Medium and low voltage distribution network electric energy quality problem treatment method and system considering low voltage flexible interconnection

Abstract

The invention discloses a medium and low voltage power distribution network electric energy quality problem treatment method and system considering low voltage flexible interconnection. The method comprises the following steps: obtaining a target medium voltage power distribution network topological structure, a low voltage AC / DC flexible interconnection power distribution area topological structure, load attributes and adjustable electric energy quality problem treatment equipment; building a middle and low voltage distribution network electric energy quality problem treatment framework considering low voltage flexible interconnection; establishing a Markov decision model based on a middle and low voltage distribution network electric energy quality problem governance architecture considering low voltage flexible interconnection; and solving the Markov decision model in combination with a reinforcement learning algorithm to obtain a medium and low voltage power distribution network equipment scheduling strategy. According to the invention, the scheduling strategy of the medium and low voltage distribution network equipment can be effectively obtained, and the efficiency and accuracy of electric energy quality management are improved. And a guiding effect is achieved for electric energy quality problem treatment of the medium and low voltage distribution network.

Description

Technical Field

[0001] The present invention relates to the technical field of power quality problem management in medium and low voltage distribution networks, and in particular to a method and system for managing power quality problems in medium and low voltage distribution networks taking low voltage flexible interconnection into consideration. Background Art

[0002] With the high proportion of distributed energy represented by photovoltaics connected to medium and low voltage distribution networks, power quality problems in medium and low voltage distribution networks have become frequent and complex, bringing new challenges to the safe, stable and economical operation of medium and low voltage distribution networks.

[0003] In terms of low-voltage distribution networks, distributed photovoltaic output is random, volatile and unpredictable. When it is connected to the low-voltage distribution network, due to the presence of three-phase asymmetric inductive and capacitive loads in the traditional distribution network, the voltage curve and current curve in the distribution network operation curve will change significantly, resulting in the third and fifth harmonics of the voltage curve and current curve exceeding the standard. Harmonics will have a great impact on the stable operation of electrical equipment in the low-voltage distribution network. For example, due to the third harmonic exceeding the standard, it will cause the motor to have difficulty in rotating and the speed will slow down. At the same time, it will cause the insulation performance of the motor to decrease and the noise to increase, which may further cause high voltage and three-phase unbalanced power quality problems in the low-voltage distribution network. In terms of medium-voltage distribution networks, when distributed photovoltaics are connected on a large scale, due to the voltage deviation between the head-end node and the photovoltaic node of the low-voltage distribution station area under its jurisdiction, photovoltaic power may be returned, which will further cause circulating current in the medium-voltage feeder, resulting in increased losses in the medium-voltage distribution line, reduced power transmission capacity of the medium-voltage distribution network, and power overload of the distribution transformer.

[0004] As the application scenarios of power electronics technology in new power systems continue to expand, various new rectifier inverters such as voltage source inverters are constantly being used, allowing low-voltage AC / DC hybrid distribution networks to replace traditional low-voltage AC distribution networks has become an industry development trend. Compared with traditional low-voltage AC distribution networks, low-voltage AC / DC hybrid distribution networks have the advantages of large distribution transformer capacity, small overall network loss, and convenient access to new sources and loads. They can effectively solve the power quality problems of low-voltage distribution networks and photovoltaic power return problems in medium-voltage distribution networks caused by large-scale photovoltaic access. However, there are many types of new sources and loads in low-voltage AC / DC hybrid distribution networks, and the equipment for managing new power quality problems is complicated. The traditional medium and low voltage distribution network equipment scheduling method is no longer suitable for the rapid management of power quality problems in medium and low voltage distribution networks considering low-voltage flexible interconnection due to the increase in calculations, and relevant research is urgently needed.

[0005] In recent years, with the continuous advancement of the integration of artificial intelligence technology and power systems, it has provided good technical support for data processing, data analysis, and dispatch strategy generation for medium and low voltage distribution networks. At the level of low-voltage AC / DC hybrid distribution networks, each intelligent agent interacts with the low-voltage distribution network environment under its jurisdiction, and considers historical equipment dispatch data to achieve distributed power quality problem management in low-voltage AC / DC distribution stations; at the level of medium-voltage distribution networks, the central intelligent agent receives information uploaded by the intelligent agents in the low-voltage substations under its jurisdiction, analyzes the information of all low-voltage substations, checks abnormal low-voltage distribution substations, and realizes centralized management of medium-voltage distribution networks through medium-voltage power quality problem management equipment.

[0006] In summary, how to develop and build a low-voltage AC / DC hybrid distribution network, form a new power system grid structure, replace the traditional low-voltage AC distribution network, and use artificial intelligence technology to achieve rapid management of power quality problems in medium and low voltage distribution networks considering low-voltage flexible interconnection is of great significance to ensuring the safe, stable and economical operation of the new power system. Summary of the invention

[0007] The purpose of this section is to summarize some aspects of embodiments of the present invention and briefly introduce some preferred embodiments. Some simplifications or omissions may be made in this section and the specification abstract and the invention title of this application to avoid blurring the purpose of this section, the specification abstract and the invention title, and such simplifications or omissions cannot be used to limit the scope of the present invention.

[0008] In view of the above existing problems, the present invention is proposed.

[0009] Therefore, the present invention provides a method and system for managing power quality problems in medium and low voltage distribution networks taking into account low voltage flexible interconnection, which can solve the problems mentioned in the background technology.

[0010] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0011] In a first aspect, the present invention provides a method for managing power quality problems in medium and low voltage distribution networks considering low voltage flexible interconnection, comprising:

[0012] Obtain the target medium-voltage distribution network topology and the low-voltage AC / DC flexible interconnected distribution station area topology, load attributes, and adjustable power quality problem management equipment, and build a medium- and low-voltage distribution network power quality problem management architecture that takes into account low-voltage flexible interconnection;

[0013] The power quality problem management framework of the medium and low voltage distribution network considering low voltage flexible interconnection includes a mathematical model for power flow calculation of the medium voltage AC distribution network and a mathematical model for power flow calculation of the low voltage AC / DC hybrid distribution network;

[0014] Establish a Markov decision model based on the governance framework of power quality issues in medium and low voltage distribution networks considering low voltage flexible interconnection;

[0015] The Markov decision model is solved in combination with a reinforcement learning algorithm to obtain a dispatching strategy for medium and low voltage distribution network equipment.

[0016] As a preferred solution of the method for managing power quality problems of medium and low voltage distribution networks considering low voltage flexible interconnection described in the present invention, wherein: the mathematical model for calculating power flow of the medium voltage AC distribution network includes: a first objective function and a first constraint condition,

[0017] The first objective function is related to the total number of nodes where voltage exceeds the limit in the medium voltage distribution network and the total number of nodes where three-phase imbalance occurs in the medium voltage distribution network;

[0018] The first constraint condition includes a first node voltage amplitude constraint, a first three-phase unbalance constraint, and a first equipment constraint.

[0019] As a preferred solution of the method for managing power quality problems of medium and low voltage distribution networks considering low voltage flexible interconnection described in the present invention, wherein: the mathematical model for power flow calculation of the low voltage AC / DC hybrid distribution network includes: a second objective function and a second constraint condition;

[0020] The second objective function is related to the total number of nodes with voltage exceeding the limit in the low-voltage AC distribution substation, the total number of nodes with voltage exceeding the limit in the low-voltage DC distribution substation, and the total number of nodes with three-phase imbalance in the low-voltage AC distribution substation;

[0021] The second constraint condition includes a second node voltage amplitude constraint, a second three-phase unbalance constraint, and a second equipment constraint.

[0022] As a preferred solution of the method for managing power quality problems in medium and low voltage distribution networks considering low voltage flexible interconnection described in the present invention, wherein: the Markov decision model for establishing a power quality problem management architecture for medium and low voltage distribution networks considering low voltage flexible interconnection includes: a state space, an action space, and a reward space;

[0023] The reward in the reward space is the inverse of the sum of the first objective function and the second objective function, and the lower the reward value, the better the strategy for managing power quality problems in medium and low voltage distribution networks.

[0024] As a preferred solution of the method for managing power quality problems of medium and low voltage distribution networks considering low voltage flexible interconnection described in the present invention, wherein: the state space includes: a medium voltage distribution network state space and a low voltage AC / DC distribution network state space;

[0025] The medium voltage distribution network state space includes medium voltage power flow distribution, medium voltage voltage distribution, operation status of medium voltage centralized photovoltaic power station and operation status of medium voltage power quality problem management equipment;

[0026] The low-voltage AC / DC distribution network state space includes low-voltage power flow distribution, low-voltage voltage distribution, low-voltage distributed photovoltaic inverter operating status and low-voltage flexible interconnection device operating status.

[0027] As a preferred solution of the method for managing power quality problems of medium and low voltage distribution networks considering low voltage flexible interconnection described in the present invention, wherein: the action space includes: the action space of the medium voltage distribution network and the action space of the low voltage AC / DC distribution network;

[0028] The medium voltage distribution network action space includes the apparent power injected into the medium voltage distribution network by different devices;

[0029] The low voltage AC / DC distribution network action space includes the apparent power injected into the low voltage AC / DC distribution station area by different devices.

[0030] As a preferred solution of the method for managing power quality problems in medium and low voltage distribution networks considering low voltage flexible interconnection described in the present invention, wherein: the Markov decision model is solved in combination with a reinforcement learning algorithm to obtain a medium and low voltage distribution network equipment scheduling strategy, including: fitting an action value function through a neural network, learning all Q values ​​corresponding to "state-action" in the interaction between a limited number of distribution network states and the distribution network environment, and learning the optimal strategy based on the Bellman optimal equation.

[0031] In a second aspect, the present invention provides a system for managing power quality issues in medium and low voltage distribution networks taking into account low voltage flexible interconnection, comprising:

[0032] The architecture building module is used to obtain the target medium-voltage distribution network topology and the low-voltage AC / DC flexible interconnected distribution station area topology, load attributes, and adjustable power quality problem management equipment, and build a medium- and low-voltage distribution network power quality problem management architecture considering low-voltage flexible interconnection;

[0033] The power quality problem management framework of the medium and low voltage distribution network considering low voltage flexible interconnection includes a mathematical model for power flow calculation of the medium voltage AC distribution network and a mathematical model for power flow calculation of the low voltage AC / DC hybrid distribution network;

[0034] Model building module, used to establish a Markov decision model for the governance architecture of power quality issues in medium and low voltage distribution networks considering low voltage flexible interconnection;

[0035] The model solving module is used to solve the Markov decision model in combination with the reinforcement learning algorithm to obtain the medium and low voltage distribution network equipment scheduling strategy.

[0036] In a third aspect, the present invention provides a computer device, comprising a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of the above-mentioned method when executing the computer program.

[0037] In a fourth aspect, the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program implements the steps of the method described above when executed by a processor.

[0038] Compared with the prior art, the beneficial effects of the present invention are as follows: the present invention proposes a method and system for managing power quality problems in medium and low voltage distribution networks considering low voltage flexible interconnection, obtains the target medium voltage distribution network topology and the low voltage AC / DC flexible interconnected distribution station area topology, load attributes, and adjustable power quality problem management equipment, and builds a medium and low voltage distribution network power quality problem management framework considering low voltage flexible interconnection; the medium and low voltage distribution network power quality problem management framework considering low voltage flexible interconnection includes a medium voltage AC distribution network flow calculation mathematical model and a low voltage AC / DC hybrid distribution network flow calculation mathematical model; establishes a Markov decision model based on the medium and low voltage distribution network power quality problem management framework considering low voltage flexible interconnection; solves the Markov decision model in combination with a reinforcement learning algorithm to obtain a medium and low voltage distribution network equipment scheduling strategy. The present invention can effectively obtain the scheduling strategy of medium and low voltage distribution network equipment and improve the efficiency and accuracy of power quality management. It plays a guiding role in the management of power quality problems in medium and low voltage distribution networks. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative labor. Among them:

[0040] Figure 1 A method flow chart of a method and system for managing power quality problems in medium and low voltage distribution networks taking into account low voltage flexible interconnection provided by an embodiment of the present invention;

[0041] Figure 2 A medium-voltage distribution network topology diagram of a method and system for managing power quality problems in medium- and low-voltage distribution networks taking into account low-voltage flexible interconnection provided by an embodiment of the present invention;

[0042] Figure 3 A low-voltage AC / DC flexible interconnected distribution area topology diagram of a method and system for managing power quality problems in medium- and low-voltage distribution networks taking low-voltage flexible interconnection into consideration, provided in one embodiment of the present invention;

[0043] Figure 4A schematic diagram of a power quality problem management architecture of a medium- and low-voltage distribution network considering low-voltage flexible interconnection, provided by an embodiment of the present invention, and a method and system for managing power quality problems of a medium- and low-voltage distribution network considering low-voltage flexible interconnection;

[0044] Figure 5 An internal structural diagram of a computer device of a method and system for managing power quality issues in medium and low voltage distribution networks taking into account low voltage flexible interconnection, provided as an embodiment of the present invention. DETAILED DESCRIPTION

[0045] In order to make the above-mentioned purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in the art without creative work should fall within the scope of protection of the present invention.

[0046] Example 1

[0047] Reference Figure 1-Figure 5 , which is the first embodiment of the present invention, and provides a method and system for managing power quality problems in medium and low voltage distribution networks considering low voltage flexible interconnection, including:

[0048] In terms of low-voltage distribution networks, distributed photovoltaic output is random, volatile and unpredictable. When it is connected to a low-voltage distribution network, it may cause high voltage and three-phase unbalanced power quality problems in the low-voltage distribution network. In terms of medium-voltage distribution networks, when distributed photovoltaics are connected on a large scale, it may cause photovoltaic power return, which further leads to circulating currents in medium-voltage feeders, resulting in increased losses in medium-voltage distribution lines, reduced power transmission capacity of medium-voltage distribution networks and other problems. Low-voltage AC / DC hybrid distribution networks can effectively solve the power quality problems of low-voltage distribution networks and photovoltaic power return problems in medium-voltage distribution networks caused by large-scale photovoltaic access. However, due to the increase in the amount of calculation, the traditional medium and low voltage distribution network equipment scheduling method is no longer suitable for the rapid management of power quality problems in medium and low voltage distribution networks considering low-voltage flexible interconnection. To this end, this application proposes a method for managing power quality problems in medium and low voltage distribution networks considering low-voltage flexible interconnection.

[0049] The present application provides a method for effectively solving the above-mentioned problems. Next, a method for managing power quality problems in medium and low voltage distribution networks considering low voltage flexible interconnection will be described in detail in combination with multiple embodiments.

[0050] Figure 1 A method flow chart of a method and system for managing power quality problems in medium and low voltage distribution networks considering low voltage flexible interconnection is shown, including:

[0051] S101, obtain the target medium-voltage distribution network topology and the low-voltage AC / DC flexible interconnected distribution station area topology, load attributes, and adjustable power quality problem management equipment, and build a medium- and low-voltage distribution network power quality problem management architecture considering low-voltage flexible interconnection;

[0052] The governance framework for power quality issues in medium and low voltage distribution networks considering low voltage flexible interconnection includes a mathematical model for power flow calculation of medium voltage AC distribution networks and a mathematical model for power flow calculation of low voltage AC / DC hybrid distribution networks;

[0053] Before deploying medium-voltage centralized intelligent entities and low-voltage distributed intelligent entities, it is necessary to clarify the network structure, load properties, and adjustable power quality problem management equipment of the medium-voltage distribution network and the low-voltage AC / DC flexible interconnected distribution station area.

[0054] As attached Figure 2 As shown in the topology diagram of the medium-voltage distribution network, the medium-voltage distribution network contains a medium-voltage centralized photovoltaic storage power station. When the intensity of sunlight is high during the day, it outputs power to the medium-voltage distribution network and its own energy storage device. When the energy storage device meets the conditions, it can provide all-day power support for the end of the medium-voltage distribution network. At the same time, the medium-voltage distribution network contains medium-voltage power quality problem management equipment. When there is a power quality problem in the medium-voltage distribution network, it can achieve self-management of the power quality problem on the medium-voltage side through the coordination of the medium-voltage centralized photovoltaic storage power station and the medium-voltage power quality problem management equipment. The relationship between high voltage (MV) and low voltage (LV) and the location of some specific equipment are shown. At the top, you can see a "medium-voltage centralized photovoltaic storage power station", marked 19-21. These are facilities used to collect and store solar energy or other renewable energy sources to provide electricity when needed. Next is a series of points numbered 2-16. These represent different nodes or locations in the circuit, each with its own number for easy identification. Between these points, there are two "medium-voltage power quality problem management devices". The purpose of these devices is to detect and resolve any power quality issues in the circuit, such as voltage instability or harmonic distortion. There are also two "medium voltage centralized photovoltaic storage power stations" at the bottom, marked as 17 and 18. These are also facilities used to collect and store renewable energy. Finally, there is a symbol that represents the conversion between high and low voltage. This is usually done by a transformer, which changes the voltage level of the alternating current so that electricity can be transmitted from high voltage to low voltage and vice versa.

[0055] As attached Figure 3As shown in the topology diagram of low-voltage AC / DC flexible interconnected distribution substations, the low-voltage AC / DC distribution network contains a high proportion of distributed photovoltaics. Considering the economic cost of the low-voltage side, it is not equipped with an integrated photovoltaic storage system and power quality problem management equipment. When distributed photovoltaic power generation occurs, high voltage and power return problems may occur. In order to achieve the management of distributed power quality problems in the low-voltage distribution network, in addition to managing power quality problems through photovoltaic inverters, the low-voltage distribution network can also use flexible interconnection devices between AC distribution substations and DC distribution substations for management. When one distribution substation has a power return problem, and the other distribution substation has a high load rate and has a certain demand for power, the power mutual assistance between the substations can be achieved through the flexible interconnection device. Through the coordination of photovoltaic inverters and flexible interconnection devices, the power quality problem management of low-voltage AC / DC flexible interconnected distribution substations can be effectively achieved. There is a node marked with "MV" on the left, which represents the power input port of the medium voltage level. From here, the current passes through the step-down transformer and enters the "AC distribution substation" below and the "DC distribution substation" on the right. Next are two main branch lines: AC distribution area: This branch consists of a series of nodes numbered 1 to 21. Node 1 is the starting point, followed by four nodes from 2 to 5 to form a path; then 6 to 10 is another path; and finally 11 to 21 is divided into two paths. "Low-voltage distributed photovoltaic" is marked on some nodes, which means that solar power generation facilities are installed in these places and can directly provide electricity to the grid. DC distribution area: This branch is also composed of a group of nodes numbered 1 to 21, arranged in a similar way to the AC branch. There are also some nodes with the "low-voltage distributed photovoltaic" logo. Between the AC and DC branches, there is also a key component - the "flexible interconnection device". This device allows power to be exchanged between the two branches. That is, if one branch produces excess energy (for example, because the power generated by solar panels exceeds the local consumption), then this excess power can be transmitted to the other branch through the flexible interconnection device for use. Vice versa, if a branch needs more power but its own production capacity is insufficient, it can also get supplementary power from other branches.

[0056] Comprehensive attachment Figure 2 And attached Figure 3 The network structure, load attributes, and adjustable power quality problem management equipment can be built. Figure 4 The power quality problem governance architecture of medium and low voltage distribution networks considering low voltage flexible interconnection is shown in the figure. In the architecture, the agent is a core concept in the field of artificial intelligence reinforcement learning. At the most basic level, an agent can be defined as an entity that can autonomously perceive information in its environment and make decisions based on this information to achieve specific goals or tasks. The key characteristics of an agent include autonomy, perception, and decision-making capabilities. Figure 4 As shown, the medium voltage central intelligent body 100 is responsible for coordinating the operation status of the substations and equipment of the medium and low voltage distribution network 200. At the medium voltage side, it is responsible for issuing dispatching commands for the medium voltage centralized photovoltaic storage power station and the medium voltage power quality problem management equipment to achieve the centralized power quality problem management of the medium voltage distribution network, and by monitoring and analyzing the operation status of the medium voltage equipment and the substation operation status, it decides on the dispatching commands for the next period. At the low voltage AC / DC distribution substation 400 level, each low voltage intelligent body 300 is responsible for monitoring the operation status of its own low voltage AC / DC distribution substation 400, and issuing dispatching management of distributed photovoltaic inverters and flexible interconnection devices to achieve distributed power quality problem management on the low voltage side. At the same time, considering that the low-voltage AC / DC distribution station 400 itself has limited management means and may not be able to achieve complete management of power quality problems, while uploading the operating status of the substation under the jurisdiction of the low-voltage intelligent body 300, the power quality problem management status is fed back to the medium-voltage central intelligent body 100. When an abnormally low-voltage substation is monitored, the medium-voltage side issues a power quality problem management instruction, mobilizes the management resources on the medium-voltage side, and achieves complete management of the power quality problems in the abnormally low-voltage AC / DC distribution station 400.

[0057] In the embodiment of the present application, the medium voltage AC distribution network power flow calculation mathematical model includes: a first objective function and a first constraint condition,

[0058] The first objective function is related to the total number of nodes with voltage exceeding the limit in the medium voltage distribution network and the total number of nodes with three-phase imbalance in the medium voltage distribution network;

[0059] The first constraint condition includes a first node voltage amplitude constraint, a first three-phase unbalance constraint, and a first device constraint.

[0060] Specifically, in the embodiment of the present application, after the management equipment of the medium voltage distribution network is dispatched, it should be ensured that there is no power quality problem in the medium voltage distribution network, so the first objective function is obtained:

[0061]

[0062] in: Represents the total number of nodes where voltage exceeds the limit in the medium voltage distribution network; Represents the total number of nodes where three-phase imbalance occurs in the medium voltage distribution network; m1 and m2 are proportional coefficients.

[0063] It should be noted that for node y and branch xy in the medium voltage distribution network:

[0064]

[0065]

[0066] Wherein: the set q(j) represents the set of first nodes of all branches with node x as the last node in the medium voltage distribution network; the set w(j) represents the set of last nodes of all branches with node x as the first node in the medium voltage distribution network; represents the active power flowing through branch xy; represents the reactive power flowing through branch xy; represents the active power injected into node x; represents the reactive power injected into node j; and They represent the resistance and reactance of branch ij respectively.

[0067] In the embodiment of the present application, the supply voltage deviation is higher than the upper limit, indicating a high voltage power quality problem, and the supply voltage deviation is lower than the lower limit, indicating a low voltage power quality problem. In order to ensure that there is no power quality problem after the medium voltage distribution network is managed, the node voltage amplitude is constrained as follows: the first node voltage amplitude constraint:

[0068]

[0069] in: and are the maximum and minimum values ​​of the voltage amplitude of the medium voltage distribution network respectively; the upper and lower limits of the voltage of the medium voltage distribution network are taken as and It is the voltage rating of the medium voltage distribution network.

[0070] The calculation formula of PVUR voltage three-phase unbalance is as follows:

[0071]

[0072] In order to ensure that there is no three-phase imbalance in the medium-voltage distribution network, the three-phase imbalance is constrained. The formula is as follows: The first three-phase imbalance constraint:

[0073]

[0074] Among them: U avg It indicates the average value of the voltage amplitude of three phases A, B and C; PVUR indicates the phase voltage unbalance rate; It represents the three-phase unbalance rate of the x-phase voltage at the node of the medium voltage distribution network. As the maximum value constraint, here we take

[0075] In order to achieve the management of power quality problems in the medium-voltage distribution network, medium-voltage centralized photovoltaic power storage stations and medium-voltage power quality management equipment are introduced to participate in the dispatch. The first equipment constraint condition is as follows:

[0076]

[0077] in: represents the medium voltage centralized photovoltaic power station at the medium voltage distribution network node x The apparent power injected into the phase, and Inject the maximum and minimum values ​​of apparent power into the medium-voltage centralized photovoltaic power station; Represents the medium voltage power quality problem management equipment at the medium voltage distribution network node x The apparent power injected into the phase; S max_VSC , S min_VSC Indicates the maximum and minimum values ​​of the apparent power output of the medium voltage power quality control equipment.

[0078] In the embodiment of the present application, the mathematical model for calculating the power flow of the low-voltage AC / DC hybrid distribution network includes: a second objective function and a second constraint condition;

[0079] The second objective function is related to the total number of nodes with voltage exceeding the limit in the low-voltage AC distribution area, the total number of nodes with voltage exceeding the limit in the low-voltage DC distribution area, and the total number of nodes with three-phase imbalance in the low-voltage AC distribution area;

[0080] The second constraint condition includes a second node voltage amplitude constraint, a second three-phase unbalance constraint, and a second device constraint.

[0081] Specifically, in the embodiment of the present application, after the management equipment of the low-voltage AC / DC hybrid distribution network is dispatched, priority should be given to ensuring that no power quality problems occur in the AC substation or the DC substation, so the second objective function is obtained:

[0082]

[0083] in: Represents the total number of nodes with voltage exceeding the limit in the low voltage AC distribution area; Represents the total number of nodes where voltage exceeds the limit in the low voltage DC distribution area; Represents the total number of nodes with three-phase imbalance in the low-voltage AC distribution station area; m3, m4, and m5 are proportional coefficients.

[0084] For node j and branch ij in the low voltage AC distribution area:

[0085]

[0086] Wherein: the set g(j) represents the set of first nodes of all branches with node j as the last node in the low-voltage AC distribution area; the set h(j) represents the set of last nodes of all branches with node j as the first node in the low-voltage AC distribution area; Represents the active power flowing through branch ij; Represents the reactive power flowing through branch ij; represents the active power injected into node j; represents the reactive power injected into node j; and They represent the resistance and reactance of branch ij respectively.

[0087] For node j and branch ij in the low voltage DC distribution area:

[0088]

[0089] in: Represents the active power flowing through branch ij; represents the active power injected into node j; and Respectively represent the current flowing through branch ij and the resistance of branch ij; V i DC , Represents the single-phase voltage amplitude at node i and node j.

[0090] The voltage amplitude of the second node is constrained as follows:

[0091]

[0092] in: and They are the maximum and minimum values ​​of the voltage amplitude in the low voltage AC distribution station area respectively; and They are the maximum and minimum values ​​of the voltage amplitude of the low-voltage AC distribution station area, respectively. Here, the upper and lower limits of the voltage in the AC and DC stations are 1.07U respectively. N and 0.90U N ; U N is the voltage rating of each station area.

[0093] The second three-phase unbalance constraint formula is as follows:

[0094]

[0095] in: It represents the three-phase unbalance rate of the phase i voltage at the node in the low-voltage AC distribution station area. As the maximum value constraint, here we take

[0096] In order to achieve low-voltage AC / DC hybrid distribution network management, distributed photovoltaic inverters and flexible AC / DC interconnection equipment are introduced to participate in the regulation. The second equipment constraint conditions are as follows:

[0097]

[0098] S min_VSC ≤S VSC ≤S max_VSC

[0099] in: Represents the distributed photovoltaic inverter at the node i of the low voltage AC and DC distribution area Reactive power injected into the phase; and The maximum and minimum values ​​of reactive power injected into distributed photovoltaic inverters; S VSC Represents the apparent power passing through the flexible AC / DC interconnection device; S max_VSC , S min_VSC Indicates the maximum and minimum values ​​of the apparent power passing through the VSC flexible interconnection device.

[0100] It should be noted that the stability and safety of the low-voltage AC / DC hybrid distribution network during the governance process can be ensured through detailed definitions and constraints. First, the clear identification of the active power and reactive power of the branch helps to accurately calculate and analyze the power flow of each branch, providing basic data for subsequent regulation and optimization. At the same time, the constraint on the node injection power ensures the stability and reliability of the node voltage and prevents voltage fluctuations caused by excessive or insufficient power injection. By setting the maximum and minimum values ​​of the voltage amplitude and the constraint of the three-phase imbalance rate, the power quality of the distribution network can be further guaranteed. These constraints not only take into account the AC station area, but also the DC station area, ensuring the voltage stability of the entire AC / DC hybrid distribution network. In terms of equipment constraints, the reactive power and apparent power of distributed photovoltaic inverters and flexible AC / DC interconnected equipment are clearly restricted, which not only fully utilizes the regulation capabilities of these devices, but also avoids the adverse effects on the distribution network caused by excessive regulation. In addition, these constraints also take into account the operating range and limitations of the equipment to ensure the normal operation and life of the equipment.

[0101] S102, establish a Markov decision model for the governance architecture of power quality issues in medium and low voltage distribution networks considering low voltage flexible interconnection;

[0102] In the embodiment of the present application, a Markov decision model for establishing a governance framework for power quality issues in medium and low voltage distribution networks considering low voltage flexible interconnection is established, including: a state space, an action space, and a reward space;

[0103] Among them, the reward in the reward space is the inverse of the sum of the first objective function and the second objective function, and the lower the reward value, the better the power quality problem management strategy of the medium and low voltage distribution network.

[0104] In an optional embodiment, the timely reward in the reward space can be expressed as:

[0105]

[0106] Among them: when r approaches 0, it means that the power quality problem management strategy of medium and low voltage distribution networks is good at this time; m1, m2, m3, m4, and m5 are proportional coefficients.

[0107] In the embodiment of the present application, the state space includes: a medium voltage distribution network state space and a low voltage AC / DC distribution network state space;

[0108] In an optional embodiment, the medium-voltage distribution network state space includes medium-voltage power flow distribution, medium-voltage voltage distribution, medium-voltage centralized photovoltaic power station operating status, and medium-voltage power quality problem management equipment operating status; the low-voltage AC / DC distribution network state space includes low-voltage power flow distribution, low-voltage voltage distribution, low-voltage distributed photovoltaic inverter operating status, and low-voltage flexible interconnection device operating status.

[0109] The different state space expressions of the two are:

[0110] s MV ={S MV ,U MV ,PV MV ,PQC MV}

[0111] s LV ={S LV ,U LV ,PV LV ,VSC LV}

[0112] Where: S MV Represents the node active power and reactive power matrix of the medium voltage distribution network; U MV Represents the node voltage amplitude matrix of the medium voltage distribution network; PV MV Indicates the operating status of the medium-voltage centralized photovoltaic power station; PQC MV Indicates the operating status of the medium voltage power quality problem management equipment; S LV Represents the node active power and reactive power matrix of the low voltage AC / DC distribution network; U LV Represents the node voltage amplitude matrix of the low voltage AC / DC distribution network; PV LV Indicates the operating status of low-voltage distributed photovoltaic inverter; VSC LV Indicates the operating status of the low voltage flexible interconnection device.

[0113] In the embodiment of the present application, the action space includes: a medium voltage distribution network action space and a low voltage AC / DC distribution network action space;

[0114] In an optional embodiment, the medium voltage distribution network action space includes the apparent power injected into the medium voltage distribution network by different devices;

[0115] The action space of low voltage AC / DC distribution network includes the apparent power injected into the low voltage AC / DC distribution area by different equipment.

[0116] Because the power quality problem management equipment of medium voltage distribution network and low voltage AC / DC hybrid distribution network is different, the action space is also different. The different action vectors of the two are:

[0117] a MV ={k1,k2,k3...,k n}

[0118] a LV ={l1,l2,l3...,l n}

[0119] Where: k corresponds to each possible dispatching situation of the governance equipment in the medium voltage distribution network; k n Represents the apparent power injected into the medium voltage distribution network by the nth device. l corresponds to each possible dispatching situation of the management equipment in the low voltage AC / DC distribution area; l n It represents the apparent power injected into the low voltage AC / DC distribution station area by the nth device.

[0120] It should be noted that by constructing a Markov decision model, the governance of power quality issues in medium and low voltage distribution networks can be systematically handled. This model can not only help to understand the state and changes of the distribution network more clearly, but also guide the formulation of more optimized governance strategies through reward mechanisms. Specifically, the reward setting in the reward space allows the economy and sustainability of the governance process to be taken into account while pursuing the governance effect of power quality issues. In addition, by distinguishing the state space and action space of medium voltage distribution networks and low voltage AC and DC distribution networks, the operation of different devices in different networks can be more accurately controlled, thereby achieving more refined governance. Finally, the advantage of this model is that it can continuously learn and optimize, and through continuous trial and error and adjustment, it will eventually find the governance strategy that best suits the current distribution network situation.

[0121] S103, solving the Markov decision model in combination with a reinforcement learning algorithm to obtain a dispatching strategy for medium and low voltage distribution network equipment.

[0122] In an embodiment of the present application, the Markov decision model is solved in combination with a reinforcement learning algorithm to obtain a dispatching strategy for medium and low voltage distribution network equipment, including: fitting the action value function through a neural network, learning all Q values ​​corresponding to "state-action" in the interaction between a limited number of distribution network states and the distribution network environment, and learning the optimal strategy based on the Bellman optimal equation.

[0123] It should be noted that the "Deep Q-learning" algorithm is a type of deep reinforcement learning. It is a Q-learning algorithm based on neural networks. It is mainly used to solve the problem that the state space in reinforcement learning problems is too large, which makes it impossible to use traditional Q-learning algorithms to solve it. The "Deep Q-learning" algorithm uses a deep neural network to approximate the Q function, so that it can handle reinforcement learning problems with high-dimensional state space. The "Deep Q-learning" algorithm can fit the action value function Q through a neural network. ε (s, a), learn the Q values ​​corresponding to all "state-action" in the interaction between a limited number of distribution network states and distribution network environment, and learn the optimal strategy ε according to the Bellman optimal equation * . Action value function Q ε (s,a), Bellman optimal equation, and optimization strategies for all discrete governance devices are shown below respectively.

[0124] Q ε (s,a)=E(r0+γr1+γ 2 r2+...+γ i r i |ε,s,a)

[0125]

[0126] ε*(s)=argminQ ε* (s,a)

[0127] Among them, Q ε (s,a) represents the action value function, s represents the state, a represents the action, r i represents the reward at time step t, γ i Represents the discount factor, which is used to measure the importance of future rewards. r(s,a) represents the immediate reward represented by state s under action a.

[0128] It should be noted that in this way, the model can gradually approach the optimal equipment scheduling strategy, thereby achieving optimal management of power quality in medium and low voltage distribution networks. It should be noted that due to the complex and changeable operating environment of the distribution network, the model solution process may require multiple iterations and adjustments to ensure that the obtained scheduling strategy can adapt to the needs of different scenarios.

[0129] In addition, in order to ensure the effectiveness and reliability of the dispatch strategy, the model needs to be fully verified and tested. By simulating different distribution network operation scenarios and fault conditions, the performance of the model under different conditions can be evaluated, so as to identify potential problems and make optimization improvements. At the same time, the model needs to be monitored and evaluated in real time to ensure that it can operate continuously and stably in actual applications.

[0130] In summary, the embodiment of the present application provides a systematic solution to the equipment scheduling problem of medium and low voltage distribution networks by constructing a Markov decision model and solving the model in combination with a reinforcement learning algorithm. This solution can not only help to understand the state and changes of the distribution network more clearly, but also formulate a more reasonable equipment scheduling strategy through optimization algorithms, thereby improving the power quality and management efficiency of the distribution network.

[0131] This embodiment also provides a system for managing power quality issues in medium and low voltage distribution networks taking into account low voltage flexible interconnection, including:

[0132] The architecture building module is used to obtain the target medium-voltage distribution network topology and the low-voltage AC / DC flexible interconnected distribution station area topology, load attributes, and adjustable power quality problem management equipment, and build a medium- and low-voltage distribution network power quality problem management architecture considering low-voltage flexible interconnection;

[0133] The governance framework for power quality issues in medium and low voltage distribution networks considering low voltage flexible interconnection includes a mathematical model for power flow calculation of medium voltage AC distribution networks and a mathematical model for power flow calculation of low voltage AC / DC hybrid distribution networks;

[0134] Model building module, used to establish a Markov decision model for the governance architecture of power quality issues in medium and low voltage distribution networks considering low voltage flexible interconnection;

[0135] The model solving module is used to solve the Markov decision model in combination with the reinforcement learning algorithm to obtain the dispatching strategy of medium and low voltage distribution network equipment.

[0136] The above-mentioned unit modules may be embedded in or independent of the processor in the computer device in the form of hardware, or may be stored in the memory in the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above-mentioned modules.

[0137] This embodiment also provides a computer device, which may be a terminal, and its internal structure diagram may be as shown in FIG. Figure 5As shown. The computer device includes a processor, a memory, a communication interface, a display screen and an input device connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be achieved through WIFI, an operator network, NFC (near field communication) or other technologies. When the computer program is executed by the processor, a method for managing power quality problems in a medium and low voltage distribution network considering low voltage flexible interconnection is implemented. The display screen of the computer device can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covered on the display screen, or a button, trackball or touchpad set on the computer device housing, or an external keyboard, touchpad or mouse.

[0138] This embodiment further provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the following steps are implemented:

[0139] Obtain the target medium-voltage distribution network topology and the low-voltage AC / DC flexible interconnected distribution station area topology, load attributes, and adjustable power quality problem management equipment, and build a medium- and low-voltage distribution network power quality problem management architecture that takes into account low-voltage flexible interconnection;

[0140] The governance framework for power quality issues in medium and low voltage distribution networks considering low voltage flexible interconnection includes a mathematical model for power flow calculation of medium voltage AC distribution networks and a mathematical model for power flow calculation of low voltage AC / DC hybrid distribution networks;

[0141] Establish a Markov decision model based on the governance framework of power quality issues in medium and low voltage distribution networks considering low voltage flexible interconnection;

[0142] The Markov decision model is solved in combination with the reinforcement learning algorithm to obtain the dispatching strategy for medium and low voltage distribution network equipment.

[0143] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

[0144] Those skilled in the art will appreciate that the embodiments of the present application can be provided as methods, systems, or computer program products. Therefore, the present application can adopt the form of complete hardware embodiments, complete software embodiments, or embodiments in combination with software and hardware. Moreover, the present application can adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code. The scheme in the embodiments of the present application can be implemented in various computer languages, for example, object-oriented programming language Java and literal scripting language JavaScript, etc.

[0145] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0146] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0147] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0148] Although the preferred embodiments of the present application have been described, those skilled in the art may make other changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications falling within the scope of the present application.

[0149] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the claims of the present application and their equivalents, the present application is also intended to include these modifications and variations.

Claims

1. A method for managing power quality problems in medium and low voltage distribution networks considering low voltage flexible interconnection, characterized in that: include: Obtain the target medium-voltage distribution network topology and the low-voltage AC / DC flexible interconnected distribution station area topology, load attributes, and adjustable power quality problem management equipment, and build a medium- and low-voltage distribution network power quality problem management architecture that takes into account low-voltage flexible interconnection; The power quality problem management framework of the medium and low voltage distribution network considering low voltage flexible interconnection includes a mathematical model for power flow calculation of the medium voltage AC distribution network and a mathematical model for power flow calculation of the low voltage AC / DC hybrid distribution network; Establish a Markov decision model based on the governance framework of power quality issues in medium and low voltage distribution networks considering low voltage flexible interconnection; The Markov decision model is solved in combination with a reinforcement learning algorithm to obtain a dispatching strategy for medium and low voltage distribution network equipment.

2. The method for managing power quality problems in medium and low voltage distribution networks considering low voltage flexible interconnection as claimed in claim 1 is characterized in that: The medium voltage AC distribution network power flow calculation mathematical model includes: a first objective function and a first constraint condition, The first objective function is related to the total number of nodes where voltage exceeds the limit in the medium voltage distribution network and the total number of nodes where three-phase imbalance occurs in the medium voltage distribution network; The first constraint condition includes a first node voltage amplitude constraint, a first three-phase unbalance constraint, and a first equipment constraint.

3. The method for managing power quality problems in medium and low voltage distribution networks considering low voltage flexible interconnection as claimed in claim 2 is characterized in that: The low-voltage AC / DC hybrid distribution network power flow calculation mathematical model includes: a second objective function and a second constraint condition; The second objective function is related to the total number of nodes with voltage exceeding the limit in the low-voltage AC distribution substation, the total number of nodes with voltage exceeding the limit in the low-voltage DC distribution substation, and the total number of nodes with three-phase imbalance in the low-voltage AC distribution substation; The second constraint condition includes a second node voltage amplitude constraint, a second three-phase unbalance constraint, and a second equipment constraint.

4. The method for managing power quality problems in medium and low voltage distribution networks considering low voltage flexible interconnection as claimed in claim 3 is characterized in that: The Markov decision model for establishing a governance framework for power quality issues in medium and low voltage distribution networks based on low voltage flexible interconnection includes: state space, action space and reward space; The reward in the reward space is the inverse of the sum of the first objective function and the second objective function, and the lower the reward value, the better the strategy for managing power quality problems in medium and low voltage distribution networks.

5. The method for managing power quality problems in medium and low voltage distribution networks considering low voltage flexible interconnection as claimed in claim 4 is characterized in that: The state space includes: a medium voltage distribution network state space and a low voltage AC / DC distribution network state space; The medium voltage distribution network state space includes medium voltage power flow distribution, medium voltage voltage distribution, operation status of medium voltage centralized photovoltaic power station and operation status of medium voltage power quality problem management equipment; The low-voltage AC / DC distribution network state space includes low-voltage power flow distribution, low-voltage voltage distribution, low-voltage distributed photovoltaic inverter operating status and low-voltage flexible interconnection device operating status.

6. The method for managing power quality problems in medium and low voltage distribution networks considering low voltage flexible interconnection as claimed in claim 5 is characterized in that: The action space includes: a medium voltage distribution network action space and a low voltage AC / DC distribution network action space; The medium voltage distribution network action space includes the apparent power injected into the medium voltage distribution network by different devices; The low voltage AC / DC distribution network action space includes the apparent power injected into the low voltage AC / DC distribution station area by different devices.

7. The method for managing power quality problems in medium and low voltage distribution networks considering low voltage flexible interconnection as claimed in claim 6 is characterized in that: The Markov decision model is solved by combining a reinforcement learning algorithm to obtain a medium and low voltage distribution network equipment dispatching strategy, including: fitting an action value function through a neural network, learning all Q values ​​corresponding to "state-action" in the interaction between a limited number of distribution network states and distribution network environments, and learning the optimal strategy based on the Bellman optimal equation.

8. A system for managing power quality issues in medium and low voltage distribution networks considering low voltage flexible interconnection, characterized in that: include: The architecture building module is used to obtain the target medium-voltage distribution network topology and the low-voltage AC / DC flexible interconnected distribution station area topology, load attributes, and adjustable power quality problem management equipment, and build a medium- and low-voltage distribution network power quality problem management architecture considering low-voltage flexible interconnection; The power quality problem management framework of the medium and low voltage distribution network considering low voltage flexible interconnection includes a mathematical model for power flow calculation of the medium voltage AC distribution network and a mathematical model for power flow calculation of the low voltage AC / DC hybrid distribution network; Model building module, used to establish a Markov decision model for the governance architecture of power quality issues in medium and low voltage distribution networks considering low voltage flexible interconnection; The model solving module is used to solve the Markov decision model in combination with the reinforcement learning algorithm to obtain the medium and low voltage distribution network equipment scheduling strategy.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images