Intelligent dispatching system and method based on new energy distribution network

Abstract

The present invention discloses an intelligent dispatching system and method based on a new energy distribution network, including a new energy distribution network acquisition module, a new energy distribution network processing module for establishing a safety impact assessment of each dispatched new energy distribution network point and an optimal dispatching model of the new energy distribution network, a new energy distribution network dispatching module, a new energy distribution network redundant energy storage dispatching module and a new energy distribution network correlation analysis module. The intelligent dispatching system of the new energy distribution network of the present invention can adapt to the new energy power grid to promote multi-energy complementarity and source-load interactive development, perform high-standard power grid operation safety management and control, and achieve clean and low-carbon development as the goal. It can coordinate and dispatch the resources of the entire system in real time for dynamic planning and development, establish a source-grid-load-storage collaborative interaction mechanism, and at the same time enhance the correlation analysis capability of the new energy power grid, comprehensively improve the computing scale and efficiency, and meet the dispatching and operation needs of the new energy power system.

Description

Technical Field

[0001] The present invention relates to the field of new energy data processing technology, and in particular to a smart dispatching system and method based on a new energy distribution network. Background Art

[0002] With the massive access and penetration of new energy, the operation characteristics of the power grid are becoming more and more complex, and the "double high" characteristics of the regional power grid are becoming more and more obvious. The characteristics of its power generation, such as randomness, volatility and dispersion, have led to a larger fluctuation in the power output of the power supply side during the day. The power grid flow is no longer the traditional "large power source flows to large loads". The power grid flow may change at any time with the different power generation conditions of new energy, and the risk of safe operation of the power grid is increasing. Therefore, at this stage, there is a lack of comprehensive analysis between the safety and dispatch of new energy distribution networks, and it is difficult to generate the optimal or stable new energy dispatch plan. In addition, the current power grid dispatch and operation characteristics analysis methods only conduct steady-state analysis on a certain operation mode and a certain section, and lack transient analysis methods for major changes in the "grid source load" ecology of the current power system, which cannot adapt to the high-standard control requirements of large power grids in the future diversified clean energy supply system. Summary of the invention

[0003] In view of the above-mentioned problems existing in the existing new energy power dispatching, the present invention is proposed.

[0004] Therefore, one of the objects of the present invention is to provide an intelligent dispatching system and method based on a new energy distribution network, which can conduct a comprehensive analysis of the power grid security and dispatching through an in-depth analysis of the operating mechanism of the new energy power grid, generate an optimal or stable new energy dispatching plan, and at the same time, autonomously understand learning and rapid fault processing, etc., to obtain an analysis of the temporary and stable operation status of the power grid, realize rapid linking of operation events, and select the plan for adjusting the stable state and optimizing dispatching.

[0005] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0006] On the one hand, the present invention provides a smart dispatching system based on a new energy distribution network, including: a new energy distribution network acquisition module, which is used to collect relevant data on the on-site environmental status of the new energy distribution network and the dispatched power output and perform data preprocessing and screening, and screen the characteristic information of meteorological factors, power output, dispatched units, dispatch time, and dispatch cost of the new energy distribution network;

[0007] The new energy distribution network processing module establishes the safety impact assessment of each dispatched new energy distribution network point and the optimal dispatch model of the new energy distribution network according to the collected data on the on-site environmental status of the new energy distribution network and the dispatched power output, and solves the solution results at the same time, and forms the optimized dispatch route data of the new energy distribution network according to the solution results; the safety impact assessment of the dispatched new energy distribution network point and the optimal dispatch model of the new energy distribution network are as follows:

[0008] The safety impact assessment is expressed as follows:

[0009]

[0010] Among them, P(X) represents the risk value solution model function expression of the dispatched new energy distribution network point; X represents the relevant data of dispatched power output collected when the meteorological factor data appears the most times, K represents the probability value of the current meteorological factor data changing to the harsh environment of new energy, ω i represents the weight value of the relevant data of dispatching power output collected for the i-th time at the current meteorological factor data, n is the total number of items collected for the i-th time, N represents the mixed weight, which represents the weight value of the power generation data of the dispatched new energy distribution network under the same meteorological factor data;

[0011] The function of the optimal dispatching model of the new energy distribution network is expressed as follows:

[0012]

[0013] Among them, V(Y) is the function expression of the optimal dispatching model of the new energy distribution network, t It is represented as the dispatching time period, k represents the number of dispatching units in the new energy distribution network, and j represents the power load node of the new energy distribution network; is the startup dispatch cost coefficient of the kth group of the new energy distribution network, α k,t For the kth group t The dispatch power of the dispatch time period, is the operation and maintenance cost coefficient of the kth group of the new energy distribution network, For the kth group t Active power output of power flow in each dispatching period; The kth group of redundant energy storage t The cost coefficient of each scheduling period, is the power value of the kth group of redundant energy storage; The cost reduction coefficient of the load in the eco state of the new energy distribution network, Q t,j For the t Schedule time period jThe load of each new energy distribution network load node;

[0014] The solution is obtained by evaluating the safety impact of the dispatched new energy distribution network points and solving the optimal dispatch model of the new energy distribution network, as follows:

[0015] f(·)=aP(X)+bV(Y); where f(·) is the activation function, a and b are the coefficients of the risk value solution model of the dispatched new energy distribution network point and the optimal dispatch model of the new energy distribution network respectively;

[0016] A new energy distribution network scheduling module is used to receive the current new energy distribution network scheduling event and respond to the new energy distribution network optimization scheduling route data generated by the analysis of the processing module, generate the scheduling distribution network route result data of the new energy distribution network, and optimize the scheduling of the new energy distribution network according to the distribution network route result data;

[0017] A redundant energy storage scheduling module for a new energy distribution network is connected to the new energy distribution network. The redundant energy storage includes a chemical battery energy storage system, a molten salt energy storage system for thermal energy storage, and a mechanical compressed air energy storage system. The redundant energy storage is used to perform peak regulation, frequency regulation, and voltage regulation functions on the new energy distribution network during operation of the new energy distribution network, that is, to regulate the new energy distribution network by calling redundant energy storage resources according to the operation requirements of the new energy distribution network.

[0018] The new energy distribution network association analysis module is connected to the new energy distribution network processing module. It is used for machine learning to conduct in-depth analysis of relevant data on the operation mechanism, on-site environmental status and dispatching power output of the new energy distribution network. At the same time, it can autonomously understand and learn the control procedures and quickly handle faults to obtain an analysis of the temporary and steady-state operation status of the power grid. It can automatically identify the system instability mechanism, quickly link with the new energy distribution network to optimize the dispatching events, and optimize the dispatching plan of the new energy distribution network in real time.

[0019] As a preferred solution of the present invention, the characteristic information of the electric energy output is combined with the real-time output power of new energy wind and photovoltaic power to draw a three-dimensional scatter plot and construct a fitting surface in the three-dimensional scatter plot. After screening out a valid training sample set based on the fitting surface, a wind and photovoltaic new energy power generation prediction model is constructed according to a logistic regression or neural network machine learning algorithm. According to the wind and photovoltaic new energy power generation prediction model, real-time dispatching power, current power active output power, and load of new energy distribution network load nodes are output.

[0020] As a preferred solution of the present invention, wherein: the new energy distribution network processing module includes a data set construction unit, a division unit, a verification unit, a generalized addition unit and an evaluation unit;

[0021] The data set construction unit is used to construct a wind, photovoltaic and new energy data set, collect relevant data on meteorological factors and their corresponding dispatched power output during normal operation in historical periods, and construct a wind, photovoltaic and new energy power generation data set;

[0022] The division unit is used for dividing the wind photovoltaic new energy power generation data set, dividing the samples of the wind photovoltaic new energy power generation data set into a training set and a prediction set, wherein the training set is used to build a model, and the prediction set is used to evaluate the prediction performance of the wind photovoltaic new energy power generation power prediction model;

[0023] The test unit is used for single factor significance test, constructing a single factor wind photovoltaic new energy power generation prediction model between a single explanatory variable and a response variable, and testing the significance of the wind photovoltaic new energy power generation prediction model;

[0024] The generalized addition unit is used to construct a generalized addition model, and the single-factor wind-photovoltaic new energy power generation prediction model that passes the significance test is added one by one to obtain a generalized addition wind-photovoltaic new energy power generation prediction model;

[0025] The evaluation unit is used to input the prediction set into the constructed generalized increased wind photovoltaic new energy power generation prediction model and output the corresponding prediction value, calculate the difference between the predicted value and the actual value through the intersection and entropy loss function, and evaluate the prediction performance of the wind photovoltaic new energy power generation prediction model.

[0026] As a preferred solution of the present invention, there are N independent and identically distributed wind and photovoltaic new energy power generation data sets X, which belong to C categories; each sample xi in the data set has a label yi, assuming that there are M expert networks, the actual value probability value given by the network of the mth generalized increase model to the ith sample xi is used as the prediction result, and combined with the prediction probability value P(x i ) is optimized through the cross entropy loss function, as follows:

[0027] The difference between the predicted value and the actual value is calculated by the cross-entropy loss function, as follows:

[0028]

[0029] Among them, H(P,Q) is the cross entropy function, P(x i ) is the predicted probability value of the wind and solar power generation power prediction model, Q(x i ) is the probability value of the actual value of the generalized increase in wind and solar power generation power, and log is the logarithm with base e.

[0030] As a preferred embodiment of the present invention, the meteorological factors include illumination information, solar radiation, wind speed and direction information, weather temperature and humidity information, precipitation information, air pressure information, evaporation information, fog and haze information, frost and hail information, seasonal changes, and climate change information;

[0031] The electrical energy output includes current, voltage and power.

[0032] As a preferred solution of the present invention, the dispatching cost characteristic information includes: energy, equipment and labor costs of new energy distribution network, new energy storage costs, distribution network investment costs, dispatching operation costs, operation and maintenance service costs and electricity price mechanism costs.

[0033] As a preferred solution of the present invention, wherein: the new energy distribution network processing module includes an impact assessment unit and a scheduling correction unit;

[0034] The impact assessment unit is used to analyze the impact between the safety impact assessment and the optimal scheduling model of the new energy distribution network, specifically as follows:

[0035]

[0036]

[0037] Among them, Winf P(X),V(Y) The risk value of the dispatched new energy distribution network point is solved by the model that affects the optimal dispatch model of the new energy distribution network. CBT P(X),V(Y) It is represented by the trust of the risk value solution model of the dispatched renewable energy distribution network point and the optimal dispatch model of the renewable energy distribution network. Similarity(P(X),V(Y)) is represented by the Pearson correlation coefficient between the risk value solution model of the dispatched renewable energy distribution network point and the solution value of the optimal dispatch model of the renewable energy distribution network.

[0038] The scheduling correction unit is used to respond to the impact degree and generate corresponding correction data according to the impact degree data, and then make corresponding adjustments to the coefficients of the risk value solution model of the scheduled new energy distribution network point and the optimal scheduling model of the new energy distribution network.

[0039] As a preferred solution of the present invention, wherein: the new energy distribution network association analysis module includes an acquisition unit, a feature extraction unit, a fault diagnosis unit, an association unit and a feedback update unit;

[0040] The acquisition unit is used to acquire data information of key nodes of the new energy distribution network, and the data information is data related to the on-site environmental status of the new energy distribution network and the dispatching power output;

[0041] The feature extraction unit is used to extract features from data information of key nodes of the new energy distribution network, so as to obtain feature extraction of fault and instability mechanism of the new energy distribution network based on time series;

[0042] The fault diagnosis unit is used to perform fault diagnosis on the fault characteristics of the new energy distribution network and generate a fault diagnosis result in combination with a manual expert or a large model expert group and based on a preset fault map of the new energy distribution network;

[0043] The association unit is used to respond to the fault diagnosis result, automatically generate and instability mechanism case event clusters in the new energy distribution network fault map, form a multi-scale representation and multi-dimensional association for a single fault, and automatically search and match the new energy distribution network after the fault and the instability solution decision;

[0044] The feedback update unit is used to send the fault diagnosis results and the matched new energy distribution network instability solution decisions to the key nodes of the new energy distribution network for feedback, generate corresponding feedback data and transmit it back to the new energy distribution network server, and update and optimize the corresponding fault problem feature data.

[0045] As a preferred solution of the present invention, the relevant data of the on-site environmental status of the new energy distribution network and the dispatching power output are preprocessed, including processing missing values, data conversion, integration and standardization.

[0046] In one aspect, the present invention provides a method for a smart dispatching system based on a new energy distribution network, comprising:

[0047] Step S10, collecting data related to the on-site environmental status of the new energy distribution network and the dispatching power output and preprocessing and screening the data;

[0048] Step S20, based on the collected data on the on-site environmental status of the new energy distribution network and the dispatched power output, establish a safety impact assessment of each dispatched new energy distribution network point and an optimal dispatch model of the new energy distribution network, and simultaneously solve the solution to obtain a solution result, and form the optimized dispatch route data of the new energy distribution network according to the solution result;

[0049] Step S30, receiving the current new energy distribution network dispatching event and responding to the new energy distribution network optimization dispatching route data, generating the dispatching distribution network route result data of the new energy distribution network, and optimizing the dispatching of the new energy distribution network according to the distribution network route result data; at the same time, through machine learning, in-depth analysis of the relevant data of the operation mechanism, on-site environmental status and dispatching power output of the new energy distribution network, and at the same time, autonomous understanding and learning of the control procedures and rapid fault processing, to obtain an analysis of the transient and steady-state operation status of the power grid, which can automatically identify the system instability mechanism, quickly link with the new energy distribution network to optimize the dispatching event, and perform real-time optimization of the dispatching plan for the new energy distribution network.

[0050] The beneficial effects of the present invention are as follows: it is adapted to the new energy grid to promote multi-energy complementarity and source-load interactive development, and to carry out safe control of grid operation at high standards, with the goal of achieving clean and low-carbon development. It can coordinate and dispatch the resources of the entire system in real time for dynamic planning and development, and establish a source-grid-load-storage collaborative interactive mechanism to meet the higher requirements for dispatch compliance, refinement, and information transparency, while enhancing the correlation analysis capabilities of the new energy grid, comprehensively improving the computing scale and efficiency, and meeting the dispatch and operation needs of the new energy power system. At the same time, it improves the resilience of responding to new energy grid failures and the recovery capacity of the new energy power system, thereby improving the lean level of dispatch decision-making and achieving the coordination and unification of new energy grid safety and market efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] 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:

[0052] Figure 1 It is a schematic diagram of the modular structure of the present invention;

[0053] Figure 2 It is a schematic diagram of the process of the present invention;

[0054] Numbers in the figure: 10, new energy distribution network acquisition module; 20, new energy distribution network processing module; 30, new energy distribution network scheduling module; 40, new energy distribution network redundant energy storage scheduling module; 50, new energy distribution network correlation analysis module. DETAILED DESCRIPTION

[0055] In order to make the purpose, technical solution and advantages of the embodiment of the present invention clearer, the technical solution of the embodiment of the present invention will be clearly and completely described below in conjunction with the drawings of the embodiment of the present invention. Obviously, the described embodiment is a part of the embodiment of the present invention, not all of the embodiments. Based on the described embodiment of the present invention, all other embodiments obtained by ordinary technicians in this field belong to the scope of protection of the present invention.

[0056] Reference Figure 1-Figure 2 , is an embodiment of the present invention, which provides a smart dispatching system and method based on a new energy distribution network, including:

[0057] The new energy distribution network acquisition module 10 is used to collect relevant data on the on-site environmental status of the new energy distribution network and the dispatched power output and perform data preprocessing and screening, and screen the characteristic information of the meteorological factors, power output, dispatching units, dispatching time, and dispatching costs of the new energy distribution network; among them, the relevant data on the on-site environmental status of the new energy distribution network and the dispatched power output and perform data preprocessing, including processing missing values, data conversion, integration and standardization.

[0058] The new energy distribution network processing module 20 establishes the safety impact assessment of each dispatched new energy distribution network point and the optimal dispatch model of the new energy distribution network according to the collected data on the on-site environmental status of the new energy distribution network and the dispatched power output, and solves the solution results at the same time, and forms the optimized dispatch route data of the new energy distribution network according to the solution results; the safety impact assessment of the dispatched new energy distribution network point and the optimal dispatch model of the new energy distribution network are as follows:

[0059] The security impact assessment is expressed as follows:

[0060]

[0061] Among them, P(X) represents the risk value solution model function expression of the dispatched new energy distribution network point; X represents the relevant data of dispatched power output collected when the meteorological factor data appears the most times, K represents the probability value of the current meteorological factor data changing to the harsh environment of new energy, ω i represents the weight value of the relevant data of dispatching power output collected for the i-th time at the current meteorological factor data, n is the total number of items collected for the i-th time, N represents the mixed weight, which represents the weight value of the power generation data of the dispatched new energy distribution network under the same meteorological factor data;

[0062] The function of the optimal dispatching model of the new energy distribution network is expressed as follows:

[0063]

[0064] Among them, V(Y) is the function expression of the optimal dispatching model of the new energy distribution network, t It is represented as the dispatching time period, k represents the number of dispatching units in the new energy distribution network, and j represents the power load node of the new energy distribution network; is the startup dispatch cost coefficient of the kth group of the new energy distribution network, α k,t For the kth group t The dispatch power of the dispatch time period, is the operation and maintenance cost coefficient of the kth group of the new energy distribution network, For the kth group t Active power output of power flow in each dispatching period; The kth group of redundant energy storage t The cost coefficient of each scheduling period, is the power value of the kth group of redundant energy storage; The cost reduction coefficient of the load in the eco state of the new energy distribution network, Q t,j For the t Schedule time period j The load of each new energy distribution network load node;

[0065] The solution is obtained by evaluating the safety impact of the dispatched new energy distribution network points and solving the optimal dispatch model of the new energy distribution network, as follows:

[0066] f(·)=aP(X)+bV(Y); where f(·) is the activation function, a and b are the coefficients of the risk value solution model of the dispatched new energy distribution network point and the optimal dispatch model of the new energy distribution network respectively;

[0067] The new energy distribution network scheduling module 30 is used to receive the current new energy distribution network scheduling event and respond to the new energy distribution network optimization scheduling route data generated by the processing module 20, generate the scheduling distribution network route result data of the new energy distribution network, and optimize the scheduling of the new energy distribution network according to the distribution network route result data;

[0068] A redundant energy storage scheduling module 40 for a new energy distribution network is connected to the new energy distribution network. The redundant energy storage includes a chemical battery energy storage system, a molten salt energy storage system for thermal energy storage, and a mechanical compressed air energy storage system. The redundant energy storage is used to perform peak regulation, frequency regulation, and voltage regulation functions on the new energy distribution network during operation of the new energy distribution network, that is, to regulate the new energy distribution network by calling redundant energy storage resources according to the operation requirements of the new energy distribution network.

[0069] The new energy distribution network association analysis module 50 is connected to the new energy distribution network processing module 20, and is used for machine learning to conduct in-depth analysis of relevant data on the operation mechanism, on-site environmental status and dispatched power output of the new energy distribution network. At the same time, it can autonomously understand and learn the control procedures and quickly handle faults to obtain an analysis of the temporary and steady-state operation status of the power grid. It can automatically identify the system instability mechanism, quickly link with the new energy distribution network to optimize the dispatching events, and optimize the dispatching plan of the new energy distribution network in real time.

[0070] Preferably, in this embodiment, the characteristic information of electric energy output is combined with the real-time output power of new energy wind and photovoltaic power to draw a three-dimensional scatter plot and construct a fitting surface in the three-dimensional scatter plot; after screening out a valid training sample set based on the fitting surface, a wind and photovoltaic new energy power generation prediction model is constructed according to a logistic regression or neural network machine learning algorithm; and the wind and photovoltaic new energy power generation prediction model outputs real-time dispatching power, current power active output power, and load of new energy distribution network load nodes.

[0071] Further, in this embodiment, the new energy distribution network processing module 20 includes a data set construction unit, a division unit, a verification unit, a generalized addition unit, and an evaluation unit;

[0072] The data set construction unit is used to construct a wind, photovoltaic and new energy data set, collect meteorological factors during normal operation in historical periods and relevant data on their corresponding dispatched power output, and construct a wind, photovoltaic and new energy power generation data set;

[0073] The partitioning unit is used for partitioning the wind and solar energy new energy power generation data set, and divides the samples of the wind and solar energy new energy power generation data set into a training set and a prediction set, wherein the training set is used to build a model, and the prediction set is used to evaluate the prediction performance of the wind and solar energy new energy power generation power prediction model;

[0074] The test unit is used for single factor significance test, to build a single factor wind photovoltaic new energy power generation prediction model between a single explanatory variable and a response variable, and to test the significance of the wind photovoltaic new energy power generation prediction model;

[0075] The generalized addition unit is used to construct a generalized addition model, and the single-factor wind and photovoltaic new energy power generation prediction model that passes the significance test is added one by one to obtain the generalized addition wind and photovoltaic new energy power generation prediction model;

[0076] The evaluation unit is used to input the prediction set into the constructed generalized incremental wind and photovoltaic new energy power generation prediction model and output the corresponding prediction value, calculate the difference between the prediction value and the actual value through the intersection and entropy loss function, and evaluate the prediction performance of the wind and photovoltaic new energy power generation prediction model.

[0077] This embodiment is based on the above and needs to be emphasized that there are N independent and identically distributed wind and photovoltaic new energy power generation data sets X, which belong to C categories; each sample xi in the data set has a label yi, assuming that there are M expert networks, the network of the mth generalized increase model gives the actual value probability value of the ith sample xi as the prediction result, and combined with the prediction probability value P(x i ) is optimized through the cross entropy loss function, as follows:

[0078] The difference between the predicted value and the actual value is calculated by the cross-entropy loss function, as follows:

[0079]

[0080] Among them, H(P,Q) is the cross entropy function, P(x i ) is the predicted probability value of the wind and solar power generation power prediction model, Q(x i ) is the probability value of the actual value of the generalized increase in wind and solar power generation power, and log is the logarithm with base e.

[0081] Specifically, in this embodiment, meteorological factors include illumination information, solar radiation, wind speed and direction information, weather temperature and humidity information, precipitation information, air pressure information, evaporation information, fog and haze information, frost and hail information, seasonal changes, and climate change information; power output includes current, voltage, and power. In addition, the dispatch cost characteristic information includes: new energy distribution network energy, equipment and labor costs, new energy storage costs, distribution network investment costs, dispatch operation costs, operation and maintenance service costs, and electricity price mechanism costs.

[0082] It should be emphasized in this embodiment that the new energy distribution network processing module 20 includes an impact assessment unit and a scheduling correction unit;

[0083] The impact assessment unit is used to analyze the impact between the safety impact assessment and the optimal dispatching model of the new energy distribution network, as follows:

[0084]

[0085] Among them, Winf P(X),V(Y) The risk value of the dispatched new energy distribution network point is solved by the model that affects the optimal dispatch model of the new energy distribution network. CBT P (X), V(Y) represents the trust of the risk value solution model of the dispatched new energy distribution network point and the optimal dispatch model of the new energy distribution network. Similarity(P(X), V(Y)) represents the Pearson correlation coefficient between the risk value solution model of the dispatched new energy distribution network point and the solution value of the optimal dispatch model of the new energy distribution network.

[0086] The dispatch correction unit is used to respond to the impact degree and generate corresponding correction data based on the impact degree data, and then make corresponding adjustments to the coefficients of the risk value solution model of the dispatched new energy distribution network point and the optimal dispatch model of the new energy distribution network.

[0087] In this embodiment, preferably, the new energy distribution network association analysis module 50 includes an acquisition unit, a feature extraction unit, a fault diagnosis unit, an association unit and a feedback update unit;

[0088] The acquisition unit is used to acquire data information of key nodes of the new energy distribution network, and the data information is data related to the on-site environmental status of the new energy distribution network and the dispatching power output;

[0089] The feature extraction unit is used to extract features from data information of key nodes of the new energy distribution network, so as to obtain feature extraction of fault and instability mechanism of the new energy distribution network based on time series;

[0090] The fault diagnosis unit is used to combine artificial experts or a large model expert group and, based on a preset fault map of the new energy distribution network, perform fault diagnosis on the fault characteristics of the new energy distribution network and generate a fault diagnosis result;

[0091] The association unit is used to respond to the fault diagnosis results, automatically generate and instability mechanism case event clusters in the fault map of the new energy distribution network, form a multi-scale representation and multi-dimensional association for a single fault, and automatically search and match the new energy distribution network after the fault and the instability solution decision;

[0092] The feedback update unit is used to send the fault diagnosis results and the matched new energy distribution network instability solution decisions to the key nodes of the new energy distribution network for feedback, generate corresponding feedback data and transmit it back to the new energy distribution network server, and update and optimize the corresponding fault problem feature data.

[0093] Based on the above, this embodiment introduces artificial intelligence technology, such as deep learning technology, to build a smart grid dispatching system. Through in-depth analysis of the grid operation mechanism, autonomous understanding and learning of control procedures, and rapid fault processing, it is possible to obtain an analysis of the current status of the grid's transient and steady-state operation, automatically identify the system's instability mechanism, quickly link operation events, and propose solutions to adjust the stable state.

[0094] In summary, the intelligent dispatching system of the new energy distribution network of the present invention can adapt to the new energy power grid to promote multi-energy complementarity and source-load interactive development, and carry out safety management and control of power grid operation with high standards, with the goal of achieving clean and low-carbon development. It can coordinate and dispatch the resources of the entire system in real time for dynamic planning and development, and establish a source-grid-load-storage collaborative interaction mechanism to meet the higher requirements for dispatch compliance, refinement, and information transparency, while enhancing the correlation analysis capabilities of the new energy power grid, comprehensively improving the computing scale and efficiency, and meeting the dispatching and operation needs of the new energy power system. At the same time, it improves the resilience to cope with new energy power grid failures and the recovery capacity of the new energy power system, thereby improving the lean level of dispatching decisions and achieving the coordination and unification of new energy power grid safety and market efficiency.

[0095] This embodiment also provides a method for a smart dispatching system based on a new energy distribution network, including:

[0096] Step S10, collecting data related to the on-site environmental status of the new energy distribution network and the dispatching power output and preprocessing and screening the data;

[0097] Step S20, based on the collected data on the on-site environmental status of the new energy distribution network and the dispatched power output, establish a safety impact assessment of each dispatched new energy distribution network point and an optimal dispatch model of the new energy distribution network, and simultaneously solve the solution to obtain a solution result, and form the optimized dispatch route data of the new energy distribution network according to the solution result;

[0098] Step S30, receiving the current new energy distribution network dispatching event and responding to the new energy distribution network optimization dispatching route data, optimizing the dispatching of the new energy distribution network according to the distribution network route result data; and optimizing the dispatching scheme of the new energy distribution network in real time at the same time; specifically receiving the current new energy distribution network dispatching event and responding to the new energy distribution network optimization dispatching route data, generating the dispatching distribution network route result data of the new energy distribution network, and optimizing the dispatching of the new energy distribution network according to the distribution network route result data; at the same time, through machine learning, in-depth analysis of the relevant data of the operation mechanism, on-site environmental status and dispatching power output of the new energy distribution network, and at the same time, autonomous understanding and learning of the control procedures and rapid fault processing, to obtain an analysis of the transient and steady-state operation status of the power grid, which can automatically identify the system instability mechanism, quickly link with the new energy distribution network to optimize the dispatching event, and optimize the dispatching scheme of the new energy distribution network in real time.

[0099] Among them, non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), erasable PROM (EPROM), electrically erasable programmable read-only memory (EEPROM) or flash memory. Volatile memory can include random access memory (RAM), which is used as an external cache. By way of example but not limitation, many forms of RAM are available. For example, static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDR SDRAM), enhanced synchronous dynamic random access memory enhanced SDRAM, ESDRAM), synchronous connection dynamic random access memory (SLDRAM) and direct memory bus random access memory (DR RAM).

[0100] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented using software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function according to the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium.

[0101] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine different embodiments or examples described in this specification and the features of different embodiments or examples, unless they are contradictory.

[0102] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Therefore, a feature defined as "first" or "second" may explicitly or implicitly include at least one of the features. In the description of this application, the meaning of "plurality" is two or more, unless otherwise clearly and specifically defined.

[0103] Any process or method description in the flow chart or otherwise described herein can be understood to represent a module, fragment or portion of a code including one or more executable instructions for implementing the steps of a specific logical function or process. And the scope of the preferred embodiment of the present application includes other implementations, in which the functions may not be performed in the order shown or discussed, including in a substantially simultaneous manner or in a reverse order according to the functions involved.

[0104] 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, which can be embodied in any computer-readable medium for use by an instruction execution system, apparatus or device such as a computer-based system, a system including a processor or other system that can fetch instructions from an instruction execution system, apparatus or device and execute instructions, or used in conjunction with these instruction execution systems, apparatuses or devices.

[0105] It should be understood that the various parts of the present application can be implemented with hardware, software, firmware or a combination thereof. In the above embodiments, multiple steps or methods can be implemented with software or firmware stored in a memory and executed by a suitable instruction execution system. All or part of the steps of the above embodiment method can be completed by instructing the relevant hardware through a program, which can be stored in a computer-readable storage medium, and when the program is executed, it includes one of the steps of the method embodiment or a combination thereof.

[0106] In addition, each functional unit in each embodiment of the present application can be integrated into a processing module, or each unit can exist physically separately, or two or more units can be integrated into one module. The above-mentioned integrated module can be implemented in the form of hardware or in the form of a software functional module. If the above-mentioned integrated module is implemented in the form of a software functional module and sold or used as an independent product, it can also be stored in a computer-readable storage medium. The storage medium can be a read-only memory, a disk or an optical disk, etc.

[0107] The above are only specific implementations of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of various changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. The intelligent dispatching system based on the new energy distribution network is characterized by: include: A new energy distribution network acquisition module (10) is used to collect data related to the on-site environmental status of the new energy distribution network and the dispatched power output, and to pre-process and screen the data, and to screen the characteristic information of the meteorological factors, power output, dispatched units, dispatch time, and dispatch cost of the new energy distribution network; The new energy distribution network processing module (20) establishes a safety impact assessment of each dispatched new energy distribution network point and an optimal dispatch model of the new energy distribution network based on the collected data on the on-site environmental status of the new energy distribution network and the dispatched electric energy output, and simultaneously performs a solution to obtain a solution result, and forms optimized dispatch route data of the new energy distribution network based on the solution result; the safety impact assessment of the dispatched new energy distribution network point and the optimal dispatch model of the new energy distribution network are as follows: The safety impact assessment is expressed as follows: Among them, P(X) represents the risk value solution model function expression of the dispatched new energy distribution network point; X represents the relevant data of dispatched power output collected when the meteorological factor data appears the most times, K represents the probability value of the current meteorological factor data changing to the harsh environment of new energy, ω i represents the weight value of the relevant data of dispatching power output collected for the i-th time at the current meteorological factor data, n is the total number of items collected for the i-th time, N represents the mixed weight, which represents the weight value of the power generation data of the dispatched new energy distribution network under the same meteorological factor data; The function of the optimal dispatching model of the new energy distribution network is expressed as follows: Among them, V(Y) is the function expression of the optimal dispatching model of the new energy distribution network, t It is represented as the dispatching time period, k represents the number of dispatching units in the new energy distribution network, and j represents the power load node of the new energy distribution network; is the startup dispatch cost coefficient of the kth group of the new energy distribution network, α k,t For the kth group t The dispatch power of the dispatch time period, is the operation and maintenance cost coefficient of the kth group of the new energy distribution network, For the kth group t Active power output of power flow in each dispatching period; The kth group of redundant energy storage t The cost coefficient of each scheduling period, is the power value of the kth group of redundant energy storage; The cost reduction coefficient of the load in the eco state of the new energy distribution network, Q t,j For the t Schedule time period j The load of each new energy distribution network load node; The solution is obtained by evaluating the safety impact of the dispatched new energy distribution network points and solving the optimal dispatch model of the new energy distribution network, as follows: f(·)=aP(X)+bV(Y); where f(·) is the activation function, a and b are the coefficients of the risk value solution model of the dispatched new energy distribution network point and the optimal dispatch model of the new energy distribution network respectively; A new energy distribution network dispatching module (30) is used to receive a current new energy distribution network dispatching event and respond to the new energy distribution network optimization dispatching route data generated by the analysis of the new energy distribution network processing module (20), generate dispatching distribution network route result data of the new energy distribution network, and perform optimization dispatching of the new energy distribution network according to the distribution network route result data; A new energy distribution network redundant energy storage scheduling module (40) is connected to the new energy distribution network, the redundant energy storage includes a chemical battery energy storage system, a thermal energy storage molten salt energy storage system and a mechanical compressed air energy storage, and is used to perform peak regulation, frequency regulation and voltage regulation functions on the new energy distribution network during operation of the new energy distribution network, that is, to regulate the new energy distribution network by calling redundant energy storage resources according to the operation requirements of the new energy distribution network; The new energy distribution network association analysis module (50) is connected to the new energy distribution network processing module (20) and is used for machine learning to deeply analyze the relevant data of the operation mechanism, on-site environmental status and dispatched power output of the new energy distribution network, and at the same time, autonomously understand and learn the control procedures and quickly handle faults to obtain an analysis of the current status of the transient and steady-state operation of the power grid, automatically identify the system instability mechanism, quickly link with the new energy distribution network to optimize the dispatching event, and optimize the dispatching plan of the new energy distribution network in real time.

2. The intelligent dispatching system based on the new energy distribution network as claimed in claim 1, characterized in that: The characteristic information of the electric energy output is combined with the real-time output power of new energy wind and photovoltaic power to draw a three-dimensional scatter plot and construct a fitting surface in the three-dimensional scatter plot. After screening out a valid training sample set based on the fitting surface, a wind and photovoltaic new energy power generation power prediction model is constructed according to a logistic regression or neural network machine learning algorithm. The wind and photovoltaic new energy power generation power prediction model outputs real-time dispatching power, current power active output power, and load of new energy distribution network load nodes.

3. The intelligent dispatching system based on the new energy distribution network as claimed in claim 2, characterized in that: The new energy distribution network processing module (20) comprises a data set construction unit, a division unit, a verification unit, a generalized addition unit and an evaluation unit; The data set construction unit is used to construct a wind, photovoltaic and new energy data set, collect relevant data on meteorological factors and their corresponding dispatched power output during normal operation in historical periods, and construct a wind, photovoltaic and new energy power generation data set; The division unit is used for dividing the wind photovoltaic new energy power generation data set, dividing the samples of the wind photovoltaic new energy power generation data set into a training set and a prediction set, wherein the training set is used to build a model, and the prediction set is used to evaluate the prediction performance of the wind photovoltaic new energy power generation power prediction model; The test unit is used for single factor significance test, constructing a single factor wind photovoltaic new energy power generation prediction model between a single explanatory variable and a response variable, and testing the significance of the wind photovoltaic new energy power generation prediction model; The generalized addition unit is used to construct a generalized addition model, and the single-factor wind-photovoltaic new energy power generation prediction model that passes the significance test is added one by one to obtain a generalized addition wind-photovoltaic new energy power generation prediction model; The evaluation unit is used to input the prediction set into the constructed generalized increased wind photovoltaic new energy power generation prediction model and output the corresponding prediction value, calculate the difference between the predicted value and the actual value through the intersection and entropy loss function, and evaluate the prediction performance of the wind photovoltaic new energy power generation prediction model.

4. The intelligent dispatching system based on the new energy distribution network as claimed in claim 3 is characterized in that: Suppose there are N independent and identically distributed wind and solar power generation data sets X, which belong to C categories; each sample xi in the data set has a label yi. Assuming there are M expert networks, the actual value probability value given by the network of the mth generalized increase model to the i-th sample xi is used as the prediction result, and combined with the predicted probability value P(x i ) is optimized through the cross entropy loss function, as follows: The difference between the predicted value and the actual value is calculated by the cross-entropy loss function, as follows: Among them, H(P,Q) is the cross entropy function, P(x i ) is the predicted probability value of the wind and solar power generation power prediction model, Q(x i ) is the probability value of the actual value of the generalized increase in wind and solar power generation power, and log is the logarithm with base e.

5. The intelligent dispatching system based on the new energy distribution network as claimed in claim 1, characterized in that: The meteorological factors include illumination information, solar radiation, wind speed and direction information, weather temperature and humidity information, precipitation information, air pressure information, evaporation information, fog and haze information, frost and hail information, seasonal changes, and climate change information; The electrical energy output includes current, voltage and power.

6. The intelligent dispatching system based on the new energy distribution network according to claim 1, characterized in that: The dispatching cost characteristic information includes: energy, equipment and labor costs of new energy distribution networks, new energy storage costs, distribution network investment costs, dispatching operation costs, operation and maintenance service costs and electricity price mechanism costs.

7. The intelligent dispatching system based on the new energy distribution network as claimed in claim 1, characterized in that: The new energy distribution network processing module (20) comprises an impact assessment unit and a scheduling correction unit; The impact assessment unit is used to analyze the impact between the safety impact assessment and the optimal scheduling model of the new energy distribution network, specifically as follows: Among them, Winf P(X),V(Y) The risk value solution model for the dispatched renewable energy distribution network point has an impact on the optimal dispatch model of the renewable energy distribution network. CBT P(X),V(Y) It is represented by the trust of the risk value solution model of the dispatched renewable energy distribution network point and the optimal dispatch model of the renewable energy distribution network. Similarity(P(X),V(Y)) is represented by the Pearson correlation coefficient between the risk value solution model of the dispatched renewable energy distribution network point and the solution value of the optimal dispatch model of the renewable energy distribution network. The scheduling correction unit is used to respond to the impact degree and generate corresponding correction data according to the impact degree data, and then make corresponding adjustments to the coefficients of the risk value solution model of the scheduled new energy distribution network point and the optimal scheduling model of the new energy distribution network.

8. The intelligent dispatching system based on the new energy distribution network as claimed in claim 1, characterized in that: The new energy distribution network association analysis module (50) comprises an acquisition unit, a feature extraction unit, a fault diagnosis unit, an association unit and a feedback update unit; The acquisition unit is used to acquire data information of key nodes of the new energy distribution network, and the data information is data related to the on-site environmental status of the new energy distribution network and the dispatching power output; The feature extraction unit is used to extract features from data information of key nodes of the new energy distribution network, so as to obtain feature extraction of fault and instability mechanism of the new energy distribution network based on time series; The fault diagnosis unit is used to perform fault diagnosis on the fault characteristics of the new energy distribution network and generate a fault diagnosis result in combination with a manual expert or a large model expert group and based on a preset fault map of the new energy distribution network; The association unit is used to respond to the fault diagnosis result, automatically generate and instability mechanism case event clusters in the new energy distribution network fault map, form a multi-scale representation and multi-dimensional association for a single fault, and automatically search and match the new energy distribution network after the fault and the instability solution decision; The feedback update unit is used to send the fault diagnosis results and the matched new energy distribution network instability solution decisions to the key nodes of the new energy distribution network for feedback, generate corresponding feedback data and transmit it back to the new energy distribution network server, and update and optimize the corresponding fault problem feature data.

9. The intelligent dispatching system based on the new energy distribution network as claimed in claim 1, characterized in that: The relevant data of the on-site environmental status of the new energy distribution network and the dispatching electric energy output are preprocessed, including processing missing values, data conversion, integration and standardization.

10. The method of the intelligent dispatching system based on the new energy distribution network according to claim 1, characterized in that: include: Step S10, collecting data related to the on-site environmental status of the new energy distribution network and the dispatched power output, and preprocessing and screening the data; Step S20, based on the collected data on the on-site environmental status of the new energy distribution network and the dispatched power output, establish a safety impact assessment of each dispatched new energy distribution network point and an optimal dispatch model of the new energy distribution network, and simultaneously solve the solution to obtain a solution result, and form the optimized dispatch route data of the new energy distribution network according to the solution result; Step S30, receiving the current new energy distribution network dispatching event and responding to the new energy distribution network optimization dispatching route data, generating the dispatching distribution network route result data of the new energy distribution network, and optimizing the dispatching of the new energy distribution network according to the distribution network route result data; at the same time, through machine learning, in-depth analysis of the relevant data of the new energy distribution network operation mechanism, on-site environmental status and dispatching power output, and at the same time, autonomous understanding and learning of the control procedures and rapid fault processing, to obtain an analysis of the transient and steady-state operation status of the power grid, which can automatically identify the system instability mechanism, quickly link with the new energy distribution network to optimize the dispatching event, and perform real-time optimization of the dispatching plan for the new energy distribution network.

Images