Scheduling method of water-wind-light complementary power generation system based on knowledge graph structure

Abstract

The invention provides a scheduling method of a water-wind-light complementary power generation system based on a knowledge graph structure, and belongs to the technical field of hybrid energy scheduling. According to the method, a scheduling rule structure of the water-wind-light complementary power generation system is designed based on an object-time period-situation-decision knowledge graph, an optimizable variable set in a knowledge graph rule is extracted, a knowledge graph scheduling rule optimization model of the water-wind-light complementary power generation system is established, and solving is completed; and proposing a graph chain reasoning method for obtaining a decision result based on the current scheduling situation, and obtaining a scheduling scheme calculated by the water-wind-light complementary power generation system according to the knowledge graph rule. Compared with a rule in a traditional scheduling function form, the knowledge graph scheduling rule has the advantages that the generating capacity is higher, the satisfaction degree of the power grid load is higher, meanwhile, the knowledge graph scheduling rule can process the multi-target scheduling requirement, and the knowledge graph scheduling rule has the advantages of being good in intuition, high in interpretability, flexible, easy to expand and the like; the method is of great significance to operation and decision-making of the water-wind-light complementary power generation system.

Description

Technical Field

[0001] The present invention belongs to the technical field of hybrid energy system scheduling, and more specifically, relates to a scheduling method for a water-wind-solar complementary power generation system based on a knowledge graph structure. Background Art

[0002] Currently, the existing technologies commonly used in the water-wind-solar complementary power generation system scheduling industry are as follows:

[0003] Hybrid energy system scheduling is a technology that considers the combined operation of multiple energy subsystems such as hydropower, wind power, or photovoltaic power generation. The water-wind-solar complementary power generation system is one of the most important typical hybrid systems in current hybrid energy system scheduling. The water-wind-solar complementary power generation system has strong randomness, volatility, and uncertainty, which increases the difficulty of obtaining a scheduling scheme for the water-wind-solar complementary power generation system. Scheduling rules for the water-wind-solar complementary power generation system are required to assist scheduling decision-makers in formulating scheduling schemes. The scheduling rules for the water-wind-solar complementary power generation system are of great significance for the operation and decision-making of the water-wind-solar complementary power generation system.

[0004] Against the background of the increasingly scarce reserves of non-renewable energy and the gradually serious damage to the natural environment, developing clean and renewable energy such as hydropower, wind power, and photovoltaic power and studying the scheduling strategies for the complementary operation of the three have become an important direction in the field of water resources and energy in China. The wind and light resources are unevenly distributed in space and unstable in time, showing strong randomness, volatility, and intermittency, making it difficult for independent wind and light subsystems to continuously output stable electricity, which restricts the power grid's ability to absorb wind and light energy. The rapid regulation ability and strong storage performance of hydropower energy can effectively alleviate the adverse effects brought by the output fluctuations of intermittent energy to the power system. At the same time, there is a certain degree of complementarity between hydropower output and wind power and photovoltaic power output at different time scales within a year and within a day. Utilizing the strong regulation advantage of hydropower and the complementary characteristics of its output with wind power and photovoltaic power, packaging and jointly operating the outputs of the three subsystems can effectively solve the problem of the absorption of concentrated grid-connected wind power and photovoltaic power. The water-wind-solar multi-energy complementary system is simultaneously affected by the multiple uncertainties of the three subsystems. The uncertainty of water-wind-solar forecasting will bring chain uncertainties to the combined scheduling of the complementary system, and the scheduling uncertainty will bring chain uncertainties to the operation decision-making, exacerbating the unstable risk of suppressing output fluctuations and regulation. Assisting decision-making through scheduling rules in uncertain scheduling scenarios is an urgent practical problem to be solved for the combined operation of the water-wind-solar multi-energy complementary system under uncertain conditions.

[0005] Problems existing in the prior art are:

[0006] The deterministic optimal scheduling of the water-wind-solar multi-energy complementary system has risks in guiding operation during real-time scheduling because it does not consider the uncertainties of forecasts such as runoff, wind speed, and solar radiation intensity. There are usually two ways to study the uncertainty scheduling rules: rule extraction and rule optimization. The former has a too long sample preparation time and there is a problem of dimension superposition in the extraction of multi-objective scheduling rules. The form of the scheduling chart in the rule optimization research is single and the rules that can be expressed are limited, and the operability of the rules for the multi-factor combination conditions of the water-wind-solar complementary system is not strong. The rules in the form of scheduling functions have limited application scenarios due to their poor intuitiveness. Therefore, how to design an intuitive and highly adaptable form of scheduling rules and optimize the multi-objective scheduling rules for the operation of the water-wind-solar complementary system under uncertain scheduling scenarios is an urgent problem to be solved. Summary of the Invention

[0007] In view of the above defects or improvement requirements of the prior art, the present invention provides a scheduling method for a water-wind-solar complementary power generation system based on a knowledge graph structure. By adopting the present invention, intuitive and highly adaptable multi-objective scheduling rules for the water-wind-solar complementary power generation system can be obtained.

[0008] To achieve the above technical features, the object of the present invention is achieved as follows: A scheduling method for a water-wind-solar complementary power generation system based on a knowledge graph structure. The scheduling method first designs a scheduling rule structure for the water-wind-solar complementary power generation system based on the "object-time-situation-decision" knowledge graph; then extracts the variable set that can be optimized in the knowledge graph rules, establishes an optimization model for the knowledge graph scheduling rules of the water-wind-solar complementary power generation system, and completes the solution; finally, based on the current scheduling situation, a graph chain reasoning method for obtaining the decision result is used to obtain the scheduling scheme calculated by the water-wind-solar complementary power generation system according to the knowledge graph rules.

[0009] Preferably, the scheduling method specifically includes the following steps:

[0010] S1, collect the basic attribute data, scheduling characteristic curve data, hydrology, and output data of the wind and solar power stations of each power station in the water-wind-solar complementary power generation system;

[0011] S2, design a scheduling rule structure for the water-wind-solar complementary power generation system based on the "object-time-situation-decision" knowledge graph, and clarify the entities, attributes, and relationships in the knowledge graph scheduling rules;

[0012] S3, extract the variable set that can be optimized from the knowledge graph scheduling rules as the decision variables of the scheduling rule optimization model;

[0013] S4. With the goal of maximizing power generation and achieving the highest degree of matching between output and load, construct the constraint conditions for the three subsystems of hydropower, wind power, and photovoltaic power generation, establish an optimization model for the scheduling rules of the knowledge graph of the hybrid hydropower, wind power, and photovoltaic power generation system, and complete the solution based on the multi-objective evolutionary algorithm;

[0014] S5. After the scheduling rules of the knowledge graph of the hybrid hydropower, wind power, and photovoltaic power generation system are optimized, propose a graph chain reasoning method for obtaining decision results based on the current scheduling situation;

[0015] S6. Based on the knowledge graph rules and the graph chain reasoning method, obtain the scheduling plan of the hybrid hydropower, wind power, and photovoltaic power generation system calculated according to the knowledge graph rules.

[0016] Preferably, the "object - time period - situation - decision" knowledge graph scheduling rule structure in S2 is specifically as follows:

[0017] (1) The scheduling object graph establishes the relationship between the calculation object entities of hydropower, wind power, and photovoltaic power through hydraulic topology connection, multi-site proximity relationship, and hybrid hydropower, wind power, and photovoltaic relationship, and assigns its characteristic values, characteristic curves, and scheduling constraint attributes to each calculation entity; there are M w , M s , M h wind power stations, photovoltaic power stations, and hydropower stations in the hybrid hydropower, wind power, and photovoltaic power generation system, then there are M w , M s , M h wind power station entities, photovoltaic power station entities, and hydropower station entities in the scheduling object graph;

[0018] (2) The scheduling time period graph mainly establishes the time period connection relationship for each scheduling time period entity, and clarifies the time period index, start time of the time period, end time of the time period, time scale, and total number of scheduling time periods attributes; there are T time periods in the entire scheduling calculation time period, then from 0 to (T - 1) are all scheduling time period graph entities, where time period 0 is the start time period entity, time period (T - 1) is the end time period entity, and there is an "immediate following" relationship between time period t and time period t + 1;

[0019] (3) The scheduling situation graph establishes the facing time period situation entity from three aspects of meteorology, water regime, and engineering situation, uses the incoming flow, reservoir head, wind speed or wind power output, solar radiation intensity value or photovoltaic power output in the facing time period as the situation attributes, and considers the combination relationship of each scheduling situation and the closed-loop relationship formed by all situations;

[0020] The scheduling situation graph has multiple condition types: incoming flow Qi, wind power and photovoltaic power generation output sum Nn, wind power output Nw, photovoltaic power output Ns, upstream water level Zu. The scheduling situation graph is one or more of the above condition types, and M types of conditions are taken as the scheduling situation graph. Each type of condition is divided into C MIf there are situation combinations, assuming that the first type of condition takes the type of incoming flow Qi, and in its possible value range it is divided into C1 segments, then the first group of condition nodes is There are a total of C1 scheduling situation nodes. For M types of conditions, there are scheduling situation nodes. The relationship between the first group of scheduling situation nodes and the time period nodes is "linked", the relationship between the same type of scheduling situation nodes is "closed-loop", and the relationship between different types of scheduling situation nodes is "combined";

[0021] (4) The scheduling decision graph completes the water, wind, and light scheduling decision for the facing time period based on the scheduling object graph, scheduling time period graph, and scheduling situation graph. It takes various decision results as entities, the water level at the end of the time period, the reservoir outflow during the time period, or the decision value of the hydropower output during the time period as attributes, and the satisfaction relationship between the situation conditions and the decision results as the relationship; the scheduling decision graph also has multiple types: outflow Qo, upstream water level Zu. Among them, the scheduling decision graph can only take 1 type as the decision variable, and each scheduling situation combination corresponds to a scheduling decision node. For M c situation combinations, there are a total of M c scheduling decision nodes. If the outflow is used as the scheduling decision variable type, then the scheduling decision nodes are

[0022] Preferably, in S3, the specific variable set that can be optimized extracted from the scheduling rules of the knowledge graph is:

[0023] The scheduling object graph and the scheduling time period graph can be completed and are determined after the scheduling requirements are determined, that is, there are no variables that still need to be optimized;

[0024] After the scheduling requirements are determined, the scheduling situation graph and the scheduling decision graph can only determine the structure, but the specific condition values corresponding to each scheduling situation entity and the decision values corresponding to each scheduling decision entity cannot be determined, and these variables need to be optimized and determined; for the t-th time period, assuming that M types of conditions are used as the scheduling situation graph, each type of condition can be divided into C M condition segments. Considering that the condition segments have a start and an end, then C M +1 variables of the scheduling situation to be optimized will be generated. For M types of conditions, a total of variables of the scheduling situation to be optimized will be generated, that is: M types of conditions will generate scheduling situation combinations, and each scheduling situation combination corresponds to a scheduling decision variable, that is, there are variables of the scheduling decision to be optimized: In the t-th time period, a total of A variable to be optimized, which will be generated in a total of T scheduling periods variables to be optimized.

[0025] Preferably, in S4, the objectives, constraints, and solution methods of the knowledge graph scheduling rule optimization model for the water-wind-solar complementary power generation system are specifically as follows:

[0026] (1) Scheduling objective:

[0027] 1) Objective 1, maximum power generation:

[0028]

[0029] In the formula, E(N) is the total power generation of the water-wind-solar complementary power generation system; N t is the output of the water-wind-solar complementary power generation system in the t-th period; T and Δt represent the total number of scheduling periods and the duration of a single scheduling period; N w,i,t , N s,j,t and N h,k,t represent the outputs of the i-th wind power station, the j-th photovoltaic power station, and the k-th hydropower station in the t-th period respectively; M w , M s , M h represent the numbers of wind power stations, photovoltaic power stations, and hydropower stations in the water-wind-solar complementary power generation system;

[0030] 2) Objective 2, highest degree of matching between output and load:

[0031]

[0032] In the formula, is the degree of matching between output and load; P t is the power load in the t-th period;

[0033] (2) Scheduling constraints:

[0034] 1) Reservoir water level constraint:

[0035]

[0036] In the formula, Zu i,t is the upstream water level of the i-th reservoir in the t-th period, and are its upper and lower limits under flood control constraints;

[0037] 2) Reservoir discharge constraint:

[0038]

[0039] In the formula, Qo i,tis the outflow of the i-th reservoir in the t-th period, and are its corresponding upper and lower bound constraints; the outflow Qo i,t is composed of the power generation flow Qg i,t and the spill flow Qa i,t ; the power generation flow Qg i,t shall not exceed the full-load flow

[0040] 3) Hydropower output constraint:

[0041]

[0042] In the formula, Nh i,t is the output of the i-th reservoir in the t-th period, and are its corresponding upper and lower bound constraints; the hydropower output is also constrained by the predicted output curve and the NHQ curve;

[0043] 4) Water balance equation:

[0044] V i,t+1 = V i,t + (Qi i,t - Qo i,t - Ev i,t )·Δt; (8)

[0045] In the formula: V i,t and V i,t+1 respectively represent the reservoir capacities of the i-th reservoir at the beginning and end of the t-th period; Qi i,t and Qo i,t are the corresponding inflow and outflow, and Ev i,t represents the evaporation water loss;

[0046] 5) Hydraulic connection between cascade hydropower stations:

[0047]

[0048] In the formula, Qitv i,t is the inter-basin flow of the upper reach of the i-th reservoir; is the flow when the upstream station flow reaches the i-th reservoir through river routing; Φ i is the set of upstream stations hydraulically connected to the i-th reservoir, is an element of Φ i ; represents the river routing model, specifically the Muskingum model or the lag routing model.

[0049] 6) Wind power constraint:

[0050]

[0051] wherein, v j,t is the wind speed of the j-th wind power station in the t-th time period, and are the cut-in and cut-out wind speeds; Nw j,t is the output of the j-th wind power station in the t-th time period, which cannot exceed the installed capacity of the corresponding wind power station

[0052] 7) Photovoltaic power generation constraint:

[0053]

[0054] wherein, Ns k,t and respectively represent the output and installed capacity of the k-th photovoltaic power generation station;

[0055] 8) Transmission channel capacity constraint:

[0056]

[0057] wherein, N g,t and respectively represent the packaged output and transmission channel capacity of the g-th water-wind-solar multi-energy complementary system;

[0058] (3) Solution method:

[0059] The knowledge graph scheduling rule optimization model of the water-wind-solar complementary power generation system is a multi-objective optimization problem. Based on this, any multi-objective evolutionary algorithm is used for solution.

[0060] Preferably, in the S5, the graph chain reasoning method for obtaining the decision result based on the current scheduling situation is specifically:

[0061] The chain reasoning is completed in five steps:

[0062] S5.1, Screen out the hydropower, wind power, and photovoltaic power objects participating in the current scheduling calculation according to the scheduling object graph, and determine the complementary scheduling relationship;

[0063] S5.2, Screen out the facing scheduling time period t from the scheduling time period graph;

[0064] S5.3, First, based on the wind power and photovoltaic power scheduling graph objects in step S5.1 and the facing time period in step S5.2, calculate and infer the sum of the wind power and photovoltaic power outputs in the time period, and then based on the hydropower scheduling graph object in step S5.1 and the facing time period in step S5.2, obtain the initial water level on the dam in the time period;

[0065] S5.4. Based on the inference of two-dimensional variables in the scheduling situation graph in step S5.3, the decision value of the hydropower output for the time period under this scheduling situation combination is obtained based on the inference of the scheduling decision graph.

[0066] S5.5. Assign the inference result in step S5.4 to the hydropower scheduling object, and based on the water balance equation and the hydropower output calculation formula, obtain the scheduling process of the reservoir water level and the reservoir outflow flow at the end of the time period.

[0067] Repeat the above five steps S5.1 - S5.5 from the start scheduling time period to the end scheduling time period to complete the scheduling decision for the entire scheduling period operating according to the rules of the water-wind-solar complementary system knowledge graph.

[0068] Preferably, on the other hand, the present invention provides a computer program for the scheduling method of a water-wind-solar complementary power generation system based on a knowledge graph, and the computer program for the scheduling method of a water-wind-solar complementary power generation system based on a knowledge graph is used to implement the scheduling method of a water-wind-solar complementary power generation system based on a knowledge graph.

[0069] Preferably, on the other hand, the present invention provides a terminal, and the terminal is at least equipped with a controller for implementing the scheduling method of a water-wind-solar complementary power generation system based on a knowledge graph.

[0070] Preferably, on the other hand, the present invention provides a computer-readable storage medium, including instructions, which when running on a computer, cause the computer to execute the scheduling method of a water-wind-solar complementary power generation system based on a knowledge graph.

[0071] Preferably, on the other hand, the present invention provides a control system for the scheduling method of a water-wind-solar complementary power generation system based on a knowledge graph, and the control system is used to implement the scheduling method of a water-wind-solar complementary power generation system based on a knowledge graph as claimed.

[0072] Preferably, on the other hand, the present invention provides a scheduling device for a water-wind-solar complementary power generation system equipped with the control system for the scheduling method of a water-wind-solar complementary power generation system based on a knowledge graph.

[0073] The present invention has the following beneficial effects:

[0074] 1. The present invention uses the rule structure of the knowledge graph to complete the optimization of the scheduling rules of the water-wind-solar complementary power generation system. This rule does not limit the rule form, has the advantages of being intuitive and clear, has strong practicability and applicability, and can be used to obtain multi-objective scheduling rules, and can guide dispatchers to make scheduling plans for the water-wind-solar complementary power generation system.

[0075] 2. The present invention uses the knowledge graph structure as the form of the scheduling rule, which has strong scalability. When the scheduling object changes or the scheduling period is extended, only the scheduling rules corresponding to the changed scheduling object and the added scheduling period need to be expanded. The previously optimized scheduling rules can be retained and continued to be used, instead of completely changing the scheduling rules for the entire object and the entire period, saving the adjustment cost brought about by the change of scheduling requirements. BRIEF DESCRIPTION OF THE DRAWINGS

[0076] The present invention will be further described below with reference to the drawings and embodiments.

[0077] Figure 1 It is a flowchart of a scheduling rule for a water-wind-solar complementary power generation system based on a knowledge graph provided by an embodiment of the present invention.

[0078] Figure 2 It is a schematic diagram of a knowledge graph scheduling rule provided by an embodiment of the present invention.

[0079] Figure 3 It is a schematic diagram of variables to be optimized provided by an embodiment of the present invention.

[0080] Figure 4 Schematic diagram of a chain reasoning method for a knowledge graph scheduling rule provided by an embodiment of the present invention.

[0081] Figure 5 Non-dominated front of a multi-objective scheduling rule provided by an embodiment of the present invention.

[0082] Figure 6 Objective values for comparison with traditional scheduling function form rules provided by an embodiment of the present invention.

[0083] Figure 7 Scheduling process calculated by the scheduling rule provided by an embodiment of the present invention.

[0084] Figure 8 Stacked output diagram calculated by the scheduling rule provided by an embodiment of the present invention.

[0085] Figure 9 Knowledge graph scheduling rule provided by an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0086] The present invention will be further described in detail below with reference to the embodiments of the drawings. The examples of the embodiments are shown in the drawings, where the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the drawings are exemplary and are intended to explain the present invention and should not be construed as limiting the present invention.

[0087] Embodiment 1:

[0088] Please refer toFigures 1-9 Based on the "object - time period - situation - decision" knowledge graph, the present invention designs the scheduling rule structure of the hybrid hydro - wind - solar power generation system, extracts the variable set that can be optimized in the knowledge graph rules, establishes and solves the optimization model of the scheduling rules of the hybrid hydro - wind - solar power generation system knowledge graph, proposes a graph - chain reasoning method to obtain the decision result based on the current scheduling situation, and obtains the scheduling scheme of the hybrid hydro - wind - solar power generation system calculated according to the knowledge graph rules.

[0089] Appendix Figure 1 The following figure shows the flow chart of the scheduling rules of the hybrid hydro - wind - solar power generation system based on the knowledge graph, which specifically includes the following steps:

[0090] S1. Collect the basic attribute data, scheduling characteristic curve data, hydrological data, and the output data of the hydro, wind, and photovoltaic power stations of the hybrid hydro - wind - solar power generation system;

[0091] S2. Design the scheduling rule structure of the hybrid hydro - wind - solar power generation system based on the "object - time period - situation - decision" knowledge graph, and clarify the entities, attributes, and relationships in the knowledge graph scheduling rules; the schematic diagram of the knowledge graph scheduling rules is as shown in Appendix Figure 2 as follows.

[0092] (1) The scheduling object graph establishes the relationships between the calculation object entities of hydropower, wind power, and photovoltaic power through hydraulic topological connections, multi - site proximity relationships, and hybrid hydro - wind - solar complementary relationships, and assigns its characteristic values, characteristic curves, and scheduling constraint attributes to each calculation entity; in the hybrid hydro - wind - solar power generation system, there are M w , M s , M h wind power stations, photovoltaic power stations, and hydropower stations respectively. Then, there are M w , M s , M h wind power station entities, photovoltaic power station entities, and hydropower station entities in the scheduling object graph;

[0093] (2) The scheduling time - period graph mainly establishes the time - period connection relationships for each scheduling time - period entity, and clarifies the attributes of time - period index, start time of the time - period, end time of the time - period, time scale, and total number of scheduling time - periods; there are T time - periods in the entire scheduling calculation time - period. Then, all entities from 0 to (T - 1) are the scheduling time - period graph entities. Among them, time - period 0 is the start - time - period entity, time - period (T - 1) is the end - time - period entity, and there is an "immediate following" relationship between time - period t and time - period t + 1;

[0094] (3) The scheduling situation graph establishes the situation entities faced in the time - period from three aspects of meteorology, water regime, and engineering situation, uses the inflow rate, water level above the dam, wind speed (or wind power output), and solar radiation intensity value (or photovoltaic power output) in the time - period faced as situation attributes, and considers the combination relationship of each scheduling situation and the closed - loop relationship formed by all situations (without omission and redundancy);

[0095] The dispatching situation graph has multiple condition types: the incoming flow Qi, the combined output of wind power and photovoltaic power Nn, the wind power output Nw, the photovoltaic power output Ns, and the upstream water level Zu. The dispatching situation graph is one or more of the above condition types. Take M types of conditions as the dispatching situation graph, and each type of condition is divided into C M condition segments, then the dispatching situation has combinations of situations. Suppose the first type of condition type takes the incoming flow Qi type, and it is divided into C1 segments within its possible value range , then the first group of condition nodes is a total of C1 dispatching situation nodes. There are dispatching situation nodes in total for M types of conditions. There is a "link" relationship between the first group of dispatching situation nodes and the time period nodes, a "closed-loop" relationship between the same type of dispatching situation nodes, and a "combination" relationship between different types of dispatching situation nodes;

[0096] (4) The dispatching decision graph completes the water-wind-solar dispatching decision for the facing time period based on the dispatching object graph, the dispatching time period graph, and the dispatching situation graph. It takes various decision results as entities, the water level at the end of the time period, the reservoir outflow during the time period, or the decision value of the hydropower output during the time period as attributes, and the satisfaction relationship between the situation conditions and the decision results as the relationship; the dispatching decision graph also has multiple types: the outflow Qo, the upstream water level Zu. Among them, however, the dispatching decision graph can only take 1 type as the decision variable. Each combination of dispatching situation corresponds to a dispatching decision node, and there are M c dispatching decision nodes in total for M c combinations of situations. If the outflow is taken as the dispatching decision variable type, then the dispatching decision node is

[0097] The detailed "object-time period-situation-decision" knowledge graph rules in terms of entities, attributes, and relationships are shown in the following table.

[0098] Table 1: Structural Explanation Table of "Object-Time Period-Situation-Decision" Knowledge Graph Rules

[0099]

[0100] S3. Extract the variable set that can be optimized from the knowledge graph dispatching rules as the decision variables of the dispatching rule optimization model, as shown in the appendix Figure 3 .

[0101] The two graphs, the dispatching object graph and the dispatching time period graph, can be completed after the dispatching requirements are determined, and they are determined, that is, there are no variables that still need to be optimized;

[0102] After the scheduling situation graph and the scheduling decision graph are determined in structure only after the scheduling requirements are determined, the conditional values corresponding to each scheduling situation entity and the decision values corresponding to each scheduling decision entity cannot be determined yet. These variables need to be optimized and determined. For the t-th time period, assuming that M types of conditions are used as the scheduling situation graph, each type of condition can be divided into C M condition segments. Considering that there is a start and an end for the condition segments, there will be C M +1 scheduling situation variables to be optimized. For M types of conditions, there will be a total of scheduling situation variables to be optimized, that is: M types of conditions will result in scheduling situation combination cases, and each scheduling situation combination corresponds to a scheduling decision variable, that is, there are scheduling decision variables to be optimized: In the t-th time period, a total of variables to be optimized will be generated. In total, for T scheduling time periods, variables to be optimized will be generated.

[0103] S4. With the goal of maximizing the power generation and the highest degree of matching between the output and the load, construct the constraint conditions for the three subsystems of hydropower, wind power, and photovoltaic power generation, establish a knowledge graph scheduling rule optimization model for the water-wind-solar complementary power generation system, and complete the solution based on the multi-objective evolutionary algorithm;

[0104] (1) Scheduling objectives:

[0105] 1) Objective 1, maximizing power generation:

[0106]

[0107] In the formula, E(N) is the total power generation of the water-wind-solar complementary power generation system; N t is the output of the water-wind-solar complementary power generation system in the t-th time period; T and Δt represent the total number of scheduling time periods and the duration of a single scheduling time period; N w,i,t , N s,j,t and N h,k,t represent the outputs of the i-th wind power station, the j-th photovoltaic power station, and the k-th hydropower station in the t-th time period respectively; M w , M s , M h represent the numbers of wind power stations, photovoltaic power stations, and hydropower stations in the water-wind-solar complementary power generation system;

[0108] 2) Objective 2, the highest degree of matching between the output and the load:

[0109]

[0110] In the formula, is the matching degree between output and load; P t is the power load in the t-th period;

[0111] (2) Scheduling constraints:

[0112] 1) Reservoir water level constraint:

[0113]

[0114] In the formula, Zu i,t is the upstream water level of the i-th reservoir in the t-th period, and are its upper and lower limits under flood control constraints;

[0115] 2) Reservoir discharge flow constraint:

[0116]

[0117] In the formula, Qo i,t is the discharge flow of the i-th reservoir in the t-th period, and are its corresponding upper and lower limit constraints; the discharge flow Qo i,t consists of the power generation flow Qg i,t and the spill flow Qa i,t ; the power generation flow Qg i,t shall not exceed the full-load flow

[0118] 3) Hydropower output constraint:

[0119]

[0120] In the formula, Nh i,t is the output of the i-th reservoir in the t-th period, and are its corresponding upper and lower limit constraints; the hydropower output is also constrained by the predicted output curve and the NHQ curve;

[0121] 4) Water balance equation:

[0122] V i,t+1 = V i,t + (Qi i,t - Qo i,t - Ev i,t )·Δt; (8)

[0123] In the formula: V i,t and V i,t+1 respectively represent the reservoir capacities of the i-th reservoir at the beginning and end of the t-th period; Qi i,t and Qo i,t are the corresponding inflow and outflow discharges, Evi,t Represents the evaporative water loss;

[0124] 5) Hydraulic connection between cascade hydropower stations:

[0125]

[0126] In the formula, Qitv i,t is the inter-basin flow of the upper reach of the i-th reservoir; is the flow at the upstream station when the flow reaches the i-th reservoir through river routing; Φ i is the set of upstream stations hydraulically connected to the i-th reservoir, is an element of Φ i ; represents the river routing model, specifically the Muskingum model or the lag routing model.

[0127] 6) Wind power constraint:

[0128]

[0129] In the formula, v j,t is the wind speed of the j-th wind power station at the t-th time period, and are the cut-in and cut-out wind speeds; Nw j,t is the output of the j-th wind power station at the t-th time period, which cannot exceed the installed capacity of the corresponding wind power station

[0130] 7) Photovoltaic power generation constraint:

[0131]

[0132] In the formula, Ns k,t and respectively represent the output and installed capacity of the k-th photovoltaic power generation station;

[0133] 8) Transmission channel capacity constraint:

[0134]

[0135] In the formula, N g,t and respectively represent the packaged output and transmission channel capacity of the g-th water-wind-solar multi-energy complementary system;

[0136] (3) Solution method:

[0137] The scheduling rule optimization model of the water-wind-solar complementary power generation system knowledge graph is a multi-objective optimization problem. Based on this, any multi-objective evolutionary algorithm is used for solution.

[0138] Preferably, in this embodiment, a multi-objective evolutionary algorithm is specifically used for solving.

[0139] S5. After the scheduling rules of the water-wind-solar complementary power generation system knowledge graph are optimized, a graph chain reasoning method for obtaining decision results based on the current scheduling situation is proposed, as shown in the appendix Figure 4 as follows.

[0140] The chain reasoning is completed in five steps:

[0141] S5.1. Screen out the hydropower, wind power, and photovoltaic objects participating in this scheduling calculation according to the scheduling object graph, and determine the complementary scheduling relationship;

[0142] S5.2. Screen out the facing scheduling period t from the scheduling period graph;

[0143] S5.3. First, calculate and infer the sum of the wind power and photovoltaic power outputs in the period based on the wind power and photovoltaic scheduling graph objects in step S5.1 and the facing period in step S5.2. Then, obtain the water level above the dam at the beginning of the period based on the hydropower scheduling graph object in step S5.1 and the facing period in step S5.2;

[0144] S5.4. Based on the inference of the two-dimensional variables in the scheduling situation graph in step S5.3, infer the decision value of the hydropower output in the period under this scheduling situation combination based on the scheduling decision graph;

[0145] S5.5. Assign the inference result in step S5.4 to the hydropower scheduling object, and obtain the scheduling process of the water level above the dam at the end of the period and the reservoir discharge flow of the reservoir based on the water balance equation and the hydropower output calculation formula;

[0146] Repeat the above five steps of S5.1 to S5.5 from the start scheduling period to the end scheduling period to complete the scheduling decision for the entire scheduling period to operate according to the rules of the water-wind-solar complementary system knowledge graph.

[0147] S6. Based on the knowledge graph rules and the graph chain reasoning method, obtain the scheduling plan calculated by the water-wind-solar complementary power generation system according to the knowledge graph rules.

[0148] Embodiment 2:

[0149] The application of the present invention will be further described below in combination with specific experiments.

[0150] The present invention takes the preliminary test and demonstration base of wind, light and water in the Yalong River Basin as the object. There are 4 wind power stations (Wodi, Dahe, Asa, Baiwu), 1 photovoltaic power station (Zhalashan), and 1 hydropower station (Guandi) in this area. For the convenience of description, Wodi, Dahe, Asa, Baiwu, Zhalashan, and Guandi are represented by the symbols W1, W2, W3, W4, S1, and H1 respectively. The installed capacities of W1, W2, W3, W4, S1, and H1 are 91.5 MW, 60 MW, 80 MW, 99 MW, 700 MW, and 2400 MW respectively. The dead water level of H1 is 1328 meters, the normal storage level is 1330 meters, and the reservoir capacity is 760 million cubic meters. The embodiments are completed using the data on July 1, 2010.

[0151] In the knowledge graph of the dispatching object of this example, there are 4 wind power station entities, 1 photovoltaic power station entity, and 1 hydropower station entity. The dispatching requirement is to obtain the dispatching rules for 24 hours within a day, so there are 24 entities in the knowledge graph of the dispatching period. Taking the inflow (Qi) of H1, the outputs of wind power (W1, W2, W3, W4) and photovoltaic power generation (S1) and their sum (Nn) as two condition types of the dispatching situation, the two types of conditions are respectively divided into 4 and 3 condition segments. Taking the outflow (Qo) of H1 as the variable of the dispatching decision graph.

[0152] The result analysis of the embodiments completed using the model proposed by the present invention is as follows:

[0153] (a) Analysis of the non-dominated front of the multi-objective dispatching rules:

[0154] The non-dominated front of the multi-objective dispatching rule optimization model in this embodiment (the scatter plot formed by the objective values of each solution generated by the multi-objective dispatching model) is as Figure 5 shown. Each scatter point represents the objective value of a solution, and each solution corresponds to a dispatching rule with a different objective balance point. Dispatching rule 1 represents the dispatching rule with the highest degree of matching between output and load, dispatching rule 50 represents the dispatching rule with the highest power generation, and rule 25 represents the dispatching rule with the most balanced two objective values. It can be seen from the figure that the two objectives have an obvious inverse relationship, that is, as the power generation increases, the matching degree between output and load decreases.

[0155] (b) Comparison with the traditional dispatching function form rules:

[0156] In order to verify the effectiveness of the knowledge graph rules proposed by the present invention, the dispatching objectives of the knowledge graph rules are compared with the dispatching objectives of the traditional dispatching function rules, as Figure 6 shown. The dispatching function rule takes the inflow as the independent variable (condition) and the outflow as the dependent variable (decision). Considering that there is no ready-made dispatching function rule for the object of this embodiment, and considering the fairness of the comparison, the dispatching function rule is also optimized using the power generation dispatching objective of this study. The scheduling function rule for the 4th period under the maximum power generation target; The scheduling function rule for the 4th period under the highest matching degree between output and load. The scheduling function form rules for other periods are similar, only with different specific values. It can be found from the figure that the power generation of the knowledge graph scheduling rule is 60.89×10 6 kWh, higher than the power generation of the traditional scheduling function rule: 60.71×10 6 kWh. The matching degree between the output and the load of the former: 0.95 is also higher than that of the latter: 0.943, verifying the effectiveness of the knowledge graph rule proposed by the present invention.

[0157] (c) Scheduling process calculated by the scheduling rule:

[0158] The scheduling process calculated by the scheduling rule is as Figure 7 shown, and the following can be analyzed from the figure:

[0159] (1) From the 3rd period to the 8th period, the water level process of Rule 1 is the lowest among the three scheduling processes, indicating that the water head of Rule 1 is the lowest among the three scheduling processes, and the power generation of Rule 1 is also the lowest. This exactly makes the output of Rule 1 more consistent with the load; a similar phenomenon can be observed from the 12th period to the 14th period. This is the reason why the matching degree of Rule 1 is the highest but the power generation is the smallest.

[0160] (2) From the 3rd period to the 8th period, the water level process of Rule 50 is the highest, and the water head is also the highest, indicating that the power generation is also the highest, but the excessive output exceeds the power load. This is the reason why the power generation of Rule 50 is the highest but the matching degree is the lowest.

[0161] (3) The water level process of Rule 25 is between the water level processes of Rule 1 and Rule 50, with neither too much power generation nor too low a matching degree, and it is an operating rule with relatively balanced targets.

[0162] The above result analysis is consistent with the theoretical understanding, indicating the correctness of the knowledge graph scheduling rule of the present invention.

[0163] (d) Output stacking diagram calculated by the scheduling rule:

[0164] The output stacking diagram calculated by the scheduling rule is as Figure 8 shown, and the following can be analyzed from the figure:

[0165] (1) During the night period (especially from 19:00 to 24:00), the wind power generation is greater than that during the day (especially from 7:00 to 13:00). The photovoltaic power generation is mainly reflected during the day (especially from 8:00 to 19:00), showing a certain natural complementarity. However, relying solely on natural complementarity is far from enough. The output of the hydropower station is adjusted through its own regulation ability and operates in complementarity with the wind power station and the photovoltaic power station, so as to make the total output as close as possible to the power load.

[0166] (2) Rule 1, Rule 25, and Rule 50 are operation rules for different requirements. Rule 1 focuses on the matching degree, so its output is the closest to compliance. Rule 50 focuses on power generation, so its total output is higher than the load most of the time. Rule 25 is a compromise between the two, so its scheduling process is also a compromise between the two.

[0167] The above result analysis is consistent with the theoretical understanding, indicating the correctness of the knowledge graph scheduling rules of the present invention.

[0168] (e) Knowledge graph scheduling rules:

[0169] (1) In the knowledge graph of scheduling objects, 6 power station entities are constructed and relevant attributes for scheduling calculation are set. There is an "adjacent" relationship among the four wind farms (Wodi, Dahe, Asa, and Baiwu). There is a "complementary" relationship between Guandi Hydropower Station, Zhalashan Photovoltaic Power Station, and the four wind power stations.

[0170] (2) In the knowledge graph of scheduling periods, a total of 24 period entities are constructed. The ID of each entity is its number. Period entity 1 and period entity 24 respectively have the attributes of "start" and "end". The time step attribute of each entity is "1 hour", and the relationship between adjacent nodes is "immediately following".

[0171] (3) In the knowledge graph of scheduling situations and decisions, the conditional nodes "Qi" and "Nn" are associated with the time period nodes by a "link" relationship. There is a "combination" relationship between the conditional nodes "Qi" and "Nn". Further expanding the knowledge graph of conditions and decisions, the "Qi" condition is divided into 4 segments, and in each segment, the "Nn" condition is divided into 3 segments, generating a total of 12 scheduling decision combination scenarios. The type of each decision entity is "Qo". The relationship between the decision node and the situation node is a "satisfy" relationship.

[0172] Example 3:

[0173] In this embodiment, a computer program for a scheduling method of a water-wind-solar hybrid power generation system based on a knowledge graph is provided. The computer program for the scheduling method of the water-wind-solar hybrid power generation system based on a knowledge graph is used for the scheduling method of the water-wind-solar hybrid power generation system based on a knowledge graph. By adopting the above computer program, the method of the present invention can be implemented through the computer program. Furthermore, the method of the present invention can be further used for actual scheduling.

[0174] Embodiment 4:

[0175] In this embodiment, a terminal is provided. The terminal is at least equipped with a controller for implementing any one of the scheduling methods of the water-wind-solar hybrid power generation system based on a knowledge graph. This controller can be used to implement the entire scheduling method of the present invention.

[0176] Embodiment 5:

[0177] In this embodiment, a computer-readable storage medium is provided, including instructions. When it runs on a computer, it enables the computer to execute the scheduling method of a water-wind-solar hybrid power generation system based on a knowledge graph. Furthermore, the portability of the application of this method is ensured.

[0178] Embodiment 6:

[0179] In this embodiment, a control system for a scheduling method of a water-wind-solar hybrid power generation system based on a knowledge graph is provided. The control system is characterized in that it is used to implement the scheduling method of the water-wind-solar hybrid power generation system based on a knowledge graph.

[0180] Embodiment 7:

[0181] A water-wind-solar hybrid power generation system scheduling device equipped with a control system for the scheduling method of the water-wind-solar hybrid power generation system based on a knowledge graph. Through the scheduling device, the flexibility of use can be enhanced.

[0182] Although the embodiments of the present invention have been shown and described, those skilled in the art can understand that various changes, modifications, substitutions, and deformations can be made to these embodiments without departing from the principles and purposes of the present invention. The scope of the present invention is defined by the claims and their equivalents.

Claims

1. A scheduling method for a water-wind-solar hybrid power generation system based on a knowledge graph structure, characterized in that, The described scheduling method, first, designs the scheduling rule structure of the hydro-wind-solar complementary power generation system based on the "object-time period-situation-decision" knowledge graph; then, extracts the variable set that can be optimized in the knowledge graph rules, establishes the optimization model of the scheduling rules of the hydro-wind-solar complementary power generation system, and completes the solution; finally, obtains the scheduling scheme calculated by the hydro-wind-solar complementary power generation system according to the knowledge graph rules through the graph chain reasoning method for the decision result based on the current scheduling situation.

2. The scheduling method of a water-wind-solar complementary power generation system based on the knowledge graph structure according to claim 1, characterized in that Specifically, the described scheduling method includes the following steps: S1, collect the basic attribute data, scheduling characteristic curve data, hydrology, and wind and solar power plant output data of each power station in the hydro-wind-solar complementary power generation system; S2, design the scheduling rule structure of the hydro-wind-solar complementary power generation system based on the "object-time period-situation-decision" knowledge graph, and clarify the entities, attributes, and relationships in the knowledge graph scheduling rules; S3, extract the variable set that can be optimized from the knowledge graph scheduling rules as the decision variables of the scheduling rule optimization model; S4, taking the maximum power generation and the highest matching degree between the output and the load as the goals, construct the constraint conditions of the three subsystems of hydropower, wind power, and photovoltaic power generation, establish the optimization model of the scheduling rules of the hydro-wind-solar complementary power generation system based on the knowledge graph, and complete the solution based on the multi-objective evolutionary algorithm; S5, after the optimization of the scheduling rules of the hydro-wind-solar complementary power generation system based on the knowledge graph is completed, propose the graph chain reasoning method for the decision result based on the current scheduling situation; S6, based on the knowledge graph rules and the graph chain reasoning method, obtain the scheduling scheme calculated by the hydro-wind-solar complementary power generation system according to the knowledge graph rules.

3. The scheduling method of a water-wind-solar complementary power generation system based on a knowledge graph structure according to claim 2, wherein The "object-time period-situation-decision" knowledge graph scheduling rule structure in S2 is specifically as follows: (1) The scheduling object graph establishes the relationship between the calculation object entities of hydropower, wind power, and photovoltaic power through the hydraulic topology connection, multi-site proximity relationship, and hydro-wind-solar complementary relationship, and assigns its characteristic values, characteristic curves, and scheduling constraint attributes to each calculation entity; There are M wind power stations, photovoltaic power stations, and hydropower stations respectively in the water-wind-solar complementary power generation system. Then, there are M w , M s , M h wind power station entities, photovoltaic power station entities, and hydropower station entities in the dispatching object spectrum; w , M s , M h photovoltaic power station entities, and hydropower station entities; (2) The scheduling time period graph mainly establishes the time period connection relationship for each scheduling time period entity, and clarifies the time period index, start time of the time period, end time of the time period, time scale, and total number of scheduling time periods attributes; If there are T time periods in the entire scheduling calculation time period, then from 0 to (T - 1) are all scheduling time period graph entities, where time period 0 is the start time period entity, time period (T - 1) is the end time period entity, and there is an "immediate" relationship between time period t and time period t + 1; (3) The scheduling situation graph establishes the situation entity faced in the time period from three aspects of meteorology, water situation, and engineering situation, uses the inflow rate, water level above the dam, wind speed or wind power output, solar radiation intensity value or photovoltaic power output in the faced time period as the situation attributes, and considers the combination relationship of each scheduling situation and the closed-loop relationship formed by all situations; The dispatching situation graph has multiple condition types: the incoming flow Qi, the combined output of wind power and photovoltaic power generation Nn, the wind power output Nw, the photovoltaic power output Ns, and the upstream water level Zu. The dispatching situation graph is one or more of the above condition types. Take M types of conditions as the dispatching situation graph, and each type of condition is divided into C M condition segments, then the dispatching situation has dispatching situation combinations. Assume that the first type of condition type is the incoming flow Qi type, and it is divided into C1 segments within its possible value range . Then the first group of condition nodes is a total of C1 dispatching situation nodes. There are dispatching situation nodes in total for M types of conditions. There is a "link" relationship between the first group of dispatching situation nodes and the time period nodes, a "closed-loop" relationship between the same type of dispatching situation nodes, and a "combination" relationship between different types of dispatching situation nodes; (4) The dispatching decision-making graph completes the water-wind-solar dispatching decision-making for the facing period based on the dispatching object graph, dispatching time period graph, and dispatching situation graph. It takes various decision-making results as entities, the water level at the end of the period, the reservoir outflow during the period, or the decision-making value of hydropower output during the period as attributes, and the satisfaction relationship between the situation conditions and the decision-making results as the relationship; the dispatching decision-making graph also has multiple types: the outflow discharge Qo, the upstream water level Zu. Among them, the dispatching decision-making graph can only take 1 type as the decision variable, and each combination of dispatching situation corresponds to a dispatching decision node, M c There are M c dispatching decision nodes for the combination of situations. If the outflow discharge is used as the type of dispatching decision variable, the dispatching decision node is 4. The scheduling method of a water-wind-solar hybrid power generation system based on a knowledge graph structure according to claim 3, characterized in that, In S3, specifically extracting the variable set that can be optimized from the knowledge graph scheduling rules is as follows: The two graphs of the scheduling object graph and the scheduling time period graph can be completed after the scheduling requirements are determined, and they are determined, that is, there are no variables that still need to be optimized; After the scheduling situation graph and the scheduling decision graph are determined in structure after the scheduling requirements are determined, the conditional values corresponding to each scheduling situation entity and the decision values corresponding to each scheduling decision entity cannot be determined yet, and these variables need to be optimized and determined; for the t-th period, assume that M types of conditions are used as the scheduling situation graph, and each type of condition can be divided into C M condition segments. Considering that the condition segments have a start and an end, C M +1 scheduling situation variables to be optimized will be generated. A total of scheduling situation variables to be optimized will be generated for M types of conditions, that is: M types of conditions will generate scheduling situation combination cases, and each scheduling situation combination corresponds to a scheduling decision variable, that is, there are scheduling decision variables to be optimized: In the t-th period, a total of variables to be optimized will be generated. A total of variables to be optimized will be generated for a total of T scheduling periods.

5. The scheduling method of a water-wind-solar complementary power generation system based on a knowledge graph structure according to claim 4, wherein In S4, the goals, constraints, and solution methods of the optimization model of the scheduling rules of the hydro-wind-solar complementary power generation system based on the knowledge graph are specifically as follows: (1) Scheduling objective: 1) Objective 1, maximum power generation: Where E(N) is the total power generation of the hybrid hydro-wind-solar power generation system; N t is the output of the hybrid hydro-wind-solar power generation system at the t-th time period; T and Δt represent the total number of scheduling time periods and the duration of a single scheduling time period; N w,i,t 、N s,j,t and N h,k,t Respectively represent the output of the i-th wind power station, the j-th photovoltaic power station, and the k-th hydropower station in the t-th period; M w 、M s 、M h Represents the number of wind power stations, photovoltaic power stations and hydropower stations in the water-wind-solar complementary power generation system; 2) Objective 2, highest degree of matching between output and load: In the formula, is the matching degree of output and load; P t is the power load at the t-th time period; (2) Scheduling constraints: 1) Reservoir water level constraint: where $Z_{u}$ i,t is the upstream water level of the $i$-th reservoir in the $t$-th period, and are its upper and lower limits under flood control constraints; 2) Reservoir discharge flow constraint: where, Qo i,t is the outflow of the i-th reservoir in the t-th period, and are its corresponding upper and lower bound constraints; the outflow Qo i,t is composed of the power generation flow Qg i,t and the spill flow Qa i,t ; the power generation flow Qg i,t shall not exceed the full-load flow 3) Hydropower output constraint: where, Nh i,t is the output of the i-th reservoir in the t-th period, and are its corresponding upper and lower bound constraints; the hydropower output is also constrained by the pre-outage curve and the NHQ curve; 4) Water balance equation: V i,t+1 = V i,t + (Qi i,t - Qo i,t - Ev i,t )·Δt; (8) Where: V i,t and V i,t+1 represent the reservoir capacities of the i-th reservoir at the beginning and end of the t-th period respectively; Qi i,t and Qo i,t are the corresponding inflow and outflow discharges, and Ev i,t represents the evaporation water loss; 5) Hydraulic connection between cascade hydropower stations: Where, Qitv i,t is the lateral flow of the upper reach of the i-th reservoir; is the flow of the upstream station when the flow reaches the i-th reservoir through river routing; Φ i is the set of upstream stations hydraulically connected to the i-th reservoir, is an element of Φ i ; represents the river routing model, specifically the Muskingum model or the lag routing model. 6) Wind power constraint: where, v j,t is the wind speed of the j-th wind power station at the t-th time period, and are the cut-in and cut-out wind speeds; Nw j,t is the output of the j-th wind power station at the t-th time period, which cannot exceed the installed capacity of the corresponding wind power station 7) Photovoltaic power generation constraint: where Ns k,t and represent the output and installed capacity of the k-th photovoltaic power station, respectively; 8) Transmission channel capacity constraint: where N g,t and represent the packaged output and transmission channel capacity of the gth group of water-wind-solar multi-energy complementary systems, respectively; (3) Solution method: The scheduling rule optimization model of the water-wind-solar complementary power generation system knowledge graph is a multi-objective optimization problem. Based on this, any multi-objective evolutionary algorithm is used for solution.

6. The scheduling method of a water-wind-solar hybrid power generation system based on a knowledge graph structure according to claim 2, characterized in that, In S5, the specific graph chain reasoning method for obtaining the decision result based on the current scheduling situation is as follows: The chain reasoning is completed in five steps: S5.1, Screen out the hydropower, wind power, and photovoltaic power objects participating in this scheduling calculation from the scheduling object graph, and determine the complementary scheduling relationship; S5.2, Screen out the facing scheduling period t from the scheduling period graph; S5.3, First, calculate and infer the sum of wind power and photovoltaic power output in the period based on the wind power and photovoltaic power scheduling graph objects in step S5.1 and the facing period in step S5.2, and then obtain the initial dam upstream water level in the period based on the hydropower scheduling graph objects in step S5.1 and the facing period in step S5.2; S5.4, Based on the inference of the two-dimensional variables in the scheduling situation graph in step S5.3, infer the decision value of the hydropower output in the period under this scheduling situation combination based on the scheduling decision graph; S5.5, Assign the inference result in step S5.4 to the hydropower scheduling object, and obtain the scheduling process of the dam upstream reservoir and the reservoir discharge flow at the end of the period based on the water balance equation and the hydropower output calculation formula; Repeat the above five steps of S5.1 - S5.5 from the start scheduling period to the end scheduling period to complete the scheduling decision for the entire scheduling period to operate according to the rules of the water-wind-solar complementary system knowledge graph.

7. A computer program for a dispatching method of a water-wind-solar complementary power generation system based on a knowledge graph, characterized in that, The computer program of the scheduling method for the water-wind-solar complementary power generation system based on the knowledge graph is used to implement the scheduling method for the water-wind-solar complementary power generation system based on the knowledge graph described in any one of claims 1 - 6.

8. A terminal, characterized in that, The terminal is at least equipped with a controller that implements the scheduling method for the water-wind-solar complementary power generation system based on the knowledge graph described in any one of claims 1 - 6.

9. A computer-readable storage medium, including instructions, when running on a computer, causes the computer to execute a scheduling method for a water-wind-solar complementary power generation system based on the knowledge graph described in any one of claims 1 - 6.

10. A control system for a dispatching method of a water-wind-solar hybrid power generation system based on a knowledge graph, characterized in that, The control system is used to implement the scheduling method for the water-wind-solar complementary power generation system based on the knowledge graph described in any one of claims 1 - 6.

11. A water-wind-solar complementary power generation system scheduling device equipped with the control system of the scheduling method for the water-wind-solar complementary power generation system based on the knowledge graph described in claim 10.

Images