the central heating system and the use of machine learning algorithms, perform data cleaning, transformation, sharing, aggregation, fusion, and iterative optimization of the information flow, control flow, data flow, and decision flow from the physical space to the virtual space of the central heating system, and establish a data model for the central heating system; After integrating the physical model, logical model, simulation model, and data model of the central heating system, through mapping reconstruction and 1:1 mirroring, establish a digital twin of the physical entities in the physical space of the central heating system in the virtual space.

3. The optimized scheduling method for a central heating system according to claim 2, characterized in that The new energy heating units include solar heating units; the traditional heating units include coal-fired boilers and cogeneration units; the heat pumps include air source heat pumps.

4. The optimized scheduling method for a central heating system according to claim 1, characterized in that In step S2, predict the heat load demand of the heating buildings and the heat supply of the new energy heating units for each scheduling period of the next day, including: Collect the secondary network supply and return water temperatures, secondary water supply flow rates, building room temperatures, and outdoor meteorological information of each historical scheduling period related to the heat load of the heating buildings; collect the operation data and external environment information of each historical scheduling period related to the heat supply of the new energy heating units; After performing data preprocessing and wavelet transform decomposition on the data information of each historical scheduling period collected related to the heat load of the heating buildings and the data information of each historical scheduling period related to the heat supply of the new energy heating units respectively, input them into the dendritic neural network model for training, establish a prediction model for the heat load demand of the heating buildings and a prediction model for the heat supply of the new energy heating units for each scheduling period of the next day, and then perform wavelet reconstruction on the data output by the models respectively to obtain the final predicted values of the heat load demand of the heating buildings and the heat supply of the new energy heating units for each scheduling period of the next day.

5. The optimized scheduling method for a central heating system according to claim 1, characterized in that, In step S3, based on the predicted values of the heat load demand of the heating buildings and the heat supply of the new energy heating units for each scheduling period of the next day, calculate the remaining heat supply for each scheduling period of the next day, including: Based on the predicted values of the heat load demand of the heating buildings for each scheduling period of the next day, combined with the delay and heat loss characteristics of heat transfer from the heat source to the heating buildings, correct the predicted values of the heat load demand of the heating buildings for each scheduling period of the next day to obtain the predicted values of the total heat supply of the heat source for each scheduling period of the next day; Based on the predicted values of the total heat supply of the heat source and the predicted values of the heat supply of the new energy heating units for each scheduling period of the next day, calculate the remaining heat supply for each scheduling period of the next day; the remaining heat supply is coordinated and supplied by traditional heating units, heat pumps, and heat storage devices.

6. The optimized scheduling method for a central heating system according to claim 1, wherein In step S4, under the conditions of maximizing the energy efficiency of the heat pumps and storing the excess heat generated by the heat pumps through the heat storage devices, predict the heat output of the heat pumps for each scheduling period of the next day, and at the same time set the combined strategies of traditional heating units, heat pumps, and heat storage devices for the remaining heat supply, including: Under the conditions of maximizing the energy efficiency of the electric heat pump and storing the excess heat generated by the electric heat pump through the heat storage device, collect the data of each historical scheduling period related to the heat output of the electric heat pump, including external environmental data, historical heat output, energy efficiency value of the electric heat pump, historical electricity price, power consumption, and target values of the supply and return water temperatures of the heat network. After data preprocessing and wavelet transform decomposition of the collected data of each historical scheduling period related to the heat output of the electric heat pump, input it into the dendritic neural network model for training to establish a prediction model for the heat output of the electric heat pump in each scheduling period of the next day, and then perform wavelet reconstruction on the data output by the model to obtain the final predicted value of the heat output of the electric heat pump in each scheduling period of the next day. Set a combined strategy for the coordinated supply of the remaining heat by the traditional heating unit, electric heat pump, and heat storage device: when the remaining heat is less than the preset first threshold, the traditional heating unit supplies heat alone, or the electric heat pump supplies heat alone, and when the heat output of the electric heat pump is excessive and the electricity price is in the low valley period, the excess heat is stored in the heat storage device; when the remaining heat is greater than the preset first threshold and less than the preset second threshold, first, the electric heat pump and the heat storage device supply heat in combination during the low electricity price period, and then, under the condition of the same heat output, it is set that the electric heat pump and / or the traditional heating unit supply heat during the flat and peak electricity price periods; when the remaining heat is greater than the second threshold, the traditional heating unit, electric heat pump, and heat storage device supply heat in combination during each scheduling period of the next day.

7. The optimized scheduling method for a centralized heating system according to claim 4 or 6, characterized in that The process of the wavelet transform decomposition includes: using wavelet transform decomposition to decompose the preprocessed data to obtain low-frequency components and high-frequency components, and then decomposing the low-frequency components, repeating until the third-level decomposition is completed to obtain each component. The dendritic neural network includes a synaptic layer, a branch layer, a cell membrane layer, and a cell body layer; the data after wavelet transform decomposition is input into the dendritic neural network model for training, including: after the data is input into the dendritic neural network, the synaptic layer performs nonlinear calculations, and then the corresponding branch layer performs multiplication operations on the operation results and summarizes them to the cell membrane layer for summation processing, and finally the processed data is transmitted to the cell body layer. If the output data exceeds the preset threshold, the neuron working state is triggered, and the operation result of the final cell body layer is output.

8. The optimized scheduling method for a central heating system according to claim 1, characterized in that, After the step S6, it further includes: using the digital twin model of the central heating system to simulate and verify the intraday scheduling plan, judging whether the heat of the heating buildings meets the standard after implementing the intraday scheduling plan, and issuing and implementing the intraday scheduling plan after it meets the standard.

Images