Energy internet integrated management method and system based on distributed pumping and storage

Abstract

The invention provides an energy internet integrated management method and system based on distributed pumping and storage, and the method comprises the steps: obtaining the real-time electric quantity data of each node through a block chain network; wherein the nodes comprise a pumped storage node and a scheduling control node; determining a power demand prediction result according to the real-time electric quantity data and the prediction model; secondly, optimizing a power demand prediction result by taking maximum energy saving and minimum energy loss of each node as targets to obtain an optimal charging and discharging strategy of each node; and finally, according to the optimal charging and discharging strategy of each node, performing multi-node collaborative scheduling optimization by predicting the power demand of each node and considering the energy saving and energy loss between the nodes, thereby dynamically adjusting the charging and discharging operation of each node in real time.

Description

Technical Field

[0001] The present invention belongs to the technical field of energy management, and in particular relates to an energy internet integrated management method and system based on distributed pumped storage. Background Art

[0002] Distributed energy systems are gradually becoming an important direction for energy development due to their flexibility, reliability and efficiency. Pumped storage technology, as a mature energy storage method, has become an important part of distributed energy systems with its large-scale energy storage capacity and high energy conversion efficiency. The concept of energy Internet is to achieve intelligent management of the entire process of energy production, transmission, distribution and consumption by deeply integrating information technology with energy technology, and to build an open, interactive and efficient energy ecosystem.

[0003] In recent years, significant achievements have been made in the field of control and dispatch optimization of distributed pumped storage systems. Existing research has mainly focused on the development of dispatch strategies based on traditional optimization algorithms and intelligent control methods. Using technologies such as linear programming, dynamic programming, and genetic algorithms, researchers have successfully improved the operating efficiency and economy of the system. In addition, by combining the Internet of Things and big data technologies, real-time monitoring and data-driven intelligent dispatching have been achieved, significantly enhancing the response speed and adaptability of the system.

[0004] However, these studies still have some shortcomings when facing the complex and changing energy Internet environment. First, the centralized control method makes the system vulnerable to single point failures and network attacks, making it difficult to ensure the reliability and security of the system. Second, the lack of transparency in data sharing and communication can easily lead to trust crises and data tampering. Finally, traditional algorithms have high computational complexity when dealing with large-scale distributed energy systems, making it difficult to achieve real-time optimization and scheduling. Summary of the invention

[0005] In view of this, the present invention provides an integrated management method and system for energy Internet based on distributed pumped storage, aiming to solve the problem of high computational complexity and difficulty in achieving real-time optimization and scheduling when dealing with large-scale distributed energy systems in the prior art.

[0006] A first aspect of an embodiment of the present invention provides an integrated management method for energy internet based on distributed pumped storage, comprising:

[0007] Through the blockchain network, real-time power data of each node is obtained; the nodes include pumped storage nodes and dispatch control nodes;

[0008] Determine the power demand forecast results based on real-time power data and forecast models;

[0009] With the goal of maximizing energy savings and minimizing energy loss at each node, the power demand forecast results are optimized to obtain the optimal charging and discharging strategy for each node;

[0010] According to the optimal charging and discharging strategy of each node, scheduling instructions are issued to each node through smart contracts to control the charging and discharging operations of each node.

[0011] In one possible implementation, the objective function used in the optimization process is:

[0012]

[0013] Among them, F3(i) is the function value of the objective function, N is the total number of nodes, is the energy storage capacity of the ith node, is the energy usage of the ith node, is the operation loss of the ith node, is the conversion loss of the i-th node, and λ is the preset weight coefficient used to balance energy saving and energy loss.

[0014] In a possible implementation, the power demand forecast result is determined based on the real-time power data and the forecast model, including:

[0015] Convert the real-time power data of each node into input tensors according to the preset time step and feature dimension;

[0016] The input tensor is fed into the prediction model to determine the power demand forecast results for each node.

[0017] In one possible implementation, the power demand forecast results are optimized with the goal of maximizing energy savings and minimizing energy loss at each node to obtain the optimal charging and discharging strategy for each node, including:

[0018] With the goal of maximizing energy saving and minimizing energy loss at each node, the particle swarm algorithm is used to optimize the power demand forecast results to obtain the optimal charging and discharging strategy for each node.

[0019] A second aspect of an embodiment of the present invention provides an integrated energy internet management system based on distributed pumped storage, characterized in that it includes: a smart contract architecture, a network topology module, and a multi-node collaborative scheduling architecture;

[0020] The smart contract architecture is used to obtain the real-time power data of each node in the network topology module through the blockchain network, and send it to the multi-node collaborative scheduling architecture; the nodes include pumped storage nodes and scheduling control nodes;

[0021] The multi-node collaborative scheduling architecture is used to determine the power demand forecast results based on real-time power data and forecast models;

[0022] The multi-node collaborative scheduling architecture is also used to optimize the power demand forecast results with the goal of maximizing energy savings and minimizing energy loss at each node, obtain the optimal charging and discharging strategy for each node, and report it to the smart contract architecture;

[0023] The smart contract architecture is also used to issue scheduling instructions to each node of the network topology module through smart contracts according to the optimal charging and discharging strategy of each node to control the charging and discharging operations of each node.

[0024] In one possible implementation, the smart contract architecture includes a node registration contract module, a data sharing contract module, and a scheduling instruction contract module;

[0025] The node registration contract module is used to record the registration parameters of each node in the network topology module when it is registered on the smart contract structure; the registration parameters include node ID, node type, public key and registration time;

[0026] The data sharing contract module is used to obtain the real-time power data of each node in the network topology module; the parameters of the real-time power data include data type, data value, timestamp and data source node ID;

[0027] The scheduling instruction contract module is used to issue scheduling instructions to each node of the network topology module through smart contracts according to the optimal charging and discharging strategy of each node; the parameters of the scheduling instruction include the scheduling instruction ID, target node ID, instruction content, execution time and execution duration.

[0028] In one possible implementation, the formula for generating the node address in the node registration contract module is:

[0029] NodeAddress=Hash(a1+b1+c1+d1)

[0030] Among them, a1 is the node ID and is a string that uniquely identifies each node; b1 is the node type used to distinguish nodes with different functions such as pumped storage and dispatching control; c1 is the public key used for node identity authentication; and d1 is the registration time, which records the registration timestamp of the node; the hash function performs a hash operation on the node ID, public key and registration time to generate a unique node address.

[0031] In a possible implementation, the structure of shared data in the data sharing contract module is:

[0032] SharedData = {e1,f1,g1,h1}

[0033] Among them, e1 is the data type used to identify data categories such as power, load or status information; f1 is the data value which is the specific data content; g1 is the timestamp used to record the generation time of the data; and h1 is the data source node ID used to identify the node that generated the data.

[0034] In a possible implementation, the structure of the scheduling instruction of the scheduling instruction contract module is:

[0035] Command = {k1,o1,r1,s1,t1}

[0036] Where: k1 is the scheduling instruction ID and is also a string that uniquely identifies each scheduling instruction; o1 is the target node ID used to identify the node that receives and executes the instruction; r1 is the instruction content used for specific operation instructions, such as charging or discharging; s1 is the scheduled execution timestamp that records the execution time instruction; t1 is the execution duration, which is used for the duration of the instruction.

[0037] In a possible implementation, the formula for setting the connection between nodes in the network topology module is:

[0038] C={(n i ,n j ) i ∈P,n j ∈C,i≠j}

[0039] Where: C is the connection set between nodes; n i is the pumped storage node; n j is the dispatching control node; P is the pumped storage node set; C is the dispatching control node set.

[0040] The distributed pumped storage-based energy internet integrated management method and system provided in the embodiment of the present invention first obtains the real-time electricity data of each node through the blockchain network; wherein the nodes include pumped storage nodes and dispatching control nodes; then, according to the real-time electricity data and the prediction model, the power demand prediction result is determined; then, with the goal of maximizing energy saving and minimizing energy loss of each node, the power demand prediction result is optimized to obtain the optimal charging and discharging strategy of each node; finally, according to the optimal charging and discharging strategy of each node, by predicting the power demand of each node and taking into account the energy saving and energy loss between each node, the coordinated scheduling optimization of multiple nodes is performed, thereby dynamically adjusting the charging and discharging operations of each node in real time. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0042] Figure 1 It is a flow chart of an implementation method of an energy internet integrated management method based on distributed pumped storage provided by an embodiment of the present invention;

[0043] Figure 2 It is a structural diagram of an energy internet integrated management system based on distributed pumped storage provided by an embodiment of the present invention;

[0044] Figure 3 It is a diagram of the smart contract architecture;

[0045] Figure 4 It is a schematic diagram of a hybrid topology;

[0046] Figure 5 It is a schematic diagram of a multi-node collaborative scheduling architecture;

[0047] Figure 6 It is a schematic diagram of the PSO construction process in the multi-node collaborative scheduling architecture;

[0048] Figure 7 It is the average response time diagram under different load conditions and power generation conditions;

[0049] Figure 8 is the average response time diagram under different renewable energy generation conditions;

[0050] Fig. 9 is a schematic diagram comparing energy efficiencies under three different load conditions in an embodiment of the present invention;

[0051] Fig.10 is a schematic diagram comparing total energy losses under three different load conditions in an embodiment of the present invention;

[0052] Fig.11 A schematic diagram comparing peak-to-valley differences under three different load conditions in an embodiment of the present invention. DETAILED DESCRIPTION

[0053] In the following description, specific details such as specific system structures, technologies, etc. are provided for the purpose of illustration rather than limitation, so as to provide a thorough understanding of the embodiments of the present invention. However, it should be clear to those skilled in the art that the present invention may be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to prevent unnecessary details from obstructing the description of the present invention.

[0054] Figure 1 It is a flow chart for implementing an integrated management method of energy internet based on distributed pumped storage provided in an embodiment of the present invention. Figure 2 Schematic diagram of the structure of the energy internet integrated management device based on distributed pumped storage provided by the embodiment of the present invention. Figure 2 As shown, the energy Internet integrated management system based on distributed pumped storage includes: a smart contract architecture 21, a network topology module 22 and a multi-node collaborative scheduling architecture 23. Figure 1 As shown in the figure, the integrated management method of energy internet based on distributed pumped storage includes:

[0055] S110, obtaining real-time electricity data of each node through the blockchain network; wherein the nodes include pumped storage nodes and dispatching control nodes.

[0056] In an embodiment of the present invention, S110 is completed by a smart contract architecture, which obtains the real-time power data of each node and sends it to a multi-node collaborative scheduling architecture.

[0057] In some embodiments, each node on the network topology module needs to be registered on the blockchain. Figure 3 It is a diagram of the smart contract architecture. Figure 3 As shown in the figure, the smart contract architecture includes a node registration contract module, a data sharing contract module, and a scheduling instruction contract module; the node registration contract module is used to record the registration parameters of each node in the network topology module when registering on the smart contract structure; the registration parameters include node ID, node type, public key, and registration time; the data sharing contract module is used to obtain the real-time power data of each node in the network topology module; the parameters of the real-time power data include data type, data value, timestamp, and data source node ID. The parameters of the scheduling instruction of the scheduling instruction contract module include scheduling instruction ID, target node ID, instruction content, execution time, and execution duration.

[0058] In some embodiments, the formula for generating the node address in the node registration contract module is:

[0059] NodeAddress=Hash(a1+b1+c1+d1) (1)

[0060] Among them, a1 is the node ID and is a string that uniquely identifies each node; b1 is the node type used to distinguish nodes with different functions such as pumped storage and dispatching control; c1 is the public key used for node identity authentication; and d1 is the registration time, which records the registration timestamp of the node; the hash function performs a hash operation on the node ID, public key and registration time to generate a unique node address.

[0061] In some embodiments, the structure of shared data in the data sharing contract module is:

[0062] SharedData={e1,f1,g1,h1} (2)

[0063] Among them, e1 is the data type used to identify data categories such as power, load or status information; f1 is the data value which is the specific data content; g1 is the timestamp used to record the generation time of the data; and h1 is the data source node ID used to identify the node that generated the data.

[0064] Figure 4 This is a schematic diagram of a hybrid topology. Figure 4 As shown, in some embodiments, the network topology module selects a hybrid topology structure, combining the advantages of star and grid topologies to achieve efficient operation and reliable control of the system, and in this network topology, the nodes are divided into pumped storage nodes and dispatching control nodes, which respectively assume different roles and permissions, and in the specific network structure, each pumped storage node is connected to two dispatching control nodes to form a basic star structure; this design ensures that the operating status and power data of each pumped storage node can be quickly transmitted to the dispatching control node, reducing communication delays and improving data transmission efficiency. At the same time, the dispatching control nodes are interconnected through a grid structure to form multiple redundant paths. This greatly enhances the reliability of the system. Even if some dispatching control nodes or connections fail, the system can still transmit data and issue instructions through other paths, thereby ensuring the stable operation of the system.

[0065] In the embodiment of the present invention, there are two types of data flows in the network topology module: one is from the pumped storage node to the dispatching control node, and the other is a bidirectional data flow between the dispatching control nodes; the pumped storage node uploads the real-time power data to the directly connected dispatching control node; the dispatching control nodes share and synchronize data through the grid structure; therefore, it is ensured that all nodes in the system can obtain the latest data information, and issue and execute dispatching instructions when necessary; the formula for data transmission is as follows:

[0066]

[0067] Where: D is the set of data transmission; n iis the i-th pumped storage node; n j The jth scheduling control node; n k The kth scheduling control node; → indicates a unidirectional data flow; Indicates bidirectional data flow.

[0068] S120, determining a power demand forecast result based on the real-time power data and the forecast model.

[0069] In the embodiment of the present invention, S120 is completed by a multi-node collaborative scheduling architecture. Figure 5 It is a schematic diagram of the multi-node collaborative scheduling architecture. Figure 5 As shown, the multi-node collaborative scheduling architecture includes a mathematical model, a prediction model and an optimization algorithm.

[0070] Among them, mathematical model is the basis for the development of scheduling algorithm, which should consider factors such as geographical location, capacity limitation, charging and discharging efficiency and power limitation. Long Short-Term Memory (LSTM) is selected as the prediction model.

[0071] In some embodiments, determining the power demand forecast result based on the real-time power data and the forecast model includes:

[0072] The real-time electricity data of each node is converted into an input tensor according to the preset time step and feature dimension; the input tensor is input into the prediction model to determine the power demand prediction results of each node.

[0073] The specific construction process of LSTM is as follows:

[0074] a. The input layer receives multidimensional time series data; assuming the time step of the input data is T and the feature dimension is F, the shape of the input tensor is (T, F);

[0075] b. The LSTM layer captures the long-term and short-term dependencies in the time series data. A total of two layers of LSTM are designed: the number of neurons in the first layer is 50, and the return_sequences = True parameter is used to output the complete sequence data as input for the second layer of LSTM, and the output shape is (T, 50); the number of neurons in the second layer is also 50, and the hidden state of the last time step is output;

[0076] c. The output layer maps the output of the LSTM layer to the target prediction value through the fully connected layer; assuming that the output is a single value (power demand or power generation prediction value), the number of neurons in the output layer is 1;

[0077] The output layer is defined as:

[0078]

[0079] Where: W h is the weight matrix; b is the bias vector.

[0080] S130, with the goal of maximizing energy savings and minimizing energy loss at each node, optimizing the power demand forecast result to obtain the optimal charging and discharging strategy for each node.

[0081] In an embodiment of the present invention, S130 is completed by a multi-node collaborative scheduling architecture. In some embodiments, the objective function used in the optimization process is:

[0082]

[0083] Among them, F3(i) is the function value of the objective function, N is the total number of nodes, is the energy storage capacity of the ith node, is the energy usage of the ith node, is the operation loss of the ith node, is the conversion loss of the i-th node, and λ is the preset weight coefficient used to balance energy saving and energy loss.

[0084] Figure 6 Schematic diagram of the PSO construction process in the multi-node collaborative scheduling architecture of the present invention. Figure 6 As shown, the optimization algorithm is used to determine the optimal charging and discharging strategy for each node based on the output results of the prediction model;

[0085] The optimization algorithm uses the PSO algorithm to optimize the scheduling strategy. The specific construction process is as follows:

[0086] a. Define the initial position and velocity of the particle swarm;

[0087] b. Each particle represents a possible scheduling strategy, including the charging and discharging decisions of each node at different time steps;

[0088] c. Let the size of the particle group be N, and the position of each particle be x i , the velocity is represented by v, and the initial position and velocity are randomly generated as:

[0089] x i (0) = random(x min ,x max ) (6)

[0090] v i (0) = random(v min ,v max ) (7)

[0091] Among them, x min and x maxare the minimum and maximum values ​​of the position respectively; v min and v max are the minimum and maximum values ​​of the speed respectively;

[0092] d. Use the following fitness function to evaluate the pros and cons of each particle's scheduling strategy and maximize the energy efficiency of the system:

[0093]

[0094] in, Energy saved for node i; is the energy used by node i; N is the particle swarm size, which is 50;

[0095] e. Finally, in each iteration, the particle's velocity and position are updated according to the following formula:

[0096] v i (t+1)=ωv i (t)+c1r1[p i -x i (t)]+c2r2[gx i (t)] (9)

[0097] x i (t+1)=x i (t)+v i (t+1) (10)

[0098] Among them, v i is the velocity of particle i in generation t; x i is the position of particle i in the tth generation; ω is the inertia weight, which is 0.5; c1, c2 are acceleration constants, both of which are 2.0; r1, r2 are random numbers in the range [0, 1]; p i is the optimal position of particle i; g is the global optimal position; in addition, the maximum number of iterations T max is 100.

[0099] S140, according to the optimal charging and discharging strategy of each node, a scheduling instruction is issued to each node through a smart contract to control the charging and discharging operation of each node.

[0100] The scheduling instruction contract module of the smart contract architecture is used to issue scheduling instructions to each node of the network topology module through smart contracts according to the optimal charging and discharging strategy of each node; the parameters of the scheduling instruction include the scheduling instruction ID, target node ID, instruction content, execution time and execution duration.

[0101] In some embodiments, the structure of the scheduling instruction of the scheduling instruction contract module is:

[0102] Command={k1,o1,r1,s1,t1} (11)

[0103] Wherein: k1 is the scheduling instruction ID and is also a string that uniquely identifies each scheduling instruction; o1 is the target node ID used to identify the node that receives and executes the instruction; r1 is the instruction content used for specific operation instructions, such as charging or discharging; s1 is the scheduled execution timestamp for recording the execution time instruction; t1 is the execution duration used for the duration of the instruction.

[0104] An implementation example is provided below to illustrate the effects of the method and system of the present invention, but it is not intended to be limiting. In the implementation example of the present invention, the simulation test conditions are: Hyperledger Fabric is selected as the blockchain platform and the smart contract deployment is completed; specifically, the consensus mechanism is set to Raft, the network scale is 10 nodes in the initial stage and supports expansion to 50 nodes, the block time is 2 seconds, the transaction throughput is 1000 transactions / second, the data encryption method is AES-256, and the identity authentication method is public key infrastructure. Historical load data and renewable energy generation data for a total of three years from 2021 to 2023 were collected from the actual power system in a certain area, with a collection frequency of once every 15 minutes, for a total of 105,120 records.

[0105] The simulation test plan is as follows:

[0106] (1) Record the average response time from the issuance of scheduling instructions to the completion of execution, and test the response speed under different load and resource conditions;

[0107] (2) Evaluate the effect of the scheduling strategy through the fitness function, record the energy efficiency of the system, and compare the improvement of the overall system performance before and after optimization;

[0108] (3) Simulate malicious nodes to attempt to tamper with data and verify the data integrity and security of the blockchain system.

[0109] Analyze the results of the above simulation tests. Figure 7 It is the average response time diagram under different load conditions and power generation conditions. Figure 7 As shown in the figure, under low load (average 30.15MW, peak 45.23MW), medium load (average 60.25MW, peak 90.34MW) and high load (average 90.17MW, peak 135.45MW) conditions, the average response time of distributed pumped storage multi-node collaborative scheduling based on blockchain is 0.47s, 0.55s and 0.69s respectively. Figure 8 is the average response time diagram under different renewable energy generation conditions. Figure 8As shown in the figure, under the conditions of low renewable energy generation (average power generation of 10.12MW), medium renewable energy generation (average power generation of 20.25MW) and high renewable energy generation (average power generation of 30.37MW), the average response time is 0.51s, 0.56s and 0.63s respectively. This shows that the system has a fast response speed under different load and resource conditions and can process scheduling instructions in real time. In terms of prediction accuracy, the mean square error and mean absolute error of the LSTM model prediction are 0.0123 and 0.0865 respectively, indicating that the model performs well in capturing the overall trend of the data and the prediction at each time step is relatively accurate.

[0110] Fig. 9 It is a schematic diagram comparing the energy efficiency under three different load conditions of the embodiment of the present invention. Fig.10 is a schematic diagram comparing total energy losses under three different load conditions in an embodiment of the present invention; Fig.11 A schematic diagram showing the comparison of peak-to-valley differences under three different load conditions in an embodiment of the present invention. Figure 9-11 As shown in the figure, under medium load conditions (average 60.25MW, peak 90.34MW), the overall energy efficiency of the system before and after PSO algorithm optimization was 77.84% and 91.47%, respectively, an increase of 13.63%. In addition, further fitness function evaluation results show that the total energy loss of the system before and after optimization was 22.16% and 8.53%, respectively, and the peak-to-valley difference of the system before and after optimization was 44.87MW and 29.58MW, respectively. This shows that the PSO optimization algorithm significantly improves the system's scheduling strategy and improves the overall performance of the system. In terms of data security, malicious nodes are introduced into the experimental environment to attempt to tamper with the data packets in transit, modify the power data and load data, and then use the hash check and consensus mechanism of the blockchain to detect and record all data tampering attempts. The results show that the data tampering success rate and data loss rate are both 0%, verifying the effectiveness of the blockchain-based system in ensuring data security and integrity.

[0111] In summary, the beneficial effects of the embodiments of the present invention are as follows: In order to solve the problems of traditional centralized control methods in terms of security, transparency and reliability, this application is proposed. First, a blockchain architecture is designed, which includes defining smart contracts and adopting a hybrid topology. Then, a multi-node collaborative scheduling algorithm is developed, in which the prediction model selects the long short-term memory (LSTM) network; the optimization algorithm selects the particle swarm optimization (PSO); the scheduling strategy dynamically adjusts the charging and discharging operations of each node according to the real-time prediction results to achieve the global optimality of the system. The model test results show that the distributed pumped storage multi-node collaborative scheduling mechanism based on blockchain has good performance in terms of response speed, prediction accuracy, scheduling effect and data security, and can provide reliable technical support for the distributed management and optimization of the energy Internet.

[0112] It should be understood that the order of execution of the steps in the above embodiment does not necessarily mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiment of the present invention.

[0113] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0114] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0115] In the embodiments provided by the present invention, it should be understood that the disclosed devices / terminals and methods can be implemented in other ways. For example, the device / terminal embodiments described above are only schematic, for example, the division of modules or units is only a logical function division, and there may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0116] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0117] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0118] If the integrated module / unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present invention implements all or part of the processes in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of the above-mentioned various method embodiments when executed by the processor. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. Computer-readable media may include: any entity or device capable of carrying computer program code, recording medium, U disk, mobile hard disk, disk, optical disk, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electrical carrier signal, telecommunication signal and software distribution medium, etc.

[0119] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention, and should be included in the protection scope of the present invention.

Claims

1. An integrated management method for energy internet based on distributed pumped storage, characterized in that: include: Obtain real-time electricity data of each node through the blockchain network; wherein the nodes include pumped storage nodes and dispatching control nodes; Determine the power demand forecast result according to the real-time power data and the forecast model; Taking the maximum energy saving and the minimum energy loss of each node as the goal, the power demand forecast result is optimized to obtain the optimal charging and discharging strategy of each node; According to the optimal charging and discharging strategy of each node, scheduling instructions are issued to each node through smart contracts to control the charging and discharging operations of each node.

2. The energy internet integrated management method based on distributed pumped storage according to claim 1 is characterized in that: The objective function used in the optimization process is: Among them, F3(i) is the function value of the objective function, N is the total number of nodes, is the energy storage capacity of the ith node, is the energy usage of the ith node, is the operation loss of the ith node, is the conversion loss of the i-th node, and λ is the preset weight coefficient used to balance energy saving and energy loss.

3. The energy internet integrated management method based on distributed pumped storage according to claim 1 is characterized in that: Determine the power demand forecast result according to the real-time power data and the forecast model, including: Convert the real-time power data of each node into input tensors according to the preset time step and feature dimension; The input tensor is input into the prediction model to determine the power demand prediction result of each node.

4. The integrated management method of energy internet based on distributed pumped storage according to claim 1 is characterized in that: With the goal of maximizing energy savings and minimizing energy loss at each node, the power demand forecast result is optimized to obtain the optimal charging and discharging strategy for each node, including: With the goal of maximizing energy saving and minimizing energy loss of each node, a particle swarm algorithm is used to optimize the power demand forecast results to obtain the optimal charging and discharging strategy for each node.

5. An integrated energy internet management system based on distributed pumped storage, characterized in that: include: Smart contract architecture, network topology module and multi-node collaborative scheduling architecture; The smart contract architecture is used to obtain real-time power data of each node in the network topology module through the blockchain network, and send it to the multi-node collaborative scheduling architecture; wherein the nodes include pumped storage nodes and scheduling control nodes; The multi-node collaborative scheduling architecture is used to determine the power demand prediction result according to the real-time power data and the prediction model; The multi-node collaborative scheduling architecture is also used to optimize the power demand forecast result with the goal of maximizing energy savings and minimizing energy loss of each node, obtain the optimal charging and discharging strategy of each node, and report it to the smart contract architecture; The smart contract architecture is also used to issue scheduling instructions to each node of the network topology module through the smart contract according to the optimal charging and discharging strategy of each node, so as to control the charging and discharging operations of each node.

6. The energy internet integrated management system based on distributed pumped storage according to claim 5 is characterized in that: The smart contract architecture includes a node registration contract module, a data sharing contract module and a scheduling instruction contract module; The node registration contract module is used to record the registration parameters of each node of the network topology module when it is registered on the smart contract structure; wherein the registration parameters include node ID, node type, public key and registration time; The data sharing contract module is used to obtain real-time power data of each node in the network topology module; the parameters of the real-time power data include data type, data value, timestamp and data source node ID; The scheduling instruction contract module is used to issue scheduling instructions to each node of the network topology module through a smart contract according to the optimal charging and discharging strategy of each node; the parameters of the scheduling instruction include scheduling instruction ID, target node ID, instruction content, execution time and execution duration.

7. The energy internet integrated management system based on distributed pumped storage according to claim 6 is characterized in that: The formula for generating the node address in the node registration contract module is: NodeAddress=Hash(a1+b1+c1+d1) Among them, a1 is the node ID and is a string that uniquely identifies each node; b1 is the node type used to distinguish nodes with different functions such as pumped storage and dispatching control; c1 is the public key used for node identity authentication; and d1 is the registration time, which records the registration timestamp of the node; the hash function performs a hash operation on the node ID, public key and registration time to generate a unique node address.

8. The energy internet integrated management system based on distributed pumped storage according to claim 6 is characterized in that: The structure of shared data in the data sharing contract module is: SharedData = {e1,f1,g1,h1} Among them, e1 is the data type used to identify data categories such as power, load or status information; f1 is the data value which is the specific data content; g1 is the timestamp used to record the generation time of the data; and h1 is the data source node ID used to identify the node that generated the data.

9. The energy internet integrated management system based on distributed pumped storage according to claim 6 is characterized in that: The structure of the scheduling instruction of the scheduling instruction contract module is: Command = {k1,o1,r1,s1,t1} Where: k1 is the scheduling instruction ID and is also a string that uniquely identifies each scheduling instruction; o1 is the target node ID used to identify the node that receives and executes the instruction; r1 is the instruction content used for specific operation instructions, such as charging or discharging; s1 is the scheduled execution timestamp that records the execution time instruction; t1 is the execution duration, which is used for the duration of the instruction.

10. The energy internet integrated management system based on distributed pumped storage according to claim 6 is characterized in that: The formula for setting the connection between nodes in the network topology module is: C={(n i ,n j )n i ∈P,n j ∈C,i≠j} Where: C is the connection set between nodes; n i is the pumped storage node; n j is the dispatching control node; P is the pumped storage node set; C is the dispatching control node set.

Images