Resource optimization scheduling method and system based on multi-port flexible interconnection

Abstract

The invention discloses a resource optimization scheduling method and system based on multi-port flexible interconnection, and relates to the technical field of power system engineering, and the method comprises the steps: collecting first power distribution data of a first object; encoding the first power distribution data to determine a first object code; obtaining second structure data according to the first object code, and constructing a second object; the method is used for predicting the harmonic waves generated in the power distribution network when the power distribution network is subjected to flexible capacity expansion, and adjusting the power resource scheduling scheme of the power distribution network according to the predicted harmonic waves and the architecture of the power distribution network. Therefore, it can be ensured that the power distribution network can adapt to access of various new energy sources, and efficient and flexible power adjustment can be achieved.

Description

Technical Field

[0001] The present invention relates to the technical field of power system engineering, and in particular to a resource optimization scheduling method and system based on multi-port flexible interconnection. Background Art

[0002] When the distribution network is exposed to extreme environmental impacts in a short period of time, the new energy equipment that supplies power to the distribution network may age or become damaged due to changes in environmental factors. For example, the main equipment that constitutes the distribution network, such as overhead lines, power cables, switches, ring network cabinets, distribution transformers, etc., operates outdoors for a long time and is often affected by harsh conditions such as wind, sun, and rain. They are prone to aging and have a high failure rate.

[0003] When different types of new energy are connected to the distribution network, they will have many impacts on the distribution network. Specifically, it may affect the quality of electric energy. For example, the power generation process of wind power generation and photovoltaic power generation is greatly affected by the weather and environment, and has the characteristics of intermittent and fluctuating. This instability will cause voltage fluctuations and affect the voltage qualification rate. When new energy is connected to the distribution network, part of the output power on the original network line is supplied by distributed power sources, and the voltage at each node on the branch point line will be enhanced, which may make the voltage level too high. In addition, the power components and rectifier inverter equipment equipped with new energy power generation equipment will generate DC and harmonics. Once the harmonics enter the power grid, the voltage of the distribution network will be deformed, which will seriously damage the quality of electric energy in actual application and shorten its service life. At the same time, harmonics will also affect the accuracy of measuring instruments and measuring equipment, and even cause the power system automatic device to operate incorrectly, affecting the normal operation of the power system. In addition, it may also have an impact on the network structure. After the new energy is connected to the distribution network, the existing one-way power radiation network will be transformed into a network interconnected between multiple weak power loops and users, which essentially changes the distribution form of the power grid. This change makes the grid structure more complex, the load direction and problems more difficult to predict, and network damage will be directly related to the load, the specific location of the power source and the actual power reserves. Summary of the invention

[0004] In view of the above-mentioned problems, the present invention is proposed.

[0005] Therefore, the technical problem solved by the present invention is that in the actual power resource dispatching process, the existing technology may fail to execute the dispatching instructions such as peak shaving, frequency regulation, and load reduction, which will pose a threat to the safe and stable operation of the power grid.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions: a resource optimization scheduling method based on multi-port flexible interconnection, comprising:

[0007] Collecting first power distribution data of a first object;

[0008] Encoding the first power distribution data to determine a first object code;

[0009] Obtaining second structure data according to the first object encoding, and constructing a second object;

[0010] The first power distribution data is input into the second object to obtain a prediction result and perform scheduling.

[0011] As a preferred solution of the resource optimization scheduling method based on multi-port flexible interconnection described in the present invention, wherein: the collecting of the first power distribution status data of the first object includes presetting a sampling frequency and collecting at multiple sampling moments.

[0012] As a preferred solution of the resource optimization scheduling method based on multi-port flexible interconnection described in the present invention, wherein: the encoding of the first power distribution data includes encoding the first power distribution data at each moment to obtain the first power distribution data attribute code.

[0013] As a preferred solution of the resource optimization scheduling method based on multi-port flexible interconnection described in the present invention, wherein: the determining of the first object code includes determining the device code of the first object according to the first power distribution data attribute code at each moment.

[0014] As a preferred solution of the resource optimization scheduling method based on multi-port flexible interconnection described in the present invention, wherein: the second structure data obtained according to the first object encoding includes obtaining the edge weight between devices according to the device attributes between the first object, and constructing the graph data at each moment.

[0015] As a preferred solution of the resource optimization scheduling method based on multi-port flexible interconnection described in the present invention, wherein: the construction of the second object includes training a prediction model according to the graph data at each moment, the prediction model is used to predict the operation data of the distribution network, and obtain the second object;

[0016] The prediction model is preferably a long short-term memory model, which includes neurons that are repeatedly used in series.

[0017] As a preferred solution of the resource optimization scheduling method based on multi-port flexible interconnection described in the present invention, wherein: the inputting of the first power distribution data into the second object to obtain the prediction result and perform scheduling includes, when formulating the resource scheduling strategy, first collecting the first power distribution data in real time and encoding it to obtain the real-time code, inputting the real-time code into the prediction model of the second object trained to a convergence state, obtaining the predicted operation data, and formulating the scheduling strategy according to the predicted first power distribution data.

[0018] As a preferred solution of the resource optimization scheduling system based on multi-port flexible interconnection described in the present invention, it includes: a data acquisition module, a data encoding module, a data prediction module, and a scheduling decision module;

[0019] The data acquisition module is used to collect power distribution data of the first object; using the connected distributed sensor and the smart meter to obtain the first power distribution status data at a preset sampling frequency;

[0020] The data encoding module is used to encode the collected first power distribution data, generate attribute codes and determine object codes, and includes a data processing unit and an object encoding unit;

[0021] The data prediction module is used to construct the second structure data based on the device code of the first object, train the prediction model, and generate the second object; it includes a graph data construction unit that generates graph data according to the inter-device attributes and inter-device edge weights of the first object; and a prediction model training unit that uses the graph data to train the long short-term memory model;

[0022] The scheduling decision module is used to generate prediction results based on real-time power distribution data and formulate resource optimization scheduling strategies.

[0023] A computer device comprises a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement a resource optimization scheduling method based on multi-port flexible interconnection.

[0024] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps of a resource optimization scheduling method based on multi-port flexible interconnection.

[0025] Beneficial effects of the present invention: The resource optimization scheduling method based on multi-port flexible interconnection provided by the present invention quantitatively characterizes the power resource configuration of the distribution network by collecting environmental data of the environment in which the distribution network is located, humanistic data of the area in which the distribution network is located, and operating data during the operation of the distribution network. And according to the environmental data, humanistic data and operating data, a harmonic prediction model is trained to predict the harmonics generated in the distribution network when the distribution network is flexibly expanded, and the power resource scheduling plan of the distribution network is adjusted according to the predicted harmonics and the architecture of the distribution network. In this way, it can be ensured that the distribution network can adapt to the access of various new energy sources and realize efficient and flexible power regulation. And before proposing the topology construction law and design method, it can be simulated, theoretical verification and simulation test can be carried out to ensure its effectiveness and reliability in practical applications. It can also timely modulate the strategy, balance adjustment and multi-terminal coordinated control technology to be finely designed to ensure that the system maintains stability and efficiency under complex and changeable operating conditions. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0027] Figure 1 An overall flow chart of a resource optimization scheduling method based on multi-port flexible interconnection provided for the first embodiment of the present invention.

[0028] Figure 2 A schematic diagram of an auto-encoding model of a resource optimization scheduling method based on multi-port flexible interconnection provided in the second embodiment of the present invention.

[0029] Figure 3 A schematic diagram of the structure of a neuron of a resource optimization scheduling method based on multi-port flexible interconnection provided in the second embodiment of the present invention.

[0030] Figure 4 A prediction model structure diagram of a resource optimization scheduling method based on multi-port flexible interconnection provided in the second embodiment of the present invention. DETAILED DESCRIPTION

[0031] 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.

[0032] Example 1, reference Figure 1-Figure 2 , is an embodiment of the present invention, and provides a resource optimization scheduling method based on multi-port flexible interconnection, comprising:

[0033] S1: Collect first power distribution data of a first object.

[0034] Furthermore, collecting the first power distribution status data of the first object includes presetting a sampling frequency and collecting data at multiple sampling moments.

[0035] In an embodiment of the present application, the first object may be a new energy power supply equipment (for example, a wind turbine, a photovoltaic generator), a distribution network line, an overhead line, a power cable, a switch, a ring main unit, a distribution transformer, etc.

[0036] Furthermore, environmental factors can affect the stability of the distribution network. Specifically, changes in environmental factors may cause changes in the output power of new energy power supply equipment (e.g., wind turbines, photovoltaic generators). For example, when the distribution network is exposed to wind, rain, and lightning, the output power of wind turbines may increase, and the output power of photovoltaic generators may decrease. And the lines of the distribution network are susceptible to natural factors such as wind, rain, and lightning. For example, lightning strikes may cause problems such as fires in distribution lines and collapse of electric poles. Strong winds may also have a negative impact on the normal operation of distribution lines. Rainy and snowy weather will also harm the stability of power supply.

[0037] In the embodiment of the present application, collecting the first power distribution status data of the first object may be collecting environmental data, cultural data, and distribution network operation data at multiple sampling moments according to a preset sampling frequency.

[0038] Among them, environmental data include but are not limited to temperature, humidity, wind speed, and number of thunderstorms. Human data include at least population density. Distribution network operation data include the equipment type of multiple new energy power supply equipment in the distribution network, the output power of the new energy power supply equipment, the output current of the new energy power supply equipment, the output voltage of the new energy power supply equipment, the supply area of ​​the new energy power supply equipment, the supply population of the new energy power supply equipment, and the power supply data sequence of the new energy power supply equipment.

[0039] In an optional embodiment, the collection of distribution data can also be a data collection enhancement method, which uses drone inspection technology to collect real-time environmental and equipment data in the distribution network area that is difficult to cover with fixed sensing equipment; and uses mobile sensing terminals (such as smart vehicles or handheld devices) to temporarily collect distribution data and environmental conditions in a specific area. Through this multi-source, multi-level collection method, comprehensive and accurate data support can be provided for the system, providing a high-quality data foundation for subsequent coding, modeling, prediction and scheduling. This data collection method is particularly suitable for complex distribution network systems with multi-port flexible interconnections.

[0040] Furthermore, with economic development, the population density in some areas has increased year by year, and the electricity load has also increased year by year. If the construction of the distribution network lags behind the demand for electricity for economic development, problems such as overload of distribution lines and insufficient distribution transformer capacity may occur, and even low voltage may occur in severe cases. If the network structure of the distribution network is unreasonable, such as the line is too long and there are no necessary branches, it will cause excessive losses in the distribution line, reduce the output voltage at the end of the line, and affect the power supply voltage and quality. If the wire diameter at the head end of the line is too small, it will also affect the output of electric energy, and in severe cases, it will cause the distribution line to be blown. In the actual power resource dispatching process, there may be a situation where dispatching instructions such as peak shaving, frequency modulation, and load reduction are not implemented effectively, which will pose a threat to the safe and stable operation of the power grid.

[0041] It should be noted that environmental data, humanistic data and distribution network operation data can be collected at multiple sampling times according to a preset sampling frequency.

[0042] S2: Encode the first power distribution data and determine a first object code.

[0043] Further, encoding the first power distribution data includes encoding the first power distribution data at each moment to obtain the first power distribution data attribute code. Determining the first object code includes determining the device code of the first object according to the first power distribution data attribute code at each moment.

[0044] In the embodiment of the present invention, encoding the first power distribution data may be to encode the environmental data, cultural data and distribution network operation data at each moment respectively to obtain the environmental code, cultural code and attribute code of the distribution network.

[0045] Specifically, a pre-trained autoencoder model can be used to encode environmental data, human data, and distribution network operation data at each moment. The schematic diagram of the autoencoder model is as follows: Figure 2 shown.

[0046] In an optional embodiment, the encoding of the power distribution data can also be based on the statistical model of the aggregation coding method to analyze the statistical characteristics of the original data at each moment, and encode it into a set of statistical characteristics. Specific steps: calculate the statistical characteristics of environmental data (such as average value, maximum value, variance); perform cluster analysis on humanities data to generate category codes; extract distribution characteristics (such as frequency distribution, distribution peak, etc.) from the distribution network operation data, and generate attribute codes based on these characteristics.

[0047] Example 2, reference Figure 1 , Figure 3 , Figure 4 , is an embodiment of the present invention, and provides a resource optimization scheduling method based on multi-port flexible interconnection, comprising:

[0048] S3: Obtain second structure data according to the first object encoding, and construct a second object.

[0049] Furthermore, obtaining the second structure data according to the encoding of the first object includes obtaining the edge weights between devices according to the inter-device attributes of the first object, and constructing graph data at each moment.

[0050] In an embodiment of the present application, the second structure data obtained according to the first object code can be, for each moment, determining the device codes of multiple new energy power supply equipment in the distribution network according to the environmental code, cultural code and attribute code, determining the edge weights between the devices according to the line attributes between the devices, and constructing the graph data at each moment according to the device codes and edge weights.

[0051] Furthermore, for each new energy power supply device, the attribute information and the power supply data sequence are spliced ​​in a preset order to obtain the graph data corresponding to each new energy power supply device. Exemplarily, the data corresponding to each node in the graph data includes [station type, output power, output current, output voltage, supply area, supply population, power supply data sequence], and the edge weights between different nodes are used to characterize the association between different new energy devices, including [line length, line rated power, line age].

[0052] In an embodiment of the present application, the second object may be constructed by training a prediction model according to the graph data at each moment, the prediction model being used to predict the operation data of the distribution network to obtain the second object;

[0053] The prediction model is preferably a long short-term memory model, which includes neurons that are repeatedly used in series, and the structure of the neurons is as follows: Figure 3 As shown, the model structure is as Figure 4 As shown, where:

[0054] Figure 3 In, x t is the graph data input at time t;

[0055] h t Represents the prediction result, that is, the label, represented by C t and t Combined, please refer to the figure below for the formula;

[0056] f t is the forgotten data, and its value range is 0 to 1. Get f t The methods include: based on the sigmoid function t and h t-1 (the prediction result at time t-1) is calculated to obtain a value between 0 and 1, and the forgotten data f t The closer it is to 0, the more predicted labels predicted by the first sample data at the previous moment need to be forgotten, and the closer it is to 1, the fewer predicted labels predicted by the first sample data at the previous moment need to be forgotten. Specifically, W f and b f is the forgotten data f t The corresponding weights and biases.

[0057] it is the input data (name is input data), get i t The methods include: t and h t-1 (the prediction result at time t-1) is calculated to obtain a value between 0 and 1; W i and b i are the weights and biases corresponding to the input data.

[0058] is the initial state value of the neuron at time t; W c and b c are the weights and biases corresponding to the initial state values.

[0059] o t is the hidden output data at time t. Get o t The methods include: based on the sigmoid function t and h t-1 (the prediction result at time t-1) is calculated to obtain a value between 0 and 1; W o and b o are the weights and biases corresponding to the hidden output data;

[0060] Ct represents the state value of the neuron at time t.

[0061] exist Figure 4 Although multiple neurons are shown, there is actually only one real neuron, and this neuron will be used cyclically. For example, when training a temperature prediction model, the basic data at time t and the basic data at time t+1 can be collected, the values ​​of the initial state and the values ​​of the initial prediction results can be randomly set in advance, and the neuron corresponding to time t can be input to obtain the prediction result at time t and the output state data; at time t+1, the input of the neuron becomes the prediction result at time t, the output state data at time t, and the basic data at time t+1, and this cycle continues until the training is completed. The loss value is determined based on the prediction result at time t and the cycle life, discharge depth, and temperature in the basic data at time t; the loss value at time t+1 is determined based on the prediction result at time t+1 and the cycle life, discharge depth, and temperature in the basic data at time t+1.

[0062] In an optional embodiment, the second object may also be constructed by implementing the following steps of a pre-trained model based on self-supervised learning:

[0063] Step 1: For large-scale unlabeled distribution network graph data, design self-supervised learning tasks, such as node prediction tasks (predicting node features) or edge prediction tasks (predicting the relationship between nodes), and learn high-quality feature representations of nodes and edges in the graph through these tasks.

[0064] Step 2: Use graph neural networks (such as GCN and GraphSAGE) to encode graph data, extract the structural features and attribute features of the graph, convert them into low-dimensional embedding vectors, and construct feature embedding representation.

[0065] In step 3, these pre-trained feature embeddings are input into the LSTM model as initialization parameters, so that the LSTM can obtain higher initial prediction capabilities from the structural information of the graph data.

[0066] Step 4: Further optimize the pre-trained initialized LSTM model, use the labeled data of the distribution network for supervised training to improve the model performance, complete the construction of the second object, and use it to predict the operation data of the distribution network with high precision, thereby significantly improving the prediction accuracy and generalization ability.

[0067] It should be noted that, the prediction model is preferably a long short-term memory model, which includes neurons that are repeatedly used in series.

[0068] S4: Input the first power distribution data into the second object to obtain a prediction result and perform scheduling.

[0069] In an embodiment of the present application, the inputting of the first power distribution data into the second object to obtain a prediction result and perform scheduling may be that, when formulating a resource scheduling strategy, the first power distribution data is first collected in real time and encoded to obtain a real-time code, the real-time code is input into a prediction model of the second object trained to a convergence state to obtain predicted operation data, and a scheduling strategy is formulated based on the predicted first power distribution data.

[0070] Among them, the predicted operation data is used to characterize the harmonics, output current, and output voltage generated by different new energy power supply equipment during operation, which are predicted based on the currently collected environmental data, cultural data, and distribution network operation data.

[0071] Furthermore, scheduling strategies are formulated based on the predicted operating data.

[0072] Specifically, a harmonic elimination strategy is formulated based on the predicted harmonic data. The output power of different new energy power supply equipment is adjusted according to the predicted output current and output voltage to ensure that the adjustment of the output current and output voltage is as small as possible, and the adjusted output current and output voltage meet the load requirements of the distribution network.

[0073] In an optional embodiment, inputting a prediction model to obtain a prediction result and performing scheduling may also be as follows: encoding the first power distribution data collected in real time and inputting it into the prediction model of a second object trained to a convergence state, and correcting the prediction result in combination with historical operation data to generate more accurate prediction operation data; dynamically adjusting the operation parameters of the new energy power supply equipment according to the prediction operation data and the corrected results, including the equipment's working mode switching, output power allocation, and operation priority setting.

[0074] Specifically, harmonic control strategies are implemented based on the predicted harmonic data. For example, the harmonic content in the distribution network can be reduced by starting or optimizing the operation of active filter devices. The power allocation strategy between devices is further optimized based on the predicted output current and output voltage. The load of some equipment is selectively reduced, and high-efficiency, low-fluctuation equipment is prioritized to achieve an overall improvement in the operating efficiency of the power supply equipment, while ensuring that the adjustment range is as small as possible and meets the real-time load requirements of the distribution network.

[0075] It should be noted that when formulating the resource scheduling strategy, the environmental data, humanities data and distribution network operation data are first collected in real time and encoded to obtain the real-time code, which is then input into the prediction model trained to a convergence state to obtain the predicted operation data.

[0076] Example 3: The following is an embodiment of the present invention, which provides a resource optimization scheduling method based on multi-port flexible interconnection. In order to verify the beneficial effects of the present invention, scientific demonstration is carried out through economic benefit calculation and simulation experiments.

[0077] First, weather environment (wind speed, visibility, precipitation, light intensity, duration of light) - impact - new energy power - impact - harmonic size Human environment (power station radiation range, population density, power consumption time, peak power consumption) - impact - distribution network architecture - impact - harmonic propagation

[0078] Demand survey: Investigate the current status of power distribution in high-density communities and the access to new energy sources, and clarify the specific needs for flexible expansion and optimized configuration. Flexible interconnection topology construction rules and design methods: Through simulation and case analysis, explore the construction rules of flexible interconnection topology under new energy access and form a design guide.

[0079] Research on modulation strategy and control technology: Research on modulation strategy, balance regulation and multi-terminal coordinated control technology to ensure the stable operation of equipment under the access of multiple new energy sources. Implementation of multi-terminal coordinated control technology: In a complex system with multiple new energy access and multiple port interactions, how to implement efficient and stable multi-terminal coordinated control technology to ensure the overall performance and security of the system is one of the difficulties in the research.

[0080] Effectiveness of field trials and feedback optimization: The field trial environment is complex, and data collection and analysis are difficult. How to effectively use field data feedback to optimize the system and ensure the practical application value of research results is another difficulty that needs to be overcome.

[0081] During the experiment, environmental data (wind speed, visibility, precipitation, light intensity), cultural data (power consumption duration, peak power consumption) and distribution network operation data (output power, voltage and current of new energy equipment) were collected according to the set sampling frequency.

[0082] Selection of test scenarios: A high-density community was selected, with a total area of ​​2 square kilometers and a population of about 15,000. Distributed photovoltaic systems and energy storage equipment were installed in the community, with a total power of 10MW and 2MW respectively, connected to multiple ports of the distribution network. Equipped with real-time monitoring equipment such as wind speed sensors, light intensity meters, and current sensors, the sampling frequency is set to 10 minutes / time. Environmental factors (wind speed, light intensity, etc.) and human factors (population density, peak electricity consumption, etc.) were set as input variables, and multi-port distribution data for 7 days were collected.

[0083] Newly collected power distribution data is input into the prediction model in real time to obtain the predicted values ​​of harmonics, current, and voltage of new energy equipment. The output power and operation mode of the equipment are dynamically adjusted based on the predicted data to ensure output stability and meet power supply needs. Based on the predicted harmonic data, a tuner is used to adjust the harmonic characteristics of specific equipment to reduce harmonic propagation.

[0084] Table 1 Experimental data table

[0085]

[0086] Data analysis and result comparison: Through the above experimental data, it can be found that the optimization strategy based on the method of the present invention effectively improves the operating stability and efficiency of the power distribution system:

[0087] The harmonic suppression effect is significant. After optimization (distribution ports E and F), the total harmonic distortion (THD) is reduced to 2.5% and 2.8% respectively, which is about 40% less than the unoptimized state (average THD is 4.37%). This shows that the prediction model has high accuracy and practicality in harmonic characteristic analysis and modulation strategy formulation.

[0088] After the optimization strategy was implemented, the adjustment range of the output power of the equipment at each distribution port was significantly reduced. For example, the output power of distribution port E was stabilized at 520kW, and the error compared with the predicted power was reduced to ±2.5%. This balanced adjustment greatly improved the operating life of the equipment. In the experiment, the output power of new energy equipment was dynamically adjusted to meet the peak power demand of the distribution network while reducing the risk of overload. For example, after the optimization of distribution port F, the output power was stabilized from 400kW to 450kW, and the output current and voltage fluctuations were significantly reduced.

[0089] Embodiment 4 is an embodiment of the present invention, which provides a resource optimization scheduling system based on multi-port flexible interconnection, including a data acquisition module, a data encoding module, a data prediction module, and a scheduling decision module;

[0090] The data acquisition module is used to collect power distribution data of the first object; the first power distribution status data is obtained at a preset sampling frequency by connecting distributed sensors and smart meters.

[0091] The data encoding module is used to encode the collected first power distribution data, generate attribute codes and determine object codes, and includes a data processing unit and an object encoding unit.

[0092] The data prediction module is used to construct second structure data based on the device code of the first object, train the prediction model, and generate the second object; it includes a graph data construction unit that generates graph data according to the device attributes and device edge weights of the first object; and a prediction model training unit that uses graph data to train a long short-term memory model.

[0093] The scheduling decision module is used to generate prediction results based on real-time power distribution data and formulate resource optimization scheduling strategies.

[0094] If the function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the methods of each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc. Various media that can store program codes.

[0095] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in conjunction with such instruction execution systems, devices or apparatuses. For the purposes of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in conjunction with such instruction execution systems, devices or apparatuses.

[0096] More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic device), a portable computer disk case (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be a paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, deciphering, or processing in another suitable manner as necessary, and then stored in a computer memory.

[0097] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, multiple steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc. It should be noted that the above embodiments are only used to illustrate the technical solution of the present invention and are not limited. Although the present invention is described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that the technical solution of the present invention can be modified or replaced by equivalents without departing from the spirit and scope of the technical solution of the present invention, which should be included in the scope of the claims of the present invention.

[0098] 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.

Claims

1. A resource optimization scheduling method based on multi-port flexible interconnection, characterized in that: include: Collecting first power distribution data of a first object; Encoding the first power distribution data to determine a first object code; Obtaining second structure data according to the first object encoding, and constructing a second object; The first power distribution data is input into the second object to obtain a prediction result and perform scheduling.

2. The resource optimization scheduling method based on multi-port flexible interconnection according to claim 1, characterized in that: The collecting of the first power distribution status data of the first object includes presetting a sampling frequency and collecting data at a plurality of sampling moments.

3. The resource optimization scheduling method based on multi-port flexible interconnection according to claim 2, characterized in that: The encoding of the first power distribution data includes encoding the first power distribution data at each moment to obtain the first power distribution data attribute code.

4. The resource optimization scheduling method based on multi-port flexible interconnection according to claim 3, characterized in that: The determining the first object code includes determining the device code of the first object according to the first power distribution data attribute code at each moment.

5. The resource optimization scheduling method based on multi-port flexible interconnection according to claim 4, characterized in that: The obtaining of the second structure data according to the encoding of the first object includes obtaining the edge weights between devices according to the inter-device attributes of the first object, and constructing graph data at each moment.

6. The resource optimization scheduling method based on multi-port flexible interconnection according to claim 5, characterized in that: The constructing the second object includes training a prediction model according to the graph data at each moment, the prediction model is used to predict the operation data of the distribution network, and obtaining the second object; The prediction model is preferably a long short-term memory model, which includes neurons that are repeatedly used in series.

7. The resource optimization scheduling method based on multi-port flexible interconnection according to claim 6, characterized in that: The method of inputting the first power distribution data into the second object to obtain a prediction result and perform scheduling includes, when formulating a resource scheduling strategy, first collecting the first power distribution data in real time and encoding it to obtain a real-time code, inputting the real-time code into a prediction model of the second object that has been trained to a convergence state to obtain predicted operation data, and formulating a scheduling strategy based on the predicted first power distribution data.

8. A system using the resource optimization scheduling method based on multi-port flexible interconnection as claimed in any one of claims 1 to 7, characterized in that: It includes data collection module, data encoding module, data prediction module and scheduling decision module; The data acquisition module is used to collect power distribution data of the first object; using the connected distributed sensor and the smart meter to obtain the first power distribution status data at a preset sampling frequency; The data encoding module is used to encode the collected first power distribution data, generate attribute codes and determine object codes, and includes a data processing unit and an object encoding unit; The data prediction module is used to construct the second structure data based on the device code of the first object, train the prediction model, and generate the second object; it includes a graph data construction unit that generates graph data according to the inter-device attributes and inter-device edge weights of the first object; and a prediction model training unit that uses the graph data to train the long short-term memory model; The scheduling decision module is used to generate prediction results based on real-time power distribution data and formulate resource optimization scheduling strategies.

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 resource optimization scheduling method based on multi-port flexible interconnection described in 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 resource optimization scheduling method based on multi-port flexible interconnection described in any one of claims 1 to 7 are implemented.

Images