Adaptive algorithm optimization control system and method for intelligent energy management

Abstract

The invention provides a self-adaptive algorithm optimization control system and method for intelligent energy management. The system comprises a data acquisition unit which acquires operation data of various energy devices in real time; the model prediction unit predicts renewable energy output and load demand within a preset time based on a machine learning algorithm by using historical data and operation data collected in real time to obtain a prediction result; the optimization engine unit constructs a multi-objective optimization model according to the prediction result and the operation data, solves the multi-objective optimization model by adopting a heuristic intelligent algorithm, and generates an optimal energy scheduling strategy; the adaptive control unit analyzes the optimal energy scheduling strategy into a control instruction which can be executed by each energy device, issues the control instruction to an execution unit, and monitors the execution state and system response of the energy device at the same time; and the execution units adjust respective operation states according to the control instruction, and cooperatively realize optimal scheduling of the whole system. The method can dynamically adapt to changes of an energy system, and the energy utilization rate is increased.

Description

Technical Field

[0001] The present invention relates to the field of smart grid and energy management, and in particular to an adaptive algorithm optimization control system and method for smart energy management. Background Art

[0002] With the large-scale access of renewable energy and the widespread application of distributed energy, traditional energy management systems can no longer meet the increasingly complex energy network control needs.

[0003] Most existing energy management systems use fixed control strategies and parameters, lack flexibility and adaptability, and have difficulty coping with uncertain factors such as load fluctuations and intermittency, resulting in low energy utilization efficiency.

[0004] Therefore, there is an urgent need for an intelligent energy management system with self-learning and self-optimization capabilities. Summary of the invention

[0005] In view of this, an object of the embodiments of the present invention is to provide an adaptive algorithm optimization control system and method for intelligent energy management to solve the above-mentioned problems existing in the prior art.

[0006] To achieve the above objectives, in a first aspect, the present invention provides an adaptive algorithm optimization control system for intelligent energy management, the system comprising:

[0007] Data acquisition unit, used to collect operating data of various energy equipment in real time;

[0008] A model prediction unit is used to predict the output and load demand of renewable energy within a preset time based on a machine learning algorithm using historical data and real-time collected operation data to obtain a prediction result;

[0009] An optimization engine unit, configured to construct a multi-objective optimization model according to the prediction results and the operation data, and solve the multi-objective optimization model using a heuristic intelligent algorithm to generate an optimal energy scheduling strategy;

[0010] An adaptive control unit, used to parse the optimal energy scheduling strategy into control instructions executable by each energy device, and send them to the execution unit, while monitoring the execution status and system response of the energy device;

[0011] The execution units are used to adjust their respective operating states according to the control instructions and collaboratively achieve optimal scheduling of the entire system.

[0012] In some possible implementations, the optimization engine unit is further used for:

[0013] The constructed multi-objective optimization model is divided into multiple sub-problems, each of which corresponds to a local optimization model of a subsystem;

[0014] The multiple subsystems solve the local optimization model in parallel to obtain local optimization results; the subsystems iteratively exchange boundary information and gradually reach global consensus using a distributed optimization algorithm.

[0015] In some possible implementations, the adaptive control unit is further configured to:

[0016] The optimization and control behaviors of the subsystems are coordinated through a distributed collaborative control strategy; wherein,

[0017] The subsystem generates a local control strategy based on the local optimization result;

[0018] The subsystems iteratively exchange status information and the local control decisions, and use a distributed game mechanism to achieve global coordination.

[0019] In some possible implementations, the optimization engine unit is further used for:

[0020] A quantum Hamiltonian model and a quantum circuit are constructed, the multi-objective optimization model is solved by a quantum algorithm, the calculation results of the multi-objective optimization model solved by the quantum algorithm are compared and integrated with the calculation results of the multi-objective optimization model solved by a heuristic intelligent algorithm, and a final optimization scheduling strategy is obtained.

[0021] In some possible implementations, the system further includes a human-computer interaction interface for inputting domain knowledge, empirical rules, or optimization preferences to form an expert knowledge base;

[0022] The optimization engine unit is also used to: construct and solve the multi-objective optimization model using the expert knowledge base, generate a knowledge-driven energy scheduling strategy, and present the knowledge-driven energy scheduling strategy to an expert user through a human-computer interaction interface.

[0023] In some possible implementations, the data acquisition unit is further used to construct an energy blockchain network, the energy equipment and the user access the energy blockchain network through the blockchain node, upload the energy data and transaction request information to the blockchain, and after verification by the consensus mechanism, store it on the chain in the form of blocks;

[0024] The adaptive control unit is also used to propagate the control instructions in the energy blockchain network in the form of transactions, and automatically verify and execute them by smart contracts.

[0025] In a second aspect, an embodiment of the present invention further provides an adaptive algorithm optimization control method for intelligent energy management, the method comprising:

[0026] Real-time collection of operating data of various energy equipment;

[0027] Based on machine learning algorithms, historical data and real-time collected operating data are used to predict renewable energy output and load demand within a preset time to obtain prediction results;

[0028] Constructing a multi-objective optimization model according to the prediction results and the operation data, and solving the multi-objective optimization model using a heuristic intelligent algorithm to generate an optimal energy scheduling strategy;

[0029] Parsing the optimal energy dispatch strategy into executable control instructions for each energy device, and sending them to the execution unit, while monitoring the execution status and system response of the energy device;

[0030] The respective operating states are adjusted according to the control instructions to collaboratively achieve optimal scheduling of the entire system.

[0031] In some possible implementations, the method further includes:

[0032] The constructed multi-objective optimization model is divided into multiple sub-problems, each sub-problem corresponds to a local optimization model of a subsystem; multiple subsystems solve the local optimization models in parallel to obtain local optimization results; the subsystems iteratively exchange boundary information and gradually reach global consensus using a distributed optimization algorithm;

[0033] The method further includes: coordinating the optimization and control behaviors of the subsystems through a distributed collaborative control strategy; wherein the subsystems generate local control strategies based on local optimization results; the subsystems iteratively exchange state information and the local control decisions, and use a distributed game mechanism to achieve global coordination;

[0034] The method further comprises:

[0035] A quantum Hamiltonian model and a quantum circuit are constructed, the multi-objective optimization model is solved by a quantum algorithm, the calculation results of the multi-objective optimization model solved by the quantum algorithm are compared and integrated with the calculation results of the multi-objective optimization model solved by a heuristic intelligent algorithm, and a final optimization scheduling strategy is obtained.

[0036] In some possible implementations, the method further includes:

[0037] Input domain knowledge, empirical rules or optimization preferences through the human-computer interaction interface to form an expert knowledge base;

[0038] The multi-objective optimization model is constructed and solved using the expert knowledge base to generate a knowledge-driven energy scheduling strategy, and the knowledge-driven energy scheduling strategy is presented to an expert user through a human-computer interaction interface.

[0039] In some possible implementations, the method further includes: constructing an energy blockchain network, wherein the energy device and the user access the energy blockchain network through a blockchain node, uploading energy data and transaction request information to the blockchain, and storing the energy data and transaction request information on the blockchain in the form of blocks after verification by a consensus mechanism;

[0040] The control instructions are propagated in the energy blockchain network in the form of transactions and automatically verified and executed by smart contracts.

[0041] In a third aspect, an embodiment of the present invention provides an electronic device, including:

[0042] one or more processors;

[0043] A storage device is used to store one or more programs. When the one or more programs are executed by the one or more processors, the one or more processors implement the method described in the second aspect.

[0044] In a fourth aspect, an embodiment of the present invention provides a computer-readable medium having a computer program stored thereon, which, when executed by a processor, implements the method described in the second aspect.

[0045] The above technical solution has the following beneficial effects:

[0046] The present invention provides an adaptive algorithm optimization control system and method for intelligent energy management, the system comprising: a data acquisition unit for real-time acquisition of operating data of various energy devices; a model prediction unit for predicting renewable energy output and load demand within a preset time based on a machine learning algorithm using historical data and real-time acquired operating data to obtain a prediction result; an optimization engine unit for building a multi-objective optimization model based on the prediction result and operating data, and using a heuristic intelligent algorithm to solve the multi-objective optimization model to generate an optimal energy scheduling strategy; an adaptive control unit for parsing the optimal energy scheduling strategy into executable control instructions for each energy device, and sending it to an execution unit, while monitoring the execution status and system response of the energy device; an execution unit for adjusting the respective operating status according to the control instruction, and collaboratively realizing the optimization scheduling of the entire system. The present invention improves energy utilization by being able to dynamically adapt to changes in the energy system. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. It is obvious that the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0048] Figure 1 It is a structural block diagram of an adaptive algorithm optimization control system for intelligent energy management according to an embodiment of the present invention;

[0049] Figure 2 is a flow chart of an adaptive algorithm optimization control method for intelligent energy management according to an embodiment of the present invention;

[0050] Figure 3 It is a functional block diagram of an electronic device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0051] Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although certain embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be construed as being limited to the embodiments described herein, which are instead provided for a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are only for exemplary purposes and are not intended to limit the scope of protection of the present disclosure.

[0052] It should be understood that the various steps described in the method embodiments of the present disclosure may be performed in different orders and / or in parallel. In addition, the method embodiments may include additional steps and / or omit the steps shown. The scope of the present disclosure is not limited in this respect.

[0053] The term "including" and its variations used herein are open inclusions, i.e., "including but not limited to". The term "based on" means "based at least in part on". The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; the term "some embodiments" means "at least some embodiments". The relevant definitions of other terms will be given in the following description.

[0054] It should be noted that the concepts such as "first" and "second" mentioned in the present disclosure are only used to distinguish different devices, modules or units, and are not used to limit the order or interdependence of the functions performed by these devices, modules or units.

[0055] It should be noted that the modifications of "one" and "plurality" mentioned in the present disclosure are illustrative rather than restrictive, and those skilled in the art should understand that unless otherwise clearly indicated in the context, it should be understood as "one or more".

[0056] The names of the messages or information exchanged between multiple devices in the embodiments of the present disclosure are only used for illustrative purposes and are not used to limit the scope of these messages or information.

[0057] Embodiment 1

[0058] Figure 1 is a structural block diagram of an adaptive algorithm optimization control system for intelligent energy management according to an embodiment of the present invention. Figure 1 As shown, the system 100 includes:

[0059] The data collection unit 110 is used to collect the operation data of various energy devices in real time.

[0060] In this embodiment, the data acquisition unit 110 is used to collect the operating parameters of various energy equipment in real time, including power generation, load demand, energy storage status, etc., and transmit the data related to the operating parameters to the prediction model and optimization engine. The data acquisition unit 110 includes various sensors, smart meters, and online monitoring devices. For example, the wind speed sensor is used to measure the real-time wind speed of the wind farm; the light intensity sensor is used to measure the light intensity of the photovoltaic power station; the smart meter is distributed on the user side to collect the user's real-time power load; the monitoring system of the energy storage equipment records the charging and discharging status of the energy storage in real time. Parameters. These distributed data acquisition devices are connected to the data center through industrial Ethernet, wireless communication, etc., and upload real-time data to the server where the prediction model and optimization engine are located. The function of the data acquisition unit 110 is to provide comprehensive, accurate, and real-time operation data support for the system.

[0061] The model prediction unit 120 is used to predict the renewable energy output and load demand within a preset time based on the machine learning algorithm using historical data and real-time collected operation data to obtain a prediction result.

[0062] In this embodiment, the model prediction unit 120 uses historical data and real-time data based on a machine learning algorithm to predict the output and load demand of renewable energy in the future, and provides input for the optimization engine unit 130. The model prediction unit 120 in this embodiment adopts an adaptive learning mechanism, and can automatically adjust the model parameters according to the prediction deviation.

[0063] Specifically, the model prediction unit 120 adopts a sequence prediction algorithm based on deep learning, such as a long short-term memory network (LSTM). The input of the model includes historical wind speed, light, load data, and external factors such as weather forecast information; the output is the predicted value of wind power, photovoltaic power generation and load demand in the next 24 hours. The model adaptively improves the prediction accuracy through continuous training and parameter adjustment. For example, when the predicted photovoltaic power generation deviates greatly from the actual value, the model will automatically adjust the network structure or weight parameters to reduce the prediction error. In this embodiment, the model prediction unit 120 can provide the optimization engine unit 130 with the expected operation of the energy system in the future period of time, and provide a basis for optimizing scheduling decisions in advance.

[0064] The optimization engine unit 130 is used to build a multi-objective optimization model based on the prediction results and operation data, and use a heuristic intelligent algorithm to solve the multi-objective optimization model to generate an optimal energy scheduling strategy.

[0065] In this embodiment, the optimization engine unit 130 receives the output of the model prediction unit 120, combines the characteristics of energy equipment, operation constraints, etc., builds a multi-objective optimization model, uses a heuristic intelligent algorithm to solve, and generates an optimal energy scheduling strategy. The optimization objectives include maximizing energy utilization efficiency, minimizing operating costs, minimizing pollutant emissions, etc. The optimization engine unit 130 is adaptive and can dynamically adjust the optimization model and algorithm parameters according to changes in system status.

[0066] Specifically, the optimization engine unit 130 adopts the multi-objective particle swarm optimization (MOPSO) algorithm, and the decision variables of the optimization model include the output scheduling plan of each power source (for example, wind power, photovoltaic, energy storage and diesel generator, etc.); the objective function includes the minimum power generation cost, the maximum utilization rate of renewable energy, the optimal load peak-shaving and valley-filling effect, etc.; the constraints include power balance, energy storage charging and discharging restrictions, spare capacity requirements, etc. The optimization engine unit 130 will adaptively generate the initial population according to the output of the prediction model, and search for the optimal scheduling strategy that meets multiple objectives through iterative optimization. For example, when the predicted wind power output is high, the optimization engine unit 130 will appropriately increase the priority scheduling weight of wind power, while considering the trade-offs of other objectives to achieve efficient utilization of wind and light resources. In this embodiment, the optimization engine unit 130 can generate a global optimal energy optimization scheduling scheme to balance multiple objectives such as energy utilization, economy, and reliability.

[0067] Specifically, heuristic intelligent algorithms are a type of algorithm used to solve complex optimization problems. Their main features are to simulate certain phenomena and processes in nature, use local information of the problem to guide the search, and find a satisfactory solution within a reasonable time. Heuristic intelligent algorithms include genetic algorithms, particle swarm optimization algorithms, ant colony algorithms, simulated annealing algorithms, etc.

[0068] The following takes the genetic algorithm as an example to specifically describe the working process of the optimization engine unit 130:

[0069] Step 1. Receiving input data: The optimization engine unit 130 receives the predicted value of renewable energy output and load demand in the future period from the model prediction unit 120, and simultaneously obtains the real-time operation data of various energy equipment.

[0070] Step 2. Construct an optimization model: Construct a multi-objective optimization model based on system configuration, equipment parameters, operating constraints, etc. The decision variables of the model are the output scheduling plans of various energy equipment. The objective function includes indicators such as energy utilization efficiency, operating costs, and pollutant emissions. The constraints include power balance, energy storage capacity limitations, and upper and lower limits of equipment output.

[0071] Step 3. Initialize the population: Randomly generate a certain number of feasible solutions as the initial population, and each individual represents a complete set of energy scheduling strategies. Individual coding can be done in real number coding or binary coding.

[0072] Step 4. Evaluate fitness: Decode each individual in the population, calculate its corresponding objective function value, and then convert the objective function value into a fitness value according to the multi-objective optimization processing method (such as weighted summation method, Pareto sorting method, etc.).

[0073] Step 5. Selection operation: Using fitness as an indicator, use selection operators such as roulette and tournament to select a portion of excellent individuals from the current population to be inherited to the next generation.

[0074] Step 6. Crossover operation: Randomly pair the selected parent individuals and perform a crossover operation with a certain probability to generate new offspring individuals. The crossover operator can be single-point crossover, multi-point crossover, arithmetic crossover, etc.

[0075] Step 7. Mutation operation: Perform mutation operation on offspring individuals with a certain probability, introduce random disturbances at certain positions of individual codes to maintain the diversity of the population. The mutation operator can use basic bit mutation, uniform mutation, Gaussian mutation, etc.

[0076] Step 8. Population update: merge the parent and offspring individuals, reselect to generate a new generation of population based on fitness, and keep the population size unchanged.

[0077] Step 9. Termination condition judgment: If the preset evolutionary generation is reached or other termination conditions are met, the individual with the highest fitness in the current population is output as the optimal solution; otherwise, return to step 4 and continue iterative optimization.

[0078] Step 10. Generate a dispatch strategy: Decode the optimal solution, obtain the optimal output dispatch curve of each energy device in the future, and form an executable energy dispatch strategy.

[0079] Taking a microgrid as an example, the system includes photovoltaic power generation, wind power generation, energy storage batteries, diesel generators and loads. Through genetic algorithm optimization and solution, the utilization rate of renewable energy can be maximized and the operating cost can be minimized under the premise of ensuring load balance. Assuming that after 100 generations of evolution, the algorithm converges to the optimal solution: in the next 24 hours, the photovoltaic output forecast value is [80,120,150,...], the wind power output forecast value is [50,60,55,...], and the load demand forecast value is [100,110,130,...]. The optimal scheduling strategy is: during the day, it is mainly powered by photovoltaic and wind power, and the excess power is stored when the electricity price is low. When the electricity price is peak, the energy storage is discharged, and the basic load is guaranteed by the diesel engine, so as to achieve safe, economical and environmentally friendly energy optimization scheduling.

[0080] The adaptive control unit 140 is used to parse the optimal energy scheduling strategy into control instructions executable by each energy device, and send them to the execution unit 150, while monitoring the execution status and system response of the energy device.

[0081] In this embodiment, the adaptive control unit 140 parses the scheduling strategy generated by the optimization engine into control instructions executable by each energy device, sends them to the execution mechanism, and monitors the execution status and system response of each device to form a closed-loop control.

[0082] Specifically, the adaptive control unit 140 adopts a real-time control strategy based on adaptive dynamic programming. It converts the optimal energy scheduling strategy (such as a scheduling curve) generated by the optimization engine unit 130 into a specific control instruction and sends it to each energy device. At the same time, the adaptive control unit 140 receives status feedback from the device and performs real-time monitoring. When the actual operation deviates from the optimized scheduling curve, the adaptive control unit 140 will adaptively adjust the control strategy and compensate for it in the next scheduling cycle to ensure the real-time optimization operation of the entire system. For example, when the wind power output in a certain period of time is lower than expected, the adaptive control unit 140 will promptly adjust the discharge power of the energy storage or the output of the diesel engine to maintain the power balance of the system. The adaptive control unit 140 in this embodiment can not only execute the optimized scheduling scheme, but also can adaptively adjust in actual operation to ensure real-time optimization of the energy system.

[0083] The execution unit 150 is used to adjust the respective operating states according to the control instructions and collaboratively achieve the optimized scheduling of the entire system.

[0084] In this embodiment, the execution unit 150 includes an energy storage device, a controllable load, a power grid control device, etc., which adjust their respective operating states according to the control instructions to collaboratively achieve optimal scheduling of the entire system.

[0085] Specifically, the execution unit 150 includes a wind turbine, a photovoltaic inverter, an energy storage converter, and a load control terminal. The wind turbine, the photovoltaic inverter, the energy storage converter, and the load control terminal adjust their own operating states accordingly according to the instructions issued by the adaptive control unit 140, such as the variable pitch angle and generator torque of the wind turbine, the maximum power point tracking (MPPT) of the photovoltaic inverter, and the charging and discharging power of the energy storage. The actuators are distributed at various nodes of the energy system, and through local optimization control, they cooperate to achieve the optimal operation of the entire system. For example, when the adaptive control unit 140 issues a demand response instruction, the load control terminal will cut off the controllable load accordingly, reduce the power demand, and cooperate with the system's peak-shaving and valley-filling strategy. In this embodiment, the dispatching control instruction responded by the execution unit 150 directly acts on the energy equipment to optimize its operating state, thereby achieving overall optimization of the energy system.

[0086] The embodiments of the present invention can dynamically adapt to changes in the energy system through adaptive prediction models and optimization algorithms, and improve the flexibility and robustness of energy management; the embodiments of the present invention adopt a multi-objective optimization model to ensure power supply reliability while taking into account energy efficiency, economy and environmental protection to achieve coordinated optimization of the energy system; the embodiments of the present invention introduce a self-learning mechanism, so that the system can continuously improve prediction and optimization performance based on historical experience and immediate feedback, and has a certain intelligent evolution capability; the embodiments of the present invention ensure the accurate execution of the scheduling plan through closed-loop control, and improve the real-time optimization level of the entire energy system. The optimization control system provided by the embodiments of the present invention can perform complete closed-loop control of data collection, prediction, optimization, control and execution of the energy system throughout its life cycle, as well as the intelligent feature of adaptive adjustment in a dynamic environment, providing a new solution for achieving efficient and optimized operation of the energy system.

[0087] In some embodiments, the optimization engine unit 130 is also used to: split the constructed multi-objective optimization model into multiple sub-problems, each sub-problem corresponding to a local optimization model of a subsystem; multiple subsystems solve the local optimization models in parallel to obtain local optimization results; and iteratively exchange boundary information between subsystems and gradually reach global consensus using a distributed optimization algorithm.

[0088] In this embodiment, since the traditional centralized optimization control may encounter problems such as heavy computational burden, high communication pressure, and poor robustness when facing large-scale complex energy systems, this embodiment adopts a distributed collaborative optimization method to divide the entire energy system into several subsystems, and each subsystem is equipped with a local optimization control unit. The subsystems coordinate and exchange information through the communication network, and optimize the local energy scheduling on the premise of satisfying the global constraints, and finally achieve the global optimum. Specifically, in the optimization engine unit 130, the centralized optimization model is divided into multiple sub-problems, each sub-problem corresponds to a local optimization model of a subsystem, and the optimization engine of each subsystem solves the local optimization sub-problem in parallel to obtain the local optimal solution; the subsystems exchange boundary information through iterative exchange, and use the distributed optimization algorithm (such as the Alternating Direction Method of Multipliers, ADMM for short) to gradually reach global consensus. At the same time, each subsystem formulates a local control strategy based on the local optimization results; at the same time, the subsystems exchange state information and control decisions through iterative exchange, and use the distributed game mechanism (such as Nash equilibrium) to achieve global coordination.

[0089] At the same time, the adaptive control unit 140 is also used to coordinate the optimization and control behavior of the subsystems through distributed collaborative control strategies; wherein the subsystems generate local control strategies based on local optimization results; the subsystems iteratively exchange state information and local control decisions, and use distributed game mechanisms to achieve global collaboration.

[0090] The distributed architecture of this embodiment can reduce the computing and communication pressure of the central node and improve the scalability and fault tolerance of the system. At the same time, the game theory method is introduced to regard each subsystem as a game participant. By designing a reasonable incentive mechanism, the subsystem is guided to maximize its own interests while taking into account the overall interests, so as to achieve system coordination under distributed optimization.

[0091] In some embodiments, the optimization engine unit 130 is also used to: construct a quantum Hamiltonian model and a quantum circuit, solve a multi-objective optimization model through a quantum algorithm, compare and fuse the calculation results of the multi-objective optimization model solved by the quantum algorithm with the calculation results of the multi-objective optimization model solved by a heuristic intelligent algorithm, and obtain a final optimization scheduling strategy.

[0092] Since the optimization scheduling problem of the energy management system is essentially a large-scale combinatorial optimization problem, when the optimization scale is large, the traditional optimization algorithm may be difficult to search for the optimal solution within a limited time. Quantum computing is an emerging computing paradigm that shows advantages over classical computing on certain issues by utilizing characteristics such as quantum superposition and entanglement. Therefore, the optimization engine optimization unit 130 in this embodiment includes a quantum computing subunit, which includes a quantum processor, a quantum compiler, a quantum algorithm library, etc. The traditional optimization model and algorithm are reconstructed and implemented in the quantum computing unit to introduce quantum computing technology into the field of energy optimization, and quantum heuristic algorithms such as quantum annealing and quantum approximate optimization algorithm (Quantum Approximate Optimization Algorithm, QAOA) are used to accelerate the solution of the combinatorial optimization problem of energy scheduling. By mapping the problem to the Hamiltonian model of quantum bits, constructing quantum circuits, and evolving and measuring on quantum processors, the solution space can be efficiently explored, the optimal or approximately optimal solution can be quickly locked, and the performance bottleneck of the classical optimization algorithm can be broken through.

[0093] The embodiment of the present invention transforms the energy scheduling problem into a quantum optimization problem, constructs a quantum Hamiltonian model and a quantum circuit. The quantum processor executes quantum algorithms, such as quantum annealing, QAOA (Quantum Approximate Optimization Algorithm, quantum optimization algorithm), etc., to solve the optimization problem, and compares and integrates the results of quantum calculation with the results of classical optimization to obtain the final optimization scheduling strategy.

[0094] Specifically, in this embodiment, quantum computing technology is introduced into the optimization engine unit 130, by constructing a quantum Hamiltonian model and a quantum circuit, using a quantum algorithm to solve a multi-objective optimization model, and comparing and integrating the quantum computing results with the classical optimization results to obtain a better energy scheduling strategy. The specific working process is as follows:

[0095] Step 1. Problem mapping: Convert the energy scheduling problem into a quantum optimization problem, define decision variables (such as the output of each energy device) and objective functions (such as energy efficiency, operating costs, etc.). Map the decision variables to quantum bits through binary or other encoding methods.

[0096] Step 2. Construct Hamiltonian model: Construct the corresponding quantum Hamiltonian model according to the objective function and constraints of the optimization problem. Hamiltonian consists of the objective function and constraints of the problem, usually including quadratic terms (representing the objective function) and linear terms (representing the constraints).

[0097] Step 3. Design quantum circuit: Design the corresponding quantum circuit according to the Hamiltonian model. The quantum circuit consists of a series of quantum gates used to evolve and operate quantum states. Quantum gates include Hadamard gates, CNOT gates, rotation gates, etc.

[0098] Step 4. Execute quantum algorithm: Run the designed quantum circuit on the quantum processor and execute the quantum algorithm for optimization and solution. Quantum optimization algorithms include:

[0099] Quantum annealing algorithm: By simulating the annealing process of the quantum system, the influence of quantum fluctuations is gradually reduced, the system converges to the ground state, and the optimal solution or approximate optimal solution to the optimization problem is obtained.

[0100] QAOA algorithm: By alternately applying the problem Hamiltonian and the mixed Hamiltonian, a variational quantum circuit is constructed, and the optimal solution of the optimization problem is approached by optimizing the circuit parameters.

[0101] Step 5. Measure and read the results: Measure the output of the quantum circuit, repeat the experiment multiple times, count the frequencies of occurrence of different solutions, and select the solution with the highest frequency as the solution to the optimization problem.

[0102] Step 6. Compare and merge the results: Compare the results of the quantum algorithm with the results of the classical heuristic algorithm (such as genetic algorithm, particle swarm algorithm, etc.) to analyze the advantages and disadvantages of the two methods. By designing a suitable fusion strategy (such as weighted average, solution space mapping, etc.), the quantum calculation results and the classical optimization results are merged to obtain the final optimization scheduling strategy.

[0103] Step 7. Generate a scheduling strategy: Decode the fused optimization results into output scheduling curves of each energy device to form an executable energy scheduling strategy.

[0104] For example: Assume that a microgrid system has multiple energy devices such as photovoltaics, wind power, and energy storage. The goal is to minimize the operating cost while meeting the load demand. First, map the decision variables (the output of each device) to quantum bits, build a Hamiltonian model, and design the corresponding quantum circuit. Then, execute the QAOA algorithm on the quantum processor to obtain a set of optimized solutions. At the same time, use the genetic algorithm to solve the same problem and obtain another set of solutions. Comparing the results of the two algorithms, it is found that the solution obtained by the QAOA algorithm is of higher quality, but the genetic algorithm is faster. Finally, a weighted fusion strategy is designed to combine the advantages of the two algorithms to obtain the final optimal scheduling strategy, that is, photovoltaics and wind power are mainly used for power supply during the day, and energy storage is used for power supply at night. At the same time, the start-stop constraints of the equipment and load balance and other conditions are considered to ultimately minimize the operating cost.

[0105] By introducing quantum computing technology, the optimization engine unit 130 can solve complex energy optimization problems more efficiently and accurately, and provide better scheduling decision-making solutions for the intelligent energy management system.

[0106] In some embodiments, the system also includes a human-computer interaction interface for inputting domain knowledge, empirical rules or optimization preferences to form an expert knowledge base; the optimization engine optimization unit 130 is also used to: use the expert knowledge base to build and solve multi-objective optimization models, generate knowledge-driven energy scheduling strategies, and present the knowledge-driven energy scheduling strategies to expert users through the human-computer interaction interface.

[0107] Specifically, in this embodiment, the optimization engine optimization unit 130 also includes a human-machine collaborative optimization subunit, which includes an expert knowledge base, user preference learning, a human-machine interactive optimization algorithm, etc. The expert user inputs domain knowledge, empirical rules, optimization preferences, etc. through the human-machine interactive interface to form an expert knowledge base. The optimization engine optimization unit 130 uses expert knowledge to guide the modeling and solving of optimization problems, embeds expert knowledge into the optimization algorithm, and generates knowledge-driven optimization results. The optimization results are presented to expert users through the human-machine interactive interface and evaluated and adjusted by experts. After multiple rounds of iterations, the optimal scheduling solution that integrates expert wisdom and mathematical optimization is obtained.

[0108] Since the optimal decision of energy scheduling depends not only on the objective system state and mathematical model, but also on people's subjective judgment and experience knowledge, in order to better play the advantages of people's professional knowledge and intelligent algorithms, this embodiment draws on the theory of cognitive science and human-computer interaction to design a framework for human-computer collaborative optimization. Expert users input high-level information such as prior knowledge of the energy system and scheduling preferences through a visual interactive interface to guide the modeling and solution of the optimization algorithm. When searching the solution space, the optimization algorithm uses expert knowledge as heuristic information to guide the search direction and improve the optimization efficiency. The optimization results are then fed back to the expert users, who evaluate and correct them based on their experience and intuition, and continuously iterate to finally obtain a scheduling plan that takes into account both expert experience and mathematical optimization. This embodiment integrates human cognitive intelligence and machine computational intelligence through human-computer collaboration, and can obtain more comprehensive, explainable, and practical optimization decisions.

[0109] In some embodiments, the data acquisition unit 110 is also used to build an energy blockchain network, where energy devices and users access the energy blockchain network through blockchain nodes, upload energy data and transaction request information to the blockchain, and after verification by the consensus mechanism, store it on the chain in the form of blocks; the adaptive control unit 140 is also used to propagate control instructions in the energy blockchain network in the form of transactions, which are automatically verified and executed by smart contracts.

[0110] Specifically, blockchain nodes are introduced into the data acquisition unit 110 and its communication network to build an energy blockchain network. Various energy devices and users access the energy blockchain network through blockchain nodes, upload energy data, transaction requests and other information to the blockchain, and store them on the chain in the form of blocks after verification by the consensus mechanism, ensuring that the data cannot be tampered with and is traceable. At the same time, the control instructions generated by the adaptive control unit 140 are propagated in the blockchain network in the form of transactions, and are automatically verified and executed by smart contracts to ensure the security and reliability of the control process. Based on the trust foundation of the blockchain, each node realizes distributed data sharing and collaborative control.

[0111] The consensus mechanism is a method for each node in the blockchain network to reach a consensus on transaction information, which is used to ensure the authenticity, consistency and immutability of the data on the chain. Consensus mechanisms include Proof of Work (PoW), Proof of Stake (PoS), Delegated Byzantine Fault Tolerance (dBFT), etc. In the energy blockchain network, the consensus mechanism is mainly used to verify the legitimacy of information such as energy data and transaction requests, and to package the verified information into blocks and append them to the chain.

[0112] Taking the PoW consensus mechanism as an example, the specific verification process is as follows:

[0113] Step 1. Energy devices or users broadcast energy data (such as power generation, power consumption, etc.) or transaction requests (such as power trading, carbon emission rights trading, etc.) in the form of transactions to the entire network through blockchain nodes.

[0114] Step 2. After receiving the transaction information, the miner node in the network verifies it, such as verifying whether the transaction format, signature, timestamp, etc. are legal, whether the transaction amount matches, etc.

[0115] Step 3. The verified transactions are packaged into the candidate block, and miners start to solve problems to compete for the right to record the block. The problem is a mathematical problem, such as performing a double SHA256 hash operation on the block header information to find a random number (Nonce) that is less than the difficulty target value.

[0116] Step 4. The miner who solves the problem first broadcasts the packaged block to the network and claims that he owns the accounting rights of the block.

[0117] Step 5. After receiving the block, other nodes verify it, including verifying the block structure, transaction legitimacy, timestamp, difficulty, etc., and check whether the miner's problem-solving results are correct.

[0118] Step 6. If more than 51% of the nodes reach a consensus that the block is legal and valid, it will be appended to the local copy of the blockchain; otherwise, the block will be discarded and the accounting right will be open to competition again.

[0119] Step 7. All nodes start the next round of mining competition based on the new block, repeating the process over and over again to build a secure and reliable chain data structure.

[0120] For example: A wind farm generates 100 pieces of power generation data every day, and publishes these data in the form of transactions to the energy blockchain network through the connected blockchain nodes. After receiving these transactions, miner node A verifies them, packages them into candidate blocks, and starts solving problems to compete for the right to record accounts. Assuming that node A solves the problem first, it broadcasts the packaged block to the entire network. Other nodes verify the block and find that the block structure is complete, the transaction is legal, the timestamp is accurate, the difficulty meets the requirements, and node A has indeed solved the correct random number, so they reach a consensus and append the block to the local blockchain. In this way, the power generation data of the wind farm is securely and reliably stored in the energy blockchain through the PoW consensus mechanism, which is convenient for subsequent energy transactions, settlements, analysis and other applications.

[0121] Since there are a large number of energy transactions and information interactions between various energy devices, users, and operators in a diversified energy Internet environment, this embodiment provides a secure and reliable data infrastructure for distributed energy management systems through blockchain technology. By building a consortium chain or a private chain, energy data, transaction records, etc. are stored on the chain, and the authenticity and credibility of the data are ensured by utilizing the characteristics of blockchain such as immutability and traceability. Smart contracts can automatically execute energy transactions and scheduling according to rules, simplify processes, and improve efficiency. The embodiments of the present invention combine blockchain technology with energy Internet of Things, edge computing and other technologies to achieve secure, efficient, and autonomous energy data management and application, and provide a reliable digital foundation for distributed energy optimization control.

[0122] The embodiments of the present invention expand the design ideas of intelligent energy management systems from different angles through cross-domain integration methods, introduce cutting-edge technologies such as distributed collaborative optimization, quantum computing, human-machine collaboration, blockchain, etc., and deeply integrate them with the energy field, breaking through the limitations of traditional energy management and providing a new solution for the intelligence, informatization, and trustworthiness of energy systems.

[0123] The embodiments of the present invention introduce the above innovative solutions into different links, units and steps of the intelligent energy management system, thereby improving the intelligence level and practical value of the system from multiple dimensions such as optimized architecture, computing paradigm, human-computer collaboration, and data credibility, and providing more advanced and reliable technical support for the efficient and optimized operation of the energy system.

[0124] Embodiment 2

[0125] Figure 2 is a flow chart of an adaptive algorithm optimization control method for intelligent energy management according to an embodiment of the present invention. Figure 2 As shown, the method comprises the following steps:

[0126] Step S11, collecting operation data of various energy devices in real time.

[0127] Specifically, in this embodiment, the operating data of each energy device is continuously collected. For example, at a certain moment, the wind speed sensor measures the average wind speed of the wind farm to be 8m / s, the illuminance sensor measures the illuminance of the photovoltaic power station to be 800W / m2, the smart meter on the user side collects the total load to be 500kW, and the monitoring system of the energy storage device shows that the current energy storage capacity is 200kWh and the charging power is 50kW. These real-time data are transmitted to the data center through the communication network to provide input for subsequent prediction and optimization.

[0128] Step S12, based on a machine learning algorithm, using historical data and real-time collected operating data, predicts the renewable energy output and load demand within a preset time to obtain a prediction result.

[0129] In this embodiment, the model prediction unit 120 uses the real-time data collected in step S11, combined with external information such as historical data and weather forecast, to predict the wind power and photovoltaic power generation output and load demand in the next 24 hours. For example, based on the current wind speed and historical data, the average output of the wind farm in the next 24 hours is predicted to be 300kW; based on the current light intensity and weather forecast, the average output of the photovoltaic power station in the next 24 hours is predicted to be 400kW; based on the historical data and characteristic analysis of the user-side load, the load demand curve in the next 24 hours is predicted to be 800kW for the peak load and 300kW for the valley load.

[0130] Step S13, constructing a multi-objective optimization model based on the prediction results and operation data, and using a heuristic intelligent algorithm to solve the multi-objective optimization model to generate an optimal energy scheduling strategy.

[0131] In this embodiment, the optimization engine unit 130 receives the prediction data generated by the prediction model, and constructs a multi-objective optimization model by considering the real-time status of the energy equipment (such as the amount of energy storage) and the operating constraints (such as the charging and discharging power limit of the energy storage, the backup capacity requirement, etc.). For example, the optimization objectives are to minimize the cost of power generation and maximize the utilization rate of renewable energy, and the output power of wind power, photovoltaics, energy storage, and diesel generators are used as decision variables, and the power balance, energy storage charging and discharging limit, etc. are used as constraints to generate a mathematical model of the optimization problem. Then, the optimization engine unit 130 uses an adaptive intelligent algorithm to solve the model and obtain the optimal output curve of each power source in the next 24 hours.

[0132] Step S14, parsing the optimal energy scheduling strategy into control instructions executable by each energy device, and sending them to the execution unit, while monitoring the execution status and system response of the energy device.

[0133] The adaptive control unit 140 converts the output curve generated by the optimization engine unit 130 into a specific control instruction and sends it to the actuators of each energy device. For example, the optimized output curve at the current moment shows that the wind turbine should operate at a power of 250kW, the photovoltaic inverter should operate at a power of 380kW, the energy storage should be charged at a power of 30kW, and the diesel generator should operate at a power of 100kW. The control unit converts these power instructions into corresponding control quantities, such as wind turbine pitch angle, inverter MPPT parameters, charging current of energy storage converter, etc., and sends them to each actuator through the communication network. At the same time, the control unit monitors the operating status of each device in real time. If it is found that the actual operation deviates from the optimized output curve (for example, the actual output of wind power is only 200kW), it will adaptively adjust the control instructions at the next moment (such as increasing the discharge power of energy storage or the output of diesel engine) to compensate for the power gap and maintain system balance.

[0134] Step S15, adjusting the respective operating states according to the control instructions to collaboratively achieve optimal scheduling of the entire system.

[0135] After receiving the control instructions from the adaptive control unit 140, each actuator adjusts its own operating parameters accordingly. For example, the wind turbine adjusts the blade angle according to the pitch angle instruction to make the generator output power reach 250kW; the photovoltaic inverter adjusts the voltage and current according to the MPPT parameters to make the output power reach 380kW; the energy storage converter controls the battery pack charging according to the charging current instruction, with a power of 30kW; the diesel generator adjusts the generator speed and excitation current according to the power instruction, with an output power of 100kW. Under the coordinated action of the actuators, the entire energy system operates according to the optimized scheduling curve, achieving optimal control under multiple objectives.

[0136] In addition, each actuator feeds back its actual operating status and key parameters to the adaptive control unit 140 in real time. The adaptive control unit 140 summarizes the status information of each device, determines the actual operating effect of the entire system, and calculates the deviation from the optimization target. For example, if it is found that the actual operating power generation cost is higher than the optimization target, or the renewable energy utilization rate is lower than expected, the control unit will feed back these deviation information to the optimization engine. The optimization engine adaptively adjusts the parameters or constraints of the optimization model accordingly, such as increasing the priority scheduling coefficient of renewable energy, and generating a better scheduling curve in the next scheduling cycle. At the same time, the actual operation data is also recorded and used to optimize the prediction model and algorithm to improve the accuracy of the next prediction and optimization.

[0137] The embodiment of the present invention forms a closed-loop control process of data collection, prediction, optimization, control, execution, and feedback by cyclically executing the above steps S11 to S15. Through adaptive prediction, optimization and control, and continuous improvement through real-time feedback, the intelligent energy management system can realize dynamic optimization and scheduling of energy in a complex and changing environment, maximize energy utilization efficiency and system economy, and take into account environmental protection and reliability requirements.

[0138] In some embodiments, the method further includes: splitting the constructed multi-objective optimization model into multiple sub-problems, each sub-problem corresponding to a local optimization model of a subsystem; multiple subsystems solve the local optimization model in parallel to obtain local optimization results; the subsystems iteratively exchange boundary information and gradually reach global consensus using a distributed optimization algorithm; or, the method further includes: coordinating the optimization and control behaviors of the subsystems through a distributed collaborative control strategy; wherein the subsystems generate local control strategies based on local optimization results; the subsystems iteratively exchange state information and local control decisions and achieve global coordination using a distributed game mechanism; or, the method further includes: constructing a quantum Hamiltonian model and a quantum circuit, solving the multi-objective optimization model through a quantum algorithm, comparing and integrating the calculation results of the multi-objective optimization model solved by the quantum algorithm with the calculation results of the multi-objective optimization model solved by a heuristic intelligent algorithm, and obtaining a final optimization scheduling strategy.

[0139] In this embodiment, since the traditional centralized optimization control may encounter problems such as heavy computational burden, high communication pressure, and poor robustness when facing large-scale complex energy systems, this embodiment adopts a distributed collaborative optimization method to divide the entire energy system into several subsystems, and each subsystem is equipped with a local optimization control unit. The subsystems coordinate and exchange information through the communication network, and optimize the local energy scheduling on the premise of satisfying the global constraints, and finally achieve the global optimum. Specifically, in the optimization engine unit 130, the centralized optimization model is divided into multiple sub-problems, each sub-problem corresponds to a local optimization model of a subsystem, and the optimization engine of each subsystem solves the local optimization sub-problem in parallel to obtain the local optimal solution; the subsystems exchange boundary information through iterative exchange, and use the distributed optimization algorithm (such as the Alternating Direction Method of Multipliers, ADMM for short) to gradually reach global consensus. At the same time, each subsystem formulates a local control strategy based on the local optimization results; at the same time, the subsystems exchange state information and control decisions through iterative exchange, and use the distributed game mechanism (such as Nash equilibrium) to achieve global coordination.

[0140] At the same time, the adaptive control unit 140 is also used to coordinate the optimization and control behavior of the subsystems through distributed collaborative control strategies; wherein the subsystems generate local control strategies based on local optimization results; the subsystems iteratively exchange state information and local control decisions, and use distributed game mechanisms to achieve global collaboration.

[0141] The distributed architecture of this embodiment can reduce the computing and communication pressure of the central node and improve the scalability and fault tolerance of the system. At the same time, the game theory method is introduced to regard each subsystem as a game participant. By designing a reasonable incentive mechanism, the subsystem is guided to maximize its own interests while taking into account the overall interests, so as to achieve system coordination under distributed optimization.

[0142] Since the optimization scheduling problem of the energy management system is essentially a large-scale combinatorial optimization problem, when the optimization scale is large, the traditional optimization algorithm may be difficult to search for the optimal solution within a limited time. Quantum computing is an emerging computing paradigm that shows advantages over classical computing on certain issues by utilizing characteristics such as quantum superposition and entanglement. Therefore, the optimization engine optimization unit 130 in this embodiment includes a quantum computing subunit, which includes a quantum processor, a quantum compiler, a quantum algorithm library, etc. The traditional optimization model and algorithm are reconstructed and implemented in the quantum computing unit to introduce quantum computing technology into the field of energy optimization, and quantum heuristic algorithms such as quantum annealing and quantum approximate optimization algorithm (QAOA) are used to accelerate the solution of the combinatorial optimization problem of energy scheduling. By mapping the problem to the Hamiltonian model of quantum bits, constructing quantum circuits, and evolving and measuring on quantum processors, the solution space can be efficiently explored, the optimal or approximately optimal solution can be quickly locked, and the performance bottleneck of the classical optimization algorithm can be broken through.

[0143] The embodiment of the present invention transforms the energy scheduling problem into a quantum optimization problem, constructs a quantum Hamiltonian model and a quantum circuit. The quantum processor executes quantum algorithms, such as quantum annealing, QAOA (Quantum Approximate Optimization Algorithm, quantum optimization algorithm), etc., to solve the optimization problem, and compares and integrates the results of quantum calculation with the results of classical optimization to obtain the final optimization scheduling strategy.

[0144] In some embodiments, the method further includes: inputting domain knowledge, empirical rules or optimization preferences through a human-computer interaction interface to form an expert knowledge base; using the expert knowledge base to construct and solve a multi-objective optimization model, generating a knowledge-driven energy scheduling strategy, and presenting the knowledge-driven energy scheduling strategy to an expert user through the human-computer interaction interface.

[0145] Specifically, in this embodiment, the optimization engine optimization unit 130 also includes a human-machine collaborative optimization subunit, which includes an expert knowledge base, user preference learning, a human-machine interactive optimization algorithm, etc. The expert user inputs domain knowledge, empirical rules, optimization preferences, etc. through the human-machine interactive interface to form an expert knowledge base. The optimization engine optimization unit 130 uses expert knowledge to guide the modeling and solving of optimization problems, embeds expert knowledge into the optimization algorithm, and generates knowledge-driven optimization results. The optimization results are presented to expert users through the human-machine interactive interface and evaluated and adjusted by experts. After multiple rounds of iterations, the optimal scheduling solution that integrates expert wisdom and mathematical optimization is obtained.

[0146] Since the optimal decision of energy scheduling depends not only on the objective system state and mathematical model, but also on people's subjective judgment and experience knowledge, in order to better play the advantages of people's professional knowledge and intelligent algorithms, this embodiment draws on the theory of cognitive science and human-computer interaction to design a framework for human-computer collaborative optimization. Expert users input high-level information such as prior knowledge of the energy system and scheduling preferences through a visual interactive interface to guide the modeling and solution of the optimization algorithm. When searching the solution space, the optimization algorithm uses expert knowledge as heuristic information to guide the search direction and improve the optimization efficiency. The optimization results are then fed back to the expert users, who evaluate and correct them based on their experience and intuition, and continuously iterate to finally obtain a scheduling plan that takes into account both expert experience and mathematical optimization. This embodiment integrates human cognitive intelligence and machine computational intelligence through human-computer collaboration, and can obtain more comprehensive, explainable, and practical optimization decisions.

[0147] In some embodiments, the method also includes: building an energy blockchain network, energy devices and users accessing the energy blockchain network through blockchain nodes, uploading energy data and transaction request information to the blockchain, and storing it on the chain in the form of blocks after verification by a consensus mechanism; propagating control instructions in the energy blockchain network in the form of transactions, and automatically verifying and executing them by smart contracts.

[0148] Specifically, blockchain nodes are introduced into the data acquisition unit 110 and its communication network to build an energy blockchain network. Various energy devices and users access the energy blockchain network through blockchain nodes, upload energy data, transaction requests and other information to the blockchain, and store them on the chain in the form of blocks after verification by the consensus mechanism, ensuring that the data cannot be tampered with and is traceable. At the same time, the control instructions generated by the adaptive control unit 140 are propagated in the blockchain network in the form of transactions, and are automatically verified and executed by smart contracts to ensure the security and reliability of the control process. Based on the trust foundation of the blockchain, each node realizes distributed data sharing and collaborative control.

[0149] Since there are a large number of energy transactions and information interactions between various energy devices, users, and operators in a diversified energy Internet environment, this embodiment provides a secure and reliable data infrastructure for distributed energy management systems through blockchain technology. By building a consortium chain or a private chain, energy data, transaction records, etc. are stored on the chain, and the authenticity and credibility of the data are ensured by utilizing the characteristics of blockchain such as immutability and traceability. Smart contracts can automatically execute energy transactions and scheduling according to rules, simplify processes, and improve efficiency. The embodiments of the present invention combine blockchain technology with energy Internet of Things, edge computing and other technologies to achieve secure, efficient, and autonomous energy data management and application, and provide a reliable digital foundation for distributed energy optimization control.

[0150] The embodiments of the present invention expand the design ideas of intelligent energy management systems from different angles through cross-domain integration methods, introduce cutting-edge technologies such as distributed collaborative optimization, quantum computing, human-machine collaboration, blockchain, etc., and deeply integrate them with the energy field, breaking through the limitations of traditional energy management and providing a new solution for the intelligence, informatization, and trustworthiness of energy systems.

[0151] The embodiments of the present invention introduce the above innovative solutions into different links, units and steps of the intelligent energy management system, thereby improving the intelligence level and practical value of the system from multiple dimensions such as optimized architecture, computing paradigm, human-computer collaboration, and data credibility, and providing more advanced and reliable technical support for the efficient and optimized operation of the energy system.

[0152] Embodiment 3

[0153] Reference below Figure 3 , which shows an electronic device suitable for implementing the embodiments of the present disclosure.

[0154] The terminal devices in the embodiments of the present disclosure may include, but are not limited to, mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Flat-panel Displays), PMPs (Portable Multimedia Players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), etc., as well as fixed terminals such as digital TVs, desktop computers, etc. Figure 3 The electronic device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present disclosure.

[0155] like Figure 3 As shown, the electronic device may include a processing device (e.g., a central processing unit, a graphics processor, etc.) 301, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 302 or a program loaded from a storage device 308 to a random access memory (RAM) 303. Various programs and data required for the operation of the electronic device are also stored in RAM 303. The processing device 301, ROM 302, and RAM 303 are connected to each other via a bus 304. An input / output (I / O) interface 305 is also connected to the bus 304.

[0156] Typically, the following devices may be connected to the I / O interface 305: input devices 306 including, for example, a touch screen, a touch pad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; output devices 307 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; storage devices 308 including, for example, a magnetic tape, a hard disk, etc.; and communication devices 309. The communication devices 309 may allow the electronic device to communicate with other devices wirelessly or by wire to exchange data. Although Figure 3 An electronic device having various devices is shown, but it should be understood that it is not required to implement or possess all the devices shown. More or fewer devices may be implemented or possessed instead.

[0157] In particular, according to an embodiment of the present disclosure, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present disclosure includes a computer program product, which includes a computer program carried on a non-transitory computer-readable medium, and the computer program contains program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from the network through the communication device 309, or installed from the storage device 308, or installed from the ROM 302. When the computer program is executed by the processing device 301, the above-mentioned functions defined in the method of the embodiment of the present disclosure are executed.

[0158] It should be noted that the computer-readable medium disclosed above may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present disclosure, a computer-readable storage medium may be any tangible medium containing or storing a program that may be used by or in combination with an instruction execution system, device or device. In the present disclosure, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, in which a computer-readable program code is carried. This propagated data signal may take a variety of forms, including but not limited to an electromagnetic signal, an optical signal, or any suitable combination of the above. The computer readable signal medium may also be any computer readable medium other than a computer readable storage medium, which may send, propagate or transmit a program for use by or in conjunction with an instruction execution system, apparatus or device. The program code contained on the computer readable medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (radio frequency), etc., or any suitable combination of the above.

[0159] In some embodiments, the client and the server may communicate using any currently known or future developed network protocol such as HTTP (HyperText Transfer Protocol), and may be interconnected with any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network ("LAN"), a wide area network ("WAN"), an internet (e.g., the Internet), and a peer-to-peer network (e.g., an adhoc network), as well as any currently known or future developed network.

[0160] The computer-readable medium may be included in the electronic device, or may exist independently without being incorporated into the electronic device.

[0161] The computer-readable medium carries one or more programs. When the one or more programs are executed by the electronic device, the electronic device:

[0162] Real-time collection of operating data of various energy equipment;

[0163] Based on machine learning algorithms, historical data and real-time collected operating data are used to predict renewable energy output and load demand within a preset time to obtain prediction results;

[0164] Construct a multi-objective optimization model based on the prediction results and operation data, and use a heuristic intelligent algorithm to solve the multi-objective optimization model to generate the optimal energy scheduling strategy;

[0165] Analyze the optimal energy dispatch strategy into executable control instructions for each energy device and send them to the execution unit, while monitoring the execution status and system response of the energy device;

[0166] Adjust their respective operating states according to control instructions and collaboratively achieve optimized scheduling of the entire system.

[0167] Computer program code for performing the operations of the present disclosure may be written in one or more programming languages ​​or a combination thereof, including, but not limited to, object-oriented programming languages, such as Java, Smalltalk (an object-oriented programming language), C++, and conventional procedural programming languages, such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., through the Internet using an Internet service provider).

[0168] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present disclosure. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some implementations as replacements, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0169] The units involved in the embodiments described in the present disclosure may be implemented by software or hardware, wherein the name of a unit does not, in some cases, limit the unit itself.

[0170] The functions described above herein may be performed at least in part by one or more hardware logic components. For example, without limitation, exemplary types of hardware logic components that may be used include: field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), and the like.

[0171] In the context of the present disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0172] The above description is only a preferred embodiment of the present disclosure and an explanation of the technical principles used. Those skilled in the art should understand that the scope of disclosure involved in the present disclosure is not limited to the technical solutions formed by a specific combination of the above technical features, but should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the above disclosed concept. For example, the above features are replaced with the technical features with similar functions disclosed in the present disclosure (but not limited to) by each other to form a technical solution.

[0173] In addition, although each operation is described in a specific order, this should not be understood as requiring these operations to be performed in the specific order shown or in a sequential order. Under certain circumstances, multitasking and parallel processing may be advantageous. Similarly, although some specific implementation details are included in the above discussion, these should not be interpreted as limiting the scope of the present disclosure. Some features described in the context of a separate embodiment can also be implemented in a single embodiment in combination. On the contrary, the various features described in the context of a single embodiment can also be implemented in multiple embodiments individually or in any suitable sub-combination mode.

[0174] Although the subject matter has been described in language specific to structural features and / or methodological logical actions, it should be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or actions described above. On the contrary, the specific features and actions described above are merely example forms of implementing the claims.

Claims

1. An adaptive algorithm optimization control system for intelligent energy management, characterized in that: The system comprises: Data acquisition unit, used to collect operating data of various energy equipment in real time; A model prediction unit is used to predict the output and load demand of renewable energy within a preset time by using historical data and real-time collected operation data based on a machine learning algorithm to obtain a prediction result; An optimization engine unit, configured to construct a multi-objective optimization model according to the prediction results and the operation data, and solve the multi-objective optimization model using a heuristic intelligent algorithm to generate an optimal energy scheduling strategy; An adaptive control unit, used to parse the optimal energy scheduling strategy into control instructions executable by each energy device, and send them to the execution unit, while monitoring the execution status and system response of the energy device; The execution units are used to adjust their respective operating states according to the control instructions and collaboratively achieve optimal scheduling of the entire system.

2. The system according to claim 1, characterized in that The optimization engine unit is also used for: The constructed multi-objective optimization model is divided into multiple sub-problems, each of which corresponds to a local optimization model of a subsystem; The multiple subsystems solve the local optimization model in parallel to obtain local optimization results; the subsystems iteratively exchange boundary information and gradually reach global consensus using a distributed optimization algorithm.

3. The system according to claim 2, characterized in that The adaptive control unit is also used for: The optimization and control behaviors of the subsystems are coordinated through a distributed collaborative control strategy; wherein, The subsystem generates a local control strategy based on the local optimization result; The subsystems iteratively exchange status information and the local control decisions, and use a distributed game mechanism to achieve global coordination.

4. The system according to claim 3, characterized in that The optimization engine unit is also used for: A quantum Hamiltonian model and a quantum circuit are constructed, the multi-objective optimization model is solved by a quantum algorithm, the calculation results of the multi-objective optimization model solved by the quantum algorithm are compared and integrated with the calculation results of the multi-objective optimization model solved by a heuristic intelligent algorithm, and a final optimization scheduling strategy is obtained.

5. The system according to claim 1, characterized in that The system also includes a human-computer interaction interface for inputting domain knowledge, empirical rules or optimization preferences to form an expert knowledge base; The optimization engine unit is also used to: construct and solve the multi-objective optimization model using the expert knowledge base, generate a knowledge-driven energy scheduling strategy, and present the knowledge-driven energy scheduling strategy to an expert user through a human-computer interaction interface.

6. The system according to claim 1, characterized in that The data acquisition unit is also used to build an energy blockchain network. The energy equipment and users access the energy blockchain network through blockchain nodes, upload energy data and transaction request information to the blockchain, and after verification by the consensus mechanism, store it on the chain in the form of blocks; The adaptive control unit is also used to: propagate the control instructions in the energy blockchain network in the form of transactions, and automatically verify and execute them by smart contracts.

7. An adaptive algorithm optimization control method for intelligent energy management, characterized in that: The method comprises: Real-time collection of operating data of various energy equipment; Based on machine learning algorithms, historical data and real-time collected operating data are used to predict renewable energy output and load demand within a preset time to obtain prediction results; Constructing a multi-objective optimization model according to the prediction results and the operation data, and solving the multi-objective optimization model using a heuristic intelligent algorithm to generate an optimal energy scheduling strategy; Parsing the optimal energy dispatch strategy into executable control instructions for each energy device, and sending them to the execution unit, while monitoring the execution status and system response of the energy device; The respective operating states are adjusted according to the control instructions to collaboratively achieve optimal scheduling of the entire system.

8. The method according to claim 7, characterized in that The method further comprises: The constructed multi-objective optimization model is divided into multiple sub-problems, each sub-problem corresponds to a local optimization model of a subsystem; multiple subsystems solve the local optimization models in parallel to obtain local optimization results; the subsystems iteratively exchange boundary information and gradually reach global consensus using a distributed optimization algorithm; The method further includes: coordinating the optimization and control behaviors of the subsystems through a distributed collaborative control strategy; wherein the subsystems generate local control strategies based on local optimization results; the subsystems iteratively exchange state information and the local control decisions, and use a distributed game mechanism to achieve global coordination; The method further comprises: A quantum Hamiltonian model and a quantum circuit are constructed, the multi-objective optimization model is solved by a quantum algorithm, the calculation results of the multi-objective optimization model solved by the quantum algorithm are compared and integrated with the calculation results of the multi-objective optimization model solved by a heuristic intelligent algorithm, and a final optimization scheduling strategy is obtained.

9. The method according to claim 7, characterized in that: The method further comprises: Input domain knowledge, empirical rules or optimization preferences through the human-computer interaction interface to form an expert knowledge base; The multi-objective optimization model is constructed and solved using the expert knowledge base to generate a knowledge-driven energy scheduling strategy, and the knowledge-driven energy scheduling strategy is presented to an expert user through a human-computer interaction interface.

10. The method according to claim 7, characterized in that The method further includes: constructing an energy blockchain network, wherein the energy equipment and the user access the energy blockchain network through a blockchain node, uploading energy data and transaction request information to the blockchain, and storing the energy data and transaction request information on the blockchain in the form of blocks after verification by a consensus mechanism; The control instructions are propagated in the energy blockchain network in the form of transactions and automatically verified and executed by smart contracts.

Images