An intelligent control method for a distribution network and heat pump coupling system

Abstract

The present invention provides an intelligent control method for a coupling system of a distribution network and a heat pump. The method constructs an objective function based on the predicted electric, cold and hot loads of the coupling system in multiple time periods, with the goal of maximizing net benefits and minimizing adjustment costs, respectively, and uses electric cold and heat balance constraints and modified balance constraints as constraints to solve the photovoltaic output of the distribution network system in each time period, the heat and cold production of the heat pump system, and the net control benefits of the corresponding time period, and allocates them among the photovoltaic panels of the distribution network system and the heating equipment and cooling equipment of the heat pump system; based on the allocation results, the photovoltaic output, the heat production of the heating equipment and the cooling production of the cooling equipment after preliminary adjustment are finally adjusted. The present invention solves the problem in the prior art that the coupling system is affected by multiple factors, and it is difficult to coordinate equipment operation, internal balance and market participation, resulting in poor energy utilization efficiency.

Description

Technical Field

[0001] The present invention belongs to the technical field of thermoelectric coupling, and in particular relates to an intelligent control method for a power distribution network and a heat pump coupling system. Background Art

[0002] In the context of energy transformation, integrated energy services have begun to develop rapidly. However, the integrated energy system involves different energy types such as electricity and heat. Due to the complex system form and the large differences in the characteristics of different energy systems, it is technically difficult to couple various types of energy systems and ensure system coordination and matching. In order to deal with these problems, the integrated energy system must introduce flexible factors.

[0003] Based on the characteristics of electric energy being difficult to store but easy to transport, and heat being delayed and easy to store, the two are well complementary. The heat pump system has high operating efficiency, can consume primary energy and electricity, and convert low-quality energy into high-quality energy. If the distribution network can be coupled with the cold and heat storage technology of electric drive units such as heat pumps, the mutual conversion and flexible scheduling of electricity and heat can be realized, effectively improving the energy utilization efficiency of the integrated energy system.

[0004] However, the current distribution network and heat pump coupling system is affected by multiple factors such as various types of internal equipment, various types of energy flows, and external market information. It is difficult to coordinate equipment operation, internal balance and market participation. In addition, the operating parameters of the coupling system are not monitored and collected in real time, and the cooling / heating output of the unit cannot be adjusted according to the real-time detection data, resulting in low system utilization. Summary of the invention

[0005] In view of the above analysis, the present invention aims to provide an intelligent control method for a distribution network and a heat pump coupling system, which is used to solve the problem in the prior art that the coupling system is affected by multiple factors, and equipment operation, internal balance and market participation are difficult to coordinate, resulting in poor energy utilization efficiency.

[0006] The purpose of the present invention is mainly achieved through the following technical solutions:

[0007] The present invention provides an intelligent control method for a power distribution network and a heat pump coupling system, comprising:

[0008] Based on the predicted electricity, cooling and heating loads of the coupled system in multiple time periods, the first objective function is constructed with the goal of maximizing net benefits, and the electricity balance constraint, cooling balance constraint and thermal balance constraint are used as constraints to solve the photovoltaic output of the distribution network system in each time period, the heat and cooling production of the heat pump system, and the maximized net benefits of the coupled system;

[0009] The second objective function is constructed with the goal of minimizing the adjustment cost, and the electric energy correction balance constraint, the thermal energy correction balance constraint and the cooling energy correction balance constraint are used as constraint conditions to solve the electric, cooling and heat adjustment amounts and the minimized adjustment cost of the coupling system in each period; and the photovoltaic output and the heat and cooling production of the heat pump system are preliminarily adjusted based on the adjustment amounts;

[0010] Based on the maximization of net benefit and minimization of adjustment cost, the net benefit of regulation of the coupling system in the corresponding period is obtained, and is allocated among the photovoltaic panels of the distribution network system and the heating equipment and cooling equipment of the heat pump system; and based on the allocation result, the preliminary adjusted photovoltaic output, the heat production of the heating equipment and the cooling production of the cooling equipment are finally adjusted.

[0011] Furthermore, the first objective function is constructed by the following method:

[0012] Based on the predicted electricity, cooling and heating loads and electricity, heating and cooling prices for each period, the energy sales revenue of the coupling system for the corresponding period is obtained;

[0013] Based on the sales volume and sales price of each period, the market interaction benefits of the corresponding period are obtained;

[0014] Based on the energy sales income, market interaction income and the startup cost, operation cost, deviation penalty cost and wind and solar power abandonment cost of the coupled system, a first objective function is constructed to maximize the net income of the coupled system.

[0015] Furthermore, the first objective function is expressed as:

[0016] ;

[0017] in, is the net benefit of the coupled system; , , , , , They are the energy sales revenue of the coupling system in period t, the revenue from interaction with the market, the startup cost, the operation cost, the deviation penalty cost and the cost of wind and solar power abandonment; is the predicted amount of electric energy, heat energy and cold energy during period t; , , is the price of electricity, heat and cooling sold during period t; , is the electricity sold and purchased by the coupling system in the external market during period t; , is the electricity selling price and electricity purchasing price in the external market during period t; , is the heat sold and purchased by the coupling system in the external market during period t; , is the heat selling price and heat purchasing price in the external market during period t; , is the cooling capacity sold and purchased by the coupled system in the external market during period t; , is the selling price and buying price of cold storage in the external market during period t; is the single start-stop cost of the heat pump system; , is the start and stop status of the heat pump system in period t and period t-1; is the photovoltaic output during period t; The heating equipment produces heat during period t; The cooling equipment produces cooling during period t; is the unit operation and maintenance cost of photovoltaic panels; The unit operation and maintenance cost of heating equipment; is the unit operation and maintenance cost of the refrigeration equipment; , , is the absolute value of the electric energy deviation, thermal energy deviation and cooling energy deviation during period t; , , are the unit deviation penalty costs for electrical energy, thermal energy, and cooling energy, respectively; , is the amount of abandoned light in period t and the unit abandoned light cost.

[0018] Furthermore, the second objective function is constructed by the following method:

[0019] Obtaining the adjustment cost of the heating equipment based on the adjustment amount of the heating equipment and the unit adjustment cost of the heating equipment;

[0020] The adjustment cost of the refrigeration equipment is obtained based on the adjustment amount of the refrigeration equipment and the unit adjustment cost of the refrigeration equipment;

[0021] Based on the adjustment amount of electricity, heat and cooling energy interacting with the external market and the adjustment cost per unit of electricity, heat and cooling energy, the adjustment cost of interacting with the market is obtained;

[0022] Based on the adjustment costs of heating equipment, cooling equipment and market interaction, a second objective function is constructed to minimize the adjustment costs.

[0023] Furthermore, the second objective function is expressed as:

[0024] ;

[0025] in, is the adjustment cost of the coupled system; , , are the adjustment costs of heating equipment, cooling equipment and interaction with the market during period t; , are the adjustment amounts of heating equipment and cooling equipment during period t respectively; , are the unit adjustment costs for heating equipment and cooling equipment, respectively; , , They are the adjustment of electric energy, thermal energy and cold energy interacting with the external market during period t; , , They are the adjustment costs per unit of electricity, heat and cooling respectively.

[0026] Furthermore, the electric energy correction balance constraint, the thermal energy correction balance constraint and the cold energy correction balance constraint are expressed as:

[0027] ;

[0028] in, Adjust the electric energy consumed by the heating equipment to produce heat for period t; The heat energy consumed by the refrigeration equipment to produce cold at time t; , , are the prediction errors of electric energy, thermal energy and cold energy in period t respectively.

[0029] Furthermore, the net regulation benefit of the coupling system is apportioned among the photovoltaic panels of the distribution network system and the heating equipment and cooling equipment of the heat pump system by the following method, including:

[0030] The Shapley value method is used to calculate the marginal contribution of photovoltaic panels, heating equipment and cooling equipment to the net benefits of coupled system regulation;

[0031] Based on the control degree and cost degree of the photovoltaic panels, heating equipment and cooling equipment, the corresponding marginal contribution values ​​are corrected respectively, and the corrected marginal contribution values ​​corresponding to the photovoltaic panels, heating equipment and cooling equipment are used as the allocation results.

[0032] Furthermore, the control degree and cost degree are respectively expressed as:

[0033] ;

[0034] ;

[0035] in, , , They are the control degrees of photovoltaic panels, heat pump system and absorption chiller respectively; , , are the costs of photovoltaic panels, heat pump systems and absorption chillers respectively; is the photovoltaic output during period t; The heating equipment produces heat during period t; The cooling equipment produces cooling during period t; , are the adjustment amounts of heating equipment and cooling equipment during period t respectively; are the marginal costs of photovoltaic panels, heat pump systems and absorption chillers respectively;

[0036] The apportionment result is expressed as:

[0037] ;

[0038] in, , , are the corrected marginal contributions corresponding to photovoltaic panels, heating equipment and cooling equipment respectively; , , are the marginal contribution values ​​corresponding to photovoltaic panels, heating equipment and cooling equipment based on the Shapley value method, , are the weight values ​​of the control degree and the cost degree respectively; is the net benefit of the coupled system.

[0039] Furthermore, after the preliminary adjusted photovoltaic output, the heat output of the heating equipment and the cooling output of the cooling equipment are finally adjusted based on the apportionment result, it also includes: collecting the heat output of the heating equipment, the cooling output of the cooling equipment, the power consumption of the heating equipment, the heat consumption of the cooling equipment, the market power sales, and the photovoltaic power output to obtain the comprehensive operation energy efficiency of the coupling system and the local consumption rate of renewable energy;

[0040] Calculate the confidence of multiple parameters of the coupled system and the comprehensive operation energy efficiency and local consumption rate of renewable energy based on association rules;

[0041] The corresponding parameters are adjusted based on the confidence level; the parameters include the inlet temperature and water flow of the heat pump condenser, the outlet temperature and water flow of the evaporator, the energy sales price, the unit deviation penalty cost and the unit wind and solar power abandonment cost.

[0042] Furthermore, the electricity, cooling and heating loads are predicted by a pre-trained rolling prediction model for electricity, cooling and heating loads;

[0043] The electric cooling and heating load rolling prediction model is based on a random forest model and is trained by the following method:

[0044] Acquire multiple normalized historical simulation data of the coupling system to construct a sample data set; the historical simulation data includes outdoor ambient temperature, system power supply, system cooling capacity and system heating capacity in multiple time periods on multiple dates;

[0045] The Bootstrap method is used to randomly sample the sample data set, select n sample data, and construct decision tree;

[0046] By using the information gain method, m features are selected from the M features of each decision tree as feature values ​​for node splitting, and each decision tree is split into leaf nodes, resulting in A random forest model consisting of decision trees;

[0047] The predicted values ​​of each decision tree are averaged as the prediction result of the random forest model;

[0048] Based on the operation of the coupling system, the measured data of the three days before the current date are continuously obtained, and the historical simulation data of the earliest corresponding days in the sample data set are replaced by the measured data, and the random forest model is dynamically superimposed and trained to obtain the rolling prediction model of the electric cooling and heating loads.

[0049] Beneficial effects of this technical solution:

[0050] 1. The present invention is based on the goals of maximizing the net benefit of the coupled system, minimizing the adjustment cost and the benefit-sharing incentive control response. By constructing a control method for system equipment operation, internal balance and market participation, the net benefit of the system is improved, the penalty cost of system deviation and the cost of wind and solar power abandonment are reduced, and each subject is encouraged to improve the scale of control response and the accuracy of the response. In addition, data mining is carried out based on comprehensive operation energy efficiency and local consumption rate of renewable energy, providing a basis for the selection of basic operation parameters of the coupled system, scientifically selecting basic operation parameters of the coupled system, and improving the energy utilization efficiency of the coupled system.

[0051] 2. The present invention constructs an intelligent control platform for coupling the distribution network and the heat pump, collects the monitoring point information in real time, and proposes a dynamic prediction method for electric heating and cooling loads that combines historical and measured data. This method can more clearly reveal the characteristics of the building itself and the changes in electric heating and cooling loads, and improve the prediction accuracy.

[0052] Other features and advantages of the present invention will be described in the following description, and part of them will become obvious from the description, or will be understood by practicing the present invention. The purpose and other advantages of the present invention can be realized and obtained by the structures particularly pointed out in the written description, claims, and drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] The accompanying drawings are only used for the purpose of illustrating specific embodiments and are not to be considered as limiting the present invention. In the entire drawings, the same reference symbols represent the same components;

[0054] Figure 1 is a flow chart of an intelligent control method for a distribution network and a heat pump coupling system according to an embodiment of the present invention;

[0055] Figure 2 It is a schematic diagram of the control architecture of the intelligent control method according to an embodiment of the present invention. DETAILED DESCRIPTION

[0056] The preferred embodiments of the present invention are described in detail below in conjunction with the accompanying drawings, wherein the accompanying drawings constitute a part of this application and are used together with the implementation cases of the present invention to illustrate the principles of the present invention, but are not used to limit the scope of the present invention.

[0057] A specific embodiment of the present invention provides an intelligent control method for a power distribution network and a heat pump coupling system, such as Figure 1 As shown, the method comprises the following steps:

[0058] Step S1: Based on the predicted electricity, cooling and heating loads of the coupled system in multiple time periods, a first objective function is constructed with the goal of maximizing net benefits, and the electricity balance constraint, cooling balance constraint and thermal balance constraint are used as constraints to solve the photovoltaic output of the distribution network system in each time period, the heat and cooling production of the heat pump system, and the maximized net benefits of the coupled system;

[0059] Specifically, this embodiment proposes a method for dynamic prediction of electricity, heat and cooling loads by combining simulation data with measured data. The method is based on the random forest algorithm and uses the historical simulation data of the coupled system to make initial predictions of electricity, heat and cooling loads. As the coupled system starts running, the measured data of the electricity, heat and cooling loads of the coupled system gradually increases, and the load data obtained by the measured data gradually replaces the simulation data to form a dynamic sample data set updated in real time. The training of the rolling prediction model of electricity, heat and cooling loads includes:

[0060] Normalize historical simulation data, construct a sample data set, and initialize model parameters; the historical simulation data includes outdoor ambient temperature, system power supply, system cooling capacity, and system heating capacity at multiple time periods on multiple dates;

[0061] The Bootstrap method is used to randomly select n samples with replacement to obtain a sample set, and then Bootstrap sampling, we get Sample sets can be constructed decision tree;

[0062] By using the information gain method, m (m≤M) features are randomly selected from the M features of each decision tree as feature values ​​for node splitting, and the features with the best splitting ability are found; the decision trees are split to leaf nodes without pruning; and the result is A random forest consisting of decision trees is constructed, and the average of the predicted values ​​of each decision tree is taken as the prediction result of the random forest model;

[0063] Based on the operation of the coupling system, the measured data of the three days before the current date are continuously obtained, and the measured data are used to replace the historical simulation data of the earliest corresponding days in the sample data set, and the random forest model is dynamically superimposed and trained to obtain the rolling prediction model of the electric, cold and hot loads. The rolling prediction model of the electric, cold and hot loads is used to predict the prediction results of the electric, cold and hot loads in multiple time periods in a day. In this embodiment, one day is divided into 24 time periods for data collection and electric, cold and hot load prediction, and the prediction sequences are obtained respectively. , , ,in, , , They are the prediction results of electricity, cooling and heating in period t respectively.

[0064] Furthermore, in order to coordinate the operation of the equipment, this embodiment constructs a first-level preliminary control strategy, that is, constructs a first objective function with the goal of maximizing net profit, and sets electrical balance constraints, thermal balance constraints, and cold balance constraints as constraints; specifically, the first objective function is constructed by the following method:

[0065] Based on the predicted electricity, cooling and heating loads and electricity, heating and cooling prices for each period, the energy sales revenue of the coupling system for the corresponding period is obtained;

[0066] Based on the sales volume and sales price of each period, the market interaction benefits of the corresponding period are obtained;

[0067] Based on the energy sales income, market interaction income and the startup cost, operation cost, deviation penalty cost and wind and solar power abandonment cost of the coupled system, a first objective function is constructed to maximize the net income of the coupled system.

[0068] Specifically, the first objective function is expressed as:

[0069] ;

[0070] in, is the net benefit of the coupled system; , , , , , They are the energy sales revenue of the coupling system in period t, the revenue from interaction with the market, the startup cost, the operation cost, the deviation penalty cost and the cost of wind and solar power abandonment; is the predicted amount of electric energy, heat energy and cold energy during period t; , , is the price of electricity, heat and cooling sold during period t; , is the electricity sold and purchased by the coupling system in the external market during period t; , is the electricity selling price and electricity purchasing price in the external market during period t; , is the heat sold and purchased by the coupling system in the external market during period t; , is the heat selling price and heat purchasing price in the external market during period t; , is the cooling capacity sold and purchased by the coupled system in the external market during period t; , is the selling price and buying price of cold storage in the external market during period t; is the single start-stop cost of the heat pump system; , is the start and stop status of the heat pump system in period t and period t-1; is the photovoltaic output during period t; The heating equipment produces heat during period t; The cooling equipment produces cooling during period t; is the unit operation and maintenance cost of photovoltaic panels; The unit operation and maintenance cost of heating equipment; is the unit operation and maintenance cost of the refrigeration equipment; , , is the absolute value of the electric energy deviation, thermal energy deviation and cooling energy deviation during period t; , , are the unit deviation penalty costs for electrical energy, thermal energy, and cooling energy, respectively; , is the amount of abandoned light in period t and the unit abandoned light cost.

[0071] As the constraints of the first-level preliminary control strategy, the electrical balance constraint, thermal balance constraint and cold balance constraint are expressed as:

[0072] ;

[0073] in, is the power consumption of the heat pump system at time t; They are the deviations of electrical energy, thermal energy and cold energy respectively; is the predicted amount of electric energy, heat energy and cold energy during period t; is the heat consumption of the absorption chiller at time t. The power consumption of the heat pump system is related to the efficiency of the heat pump system, which is expressed by the following formula:

[0074] ;

[0075] in, is the heat pump system efficiency; It is the ratio of the actual outlet temperature of the evaporator to the rated outlet temperature of the evaporator; It is the ratio of the actual flow rate of the evaporator to the rated flow rate; It is the ratio of the actual inlet temperature of the condenser to the rated inlet temperature of the condenser; It is the ratio of the actual flow rate of the condenser to the rated flow rate; is the constant term coefficient; , are the linear and quadratic regression coefficients of the evaporator outlet temperature ratio; , are the linear and quadratic regression coefficients of the evaporator flow ratio; , are the linear and quadratic regression coefficients of the condenser inlet temperature ratio; , are the linear and quadratic regression coefficients of the condenser flow ratio.

[0076] This embodiment uses the first-level preliminary control strategy to maximize net profit, regulates the operation of the heating equipment and cooling equipment of the heat pump system, the operation of the photovoltaic panels of the distribution network system, and the interaction strategy between the coupling system and the external market, thereby improving the energy utilization rate of the coupling system.

[0077] Step S2: constructing a second objective function with the goal of minimizing the adjustment cost, taking the electric energy correction balance constraint, the thermal energy correction balance constraint and the cooling energy correction balance constraint as constraint conditions, solving to obtain the electric, cooling and heat adjustment amounts and the minimized adjustment cost of the coupling system in each period; and making preliminary adjustments to the photovoltaic output and the heat and cooling production of the heat pump system based on the adjustment amounts;

[0078] Specifically, in order to balance the adjustment cost, this embodiment takes minimizing the adjustment cost as the goal, constructs a second-level control correction strategy, that is, constructs a second objective function, and sets the electric energy correction balance constraint, the thermal energy correction balance constraint and the cold energy correction balance constraint as constraint conditions; specifically, the second objective function is constructed by the following method:

[0079] Obtaining the adjustment cost of the heating equipment based on the adjustment amount of the heating equipment and the unit adjustment cost of the heating equipment;

[0080] The adjustment cost of the refrigeration equipment is obtained based on the adjustment amount of the refrigeration equipment and the unit adjustment cost of the refrigeration equipment;

[0081] Based on the adjustment amount of electricity, heat and cooling energy interacting with the external market and the adjustment cost per unit of electricity, heat and cooling energy, the adjustment cost of interacting with the market is obtained;

[0082] Based on the adjustment costs of heating equipment, cooling equipment and market interaction, a second objective function is constructed to minimize the adjustment costs.

[0083] Specifically, the second objective function is expressed as:

[0084] ;

[0085] in, is the adjustment cost of the coupled system; , , are the adjustment costs of heating equipment, cooling equipment and interaction with the market during period t; , are the adjustment amounts of heating equipment and cooling equipment during period t respectively; , are the unit adjustment costs for heating equipment and cooling equipment, respectively; , , They are the adjustment of electric energy, thermal energy and cold energy interacting with the external market during period t; , , They are the adjustment costs per unit of electricity, heat and cooling respectively.

[0086] As the constraint conditions of the second objective function, the electric energy correction balance constraint, the thermal energy correction balance constraint and the cold energy correction balance constraint are expressed as:

[0087] ;

[0088] in, Adjust the electric energy consumed by the heating equipment to produce heat for period t; The heat energy consumed by the refrigeration equipment to produce cold at time t; , , are the prediction errors of electric energy, thermal energy and cold energy in period t respectively.

[0089] This embodiment adopts the second-level control correction strategy with the goal of minimizing the adjustment cost. By adjusting the heat production of the heating equipment of the heat pump system, the cooling production of the refrigeration equipment, and the external market interaction, it compensates for the system control error caused by the electricity, cooling, and heat prediction errors. While reducing the control cost, it improves the system energy utilization rate and further improves the net benefit of the coupling system.

[0090] Step S3: Based on the maximization of net benefit and minimization of adjustment cost, the net benefit of regulation of the coupling system in the corresponding period is obtained, and the net benefit is allocated among the photovoltaic panels of the distribution network system and the heating equipment and cooling equipment of the heat pump system; and based on the allocation result, the preliminary adjusted photovoltaic output, the heat production of the heating equipment and the cooling production of the cooling equipment are finally adjusted.

[0091] Specifically, in order to stimulate the economy of regulation of each subject in the coupled system, this embodiment constructs a third-level incentive regulation response strategy, that is, an incentive mechanism of the improved Shapley value method considering multi-dimensional factors is adopted to apportion the net benefit of system regulation among the three subjects of photovoltaic panels, heating equipment of the heat pump system and cooling equipment.

[0092] First, based on the maximization of net benefit and minimization of adjustment cost, the regulation net benefit of the coupling system in the corresponding period is obtained, which is expressed as:

[0093] ;

[0094] in, is the net benefit of regulation of the coupled system.

[0095] Furthermore, the net benefits of system regulation are shared among the photovoltaic panels, the heating equipment of the heat pump system, and the cooling equipment.

[0096] For the Shapley value method, the set of participants is:

[0097] ;

[0098] For the Alliance The marginal contribution value of the kth participant is expressed by the following formula, which is the traditional Shapley value:

[0099] ;

[0100] in, is the Shapley value of the kth participant, ; Among them, pv represents photovoltaic panels, hb represents heating equipment, and xs represents cooling equipment; is the weighted probability; For sub-alliance Contains the benefits of participant k; For sub-alliance The benefits of participant k are not included; the traditional Shapley values ​​of photovoltaic panels, heating equipment of heat pump system, and cooling equipment are expressed as , , .

[0101] The Shapley value method also needs to satisfy that the benefits of any cooperative alliance are greater than the benefits of no alliance, and the benefits of an alliance without any participants are 0. The following formula is used to express the constraints that the Shapley value method needs to satisfy:

[0102] ;

[0103] in, and Alliance and of revenue, and ; m is the number of sub-alliances.

[0104] Furthermore, the control degree and cost degree are introduced to modify the traditional Shapley value, so as to encourage the coupling subject to respond to the coupling system control in a timely and accurate manner. The greater the control degree, the higher the subject's response degree and the higher the benefit sharing value, and vice versa; the greater the cost degree, the higher the coupling system control cost, which means the lower the economic efficiency of controlling the subject and the lower the benefit sharing value. The control degree and cost degree of each subject are expressed by the following formula:

[0105] ;

[0106] ;

[0107] in, , , They are the control degrees of photovoltaic panels, heat pump system and absorption chiller respectively; , , are the costs of photovoltaic panels, heat pump systems and absorption chillers respectively; is the photovoltaic output during period t; The heating equipment produces heat during period t; The cooling equipment produces cooling during period t; , are the adjustment amounts of heating equipment and cooling equipment during period t respectively; is the marginal cost of photovoltaic panels, heat pump system and absorption chiller;

[0108] The apportionment result is expressed as:

[0109] ;

[0110] in, , , are the corrected marginal contributions corresponding to photovoltaic panels, heating equipment and cooling equipment respectively; , , are the marginal contribution values ​​corresponding to photovoltaic panels, heating equipment and cooling equipment based on the Shapley value method, , are the weight values ​​of the control degree and the cost degree respectively; is the net benefit of the coupled system.

[0111] In particular, after the preliminary adjusted photovoltaic output, the heat output of the heating equipment and the cooling output of the cooling equipment are finally adjusted based on the apportionment results, this embodiment also constructs a distribution network and heat pump coupling data mining model, specifically including: collecting the heat output of the heating equipment, the cooling output of the cooling equipment, the power consumption of the heating equipment, the heat consumption of the cooling equipment, the market electricity sales, and the photovoltaic power generation, and obtaining the comprehensive operation energy efficiency of the coupling system and the local consumption rate of renewable energy;

[0112] Calculate the confidence of multiple parameters of the coupled system and the comprehensive operation energy efficiency and local consumption rate of renewable energy based on association rules;

[0113] Adjust corresponding parameters based on the confidence level; the parameters include the inlet temperature and water flow rate of the heat pump condenser, the outlet temperature and water flow rate of the evaporator, the energy selling price, the unit deviation penalty cost and the unit wind and solar power abandonment cost;

[0114] That is, based on the three-level control results, this embodiment further uses front-end intelligent instruments to collect heat production of heat pump units, cooling capacity of absorption chillers, power consumption of heat pump units, heat consumption of absorption chillers, market power sales, and photovoltaic power production, and collects the data to the computer end, and applies software to perform data mining to analyze the comprehensive operation energy efficiency of the coupling system and the local consumption rate of renewable energy. Specifically, the comprehensive operation energy efficiency of the coupling system and the local consumption rate of renewable energy are expressed by the following formula:

[0115] ;

[0116] in, , They are the comprehensive operation energy efficiency of the coupled system and the local consumption rate of renewable energy; is the power consumption of the heat pump system at time t; is the heat consumption of the absorption refrigerator at time t.

[0117] Furthermore, association rules are used to explore the relationship between different heat pump parameter settings and the coupled system operating energy efficiency and renewable energy local consumption rate, thereby providing a basis for the reasonable setting of parameters, including the ratio of the actual evaporator outlet temperature to the rated evaporator outlet temperature. , Ratio of actual evaporator flow to rated flow ; Ratio of actual condenser inlet temperature to rated condenser inlet temperature ; Ratio of actual condenser flow to rated flow , energy sales price, unit deviation penalty cost and unit wind and solar power abandonment cost, etc.

[0118] Specifically, the following formula is used to express the confidence level of different parameters, operating energy efficiency and local consumption rate of renewable energy:

[0119] ;

[0120] ;

[0121] in, For parameter settings; The intensity of certainty associated with the comprehensive operational energy efficiency of the coupled system for parameter setting; The support level associated with the comprehensive operational energy efficiency of the coupled system for parameter setting; The support set for the parameter; Setting the intensity of certainty associated with the local consumption rate of renewable energy for the parameter; In order to establish the support degree associated with the local consumption rate of renewable energy through parameter settings, this embodiment calculates the confidence degree of the operating energy efficiency and the local consumption rate of renewable energy for different settings of parameters such as the inlet temperature and water flow rate of the heat pump condenser, the outlet temperature and water flow rate of the evaporator, the energy sales price, the unit deviation penalty cost, and the unit wind and solar power abandonment cost.

[0122] Finally, according to the results of association rule mining, the inlet temperature and water flow of the heat pump condenser, the outlet temperature and water flow of the evaporator, the energy sales price, the unit deviation penalty cost and the unit wind and solar power abandonment cost are reasonably adjusted. Through the reasonable configuration of parameters, the coordinated operation capability and system benefits of the system are further improved.

[0123] The intelligent control method of the power distribution network and heat pump coupling system of the present invention can be realized through an intelligent control platform. Based on the real-time monitoring and collection of the operating parameters of the power distribution network and heat pump coupling system, data storage and statistical analysis, intelligent control and other functional requirements, this embodiment constructs an intelligent control platform for the power distribution network and heat pump coupling system, and realizes the intelligent control of the power distribution network and heat pump coupling system. The intelligent control platform can be composed of a perception control layer, a network transmission layer and an application management layer. The perception control layer is the bottom "input-output" interface for constructing the application of the power distribution network and heat pump coupling system, which includes four functions: perception, identification, control and execution. Perception is to use various software and hardware to collect data on characteristics such as equipment attributes, equipment status and behavior, such as using temperature sensors to collect outdoor ambient temperature, evaporator water outlet temperature, and condenser inlet temperature, using pressure sensors to collect evaporator water flow and condenser water flow, and using electric energy meters, heat energy meters and cold energy meters to collect system power supply, system cooling capacity, system heating capacity, different components cumulative energy production, system cumulative energy production, different components energy consumption and other data. Identification is to establish a corresponding relationship between data and equipment to clarify the object represented by the data. Control is to convert the expected goals into specific control signals and instructions. Execution is to change the operating state according to the control signals and instructions. The operating state includes changes in equipment status, personnel, specific operation procedures and organizational forms. The network transmission layer provides a communication channel for information exchange between the application management layer and the perception control layer. It can be transmitted using RS-485 bus, M-Bus bus, optical fiber, IP, private network, etc. The application management layer is the application management center of the entire system, responsible for information collection, system control optimization, data mining and other tasks of the entire system.

[0124] In summary, the intelligent control method of the power distribution network and heat pump coupling system of the present invention builds an intelligent control platform and control scheme, monitors the operation parameters of the coupling system in real time, and predicts the electric cooling and heating loads of the system in a rolling manner, and builds a three-level control strategy, such as Figure 2 As shown in the figure, it includes the first-level preliminary control strategy, the second-level control correction strategy and the third-level incentive control response strategy, which realizes the three-level coordination of system equipment operation, internal balance and market participation, and promotes the relative optimization of economy, efficiency and environmental protection; and by exploring the correlation between the comprehensive energy efficiency of the coupled system, the local consumption rate of renewable energy and the parameter setting, it lays a theoretical foundation for the scientific and reasonable setting of parameters, and greatly improves the energy utilization rate of the coupled system.

[0125] Those skilled in the art will appreciate that all or part of the processes of the above-mentioned embodiments can be implemented by instructing related hardware through a computer program, and the program can be stored in a computer-readable storage medium, wherein the computer-readable storage medium is a disk, an optical disk, a read-only storage memory, or a random access memory, etc.

[0126] The above description is only a preferred specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any changes or substitutions that can be easily conceived by any technician familiar with the technical field within the technical scope disclosed by the present invention should be covered within the protection scope of the present invention.

Claims

1. An intelligent control method for a distribution network and a heat pump coupling system, characterized in that: include: Based on the predicted electricity, cooling and heating loads of the coupled system in multiple time periods, a first objective function is constructed with the goal of maximizing net profit, and the electricity balance constraint, cooling balance constraint and heat balance constraint are used as constraints to solve the photovoltaic output of the distribution network system in each time period, the heat and cooling production of the heat pump system and the maximized net profit of the coupled system; the first objective function is constructed by the following method: based on the predicted electricity, cooling and heating loads and electricity, heat and cooling prices of each time period, the energy sales revenue of the coupled system in the corresponding time period is obtained; Based on the energy sales and energy sales price of each period, the market interaction income of the corresponding period is obtained; based on the energy sales income, the market interaction income and the startup cost, operation cost, deviation penalty cost and wind and solar abandonment cost of the coupling system, a first objective function with the goal of maximizing the net income of the coupling system is constructed; the first objective function is expressed as: ； in, is the net benefit of the coupled system; , , , , , They are the energy sales revenue of the coupling system in period t, the revenue from interaction with the market, the startup cost, the operation cost, the deviation penalty cost and the cost of wind and solar power abandonment; , , is the predicted amount of electric energy, heat energy and cold energy during period t; , , is the price of electricity, heat and cooling sold during period t; , is the electricity sold and purchased by the coupling system in the external market during period t; , is the electricity selling price and electricity purchasing price in the external market during period t; , is the heat sold and purchased by the coupling system in the external market during period t; , is the heat selling price and heat purchasing price in the external market during period t; , is the cooling capacity sold and purchased by the coupled system in the external market during period t; , is the selling price and buying price of cold storage in the external market during period t; is the single start-stop cost of the heat pump system; , is the start and stop status of the heat pump system in period t and period t-1; is the photovoltaic output during period t; The heating equipment produces heat during period t; The cooling equipment produces cooling during period t; is the unit operation and maintenance cost of photovoltaic panels; The unit operation and maintenance cost of heating equipment; is the unit operation and maintenance cost of the refrigeration equipment; , , is the absolute value of the electric energy deviation, thermal energy deviation and cooling energy deviation during period t; , , are the unit deviation penalty costs for electrical energy, thermal energy, and cooling energy, respectively; , is the amount of abandoned light and the unit abandoned light cost in period t; The second objective function is constructed with the goal of minimizing the adjustment cost, and the electric energy correction balance constraint, the thermal energy correction balance constraint and the cooling energy correction balance constraint are used as constraints to solve the electric, cooling and heat adjustment amounts and the minimized adjustment cost of the coupling system in each period; and the photovoltaic output and the heat production and cooling production of the heat pump system are preliminarily adjusted based on the adjustment amount; the second objective function is constructed by the following method: the adjustment cost of the heating equipment is obtained based on the adjustment amount of the heating equipment and the unit adjustment cost of the heating equipment; the adjustment cost of the cooling equipment is obtained based on the adjustment amount of the cooling equipment and the unit adjustment cost of the cooling equipment; the adjustment cost of the interaction with the market is obtained based on the electric energy, thermal energy, cooling energy adjustment amount and the unit electric energy, thermal energy and cooling energy adjustment cost interacting with the external market; the second objective function with the goal of minimizing the adjustment cost is constructed based on the heating equipment, cooling equipment and the adjustment cost of interacting with the market; the second objective function is expressed as: ； in, is the adjustment cost of the coupled system; , , are the adjustment costs of heating equipment, cooling equipment and interaction with the market during period t; , are the adjustment amounts of heating equipment and cooling equipment during period t respectively; , are the unit adjustment costs for heating equipment and cooling equipment, respectively; , , They are the adjustment of electric energy, thermal energy and cold energy interacting with the external market during period t; , , They are the adjustment costs per unit of electrical energy, heat energy and cooling energy respectively; Based on the maximization of net benefit and minimization of adjustment cost, the net benefit of regulation of the coupling system in the corresponding period is obtained, and is allocated among the photovoltaic panels of the distribution network system and the heating equipment and cooling equipment of the heat pump system; and based on the allocation result, the preliminary adjusted photovoltaic output, the heat production of the heating equipment and the cooling production of the cooling equipment are finally adjusted.

2. The intelligent control method of the power distribution network and heat pump coupling system according to claim 1 is characterized in that: The electric energy correction balance constraint, the thermal energy correction balance constraint and the cold energy correction balance constraint are expressed as: ； in, Adjust the electric energy consumed by the heating equipment to produce heat for period t; The heat energy consumed by the refrigeration equipment to produce cold at time t; , , are the prediction errors of electric energy, thermal energy and cold energy in period t respectively.

3. The intelligent control method of the power distribution network and heat pump coupling system according to claim 1 is characterized in that: The net benefits of the coupled system regulation are apportioned among the photovoltaic panels of the distribution network system and the heating and cooling equipment of the heat pump system through the following methods, including: The Shapley value method is used to calculate the marginal contribution of photovoltaic panels, heating equipment and cooling equipment to the net benefits of coupled system regulation; Based on the control degree and cost degree of the photovoltaic panels, heating equipment and cooling equipment, the corresponding marginal contribution values ​​are corrected respectively, and the corrected marginal contribution values ​​corresponding to the photovoltaic panels, heating equipment and cooling equipment are used as the allocation results.

4. The intelligent control method of the power distribution network and heat pump coupling system according to claim 3 is characterized in that: The control degree and cost degree are respectively expressed as: ； ； in, , , They are the control degrees of photovoltaic panels, heat pump system and absorption chiller respectively; , , are the costs of photovoltaic panels, heat pump systems and absorption chillers respectively; is the photovoltaic output during period t; The heating equipment produces heat during period t; The cooling equipment produces cooling during period t; , are the adjustment amounts of heating equipment and cooling equipment during period t respectively; , , is the marginal cost of photovoltaic panels, heat pump system and absorption chiller; The apportionment result is expressed as: ； in, , , are the corrected marginal contributions corresponding to photovoltaic panels, heating equipment and cooling equipment respectively; , , are the marginal contribution values ​​corresponding to photovoltaic panels, heating equipment and cooling equipment based on the Shapley value method, , are the weight values ​​of the control degree and the cost degree respectively; is the net benefit of the coupled system.

5. The intelligent control method of the power distribution network and heat pump coupling system according to claim 1 is characterized in that: After the preliminary adjusted photovoltaic output, the heat output of the heating equipment and the cooling output of the cooling equipment are finally adjusted based on the apportionment results, it also includes: collecting the heat output of the heating equipment, the cooling output of the cooling equipment, the power consumption of the heating equipment, the heat consumption of the cooling equipment, the market power sales, and the photovoltaic power output to obtain the comprehensive operating energy efficiency of the coupling system and the local consumption rate of renewable energy; Calculate the confidence of multiple parameters of the coupled system and the comprehensive operation energy efficiency and local consumption rate of renewable energy based on association rules; The corresponding parameters are adjusted based on the confidence level; the parameters include the inlet temperature and water flow of the heat pump condenser, the outlet temperature and water flow of the evaporator, the energy sales price, the unit deviation penalty cost and the unit wind and solar power abandonment cost.

6. The intelligent control method of the power distribution network and heat pump coupling system according to claim 1, characterized in that: The electricity, cooling and heating loads are predicted by a pre-trained rolling prediction model for electricity, cooling and heating loads; The electric cooling and heating load rolling prediction model is based on a random forest model and is trained by the following method: Acquire multiple normalized historical simulation data of the coupling system to construct a sample data set; the historical simulation data includes outdoor ambient temperature, system power supply, system cooling capacity and system heating capacity in multiple time periods on multiple dates; The Bootstrap method is used to randomly sample the sample data set, select n sample data, and construct decision tree; By using the information gain method, m features are selected from the M features of each decision tree as feature values ​​for node splitting, and each decision tree is split into leaf nodes, resulting in A random forest model consisting of decision trees; The predicted values ​​of each decision tree are averaged as the prediction result of the random forest model; Based on the operation of the coupling system, the measured data of the three days before the current date are continuously obtained, and the historical simulation data of the earliest corresponding days in the sample data set are replaced by the measured data, and the random forest model is dynamically superimposed and trained to obtain the rolling prediction model of the electric cooling and heating loads.

Images