Smart grid load balancing control method and system

Abstract

This invention belongs to the field of smart grid technology and discloses a smart grid load balancing control method and system. The method includes: dividing the power grid into multiple regions based on predetermined rules; identifying overloaded regions with insufficient power supply based on the regional power supply and regional power consumption; formulating and executing a load balancing strategy for the overloaded regions using a natural heuristic optimization algorithm, wherein the load balancing strategy is a load scheduling strategy with the goal of minimizing scheduling time; calculating priority coefficients for electrical equipment in the overloaded regions, and supplying power to each electrical equipment according to the priority coefficients. This invention achieves effective load balancing and optimized allocation of the smart grid, maximizing emergency power supply during natural disasters, thereby improving the grid operation level and public welfare guarantee capabilities, and enhancing the power supply reliability and power consumption efficiency of the grid.

Description

Technical Field

[0001] This invention relates to the field of smart grid technology, and more specifically, to a smart grid load balancing control method and system. Background Technology

[0002] A smart microgrid is a miniaturized, self-sufficient power network that integrates distributed generation, energy storage systems, controllable loads, and an energy management system. Distributed generation includes renewable energy sources such as solar photovoltaic, wind power, and small-scale hydropower. Energy storage systems store electricity when there is surplus power and release it during peak demand periods. Controllable loads can flexibly adjust their power consumption based on grid conditions. Through advanced big data analytics, artificial intelligence, and machine learning technologies, smart microgrids can accurately and efficiently allocate and utilize power resources, achieving a dynamic balance between grid supply and demand, and significantly improving the overall efficiency and stability of the grid system.

[0003] Document CN118263843A discloses a method for energy conservation and carbon reduction control in regional distribution networks, including: establishing a regional distribution network model based on the operation data of the regional distribution network, and performing power flow calculations on the model to obtain voltage and power distribution; conducting sensitivity analysis based on voltage and power distribution change data to select sensitive nodes as reactive power compensation nodes; monitoring the voltage of reactive power compensation nodes in real time, issuing reactive power compensation commands according to a preset reactive power control strategy to suppress voltage fluctuations; determining a disconnector reconfiguration scheme using distribution network reconfiguration software based on the objectives of minimizing line losses, maximizing photovoltaic absorption, and load balancing; formulating and executing a disconnector operation plan based on the reconfiguration scheme to complete the line reconfiguration; improving the adaptability of the distribution network to the intermittent characteristics of photovoltaic power generation, enhancing the absorption capacity of distributed photovoltaic power, and achieving coordinated voltage control within the region to ensure the efficient, stable, and safe operation of the distribution network.

[0004] However, most existing smart microgrid load balancing control technologies primarily focus on minimizing line losses and maximizing photovoltaic (PV) absorption, often neglecting the crucial factor of dispatch time. In situations where minimizing dispatch time is critical, such as in areas experiencing sudden natural disasters (earthquakes, mudslides, typhoons, etc.) or man-made disasters (fires), the increased demand for various emergency facilities, such as hospitals, fire stations, and rescue centers, leads to a significant surge in electricity demand. This means additional power is needed to maintain the normal operation of medical equipment, communication systems, and lighting, ensuring the smooth progress of rescue operations. To achieve rapid rescue and safeguard lives, load balancing should prioritize ensuring swift and effective support for rescue operations and the operation of critical facilities; in other words, load balancing should fully consider minimizing dispatch time.

[0005] In view of this, the present invention proposes a smart grid load balancing control method and system to solve the above problems. Summary of the Invention

[0006] To overcome the aforementioned deficiencies of the prior art and achieve the above objectives, the present invention provides the following technical solution: a smart grid load balancing control method, comprising:

[0007] The power grid is divided into multiple zones based on predetermined rules;

[0008] Based on regional power supply and regional electricity consumption, identify overloaded areas with insufficient power supply;

[0009] A load balancing strategy is formulated and executed for overloaded areas using a natural heuristic optimization algorithm. The load balancing strategy is a load scheduling strategy with the goal of minimizing scheduling time.

[0010] Priority coefficients are calculated for electrical equipment in overloaded areas, and power is supplied to each piece of equipment based on these priority coefficients.

[0011] Furthermore, the steps for developing a load balancing strategy include:

[0012] Step 1: Randomly generate a set of solutions, which includes multiple scheduling sets; set set labels for the scheduling sets; preset the iteration threshold;

[0013] Step 2: Define the fitness function, using scheduling time as the evaluation metric;

[0014] Step 3: Iteratively optimize the solution through cloning, mutation, and recombination operations. When the preset number of iterations is reached, select the set label with the highest fitness and obtain the corresponding scheduling set based on the set label.

[0015] Furthermore, the method for identifying overloaded areas with insufficient power supply includes:

[0016] An overloaded area refers to a region where the power supply is less than the power consumption.

[0017] The sum of electricity consumption in each region is the regional electricity consumption; the sum of power generation in each region is the regional power generation; the sum of energy storage in each region is the regional energy storage; the sum of regional power generation and regional energy storage in each region is the regional power supply; energy storage is the amount of electrical energy stored in each energy storage unit within the region.

[0018] Further, in step 1, except for the overloaded area, all energy storage units in all areas are marked as scheduling units; all scheduling units are randomly combined, and the combination result is taken as a unit set; the energy storage of the scheduling units in each unit set is added together to obtain the total energy storage; the electricity consumption of the overloaded area is marked as the overload electricity consumption; the total energy storage of each unit set is compared with the overload electricity consumption, and the unit sets with total energy storage greater than or equal to the overload electricity consumption are retained and marked as deployment sets;

[0019] Subtract the overload power consumption from the total energy storage of each deployment set to obtain the energy storage difference; compare the energy storage of each scheduling unit in each deployment set with the energy storage difference in turn, retain the deployment sets in which the energy storage of each scheduling unit is greater than or equal to the energy storage difference, and mark them as scheduling sets; set a different numerical label for each scheduling set and mark it as a set label.

[0020] Furthermore, in step 2, the method for obtaining the scheduling time includes:

[0021] Retrieve all scheduling units in the scheduling set and mark them as analysis units;

[0022] The process involves: acquiring the power grid topology and drawing a topology diagram, including nodes and edges; obtaining the routes between each analysis unit and each node in the overloaded area based on the topology diagram; obtaining the length of each transmission line in each route based on the topology diagram; summing the transmission line lengths corresponding to each route to obtain the total length of each route; comparing the total lengths of multiple routes corresponding to each analysis unit and taking the smallest total length as the shortest length for that analysis unit; dividing the shortest length of each analysis unit by the speed of light to obtain the transmission time for each analysis unit; pre-setting a set of startup times, which includes the startup time of each energy storage unit in the power grid, where the startup time is the time consumed from startup to the start of power transmission; and obtaining the startup time corresponding to each analysis unit based on the set of startup times.

[0023] Add the transmission time of each analysis unit to the corresponding startup time to obtain the scheduling time of each analysis unit; compare the scheduling times of each analysis unit and take the scheduling time with the largest value as the scheduling time of the scheduling set.

[0024] Furthermore, step 3 also includes verifying whether the energy storage of the new scheduling set meets the constraints after mutation and recombination. The constraints are that the total energy storage of the new scheduling set covers the overloaded electricity consumption, and the energy storage of the scheduling unit is greater than the energy storage difference.

[0025] Furthermore, the method for calculating the priority factor for electrical equipment in the overloaded area includes:

[0026] Collect the power value of each electrical device in the overload area; compare the power value of each electrical device with 0, mark the electrical devices with a power value greater than 0 as operating devices, and do not mark the electrical devices with a power value equal to 0; set different digital tags for the electrical devices in the overload area and mark them as device tags; obtain the device tag corresponding to each operating device and mark it as an operating tag;

[0027] Collect regional images of the overloaded area, use a trained disaster identification model to identify the regional images, and output the identification results as digital labels corresponding to the natural disaster types. Mark the digital labels corresponding to the natural disaster types as disaster labels. Take an equipment label and a disaster label as a set of analysis data, and input each set of analysis data into a trained priority analysis model to predict the corresponding priority coefficient.

[0028] Furthermore, the method also includes: collecting and analyzing the operating parameters of each electrical device in the overload area, filtering out the electrical devices that are online, and marking them as operating devices;

[0029] Operating parameters include power, temperature, and vibration values. The device tag for each electrical device is acquired, and the device tag and operating parameters for each device are used as a set of test data. Each set of test data is sequentially input into the trained state analysis model to predict the state tag for each electrical device. The state tag is the numerical label corresponding to the device state, which includes operating state, standby state, power-off state, and fault state. Different device states correspond to different numerical labels.

[0030] Online status includes running status and standby status; the status label corresponding to the running status is marked as the running label, and the status label corresponding to the standby status is marked as the standby label; the running label and the standby label are used as the status labels corresponding to the online status; the status label of each electrical device is compared with the status label of the online status; electrical devices with status labels that are the same as the running label or the standby label are selected and marked as running devices.

[0031] A smart grid load balancing control system, implementing smart grid load balancing control methods, including:

[0032] The microgrid partitioning module divides the power grid into multiple regions based on predetermined rules.

[0033] The overload determination module identifies overloaded areas with insufficient power supply based on the area's power supply and power consumption.

[0034] The load balancing module is used to formulate and execute load balancing strategies for overloaded areas using a natural heuristic optimization algorithm. The load balancing strategy is a load scheduling strategy with the goal of minimizing scheduling time.

[0035] The sequential power supply module is used to calculate the priority coefficient of electrical equipment in the overload area and supply power to each electrical equipment according to the priority coefficient.

[0036] The status analysis module is used to collect and analyze the operating parameters of each electrical device in the overload area, filter out the electrical devices that are online, and mark them as operating devices.

[0037] The technical effects and advantages of the smart grid load balancing control method and system of this invention are as follows:

[0038] 1. By dividing the region and collecting energy data, real-time monitoring of each area of ​​the power grid is carried out to accurately identify overloaded areas; taking into full account the scheduling time factor, the cloning selection algorithm is used to formulate and execute load balancing strategies for overloaded areas; and combined with the specific electrical equipment and natural disaster types in the overloaded areas, the priority power supply order of each electrical equipment is calculated to effectively ensure priority power supply to life safety facilities; thus realizing the effective balancing and optimized allocation of smart grid loads, maximizing the guarantee of emergency power supply during natural disasters, thereby improving the power grid operation level and people's livelihood protection capabilities, and improving the power supply reliability and power consumption efficiency of the power grid.

[0039] 2. Employing multi-source information fusion technology, the system integrates collected multi-dimensional operating parameters of electrical equipment, such as power, temperature, and vibration values. Through deep learning technology, it further subdivides the operating status, standby status, shutdown status, and fault status of electrical equipment, achieving end-to-end identification of equipment status. This enables more accurate identification of the actual equipment status, avoiding misjudgments of equipment status caused by single judgments. Consequently, it provides a more reliable basis for power grid load dispatching, ensures priority power supply to critical emergency equipment, and improves emergency rescue efficiency and the reliability of power grid load balance control. Attached Figure Description

[0040] Figure 1 This is a schematic diagram of the smart grid load balancing control system according to Embodiment 1 of the present invention;

[0041] Figure 2 This is a flowchart illustrating the steps of formulating a load balancing strategy in Embodiment 1 of the present invention.

[0042] Figure 3 This is a schematic diagram of the smart grid load balancing control system according to Embodiment 2 of the present invention;

[0043] Figure 4 This is a flowchart of the smart grid load balancing control method according to Embodiment 3 of the present invention. Detailed Implementation

[0044] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0045] Example 1:

[0046] Please see Figure 1 and Figure 2 As shown, this embodiment provides a smart grid load balancing control system, including a microgrid partitioning module, an overload determination module, a load balancing module, and a sequential power supply module; each module is connected via wired and / or wireless means to realize data transmission between modules.

[0047] The microgrid zoning module divides the power grid into multiple regions based on predetermined rules, such as geographic information and energy topology, combining the main power grid and microgrids into multi-level autonomous units. This regional division facilitates the collection of energy data from each region, monitors load changes in each region, and enhances load management capabilities. Furthermore, it enables individual load analysis and control for each region, achieving optimized load balancing within that region.

[0048] The overload determination module identifies overloaded areas with insufficient power supply based on the area's power supply and power consumption.

[0049] Methods for identifying overloaded areas with insufficient power supply include:

[0050] Energy data is collected for each area; the energy data includes electricity consumption, power generation, and energy storage; electricity consumption is the amount of electricity used by each electrical device in the area, which is obtained by smart meters installed on the electrical devices in the area; power generation is the amount of electricity generated by each power generation unit in the area, which is obtained by power sensors installed at the output end of the power generation unit in the area; energy storage is the amount of electricity stored in each energy storage unit in the area, which is obtained by the energy storage management system built into each energy storage unit. The energy storage management system has a built-in battery management module to monitor the amount of electricity stored in the energy storage unit.

[0051] The sum of electricity consumption in each region is the regional electricity consumption; the sum of power generation in each region is the regional power generation; the sum of energy storage in each region is the regional energy storage; the sum of regional power generation and regional energy storage in each region is the regional power supply; the regional power supply of each region is compared with the corresponding regional electricity consumption to determine whether each region is in an overload state. An overloaded region is a region where the regional power supply is less than the regional electricity consumption. Regions that are not in an overload state are not marked.

[0052] The load balancing module is used to formulate and execute load balancing strategies for overloaded areas using natural heuristic optimization algorithms to achieve load balancing in overloaded areas. The load balancing strategy is a load scheduling strategy with the goal of minimizing scheduling time.

[0053] Naturally inspired optimization algorithms include genetic algorithms, particle swarm optimization, simulated annealing, and clonal selection. This embodiment uses the clonal selection algorithm as an example to introduce the formulation of load balancing strategies. Figure 2 As shown, the steps for developing a load balancing strategy include:

[0054] Step 1: Randomly generate a set of solutions, which includes multiple scheduling sets; set set labels for the scheduling sets; preset the iteration threshold;

[0055] Step 2: Define the fitness function, using scheduling time as the evaluation metric;

[0056] Step 3: Iteratively optimize the solution through cloning, mutation, and recombination operations. When the preset number of iterations is reached, select the set label with the highest fitness and obtain the corresponding scheduling set based on the set label.

[0057] All energy storage units in all regions except overloaded areas are marked as dispatch units. All dispatch units are randomly combined, and each combination result is considered as a unit set. The energy storage of dispatch units in each unit set is summed sequentially to obtain the aggregate energy storage. The electricity consumption of overloaded areas is marked as overload electricity consumption. The aggregate energy storage of each unit set is compared with the overload electricity consumption, and unit sets with aggregate energy storage greater than or equal to the overload electricity consumption are retained and marked as deployment sets. This ensures that the electricity dispatchable by each deployment set can meet the electricity demand of overloaded areas during energy dispatch.

[0058] Subtract the overload power consumption from the total energy storage of each deployment set to obtain the energy storage difference; compare the energy storage of each scheduling unit in each deployment set with the energy storage difference in turn, retain the deployment sets in which the energy storage of each scheduling unit is greater than or equal to the energy storage difference, and mark them as scheduling sets; set a different numerical label for each scheduling set and mark it as a set label.

[0059] For example, if the overloaded electricity consumption is 15, and the total energy storage of the first deployment set is 22, then the energy storage difference of the first deployment set is 7. The energy storage of each scheduling unit is 2, 4, 7, and 9 respectively. Since 2 and 4 are both less than 7, the first deployment set only needs energy storage units with energy storage of 7 and 9 to meet the electricity demand of the overloaded area, and does not need energy storage units with energy storage of 2 and 4. Therefore, the first deployment set is not marked as a scheduling set. If the total energy storage of the second deployment set is 20, then the energy storage difference of the second deployment set is 5. The energy storage of each scheduling unit is 6, 7, and 7 respectively. Since 6, 7, and 7 are all greater than 5, all scheduling units in the second deployment set are needed to meet the electricity demand of the overloaded area. Therefore, the second deployment set is marked as a scheduling set.

[0060] It should be understood that the purpose of selecting the scheduling set from the deployment set is to avoid redundant scheduling units in the scheduling set, making the scheduling process more streamlined and efficient, reducing the complexity of the scheduling process, and improving the decision-making speed; and to maximize the use of existing resources, avoiding resource waste and redundancy; at the same time, redundant scheduling units will lead to unnecessary energy consumption, and by removing redundant scheduling units, energy consumption can be reduced and the overall efficiency of the system can be improved.

[0061] Methods for obtaining scheduling time include:

[0062] Retrieve all scheduling units in the scheduling set and mark them as analysis units;

[0063] The topology of the power grid is obtained and a topology diagram is drawn. The topology is obtained by those skilled in the art from the power grid company. The topology includes nodes (such as substations, distribution cabinets, and generation units) and edges (such as transmission lines and distribution lines). The routes between each analysis unit and each node in the overloaded area are obtained from the topology diagram. The length of each transmission line in each route is obtained from the topology diagram. The transmission line lengths corresponding to each route are added together sequentially to obtain the total length of each route. The total lengths of multiple routes corresponding to each analysis unit are compared, and the total length with the smallest value is taken as the shortest length of the corresponding analysis unit. The shortest length of each analysis unit is divided by the speed of light to obtain the transmission time of each analysis unit.

[0064] A preset start-up time set is provided, which includes the start-up time of each energy storage unit in the power grid. The start-up time is the time consumed by the energy storage unit from start-up to the start of power transmission. The start-up time set is obtained by those skilled in the art by measuring the time consumed by each energy storage unit in the power grid from start-up to the start of power transmission during historical power grid load balancing. The start-up time corresponding to each analysis unit is obtained based on the start-up time set.

[0065] Add the transmission time of each analysis unit to the corresponding startup time to obtain the scheduling time of each analysis unit; compare the scheduling times of each analysis unit and take the scheduling time with the largest value as the scheduling time of the scheduling set.

[0066] It should be noted that the propagation speed of electrical energy in high-voltage transmission lines is close to the speed of light, with very small differences, and there is no need to consider the slight differences in propagation speed between different lines. Therefore, when calculating the scheduling time, the speed of electrical energy scheduling is replaced by the speed of light.

[0067] In step 3 above, the cloning operation explains that, based on the fitness function (minimizing scheduling time), a scheduling set with high fitness is selected for replication. Scheduling sets with higher fitness (shorter scheduling time) are replicated more frequently. The mutation operation randomly adjusts some scheduling units in the cloned scheduling set to increase population diversity. The recombination operation swaps some scheduling units between the two parent scheduling sets to generate new offspring, exploring new regions of the solution space through crossover and recombination while inheriting the superior characteristics of the parents.

[0068] Constraint handling: After mutation and recombination, it is necessary to verify whether the energy storage of the new scheduling set meets the constraints. The constraints are that the total energy storage of the new scheduling set must cover the overload power consumption, and the energy storage of the scheduling unit must be greater than the energy storage difference, so as to ensure that the algorithm can efficiently optimize the scheduling time under the physical constraints of the power grid.

[0069] The sequential power supply module is used to calculate the priority coefficient of electrical equipment in the overload area and supply power to each electrical equipment according to the priority coefficient to achieve load balance among the electrical equipment.

[0070] Methods for calculating priority factors for electrical equipment in overloaded areas include:

[0071] The power value of each electrical device in the overload area is collected. The power value of each electrical device is obtained by the power sensor built into each electrical device. The power value of each electrical device is compared with 0. The electrical devices with a power value greater than 0 are marked as operating devices, and the electrical devices with a power value equal to 0 are not marked. Since the power value must be greater than or equal to 0, there is no case where the power value is less than 0.

[0072] Different digital tags are set for electrical equipment in the overload area and marked as equipment tags; the equipment tag corresponding to each operating device is obtained and marked as an operating tag.

[0073] The system collects regional images of the overloaded areas using satellite remote sensing technology. This technology uses satellite sensors (such as optical satellites and radar satellites) to detect and photograph various areas of the power grid, acquiring large-scale, high-resolution image data. A trained disaster identification model is then used to identify the regional images and output the identification results, which are numerical labels corresponding to the types of natural disasters, such as earthquakes, floods, and forest fires.

[0074] The specific training process of the disaster identification model includes:

[0075] Pre-collect *e* regional images, where *e* is an integer greater than 1. Label the natural disaster phenomena in each regional image as natural disaster types. Convert different natural disaster types into numerical labels, ensuring they are not identical to the device labels. For example, earthquake is labeled as 1, flood as 2, and forest fire as 3. Divide the labeled regional images into training and testing sets, using 70% of the regional images as the training set and 30% as the testing set. Train the disaster recognition model using the training set and test it using the testing set. A preset error threshold is set; when the mean prediction error of all regional images in the testing set is less than the threshold, the disaster recognition model is output. The formula for calculating the mean prediction error is... ,in The mean of the prediction error. The region image number is used to represent the area. For the first Predicted annotations for the Zhang region image For the first The actual annotation corresponding to the Zhang area image, where U is the number of area images in the test set; the error threshold is preset according to the accuracy required by the disaster identification model;

[0076] The disaster identification model mentioned above is specifically a convolutional neural network model.

[0077] The numerical labels corresponding to the types of natural disasters are marked as disaster tags;

[0078] Each set of analysis data, consisting of an equipment tag and a disaster tag, is input into a pre-trained priority analysis model to predict the corresponding priority coefficient.

[0079] The training process of the priority analysis model includes:

[0080] G sets of analysis data are collected in advance, and a corresponding priority coefficient is set for each of the g sets of analysis data, where g is an integer greater than 1. The analysis data and the corresponding priority coefficients are converted into a set of feature vectors. The priority coefficients corresponding to the analysis data are set by those skilled in the art during the historical power grid load balancing process, by collecting g sets of analysis data, and under the natural disaster conditions corresponding to the disaster labels of each set of analysis data, according to the actual priority operation degree of the electrical equipment corresponding to the corresponding equipment labels. The corresponding priority coefficients are set for the g sets of analysis data in sequence.

[0081] For example, in areas affected by natural disasters, medical equipment should be prioritized over communication equipment, which in turn should be prioritized over lighting equipment. This is because natural disasters typically result in a large number of casualties, requiring emergency medical care. Communication equipment is the next priority, as restoring communication plays a crucial role in intelligence transmission and search and rescue command. Lighting equipment is the last priority. As for medical equipment, in the event of an earthquake, intensive care equipment should be prioritized over routine medical equipment because there may be a large number of critically ill patients. In the event of a flood, equipment for treating infectious diseases should have the highest priority to prevent the spread of infectious diseases. In the event of a forest fire, respiratory treatment equipment should be prioritized over other medical equipment because the smoke and dust generated by the fire have a significant impact on the respiratory system.

[0082] Each set of feature vectors is used as input to the priority analysis model, which outputs a set of predicted priority coefficients corresponding to each set of analyzed data and uses the actual priority coefficients corresponding to each set of analyzed data as the prediction target. The actual priority coefficients are the priority coefficients corresponding to the analyzed data that have been collected beforehand. The training objective is to minimize the sum of prediction errors for all analyzed data. The formula for calculating the prediction error is as follows: ,in The prediction error is represented by K, where K is the group number of the feature vector corresponding to the analyzed data. Let K be the prediction priority coefficient corresponding to the Kth group of analyzed data. Let be the actual priority coefficient corresponding to the Kth group of analysis data; train the priority analysis model until the sum of prediction errors converges and then stop training.

[0083] The aforementioned priority analysis model is specifically a deep neural network model; it includes an input layer, hidden layers, and an output layer; each hidden layer contains multiple neurons, and each neuron is connected to the neurons in the next layer. The connections contain weights that determine the importance and influence of data transmission in the neural network; each neuron between the hidden layer and the output layer applies an activation function, which introduces non-linearity, allowing the network to learn more complex patterns and features.

[0084] It should be noted that the reason for supplying power to each electrical device according to the priority coefficient is that, since the dispatch set includes multiple dispatch units, each dispatch unit dispatches energy to the overload area at different times. Supplying the power that is prioritized to the overload area to the electrical devices with higher priority coefficients can effectively utilize limited power resources, maximize the protection of life safety, maintain public safety and improve rescue efficiency; it not only helps to respond to disasters in a timely manner, but also reduces secondary disasters and losses, and provides reliable power support to disaster areas.

[0085] This embodiment uses regional division and energy data collection to monitor various areas of the power grid in real time and accurately identify overloaded areas. Taking into full account scheduling time factors, it employs a cloning selection algorithm to formulate and execute load balancing strategies for overloaded areas. Furthermore, by combining the specific electrical equipment and natural disaster types within the overloaded areas, it calculates the priority power supply order for each electrical device, effectively ensuring priority power supply to life-saving facilities. This achieves effective load balancing and optimized allocation of the smart grid, maximizing emergency power supply during natural disasters, thereby improving the grid's operational level and public welfare capabilities, and enhancing the grid's power supply reliability and efficiency.

[0086] Example 2:

[0087] Please see Figure 3 As shown, this embodiment further improves upon the design of Embodiment 1. In Embodiment 1, the device operation is determined by the relationship between the power value and 0. However, in reality, when a device malfunctions or operates abnormally, the power value may not be 0, but no power supply is needed to avoid energy waste. When a device is in standby or hibernation mode, the power value may be 0, but power supply is still required to prevent automatic shutdown after a complete power outage, ensuring rapid startup and use when needed. If the method in Embodiment 1 is still used to determine device operation, misjudgments of device operation status may occur, resulting in life safety facilities not being given priority power supply, thus affecting emergency rescue work. Therefore, the smart grid load balancing control system provided in this embodiment also includes a status analysis module.

[0088] The status analysis module is used to collect and analyze the operating parameters of each electrical device in the overload area, filter out the electrical devices that are online, and mark them as operating devices.

[0089] Operating parameters include power, temperature, and vibration values; power values ​​are obtained by a power sensor installed in each electrical device; temperature values ​​are obtained by a temperature sensor installed in each electrical device; and vibration values ​​are obtained by a vibration sensor installed in each electrical device.

[0090] Obtain the device tag for each electrical device, and use the device tag and operating parameters corresponding to each device as a set of test data. Input each set of test data into the trained state analysis model in sequence to predict the state tag corresponding to each electrical device. The state tag is the numerical tag corresponding to the device state. The device state includes operating state, standby state, power-off state, and fault state. Different device states correspond to different numerical tags. The training process of the state analysis model is the same as the training process of the priority analysis model, and both are deep neural network models.

[0091] Online status includes running status and standby status; the status label corresponding to the running status is marked as the running label, and the status label corresponding to the standby status is marked as the standby label; the running label and the standby label are used as the status labels corresponding to the online status; the status label of each electrical device is compared with the status label of the online status; electrical devices with status labels that are the same as the running label or the standby label are selected and marked as running devices.

[0092] It should be noted that the reason for judging the equipment status of electrical appliances through operating parameters is that when the electrical appliance is in operation, the operating parameters are all within their corresponding normal ranges; when the electrical appliance is in standby mode, the operating parameters will decrease, with the power value possibly equal to 0. However, since the equipment is still online, there is still vibration and heat dissipation, so the vibration value should be greater than 0 but less than the vibration value during operation, and the temperature value should be higher than the ambient temperature but lower than the temperature value during operation; when the electrical appliance is off, both the power and vibration values ​​are 0, and the temperature value should be close to the ambient temperature; when the electrical appliance is in a faulty state, it will affect the normal operation of the equipment, so at least one of the operating parameters will be outside its corresponding normal range. In summary, the corresponding operating parameters of electrical appliances are different in different equipment states, so the equipment status of electrical appliances can be accurately judged through operating parameters.

[0093] This embodiment employs multi-source information fusion technology to integrate multi-dimensional operating parameters of electrical equipment, such as power, temperature, and vibration values. Through deep learning technology, it subdivides the operating status, standby status, shutdown status, and fault status of electrical equipment, achieving end-to-end identification of equipment status. This enables more accurate identification of the actual equipment status and avoids misjudgments of equipment status caused by single judgments. Consequently, it provides a more reliable basis for power grid load dispatching, ensures priority power supply to critical emergency equipment, and improves emergency rescue efficiency and the reliability of power grid load balance control.

[0094] Example 3:

[0095] Please see Figure 4As shown, parts not described in detail in this embodiment are described in Embodiments 1 and 2. A smart grid load balancing control method is provided, the method including:

[0096] The power grid is divided into multiple zones based on predetermined rules;

[0097] Based on regional power supply and regional electricity consumption, identify overloaded areas with insufficient power supply;

[0098] A load balancing strategy is formulated and executed for overloaded areas using a natural heuristic optimization algorithm. The load balancing strategy is a load scheduling strategy with the goal of minimizing scheduling time.

[0099] Priority coefficients are calculated for electrical equipment in overloaded areas, and power is supplied to each piece of equipment based on these priority coefficients.

[0100] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in the present invention should be included within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.

[0101] In conclusion, the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A smart grid load balancing control method, characterized in that, include: The power grid is divided into multiple zones based on predetermined rules; Based on regional power supply and regional electricity consumption, identify overloaded areas with insufficient power supply; A load balancing strategy is formulated and executed for overloaded areas using a natural heuristic optimization algorithm. The load balancing strategy is a load scheduling strategy with the goal of minimizing scheduling time, and the natural heuristic optimization algorithm is the clone selection algorithm. Priority coefficients are calculated for electrical equipment in overloaded areas, and power is supplied to each piece of equipment according to the priority coefficients. The steps to develop a load balancing strategy include: Step 1: Randomly generate a set of solutions, which includes multiple scheduling sets; set set labels for the scheduling sets; preset the iteration threshold; Step 2: Define the fitness function, using scheduling time as the evaluation metric; Step 3: Iteratively optimize the solution through cloning, mutation, and recombination operations. When the preset number of iterations is reached, select the set label with the highest fitness and obtain the corresponding scheduling set based on the set label. In step 2, the method for obtaining the scheduling time includes: Retrieve all scheduling units in the scheduling set and mark them as analysis units; The process involves: acquiring the power grid topology and drawing a topology diagram, including nodes and edges; obtaining the routes between each analysis unit and each node in the overloaded area based on the topology diagram; obtaining the length of each transmission line in each route based on the topology diagram; summing the transmission line lengths corresponding to each route to obtain the total length of each route; comparing the total lengths of multiple routes corresponding to each analysis unit and taking the smallest total length as the shortest length for that analysis unit; dividing the shortest length of each analysis unit by the speed of light to obtain the transmission time for each analysis unit; pre-setting a set of startup times, which includes the startup time of each energy storage unit in the power grid, where the startup time is the time consumed from startup to the start of power transmission; and obtaining the startup time corresponding to each analysis unit based on the set of startup times. Add the transmission time of each analysis unit to the corresponding startup time to obtain the scheduling time of each analysis unit; compare the scheduling times of each analysis unit and take the scheduling time with the largest value as the scheduling time of the scheduling set.

2. The smart grid load balancing control method according to claim 1, characterized in that, The method for identifying overloaded areas with insufficient power supply includes: An overloaded area refers to a region where the power supply is less than the power consumption. The sum of electricity consumption in each region is the regional electricity consumption; the sum of power generation in each region is the regional power generation; the sum of energy storage in each region is the regional energy storage; the sum of regional power generation and regional energy storage in each region is the regional power supply; energy storage is the amount of electrical energy stored in each energy storage unit within the region.

3. The smart grid load balancing control method according to claim 2, characterized in that, In step 1, except for the overloaded area, all energy storage units in all areas are marked as scheduling units; all scheduling units are randomly combined, and the result of one combination is a unit set; the energy storage of the scheduling units in each unit set is added together to obtain the total energy storage; the electricity consumption of the overloaded area is marked as the overload electricity consumption; the total energy storage of each unit set is compared with the overload electricity consumption, and the unit sets with total energy storage greater than or equal to the overload electricity consumption are retained and marked as deployment sets; Subtract the overload power consumption from the total energy storage of each deployment set to obtain the energy storage difference; compare the energy storage of each scheduling unit in each deployment set with the energy storage difference in turn, retain the deployment sets in which the energy storage of each scheduling unit is greater than or equal to the energy storage difference, and mark them as scheduling sets; set a different numerical label for each scheduling set and mark it as a set label.

4. The smart grid load balancing control method according to claim 2, characterized in that, Step 3 also includes verifying, after mutation and recombination, whether the energy storage of the new scheduling set meets the constraints. The constraints are that the total energy storage of the new scheduling set covers the overloaded electricity consumption, and the energy storage of the scheduling unit is greater than the energy storage difference.

5. The smart grid load balancing control method according to claim 4, characterized in that, The method for calculating the priority factor of electrical equipment in the overload area includes: Collect the power value of each electrical device in the overload area; compare the power value of each electrical device with 0, mark the electrical devices with a power value greater than 0 as operating devices, and do not mark the electrical devices with a power value equal to 0; set different digital tags for the electrical devices in the overload area and mark them as device tags; obtain the device tag corresponding to each operating device and mark it as an operating tag; Collect regional images of the overloaded area, use a trained disaster identification model to identify the regional images, and output the identification results as digital labels corresponding to the natural disaster types. Mark the digital labels corresponding to the natural disaster types as disaster labels. Take an equipment label and a disaster label as a set of analysis data, and input each set of analysis data into a trained priority analysis model to predict the corresponding priority coefficient.

6. The smart grid load balancing control method according to claim 5, characterized in that, The method further includes: collecting and analyzing the operating parameters of each electrical device in the overload area, filtering out the electrical devices that are online, and marking them as operating devices; Operating parameters include power, temperature, and vibration values. The device tag for each electrical device is acquired, and the device tag and operating parameters for each device are used as a set of test data. Each set of test data is sequentially input into the trained state analysis model to predict the state tag for each electrical device. The state tag is the numerical label corresponding to the device state, which includes operating state, standby state, power-off state, and fault state. Different device states correspond to different numerical labels. Online status includes running status and standby status; the status label corresponding to the running status is marked as the running label, and the status label corresponding to the standby status is marked as the standby label; the running label and the standby label are used as the status labels corresponding to the online status; the status label of each electrical device is compared with the status label of the online status; electrical devices with status labels that are the same as the running label or the standby label are selected and marked as running devices.

7. A smart grid load balancing control system, implementing the smart grid load balancing control method according to any one of claims 1-6, characterized in that, include: The microgrid partitioning module divides the power grid into multiple regions based on predetermined rules. The overload determination module identifies overloaded areas with insufficient power supply based on the area's power supply and power consumption. The load balancing module is used to formulate and execute load balancing strategies for overloaded areas using a natural heuristic optimization algorithm. The load balancing strategy is a load scheduling strategy with the goal of minimizing scheduling time. The sequential power supply module is used to calculate the priority coefficient of electrical equipment in the overload area and supply power to each electrical equipment according to the priority coefficient.

Images