Distributed energy resource intelligent scheduling method based on Internet of Things

Abstract

The invention discloses a distributed energy resource intelligent scheduling method based on the Internet of Things, and relates to the technical field of the Internet of Things, and the method comprises the steps: collecting operation data of distributed energy equipment, carrying out the preprocessing of the operation data, obtaining an equipment operation data set, carrying out the group intelligent initialization of the equipment operation data set, and generating an initial pheromone matrix; carrying out local optimization on the equipment operation data set and the initial pheromone matrix to generate an updated pheromone matrix and an equipment candidate scheduling scheme, and carrying out screening and verification to generate a local optimal scheduling scheme; receiving a local optimal scheduling scheme by adopting a quantum computing node, taking the local optimal scheduling scheme as an initial solution, constructing a global optimization problem, outputting a global optimal scheduling scheme, and converting the global optimal scheduling scheme into a global scheduling instruction; according to the method, by formulating a global optimization problem, equipment interaction, economic factors and multi-dimensional constraints in a network range are captured, coordination and constraint compliance among equipment are realized, and the problem of instability of a power grid is prevented.

Description

Technical Field

[0001] The present invention relates to the technical field of the Internet of Things, and in particular to an intelligent scheduling method for distributed energy resources based on the Internet of Things. Background Art

[0002] The intelligent scheduling technology of distributed energy resources (DERs) has developed rapidly with the wide application of smart grids and renewable energy. In recent years, the integration of the Internet of Things, edge computing, and artificial intelligence has significantly improved the operation efficiency and coordination ability of distributed energy devices (such as photovoltaic panels, energy storage batteries, and electric vehicle chargers). Traditional scheduling methods mostly adopt centralized optimization models, and allocate the output of distributed energy devices through linear programming or heuristic algorithms (such as genetic algorithms) to achieve supply-demand balance and cost minimization. Recent technological advancements have introduced swarm intelligence algorithms, which optimize local scheduling by simulating the behavior of biological groups and combine Internet of Things sensors to achieve real-time data collection, further improving the scheduling accuracy. In addition, the rise of quantum computing technology provides a new path for solving complex multi-dimensional optimization problems. These technologies have made remarkable progress in improving energy utilization efficiency, reducing scheduling costs, and enhancing grid stability, especially in scenarios such as microgrids and virtual power plants.

[0003] However, there are still some areas that need improvement in the current technical solutions. For example, although swarm intelligence algorithms can effectively solve complex optimization problems, in practical applications, how to accurately initialize the pheromone matrix to reflect the interaction effects between different distributed energy devices is still a challenge; in addition, the ability in global optimization is limited, especially when considering multi-dimensional constraint conditions, it is difficult to find a global optimal solution that satisfies all constraints and minimizes costs. Summary of the Invention

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

[0005] Therefore, the present invention provides an intelligent scheduling method for distributed energy resources based on the Internet of Things to solve the problems of how to accurately reflect the interaction effects between distributed energy devices and find a global optimal solution that satisfies the constraints and minimizes costs.

[0006] To solve the above technical problems, the present invention provides the following technical solutions: In a first aspect, the present invention provides an intelligent scheduling method for distributed energy resources based on the Internet of Things, which includes, Collect the operation data of distributed energy devices and perform preprocessing to obtain a device operation data set, and perform swarm intelligence initialization on the device operation data set to generate an initial pheromone matrix; Perform local optimization on the device operation dataset and the initial pheromone matrix to generate an updated pheromone matrix and a device candidate scheduling plan, and generate a locally optimal scheduling plan through screening and verification; Use a quantum computing node to receive the locally optimal scheduling plan, use the locally optimal scheduling plan as the initial solution to construct a global optimization problem, output the global optimal scheduling plan, and at the same time convert it into a global scheduling instruction; Send the global scheduling instruction to the distributed energy device through the Internet of Things for execution, obtain the device execution status dataset, and perform an evaluation to generate a scheduling feedback report.

[0007] As a preferred solution of the intelligent scheduling method for distributed energy resources based on the Internet of Things according to the present invention, wherein: obtaining the device operation dataset means collecting real-time operation data from the distributed energy device using Internet of Things sensors, and performing denoising and integrity check operations on the collected real-time operation data to obtain the device operation dataset.

[0008] As a preferred solution of the intelligent scheduling method for distributed energy resources based on the Internet of Things according to the present invention, wherein: generating the initial pheromone matrix means extracting parameters from the device operation dataset, establishing the initial pheromone matrix, calculating the initial pheromone concentration of each pair in the initial pheromone matrix, and assigning roles to the distributed energy devices to complete the establishment of the initial pheromone matrix.

[0009] As a preferred solution of the intelligent scheduling method for distributed energy resources based on the Internet of Things according to the present invention, wherein: generating the updated pheromone matrix and the device candidate scheduling plan means using an improved ant colony algorithm to optimize the device operation dataset and the initial pheromone matrix to generate candidate output values; The edge computing node receives the candidate output values and uses a reverse learning mechanism to update the initial pheromone matrix to generate an updated pheromone matrix and a device candidate scheduling plan.

[0010] As a preferred solution of the intelligent scheduling method for distributed energy resources based on the Internet of Things according to the present invention, wherein: generating the locally optimal scheduling plan through screening and verification means selecting the scheduling path with the highest pheromone concentration from the updated pheromone matrix, and extracting the candidate output values and operation status corresponding to the selected scheduling path from the locally optimal scheduling plan to form a preliminary optimal solution; Perform constraint verification on the preliminary optimal solution, and use the preliminary optimal solution that passes the constraint verification as the locally optimal scheduling plan.

[0011] As a preferred embodiment of the intelligent scheduling method for distributed energy resources based on the Internet of Things according to the present invention, wherein: the quantum computing node is used to receive the local optimal scheduling plan and use the local optimal scheduling plan as the initial solution, and constructing the global optimization problem means mapping the local optimal scheduling plan to the initial spin state of the quantum Ising model and defining the Hamiltonian of the quantum Ising model; The Lagrange multiplier method is used to embed constraints into the Hamiltonian to complete the construction of the global optimization problem.

[0012] As a preferred embodiment of the intelligent scheduling method for distributed energy resources based on the Internet of Things according to the present invention, wherein: outputting the global optimal scheduling plan and simultaneously converting it into a global scheduling instruction means performing quantum annealing within a set time and number of iterations, and a candidate solution is generated in each iteration; Evaluate the Hamiltonian energy of each candidate solution, find the lowest energy state of the Hamiltonian, and obtain the initial global optimal scheduling plan; The initial global optimal scheduling plan is optimized and constraint-verified using classical gradient descent to generate the global optimal scheduling plan, and the global optimal scheduling plan includes the device IDs, output states, and power allocations of all distributed energy devices; Map the output state and power allocation to executable commands according to the types of distributed energy devices, and assign priorities to the distributed energy devices.

[0013] As a preferred embodiment of the intelligent scheduling method for distributed energy resources based on the Internet of Things according to the present invention, wherein: the global scheduling instruction is sent to the distributed energy device through the Internet of Things and executed to obtain the device execution status data set, and an evaluation is performed to generate a scheduling feedback report, which specifically includes the following steps: Perform constraint verification on the global scheduling instruction, parse and execute the verified global scheduling instruction to obtain the device execution status data set; Evaluate the device execution status data. If it is less than the expected value, perform dynamic optimization. The dynamic optimization means using the trained LSTM to output the supply and demand trend of the next scheduling period, and adjusting the quantum Ising model according to the supply and demand trend to obtain the scheduling feedback report.

[0014] In a second aspect, the present invention provides a computer device, including a memory and a processor, and the memory stores a computer program, wherein: when the computer program is executed by the processor, any step of the intelligent scheduling method for distributed energy resources based on the Internet of Things as described in the first aspect of the present invention is implemented.

[0015] In a third aspect, the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein: when the computer program is executed by a processor, any step of the method for intelligent scheduling of distributed energy resources based on the Internet of Things as described in the first aspect of the present invention is implemented.

[0016] The beneficial effects of the present invention are as follows: creating a customized initial pheromone matrix that reflects economic (electricity price / load demand) and operating factors, while using role assignment to align optimization with device functions, then guiding local update optimization by prioritizing cost-effective device interactions and ensuring compliance with role-specific constraints, and finally embedding real conditions into the swarm intelligence framework to improve optimization efficiency, accelerate convergence to a low-cost plan, and ensure functional alignment; in addition, by formulating a global optimization problem, capturing device interactions, economic factors, and multi-dimensional constraints within the network, the overall optimization of a large-scale energy network is achieved, ensuring device coordination and constraint compliance, and preventing problems such as grid instability. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for the description of the embodiments will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments of the present invention, and those of ordinary skill in the art can obtain other drawings based on these drawings without creative efforts.

[0018] Figure 1 It is a flowchart of the method for intelligent scheduling of distributed energy resources based on the Internet of Things.

[0019] Figure 2 It is a schematic diagram of the intelligent scheduling architecture of distributed energy resources.

[0020] Figure 3 It is a diagram of the local optimization and pheromone matrix update mechanism.

[0021] Figure 4 It is a diagram of the construction of the global optimization problem and the quantum annealing process. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0022] In order to make the above objects, features, and advantages of the present invention more obvious and understandable, the following detailed description of the specific embodiments of the present invention will be made in conjunction with the accompanying drawings of the specification.

[0023] Many specific details are set forth in the following description in order to provide a thorough understanding of the present invention, but the present invention may be practiced in other ways different from those described herein. Those skilled in the art can make similar extensions without departing from the spirit of the present invention, so the present invention is not limited by the specific embodiments disclosed below.

[0024] Second, the "one embodiment" or "embodiment" referred to herein means a specific feature, structure, or characteristic that may be included in at least one implementation manner of the present invention. The appearances of "in one embodiment" in different places in this specification do not all refer to the same embodiment, nor are they separate or alternative embodiments that are mutually exclusive of other embodiments.

[0025] Referring to Figures 1 to 4 , which is an embodiment of the present invention. This embodiment provides an intelligent scheduling method for distributed energy resources based on the Internet of Things, including the following steps: S1. Collect the operation data of distributed energy devices and perform preprocessing to obtain a device operation data set, and perform swarm intelligence initialization on the device operation data set to generate an initial pheromone matrix.

[0026] Specifically, it includes the following steps. S1.1. Equip distributed energy devices (such as photovoltaic panels, energy storage batteries, and electric vehicle charging piles) with Internet of Things sensors. The Internet of Things sensors perform big data collection, and collect the operation data of distributed energy devices in real time to generate a large amount of high-frequency data streams. The big data collection covers many contents.

[0027] For example: photovoltaic power generation, the state of charge of the energy storage battery, electric vehicle charging demand, user-side load demand, and real-time grid electricity price. This reflects the scale of big data collection. The Internet of Things sensors encapsulate the collected raw data into data packets and transmit the raw data generated by big data collection to the local edge computing node through a low-power wide area network.

[0028] S1.2. The edge computing node preprocesses the raw data generated by big data collection. Perform a denoising operation. The denoising uses the Kalman filtering algorithm. For example, for the data of photovoltaic power generation, the state of charge of the energy storage battery, electric vehicle charging demand, and user-side load demand, eliminate the influence of sensor noise and environmental interference (such as light fluctuations and grid voltage jitters). The Kalman filtering algorithm is based on the state space model, with the input being the raw data and the noise covariance (set to 0.01), and generates the denoised data.

[0029] The denoised data is checked for integrity to ensure the quality of the big data collection data. For example, the photovoltaic power generation must not be negative (if it is less than 0, it is marked as abnormal); the energy storage battery charge state range is 0% to 100% (if it exceeds, it is marked as abnormal); the electric vehicle charging demand and the user-side load demand must not be negative; the real-time power price of the power grid must not be less than 0 yuan / kWh. The edge computing node traverses each data packet and checks the above rules. If an abnormal data point is found (for example, the photovoltaic power generation is -0.1kW), the data point is removed and interpolated from the cached data of the last 5 seconds. The interpolation method is linear interpolation. The data that passes the integrity check is formatted and stored to obtain the device operation data set, including the device ID, data type, value and timestamp.

[0030] Preferably, high-precision and real-time data collection is achieved through big data collection. Deploying IoT sensors on distributed energy equipment can perform big data collection and generate high-frequency, large-scale data streams to capture operating parameters. This high-precision, real-time data collection provides a reliable foundation for subsequent intelligent scheduling, and can make accurate decisions in dynamic energy environments where conditions such as light intensity or grid demand fluctuate rapidly.

[0031] S1.2. Extract the initial electricity price and load demand from the device operation data set to initialize the pheromone matrix of the ant colony algorithm of swarm intelligence. The pheromone matrix initialization process calculates the initial pheromone concentration for each pair of relationships between distributed energy devices. The pheromone matrix is a two-dimensional array with the dimension of the number of distributed energy devices multiplied by the number of distributed energy devices. For example, 1000 distributed energy devices correspond to a matrix of 1000 rows and 1000 columns. Each matrix element represents the pheromone concentration from distributed energy device 1 to distributed energy device 2.

[0032] The calculation of the initial pheromone concentration is based on the following steps: First, take a constant (such as 10, used to normalize the pheromone concentration) and multiply it by the communication delay (in milliseconds) between distributed energy devices i and distributed energy devices j to obtain a product; then, divide the product by the number 1 to obtain the basic pheromone concentration. The communication delay is obtained by measuring the round-trip time of the MQTT (Message Queue Telemetry Transport Protocol) message by the edge computing node. Specifically, the edge computing node sends a test message to distributed energy devices i and distributed energy devices j, records the difference between the message sending time and the receiving time, repeats this process, and takes the average of the time difference.

[0033] To reflect the economic and load impacts of the initial electricity price and load demand, the basic pheromone concentration is further weighted and adjusted. The adjustment process is as follows: divide the initial electricity price (unit: yuan per kilowatt-hour) by the load demand (unit: kilowatt) to obtain the ratio of electricity price to load; multiply this ratio by the weight factor 0.1 to obtain the weighted term; add 1 to the weighted term to obtain the adjustment factor; multiply the basic pheromone concentration by the adjustment factor to obtain the final initial pheromone concentration, complete the initial pheromone matrix, and store it.

[0034] Based on the device operation dataset, the roles of distributed energy devices are assigned as follows. Extract the device ID and data type from the standardized device operation dataset, and assign a unique identifier and role to each distributed energy device. The unique identifier directly uses the device ID in the standardized device operation dataset to ensure consistency. The role assignment is based on the device type, and the rules are as follows: photovoltaic panels are assigned the "power generation" role, energy storage batteries are assigned the "energy storage" role, electric vehicle chargers and user-side loads are assigned the "load" role.

[0035] Preferably, the pheromone matrix of the ant colony algorithm of swarm intelligence is initialized using the data extracted from the device operation dataset to ensure that the initial pheromone matrix accurately reflects the economic and operating environment of distributed energy devices.

[0036] S2. Use the improved ant colony algorithm to perform local optimization on the device operation dataset and the initial pheromone matrix, generate an updated pheromone matrix and a device candidate scheduling plan, and generate a locally optimal scheduling plan through screening and verification.

[0037] Specifically, it includes the following steps. S2.1 Extract the electricity price, load demand, and energy storage battery state of charge from the device operation dataset as external inputs. The edge computing node drives the improved ant colony algorithm for local optimization calculation, treating each distributed energy device as an "ant". Each distributed energy device calculates the output adjustment strategy based on the initial pheromone matrix and external inputs. The goal of the improved ant colony algorithm is to minimize the scheduling cost of the local area. The scheduling cost is calculated as follows: for all distributed energy devices, multiply the electricity price by the output (kilowatts) of each distributed energy device, and then sum all the products to obtain the total cost (yuan). The optimization process needs to meet the supply-demand balance candidate, that is, the absolute value of the difference between the sum of the outputs of all distributed energy devices and the load demand, divided by the load demand, should be less than 0.001 (error less than 0.1%). At the same time, it is necessary to meet the device capacity constraint, that is, the output of each distributed energy device shall not exceed its rated power. The distributed energy devices exchange pheromone update results through communication, and the edge computing node executes algorithm iteration in real time to calculate the candidate output value and operating state of each distributed energy device (for example, the charging, discharging, or idle mode of the energy storage battery). The candidate output value selects the highest probability path based on the pheromone concentration, and the path probability is jointly determined by the pheromone concentration and the heuristic factor (the ratio of the electricity price to the load demand).

[0038] S2.2 The edge computing node receives the candidate output value and the initial pheromone matrix, performs pheromone update of the improved ant colony algorithm, and generates a local optimal scheduling plan: The pheromone update adopts a reverse learning mechanism, and the update process is as follows: for each element of the pheromone matrix (representing the pheromone concentration from distributed energy device i to distributed energy device j), first multiply the current pheromone concentration by 0.9 (1 minus the evaporation coefficient 0.1) to obtain the evaporated concentration; then, add the optimal path increment; and then add the reverse learning term. The reverse learning term is calculated as follows: take the number 1 divided by the absolute value of the worst path increment, and then multiply by the reverse learning weight 0.05. The optimal path increment is calculated as follows: take the constant 1 divided by the lowest scheduling cost to obtain the optimal path increment value, where the lowest scheduling cost is based on the path with the lowest cost among the candidate output values (the cost is the sum of the products of the electricity price and the output). The worst path increment is calculated as follows: take the constant 1 divided by the highest scheduling cost to obtain the increment value, where the highest scheduling cost is based on the path with the highest cost among the candidate output values. Obtain the updated pheromone matrix and the device candidate scheduling plan (device ID, candidate output value, operating state, timestamp).

[0039] Screen and verify the updated pheromone matrix and the device candidate scheduling scheme to generate a locally optimal scheduling scheme. Verify the updated pheromone matrix to ensure that all elements are non - negative, and then screen the device candidate scheduling scheme according to the updated pheromone matrix. Specifically: for each distributed energy device, select the path with the highest pheromone concentration, determine its candidate output value and operating status as the preliminary optimal solution, and conduct constraint verification on the preliminary optimal solution, verifying the supply - demand balance constraint and the device capacity constraint. The preliminary optimal solution that passes the verification is confirmed as the locally optimal scheduling scheme.

[0040] Preferably, optimize the local scheduling through an improved ant colony algorithm to minimize the scheduling cost and ensure economic and efficient energy distribution within a local area. Dynamically adapt to economic and operating conditions, thereby reducing energy costs (for example, prioritize low - cost distributed energy devices during high electricity prices).

[0041] S3. Receive the locally optimal scheduling scheme by the quantum computing node, use the locally optimal scheduling scheme as the initial solution to construct a global optimization problem, output the globally optimal scheduling scheme, and at the same time convert it into a global scheduling instruction.

[0042] Specifically, it includes the following steps. S3.1. The cloud quantum computing node receives the locally optimal scheduling scheme uploaded by the edge computing node. The locally optimal scheduling scheme includes the output value and status of each distributed energy device (such as photovoltaic panels, energy storage batteries, electric vehicle chargers). Use the locally optimal scheduling scheme as the initial solution to construct a global optimization problem.

[0043] The cloud quantum computing node maps the scheduling problem of distributed energy resources to a quantum Ising model to achieve global optimization. The Hamiltonian of the quantum Ising model is defined as the sum of two parts: the first part is the interaction between all pairs of distributed energy devices, calculated as the sum of the products of the coupling coefficients of each pair of devices (distributed energy device i and distributed energy device j) and the output states of distributed energy device i and distributed energy device j, and then taking the negative value; the second part is the external field of each distributed energy device, calculated as the sum of the products of the external field coefficients of each distributed energy device and its output state, and then taking the negative value. The output state of the distributed energy device is represented as - 1 (off) or + 1 (on). The coupling coefficient is dynamically generated by the energy complementarity rate. Based on the synergy between photovoltaic and energy storage, it is calculated as: take a constant (such as 0.1) multiplied by the product of the output of distributed energy device i and the output of distributed energy device j, and then divide by the communication delay between them (in milliseconds, obtained by measuring the round - trip time of MQTT messages through the edge computing node).

[0044] For example, if the output of distributed energy device i is 10 kilowatts, the output of distributed energy device j is 5 kilowatts, and the communication delay is 2 milliseconds, then the coupling coefficient is 0.1 multiplied by 10 multiplied by 5 divided by 2, which equals 2.5. The external field coefficient is determined by the device capacity and electricity price, and is calculated as: taking a constant (such as 0.05) multiplied by the product of the device capacity and electricity price of distributed energy device i. For example, if the device capacity of distributed energy device i is 20 kilowatts and the electricity price is 0.5 yuan per kilowatt-hour, then the external field coefficient is 0.05 multiplied by 20 multiplied by 0.5, which equals 0.5.

[0045] The global optimization problem needs to satisfy multi-dimensional constraints, including supply-demand balance, distributed energy device capacity, and grid stability (such as voltage fluctuation less than ±5%). These constraints are embedded into the Hamiltonian of the quantum Ising model through the Lagrange multiplier method. The calculation of the penalty function is: taking a constant (such as 10) multiplied by the square of the difference between the sum of the outputs of all distributed energy devices and the load demand. The penalty function is the penalty function used to embed the supply-demand balance constraint, and is specifically used to handle the deviation between the sum of the outputs of all distributed energy devices and the load demand in the global optimization problem.

[0046] For example, if the sum of the outputs of distributed energy devices is 100 kilowatts and the load demand is 102 kilowatts, then the penalty function is 10 multiplied by the square of (100 minus 102), which equals 40. The cloud quantum computing node maps the output values and states of the local optimal scheduling scheme to the initial spin states (-1 or +1) of the quantum Ising model, and adjusts the Hamiltonian parameters according to the constraints to complete the construction of the global optimization problem.

[0047] Furthermore, integrating multi-dimensional constraints into the Hamiltonian of the quantum Ising model through Lagrange ensures that the global optimal scheduling scheme is both feasible and stable, thus preventing problems such as power shortages or grid instability in large-scale energy networks.

[0048] S3.2. The quantum annealing processor starts from the initial spin state of the local optimal scheduling scheme and executes the annealing process. By gradually reducing the energy of the quantum system, it searches for the lowest energy state of the Hamiltonian. The lowest energy state corresponds to the global optimal scheduling scheme, representing the output states and power allocations of all distributed energy devices. Set the annealing time and number of times (e.g., 500 microseconds, repeated 100 times) to obtain the lowest energy solution. Each annealing generates a candidate solution, including the spin state (-1 or +1) of each distributed energy device and the corresponding output value (based on the mapping of the distributed energy device capacity and state. For example, the +1 state corresponds to 80% of the rated power). Evaluate the Hamiltonian energy of each candidate solution. The energy calculation includes the interaction term (the sum of the products of the coupling coefficient and the spin state), the external field term (the sum of the external field coefficient and the spin state), and the penalty function term. For example, if the supply-demand deviation of a candidate solution is 2 kW, the Hamiltonian energy includes the penalty function term 10 times the square of 2, which is equal to 40, increasing the energy value and reducing the preferred probability of this solution. Select the solution with the lowest energy from the number of annealings as the initial global optimal scheduling scheme of the quantum annealing.

[0049] Preferably, using quantum annealing for high-precision optimization significantly improves the accuracy and speed of finding the lowest energy state of the Hamiltonian, which corresponds to the global optimal scheduling scheme.

[0050] To handle quantum computing noise (e.g., qubit decoherence or thermal noise), a quantum-classical hybrid algorithm is used to further optimize the initial solution of the quantum annealing. Starting from the initial global optimal scheduling scheme provided by the quantum annealing, the classical gradient descent algorithm iteratively adjusts the output values to minimize the local error (the error is defined as the deviation of the Hamiltonian energy from the ideal lowest energy). The classical gradient descent adjusts the output of each distributed energy device based on the gradient of the Hamiltonian (the partial derivative with respect to the output value). Set the number of iterations, such as 10 times. Each iteration calculates the output adjustment amount of all distributed energy devices. The adjustment amount is determined by multiplying the gradient by the learning rate (e.g., 0.01). The optimized solution includes the device ID, output state (on or off), and power allocation of each distributed energy device. Perform constraint verification on the optimized solution (supply-demand balance constraint, distributed energy device capacity constraint, and grid stability constraint). The solution that passes the verification is confirmed as the global optimal scheduling scheme, including the device ID, output state, and power allocation of all distributed energy devices.

[0051] S3.3. Convert the global optimal scheduling plan into global scheduling instructions. Traverse each distributed energy device in the global optimal scheduling plan, retain the distributed energy device ID and output value, and assign priorities according to the device type and output value. The priority is an integer ranging from 1 to 10. For example, when the output of a photovoltaic panel is greater than 50% of its rated power, the priority is set to 8; when the energy storage battery is discharging, the priority is set to 6; the priority of an electric vehicle charging pile is set to 4.

[0052] S4. Send the global scheduling instructions to the distributed energy devices through the Internet of Things and execute them to obtain the device execution status data set. Specifically, it includes the following steps. S4.1. To ensure the feasibility of the global scheduling instructions under the local conditions of the real world, it is necessary to verify the feasibility of the global scheduling instructions. The verification uses linear constraint checking, including two constraints: First, the distributed energy device capacity constraint, which ensures that the output value of each distributed energy device does not exceed its rated power; Second, the supply-demand balance constraint, which ensures that the absolute difference between the total output of all distributed energy devices and the load demand divided by the load demand is less than 0.001 (the error is less than 0.1%). If the global scheduling instructions are not feasible (for example, overloading or supply-demand error exceeding the standard), then generate backup instructions from the device candidate scheduling plan. The backup instructions select the path with the second-highest pheromone concentration from the device candidate scheduling plan and adjust the output value to meet the device capacity constraint and the supply-demand balance constraint.

[0053] Send the verified global scheduling instructions or backup instructions to the distributed energy devices. The distributed energy devices receive and parse the instructions and perform corresponding actions. The inverter of the photovoltaic panel adjusts the output power according to the instructions. For example, adjust the output from 7 kilowatts to 8.5 kilowatts. The energy storage battery switches the operation mode (charging, discharging, idle) according to the instructions. For example, switch from the charging mode to the discharging mode. The distributed energy devices upload the execution status once per second. The edge computing node receives and calculates the scheduling efficiency in real time, including the energy utilization rate and the cost savings rate; the calculation method of the energy utilization rate is: the actual total output divided by the load demand, the target > 95%. The calculation method of the cost savings rate is: based on the comparison of the electricity price and the cost of the actual output, the target > 10%. Summarize the execution status of all distributed energy devices to generate the device execution status data set. The device execution status data set includes the device ID, actual output, status, and timestamp.

[0054] S5. Evaluate according to the device execution status data set and generate a scheduling feedback report.

[0055] Specifically, it includes the following steps. S5.1. Calculate the objective function value based on the device execution status dataset to evaluate the scheduling effect, which includes three indicators: cost, energy utilization rate, and grid stability. Compare the objective function value with the expected value: the expected value is that the cost is lower than the budget, the energy utilization rate is higher than 90%, and the voltage fluctuation is less than ±5%. If the deviation of any indicator exceeds 0.1%, trigger dynamic optimization.

[0056] The dynamic optimization is to use LSTM (Long Short-Term Memory Network) to predict the supply and demand trend in the next scheduling period (e.g., 1 hour). The input of the Long Short-Term Memory Network is the device execution status dataset in the past 24 hours, including the actual output, status, load demand, and electricity price of each distributed energy device. And it is normalized to the range of 0 to 1. The Long Short-Term Memory Network is configured with 3 layers, using the tanh activation function, and the training weights are based on historical data, such as the data in the past seven days. The output of the Long Short-Term Memory Network is the predicted power generation and load demand in the next hour. Based on the predicted power generation and load demand, the cloud quantum computing node adjusts the swarm intelligence parameters and the quantum Ising model to optimize the next scheduling period.

[0057] Send the adjusted parameters to the edge computing node to update the pheromone matrix and the Hamiltonian of the quantum Ising model. The cloud quantum computing node generates a feedback report to evaluate the scheduling performance. The scheduling efficiency includes the energy utilization rate, cost savings rate, and prediction error. The prediction error is the deviation between the Long Short-Term Memory Network prediction value and the actual value. The feedback report contains fields: energy utilization rate, cost savings rate, prediction error, and timestamp. Thus, this scheduling task is completed.

[0058] This embodiment also provides a computer device, which is applicable to the situation of the intelligent scheduling method of distributed energy resources based on the Internet of Things, including: a memory and a processor; the memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions to implement the intelligent scheduling method of distributed energy resources based on the Internet of Things as proposed in the above embodiment.

[0059] The computer device may be a terminal, which includes a processor, a memory, a communication interface, a display screen, and an input device connected via a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage medium. The communication interface of the computer device is used to communicate with external terminals in a wired or wireless manner. The wireless manner can be implemented through WIFI, carrier networks, NFC (Near Field Communication), or other technologies. The display screen of the computer device can be a liquid crystal display screen or an electronic ink display screen. The input device of the computer device can be a touch layer covering the display screen, or buttons, trackballs, or touchpads provided on the housing of the computer device, or an external keyboard, touchpad, or mouse, etc.

[0060] This embodiment also provides a storage medium, on which a computer program is stored. When the program is executed by a processor, it implements the method for intelligent scheduling of distributed energy resources based on the Internet of Things as proposed in the above embodiment; the storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (Static Random Access Memory, abbreviated as SRAM), electrically erasable programmable read-only memory (Electrically Erasable Programmable Read-Only Memory, abbreviated as EEPROM), erasable programmable read-only memory (Erasable Programmable Read Only Memory, abbreviated as EPROM), programmable read-only memory (Programmable Red-Only Memory, abbreviated as PROM), read-only memory (Read-Only Memory, abbreviated as ROM), magnetic memory, flash memory, magnetic disks, or optical discs.

[0061] In summary, the present invention improves the optimization efficiency, accelerates convergence to a low-cost plan, and ensures functional alignment by: creating a customized initial pheromone matrix that reflects economic (electricity price / load demand) and operational factors, while using role assignment to keep the optimization consistent with device functions, then guiding the local update optimization by prioritizing cost-effective device interactions and ensuring compliance with role-specific constraints, and finally embedding real conditions into the swarm intelligence framework; in addition, by formulating a global optimization problem that captures network-wide device interactions, economic factors, and multi-dimensional constraints, it realizes the overall optimization of large-scale energy networks, ensures device coordination and constraint compliance, and prevents problems such as power grid instability.

[0062] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit them. Although the present invention has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that the technical solutions of the present invention can be modified or equivalently replaced without departing from the spirit and scope of the technical solutions of the present invention, and they should all be covered within the scope of the claims of the present invention.

Claims

1. An intelligent scheduling method for distributed energy resources based on the Internet of Things, characterized in that: including Collect the operation data of distributed energy devices and perform preprocessing to obtain a device operation data set, and perform swarm intelligence initialization on the device operation data set to generate an initial pheromone matrix; Perform local optimization on the device operation data set and the initial pheromone matrix to generate an updated pheromone matrix and a device candidate scheduling plan, and generate a locally optimal scheduling plan through screening and verification; Use a quantum computing node to receive the locally optimal scheduling plan, use the locally optimal scheduling plan as the initial solution, construct a global optimization problem, output the global optimal scheduling plan, and convert it into a global scheduling instruction at the same time; Send the global scheduling instruction to the distributed energy device through the Internet of Things and execute it to obtain a device execution status data set, and perform an evaluation to generate a scheduling feedback report.

2. The intelligent scheduling method for distributed energy resources based on the Internet of Things according to claim 1, wherein: The obtaining of the device operation data set refers to collecting real-time operation data from the distributed energy device using an Internet of Things sensor, and performing denoising and integrity check operations on the collected real-time operation data to obtain the device operation data set.

3. The intelligent scheduling method for distributed energy resources based on the Internet of Things according to claim 2, wherein: The generating of the initial pheromone matrix refers to establishing an initial pheromone matrix based on the parameters extracted from the device operation data set, calculating the initial pheromone concentration of each pair in the initial pheromone matrix, and assigning roles to the distributed energy devices to complete the establishment of the initial pheromone matrix.

4. The intelligent scheduling method for distributed energy resources based on the Internet of Things according to claim 3, wherein: The generating of the updated pheromone matrix and the device candidate scheduling plan refers to using an improved ant colony algorithm to optimize the device operation data set and the initial pheromone matrix to generate candidate output values; The edge computing node receives the candidate output values and uses a reverse learning mechanism to update the initial pheromone matrix to generate an updated pheromone matrix and a device candidate scheduling plan.

5. The intelligent scheduling method for distributed energy resources based on the Internet of Things according to claim 4, characterized in that: The generating of the locally optimal scheduling plan through screening and verification refers to selecting the scheduling path with the highest pheromone concentration from the updated pheromone matrix, and extracting the candidate output values and operation status corresponding to the selected scheduling path from the locally optimal scheduling plan to form a preliminary optimal solution; Perform constraint verification on the preliminary optimal solution, and use the preliminary optimal solution that passes the constraint verification as the locally optimal scheduling plan.

6. The intelligent scheduling method for distributed energy resources based on the Internet of Things according to claim 5, wherein: The using of the quantum computing node to receive the locally optimal scheduling plan and using the locally optimal scheduling plan as the initial solution to construct a global optimization problem refers to mapping the locally optimal scheduling plan to the initial spin state of the quantum Ising model and defining the Hamiltonian of the quantum Ising model; Use the Lagrange multiplier method to embed constraints into the Hamiltonian to complete the construction of the global optimization problem.

7. The intelligent scheduling method for distributed energy resources based on the Internet of Things according to claim 6, characterized in that: The outputting of the global optimal scheduling plan and converting it into a global scheduling instruction at the same time refers to performing quantum annealing within a set time and number of iterations, and generating a candidate solution in each iteration; Evaluate the Hamiltonian energy of each candidate solution, search for the lowest energy state of the Hamiltonian to obtain an initial global optimal scheduling plan; Optimize and perform constraint verification on the initial global optimal scheduling plan using classical gradient descent to generate the global optimal scheduling plan, and the global optimal scheduling plan includes the device IDs, output states, and power allocations of all distributed energy devices; Map the output state and power allocation to executable commands according to the type of distributed energy device, and assign priorities to the distributed energy devices.

8. The intelligent scheduling method for distributed energy resources based on the Internet of Things according to claim 7, characterized in that: Send global scheduling instructions to distributed energy devices through the Internet of Things and execute them to obtain a device execution status data set, and conduct an evaluation to generate a scheduling feedback report, which specifically includes the following steps: Conduct constraint verification on the global scheduling instructions, parse and execute the verified global scheduling instructions to obtain a device execution status data set; Evaluate the device execution status data. If it is less than the expected value, perform dynamic optimization. The dynamic optimization refers to using the trained LSTM to output the supply and demand trend of the next scheduling cycle, and adjusting the quantum Ising model according to the supply and demand trend to obtain a scheduling feedback report.

9. A computer device, comprising a memory and a processor, the memory storing a computer program, characterized in that: When the processor executes the computer program, it implements the steps of the Internet of Things-based intelligent scheduling method for distributed energy resources according to any one of claims 1 to 8.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by the processor, it implements the steps of the Internet of Things-based intelligent scheduling method for distributed energy resources according to any one of claims 1 to 8.

Images