Multi-element novel energy storage aggregation scheduling system based on intelligent power grid optimization algorithm

Abstract

The invention discloses a multi-element novel energy storage aggregation scheduling system based on an intelligent power grid optimization algorithm, which belongs to the technical field of intelligent power grids and comprises an acquisition module, an optimization server module, an intelligent algorithm module and an energy scheduling module. The energy scheduling module comprises an energy scheduling module based on a genetic algorithm, an energy scheduling module based on a neural network and an energy scheduling module based on fuzzy logic; the acquisition module acquires power grid equipment information data in an area; the acquisition module sends acquired power grid equipment information data to the optimization server module; the energy scheduling module based on the genetic algorithm in the energy scheduling module can optimize energy scheduling by applying the genetic algorithm, the generation, transformation, transmission and consumption processes of each energy are abstracted into gene codes, and the gene codes are optimized through the selection, intersection and variation processes of the genetic algorithm. And obtaining an optimal solution so as to realize energy scheduling.

Description

Technical Field

[0001] The present application belongs to the field of smart grid technology, and specifically, relates to a new multi-element energy storage aggregation scheduling system based on a smart grid optimization algorithm. Background Art

[0002] With the increase in the scale of different types of energy storage such as electrochemical, compressed air, and gravity, new types of energy storage have become a research hotspot by optimizing internal power distribution, achieving mutual coordination and support, jointly coping with peak-shaving problems, and improving system operation efficiency.

[0003] Power grid dispatching is an effective management method to ensure the safe and stable operation of the power grid, reliable external power supply, and orderly progress of various types of power production. The specific work content of power dispatching is to judge the safety and economic operation status of the power grid based on the data information fed back by various information collection equipment, or the information provided by monitoring personnel, combined with the actual operation parameters of the power grid, such as voltage, current, frequency, load, etc., comprehensively consider the development of various production work, issue operation instructions through telephone or automatic system, and command on-site operators or automatic control systems to make adjustments, such as adjusting generator output, adjusting load distribution, switching capacitors, reactors, etc., so as to ensure the continuous safe and stable operation of the power grid. In recent years, with the continuous development of science and technology, modern monitoring and control methods have been continuously improved, and the technical support for power dispatching has become increasingly powerful.

[0004] However, the dispatching system in the existing technology still has certain shortcomings. During the operation of the existing dispatching system, the multi-objective algorithm may not be able to simultaneously calculate the multiple requirements of operating costs, new energy consumption, and load supply, which may make it impossible to calculate the optimal energy dispatching plan in the fastest time. Summary of the invention

[0005] In order to solve the above problems and technical defects, the embodiment of the present application adopts the following technical solution, a multi-element new energy storage aggregation scheduling system based on a smart grid optimization algorithm, including:

[0006] Acquisition module, optimization server module, intelligent algorithm module and energy scheduling module;

[0007] The energy scheduling module includes an energy scheduling module based on genetic algorithm, an energy scheduling module based on neural network and an energy scheduling module based on fuzzy logic;

[0008] The acquisition module acquires information data of power grid equipment in the area;

[0009] The acquisition module sends the collected power grid equipment information data to the optimization server module;

[0010] The optimization server module combines with the intelligent algorithm module to process the collected power grid equipment information data, and converts the processed power grid equipment information data into control signals and sends them to the energy dispatch module;

[0011] The energy scheduling module combines with the intelligent algorithm module to calculate the optimal scheduling algorithm;

[0012] The power grid equipment in the area is dispatched and operated according to the optimal dispatching algorithm.

[0013] Preferably, the data in the power grid equipment information data collected by the acquisition module in the area are historical data and message information;

[0014] The historical data includes historical load values, historical output values ​​of distributed power sources and historical meteorological condition values;

[0015] The message information includes the address information of the power grid equipment, the protocol type adopted by the power grid equipment, the collection cycle, the information body address of the parameter, the collection instruction set of the information point, the response process of the parameter collection, and the data protocol type.

[0016] Furthermore, the specific algorithm steps of the energy scheduling module based on genetic algorithm are as follows:

[0017] Step S1, randomly generating an initial group consisting of a group of initial individuals;

[0018] Step S2, calculating the fitness of each initial individual in the initial population;

[0019] Step S3, applying replication, crossover, and mutation operators to generate the next generation population;

[0020] Step S4: Take the best performing individual in the group as the final execution result.

[0021] Furthermore, the calculation formula for all initial individual fitness in step S2 is as follows:

[0022]

[0023] M is the population size.

[0024] Furthermore, the calculation formula of the fitness of a single initial individual in step S2 is as follows:

[0025]

[0026] j=1.

[0027] Preferably, the method in which the energy scheduling module based on the neural network is in operation is as follows:

[0028] The access network device receives energy data in encrypted form from a plurality of terminals within a service area of ​​the access network device;

[0029] The access network device performs homomorphic calculation on the energy data in ciphertext form of each of the multiple terminals to obtain the energy data in ciphertext form of the service area;

[0030] The access network device performs noise reduction processing on the ciphertext energy data of the service area through a deep neural network to obtain the noise reduced ciphertext energy data;

[0031] The access network device sends the energy data in encrypted form after noise reduction;

[0032] The access network device performs homomorphic calculation on the energy data in ciphertext form of each of the multiple terminals to obtain the energy data in ciphertext form of the service area, including: the access network device performs homomorphic calculation on the energy data in ciphertext form of each of the multiple terminals to obtain the charging probability in ciphertext form of each of the multiple terminals, and the multiple terminals have a total of multiple charging probabilities in ciphertext form;

[0033] The access network device performs homomorphic calculation on the multiple charging probabilities in ciphertext form to obtain energy data of the service area in ciphertext form.

[0034] Preferably, the fuzzy logic-based energy scheduling module operates as follows:

[0035] Setting a power balance relationship among renewable energy, power grid, load and energy storage system, and setting an objective function according to the power balance relationship; setting constraint conditions of the objective function;

[0036] The objective function is solved by fuzzy logic reasoning to obtain the output control amount of the output power of the energy storage system and the thermal unit;

[0037] The adaptive determination process of parameters in fuzzy logic reasoning is optimized by artificial sheep algorithm.

[0038] Furthermore, the objective function is expressed as follows:

[0039] minPVR+cos t norm

[0040] PVR is the energy output and t is the time.

[0041] Furthermore, the constraints of the objective function include a maximum state of charge threshold and a minimum state of charge threshold of the energy storage system.

[0042] Compared with the prior art, the beneficial effects of the embodiments of the present application are:

[0043] (1) The energy scheduling module based on genetic algorithm in the present application can optimize energy scheduling by applying genetic algorithm, abstract the generation, conversion, transmission and consumption process of each energy into genetic code, optimize the genetic code through the selection, crossover and mutation process of genetic algorithm, obtain the optimal solution and realize energy scheduling.

[0044] The present application can simulate the learning and memory process of the human brain through the neural network-based energy scheduling module in the energy scheduling module. In the smart grid system, the neural network-based energy scheduling module can input the supply and consumption of various energy sources into the neural network, and after training, the neural network can autonomously learn and optimize and output the optimal energy scheduling plan.

[0045] The present application performs fuzzy processing on energy scheduling through an energy scheduling module based on fuzzy logic in the energy scheduling module, and derives the optimal energy scheduling plan through the fuzzy reasoning method. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] In the attached picture:

[0047] Figure 1 A schematic diagram of the system structure of an embodiment of the present application;

[0048] Figure 2 This is a schematic diagram of the structure of the energy scheduling module in the embodiment of the present application;

[0049] Figure 3 This is a flow chart of an energy scheduling module based on a genetic algorithm in an embodiment of the present application;

[0050] Figure 4 This is a flow chart of an energy scheduling module based on fuzzy logic in an embodiment of the present application. DETAILED DESCRIPTION

[0051] In order to make the purpose, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Generally, the components of the embodiments of the present application described and shown in the drawings here can be arranged and designed in various different configurations.

[0052] Example

[0053] like Figure 1-Figure 4 As shown in the figure, the multi-element new energy storage aggregation dispatching system based on the smart grid optimization algorithm includes:

[0054] Acquisition module, optimization server module, intelligent algorithm module and energy scheduling module;

[0055] The energy scheduling module includes an energy scheduling module based on genetic algorithm, an energy scheduling module based on neural network and an energy scheduling module based on fuzzy logic;

[0056] The acquisition module collects information data of power grid equipment in the area;

[0057] The acquisition module sends the collected power grid equipment information data to the optimization server module;

[0058] The optimization server module combines with the intelligent algorithm module to process the collected power grid equipment information data, and converts the processed power grid equipment information data into control signals and sends them to the energy dispatch module;

[0059] The energy scheduling module combines with the intelligent algorithm module to calculate the optimal scheduling algorithm;

[0060] The power grid equipment in the area is dispatched and operated according to the calculated optimal dispatch algorithm.

[0061] The data of the power grid equipment information data in the acquisition module acquisition area are historical data and message information;

[0062] Historical data includes historical load values, historical output values ​​of distributed power sources, and historical meteorological conditions values;

[0063] The message information includes the address information of the power grid equipment, the protocol type adopted by the power grid equipment, the collection cycle, the information body address of the parameter, the collection instruction set of the information point, the response process of the parameter collection, and the data protocol type.

[0064] The specific algorithm steps of the energy scheduling module based on genetic algorithm are as follows:

[0065] Step S1, randomly generating an initial group consisting of a group of initial individuals;

[0066] Step S2, calculating the fitness of each initial individual in the initial population;

[0067] Step S3, applying replication, crossover, and mutation operators to generate the next generation population;

[0068] Step S4: Take the best performing individual in the group as the final execution result.

[0069] The calculation formula for all initial individual fitness in step S2 is as follows;

[0070]

[0071] M is the population size.

[0072] The calculation formula for the fitness of a single initial individual in step S2 is as follows:

[0073]

[0074] j=1.

[0075] The method of operating the energy scheduling module based on neural network is as follows:

[0076] The access network device receives energy data in encrypted form from a plurality of terminals within a service area of ​​the access network device;

[0077] The access network equipment performs homomorphic calculation on the energy data in encrypted form of multiple terminals to obtain the energy data in encrypted form of the service area;

[0078] The access network equipment uses a deep neural network to perform noise reduction processing on the ciphertext energy data of the service area to obtain the ciphertext energy data after noise reduction;

[0079] The access network device sends the energy data in the form of ciphertext after noise reduction;

[0080] The access network device performs homomorphic calculation on the energy data in ciphertext form of each of the multiple terminals to obtain the energy data in ciphertext form of the service area, including: the access network device performs homomorphic calculation on the energy data in ciphertext form of each of the multiple terminals to obtain the charging probability in ciphertext form of each of the multiple terminals, and the multiple terminals have a plurality of charging probabilities in ciphertext form;

[0081] The access network device performs homomorphic calculations on multiple charging probabilities in ciphertext form to obtain energy data of the service area in ciphertext form.

[0082] The fuzzy logic based energy dispatch module operates as follows:

[0083] Set the power balance relationship between renewable energy, power grid, load and energy storage system, set the objective function according to the power balance relationship; set the constraint conditions of the objective function;

[0084] The objective function is solved through fuzzy logic reasoning to obtain the output control quantity of the output power of the energy storage system and the thermal unit;

[0085] The adaptive determination process of parameters in fuzzy logic reasoning is optimized by artificial sheep algorithm.

[0086] The expression of the objective function is as follows:

[0087] minPVR+cos t norm

[0088] PVR is the energy output and t is the time.

[0089] The constraints of the objective function include the maximum state of charge threshold and the minimum state of charge threshold of the energy storage system.

[0090] The present application can optimize energy scheduling by applying genetic algorithms through the energy scheduling module based on genetic algorithms in the energy scheduling module, abstract the generation, conversion, transmission and consumption processes of various energy sources into genetic codes, optimize the genetic codes through the selection, crossover and mutation processes of genetic algorithms, and obtain the optimal solution to achieve energy scheduling.

[0091] The present application can simulate the learning and memory process of the human brain through the neural network-based energy scheduling module in the energy scheduling module. In the smart grid system, the neural network-based energy scheduling module can input the supply and consumption of various energy sources into the neural network, and after training, the neural network can autonomously learn and optimize and output the optimal energy scheduling plan.

[0092] The present application performs fuzzy processing on energy scheduling through an energy scheduling module based on fuzzy logic in the energy scheduling module, and derives the optimal energy scheduling plan through the fuzzy reasoning method.

[0093] The above-mentioned embodiments only express the preferred implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for ordinary technicians in this field, several modifications, improvements and substitutions can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application.

Claims

1. A new multi-element energy storage aggregation dispatching system based on smart grid optimization algorithm, characterized by: include: Acquisition module, optimization server module, intelligent algorithm module and energy scheduling module; The energy scheduling module includes an energy scheduling module based on genetic algorithm, an energy scheduling module based on neural network and an energy scheduling module based on fuzzy logic; The acquisition module acquires information data of power grid equipment in the area; The acquisition module sends the collected power grid equipment information data to the optimization server module; The optimization server module combines with the intelligent algorithm module to process the collected power grid equipment information data, and converts the processed power grid equipment information data into control signals and sends them to the energy dispatch module; The energy scheduling module combines with the intelligent algorithm module to calculate the optimal scheduling algorithm; The power grid equipment in the area is dispatched and operated according to the optimal dispatching algorithm.

2. The multi-element new energy storage aggregation dispatching system based on the smart grid optimization algorithm according to claim 1 is characterized in that: The power grid equipment information data collected by the collection module is historical data and message information; The historical data includes historical load values, historical output values ​​of distributed power sources and historical meteorological condition values; The message information includes the address information of the power grid equipment, the protocol type adopted by the power grid equipment, the collection cycle, the information body address of the parameter, the collection instruction set of the information point, the response process of the parameter collection, and the data protocol type.

3. The multi-element new energy storage aggregation dispatching system based on the smart grid optimization algorithm according to claim 1 is characterized in that: The specific algorithm steps of the energy scheduling module based on genetic algorithm are as follows: Step S1, randomly generating an initial group consisting of a group of initial individuals; Step S2, calculating the fitness of each initial individual in the initial population; Step S3, applying replication, crossover, and mutation operators to generate the next generation population; Step S4: Take the best performing individual in the group as the final execution result.

4. The multi-element new energy storage aggregation dispatching system based on the smart grid optimization algorithm according to claim 3 is characterized in that: The calculation formula of all initial individual fitness in step S2 is as follows: M is the population size.

5. The multi-element new energy storage aggregation dispatching system based on the smart grid optimization algorithm according to claim 4 is characterized in that: The calculation formula of the fitness of a single initial individual in step S2 is as follows: j＝1。 6. The multi-element new energy storage aggregation dispatching system based on the smart grid optimization algorithm according to claim 1 is characterized in that: The method of the energy scheduling module based on the neural network in operation is as follows: The access network device receives energy data in encrypted form from a plurality of terminals within a service area of ​​the access network device; The access network device performs homomorphic calculation on the energy data in ciphertext form of each of the multiple terminals to obtain the energy data in ciphertext form of the service area; The access network device performs noise reduction processing on the ciphertext energy data of the service area through a deep neural network to obtain the noise-reduced ciphertext energy data; The access network device sends the energy data in encrypted form after noise reduction; The access network device performs homomorphic calculation on the energy data in ciphertext form of each of the multiple terminals to obtain the energy data in ciphertext form of the service area, including: the access network device performs homomorphic calculation on the energy data in ciphertext form of each of the multiple terminals to obtain the charging probability in ciphertext form of each of the multiple terminals, and the multiple terminals have a total of multiple charging probabilities in ciphertext form; The access network device performs homomorphic calculation on the multiple charging probabilities in ciphertext form to obtain energy data of the service area in ciphertext form.

7. The multi-element new energy storage aggregation dispatching system based on the smart grid optimization algorithm according to claim 1 is characterized in that: The fuzzy logic based energy scheduling module operates as follows: Setting a power balance relationship among renewable energy, power grid, load and energy storage system, and setting an objective function according to the power balance relationship; setting constraint conditions of the objective function; The objective function is solved by fuzzy logic reasoning to obtain the output control amount of the output power of the energy storage system and the thermal unit; The adaptive determination process of parameters in fuzzy logic reasoning is optimized by artificial sheep algorithm.

8. The multi-element new energy storage aggregation dispatching system based on the smart grid optimization algorithm according to claim 7 is characterized in that: The expression of the objective function is as follows: minPVR+cos t norm PVR is the energy output and t is the time.

9. The multi-element new energy storage aggregation dispatching system based on the smart grid optimization algorithm according to claim 8 is characterized in that: The constraint conditions of the objective function include a maximum state of charge threshold and a minimum state of charge threshold of the energy storage system.

Images