An energy storage monitoring method and system based on artificial intelligence

Abstract

The present invention is applicable to the field of energy storage monitoring technology, and in particular relates to an energy storage monitoring method and system based on artificial intelligence, the method comprising: S100: establishing an energy contract template, embedding the use rights of energy-saving equipment, determining energy-consuming units in the area, generating an energy management agreement, issuing the use rights of energy-saving equipment to the energy-consuming units, and establishing a profit sharing mechanism; S200: transmitting the redundant electricity flowing in the energy-saving equipment to the energy storage device, configuring a one-to-one correspondence between the energy storage device and the energy-consuming unit, defining the energy storage device as a node, extracting the attributes of the node, and determining the coverage range of each node. The present invention can avoid peak electricity prices and improve the energy independence of energy-consuming units by constructing a microgrid. Through an open interface, the energy storage device can be connected to the power system. While providing continuous power supply guarantee for the energy-consuming units, it can also smooth the peaks and valleys of the power system and improve the stability of the power system.

Description

Technical Field

[0001] The present invention relates to the field of energy storage monitoring technology, and in particular to an energy storage monitoring method and system based on artificial intelligence. Background Art

[0002] Energy storage is the process of storing electrical energy and releasing it when needed. Its primary purpose is to balance electricity supply and demand. By storing excess energy and providing it during peak demand, it improves the stability and efficiency of the power system. Energy storage methods include, at a minimum, batteries, flywheels, compressed air, and pumped hydro.

[0003] Energy storage monitoring refers to the process of real-time monitoring and management of energy storage systems. AI-based energy storage monitoring uses AI algorithms to process and analyze energy storage systems in real time to ensure normal system operation. This technology can not only predict power demand and optimize the charging and discharging strategies of energy storage systems, but also reduce peak loads and fill valleys in power loads.

[0004] However, currently there are relatively few participants in energy storage, and its ability to balance the power system is relatively limited; therefore, "how to give full play to the subjective initiative of enterprises and encourage them to store energy" is the technical problem that the present invention needs to solve. Summary of the Invention

[0005] The purpose of the present invention is to provide an energy storage monitoring method and system based on artificial intelligence to solve the problem raised in the above background technology of "how to give full play to the subjective initiative of enterprises and encourage them to store energy".

[0006] To achieve the above object, the present invention provides the following technical solutions:

[0007] An energy storage monitoring method based on artificial intelligence, the method comprising:

[0008] S100: Establish an energy contract template, embed the use rights of energy-saving equipment, identify energy-consuming units in the area, generate an energy management agreement, issue the use rights of energy-saving equipment to the energy-consuming units, and establish a profit sharing mechanism;

[0009] S200: Transmitting redundant power flowing through the energy-saving device to the energy storage device, configuring a one-to-one correspondence between the energy storage device and the energy-consuming unit, defining the energy storage device as a node, extracting node attributes, determining the coverage of each node, aggregating all nodes, constructing a microgrid, and marking interfaces of the microgrid;

[0010] S300: Traverse the load within the node, where the load is used to characterize the equipment currently using electricity, use a machine learning algorithm to predict the load change of the node, compare the changing load with the redundant power, and determine whether there is a power gap in the microgrid. If so, open the interface to the power system.

[0011] Furthermore, the S100 includes:

[0012] inserting a tag generated by an energy management protocol into the node;

[0013] Based on the electricity consumption of the energy-consuming unit, a reward coefficient is determined and the revenue sharing mechanism is modified.

[0014] Furthermore, the S100 further includes:

[0015] Calculate the current electricity consumption of the energy-consuming units, conduct energy consumption assessment, and obtain the power consumption of the load;

[0016] Based on the evaluation results, improvement points are found, the energy-saving equipment is deployed, and redundant power is determined.

[0017] Furthermore, the S100 further includes:

[0018] Integrate the redundant electricity and the preset exchange mechanism to calculate the income of the energy-consuming unit, and distribute the income using the income sharing mechanism;

[0019] The revenue is refreshed according to changes in electricity prices in the power system.

[0020] Furthermore, the S200 includes:

[0021] Embedding a coordination strategy into the nodes to generate a scheduling architecture, and transferring the nodes into the scheduling architecture to construct a microgrid;

[0022] An interface in the microgrid is determined, wherein the interface includes an incoming line and an outgoing line, wherein the incoming line points to the power system and the outgoing line points to the node.

[0023] Furthermore, the S300 includes:

[0024] The microgrid is divided into sections to construct off-grid encirclement circles, and feedback power is determined, wherein there is no power shortage at nodes in the off-grid encirclement circles;

[0025] Based on the off-grid encirclement circle, a transmission link for feedback power is established.

[0026] Furthermore, the method further comprises:

[0027] Integrating the nodes and loads into a virtual power plant, and utilizing the virtual power plant to smooth the peaks and valleys of the power system based on the electricity price changes;

[0028] The nodes are expanded to establish an energy sharing platform and integrate a pre-built redundant electricity trading mechanism.

[0029] Furthermore, the system includes:

[0030] Establish a module for creating energy contract templates, embedding the use rights of energy-saving equipment, identifying energy users in the region, generating energy management agreements, issuing use rights of energy-saving equipment to the energy users, and establishing a revenue sharing mechanism;

[0031] a marking module for transferring the redundant power flowing through the energy-saving device to the energy storage device, configuring a one-to-one correspondence between the energy storage device and the energy-consuming unit, defining the energy storage device as a node, extracting the node attributes, determining the coverage of each node, aggregating all nodes, constructing a microgrid, and marking the interfaces of the microgrid;

[0032] The judgment module is used to traverse the load within the node, where the load is used to characterize the equipment currently using electricity, use a machine learning algorithm to predict the load change of the node, compare the changing load with the redundant power, and determine whether there is a power gap in the microgrid. If so, open the interface to the power system.

[0033] Furthermore, the establishment module includes:

[0034] a generating unit, configured to insert a label generated by an energy management protocol into the node;

[0035] a correction unit, configured to determine a reward coefficient according to the power consumption of the energy-consuming unit and to correct the revenue sharing mechanism;

[0036] An acquisition unit, configured to calculate the current electricity consumption of the energy-consuming unit, perform energy consumption evaluation, and obtain the electricity consumption of the load;

[0037] a determination unit, configured to find improvement points based on the evaluation results, deploy the energy-saving equipment, and determine redundant power;

[0038] a distribution unit, configured to integrate the redundant power and a preset exchange mechanism, calculate the revenue of the energy-consuming unit, and distribute the revenue using the revenue sharing mechanism;

[0039] A refreshing unit is used to refresh the revenue according to the change of electricity price in the power system.

[0040] Furthermore, the marking module includes:

[0041] A construction unit, configured to generate a scheduling architecture according to the power coordination strategy, and transfer the nodes into the scheduling architecture to construct a microgrid;

[0042] The pointing unit is used to determine an interface in the microgrid, wherein the interface includes an incoming line and an outgoing line, wherein the incoming line points to the power system and the outgoing line points to the node.

[0043] Compared with the prior art, the present invention has the following beneficial effects:

[0044] 1. By generating an energy management protocol, it is possible to reduce the electricity consumption of energy-consuming units, lower electricity bills, and help energy-consuming units achieve dual benefits of economic and environmental benefits. By inputting redundant power into energy storage devices, it is possible to optimize energy storage use and improve energy utilization. By building a microgrid, it is possible to reduce the peak electricity prices of energy-consuming units and improve their energy independence. Through open interfaces, energy storage devices can be connected to the power system, providing continuous power supply to energy-consuming units while also shaving peaks and valleys in the power system, thereby improving the stability of the power system.

[0045] 2. By building a virtual power plant, the redundant electricity of energy-consuming units can be sold, which not only reduces the electricity costs of energy-consuming units but also further improves the stability of the power system. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] Figure 1 A flowchart of an artificial intelligence-based energy storage monitoring method provided in an embodiment of the present invention;

[0047] Figure 2 A first sub-flow diagram of the energy storage monitoring method based on artificial intelligence provided by an embodiment of the present invention;

[0048] Figure 3 A second sub-flow diagram of the energy storage monitoring method based on artificial intelligence provided by an embodiment of the present invention;

[0049] Figure 4 A third sub-flow chart of the artificial intelligence-based energy storage monitoring method provided in an embodiment of the present invention;

[0050] Figure 5 A block diagram of the composition of an artificial intelligence-based energy storage monitoring system provided in an embodiment of the present invention;

[0051] Figure 6 A block diagram of the components of the establishment module in the artificial intelligence-based energy storage monitoring system provided by an embodiment of the present invention;

[0052] Figure 7 A block diagram of the marking module in the artificial intelligence-based energy storage monitoring system provided by an embodiment of the present invention;

[0053] Figure 8 This is a block diagram of the composition of the judgment module in the artificial intelligence-based energy storage monitoring system provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0054] In order to make the purpose, technical solutions and advantages of the present invention more clearly understood, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0055] In Example 1, Figure 1 The implementation process of the energy storage monitoring method based on artificial intelligence provided by an embodiment of the present invention is shown and described in detail below:

[0056] S100: Establish an energy contract template, embed the use rights of energy-saving equipment, determine the energy-consuming units in the area, generate an energy management agreement, issue the use rights of energy-saving equipment to the energy-consuming units, and establish a profit sharing mechanism.

[0057] An energy contract template is established, which is signed by the energy-consuming unit and the energy-saving equipment supplier. Once signed, the energy-consuming unit is given access to the energy-saving equipment, an energy management agreement is generated, and a profit-sharing mechanism is established.

[0058] In this embodiment, energy users sign an energy management agreement with energy-saving equipment suppliers. The suppliers provide energy-saving equipment, and the resulting revenue (i.e., electricity cost savings) is shared between the energy users and the equipment suppliers. The specific sharing ratio and details are described in the revenue sharing mechanism. This approach has the benefit of both saving electricity and improving the stability of the load for both the energy users and the power system.

[0059] S200: The redundant power flowing in the energy-saving device is transmitted to the energy storage device, a one-to-one correspondence between the energy storage device and the energy-consuming unit is configured, and the energy storage device is defined as a node. The attributes of the node are extracted, the coverage range of each node is determined, all nodes are aggregated, a microgrid is constructed, and the interfaces of the microgrid are marked.

[0060] The redundant power circulating in the energy-saving device is transmitted to the energy storage device, where the redundant power is the power saved by the energy-saving device. This part of the power can be stored by the lithium battery, mechanical energy storage module, etc. in the energy-saving device, or it can be directly transmitted to the energy storage device, where the energy storage device can be a battery energy storage system, a mechanical energy storage system, or a hybrid energy storage system; one or several energy-consuming units correspond to one energy storage device, and the energy storage device is defined as a node, and the properties of the node are determined, where the properties are the capacity, number of cycles and energy density of the energy storage device; since the capacity of the energy storage device is limited, it can only store and coordinate the redundant power of a limited number of energy-consuming units, so it is necessary to determine the coverage of the node according to the properties of the node, integrate all the nodes in the area, build a microgrid, and open the interface of the microgrid to the power system in the area, and use the microgrid to balance the load of the power system.

[0061] S300: Traverse the load within the node, where the load is used to characterize the equipment currently using electricity, use a machine learning algorithm to predict the load change of the node, compare the changing load with the redundant power, and determine whether there is a power gap in the microgrid. If so, open the interface to the power system.

[0062] Traverse all loads within the node, use machine learning algorithms to predict load changes, and compare the load with redundant power. The load is the power required by the energy-consuming unit, and the redundant power is the power stored in the energy storage unit. If the redundant power is less than the load, it means there is a power gap. In this case, it is necessary to open the interface and use the power system to fill the power gap.

[0063] In Example 2, Figure 2 The implementation process of the energy storage monitoring method based on artificial intelligence provided by an embodiment of the present invention is shown. S100 is described in detail below:

[0064] S101: inserting a label generated by an energy management protocol into the node.

[0065] Insert a label into the node, where the label is generated by the energy management protocol and contains specific details of the energy management protocol.

[0066] S102: Determine a reward coefficient based on the power consumption of the energy-consuming unit and modify the profit sharing mechanism.

[0067] The reward coefficient is determined based on the electricity consumption of the energy-consuming unit and the electricity consumption after using energy-saving equipment. For example, if an energy-consuming unit saves 30% of electricity after using energy-saving equipment, different reward coefficients can be given according to the specific proportion. By using the profit-sharing mechanism to give rewards, the enthusiasm of energy-consuming units to use energy-saving equipment can be increased.

[0068] In Example 3, Figure 2 The implementation process of the energy storage monitoring method based on artificial intelligence provided by an embodiment of the present invention is shown. S100 is further described in detail below.

[0069] S103: Calculate the current electricity consumption of the energy-consuming unit, perform energy consumption evaluation, and obtain the power consumption of the load.

[0070] Statistics are compiled on the electricity consumption status of energy-consuming units, including electricity consumption data of each production equipment in different time periods, electricity consumption of production equipment in each department, etc. Energy consumption of each production equipment is evaluated to determine the amount of electricity required for a certain period of production.

[0071] S104: Find improvement points based on the evaluation results, deploy the energy-saving equipment, and determine redundant power.

[0072] Based on the evaluation results of each production equipment, we find out the improvement points and deploy energy-saving equipment on the production equipment within the energy-consuming unit. We use the electricity saved by the energy-saving equipment, which is also redundant electricity.

[0073] For example, the evaluation result of a certain production equipment is that its electricity efficiency is low and it requires an additional 5% of electricity consumption; the improvement point can be to start it during the low-power consumption period and replace the equipment with new ones.

[0074] In Example 4, Figure 2 The implementation process of the energy storage monitoring method based on artificial intelligence provided by an embodiment of the present invention is shown. S100 is further described in detail below.

[0075] S105: Integrate the redundant electricity and the preset exchange mechanism, calculate the income of the energy-consuming unit, and distribute the income using the income sharing mechanism.

[0076] Create a mechanism to exchange excess power for revenue. This mechanism involves exchanging excess power for the power system at full price or at a discount, or using excess power to reduce or waive electricity bills for energy users. Calculate the revenue for energy users, and determine the profit split between them and energy-saving equipment suppliers based on a revenue-sharing mechanism. This is then distributed.

[0077] S106: Refresh the revenue according to the change of electricity price in the power system.

[0078] Based on the real-time electricity price in the power system, the total electricity price of the redundant electricity is calculated, and the profits of energy-consuming units and energy-saving equipment suppliers are refreshed based on this total electricity price.

[0079] In Example 5, Figure 3The implementation process of the energy storage monitoring method based on artificial intelligence provided by an embodiment of the present invention is shown. S200 is described in detail below.

[0080] S201: Embed a coordination strategy into the node, generate a scheduling architecture, and transfer the node into the scheduling architecture to build a microgrid.

[0081] Embed a coordination strategy into the node, where the coordination strategy is the process of transferring redundant electricity among different energy-consuming units, generate a scheduling architecture for redundant electricity, transfer the nodes into the scheduling architecture, and build a microgrid. In other words, by utilizing the microgrid, energy-consuming units can transfer the saved electricity to other units for a fee or free of charge, thereby achieving electricity self-sufficiency for each energy-consuming unit in the region.

[0082] S202: Determine an interface in the microgrid, where the interface includes an incoming line and an outgoing line, where the incoming line points to the power system and the outgoing line points to the node.

[0083] Determine the incoming and outgoing lines in the microgrid, where the incoming lines are connected to the power system. When the redundant power in the microgrid is not enough to be self-sufficient, it can be supplemented by the power system. In other words, by utilizing the microgrid, the power system can be peak-shaving and valley-flattening to stabilize the power system load. The outgoing lines of the microgrid point to the nodes, and the nodes are used as the source of power in the microgrid.

[0084] In Example 6, Figure 4 The implementation process of the energy storage monitoring method based on artificial intelligence provided by an embodiment of the present invention is shown. S300 is described in detail below:

[0085] S301: Divide the microgrid, construct an off-grid encirclement circle, and determine the amount of feedback power, wherein there is no power shortage at the nodes in the off-grid encirclement circle.

[0086] The microgrid is divided into multiple areas, and the areas are used to construct an off-grid enclosure circle. That is to say, the redundant power within the off-grid enclosure circle is greater than the load, that is, the energy-consuming units within the off-grid enclosure circle can achieve self-sufficiency and even generate excess power, which is feedback power.

[0087] S302: Building a transmission link for feedback power based on the off-grid encirclement circle.

[0088] The feedback power is transmitted to the power system through the external transmission link, thus realizing power consumption feedback.

[0089] In Example 7, different from Example 1, in this embodiment of the present invention, the method further includes:

[0090] Integrating the nodes and loads into a virtual power plant, and utilizing the virtual power plant to smooth the peaks and valleys of the power system based on the electricity price changes;

[0091] Expand the nodes, establish an energy sharing platform, and integrate a pre-built redundant electricity trading mechanism.

[0092] Nodes and loads are used to generate virtual power plants, and the power system is smoothed and peak-valleyed according to changes in electricity prices and electricity loads. At the same time, nodes are used to build an energy sharing platform, and a redundant electricity trading mechanism is embedded in the energy sharing platform so that redundant electricity between nodes can be traded between energy-consuming units. The redundant electricity trading mechanism is the specific trading method of redundant electricity.

[0093] In this application, energy-saving equipment suppliers provide energy-saving equipment to energy-consuming units, where the energy-saving equipment should include: photovoltaic power generation systems, cogeneration systems; node equipment can also be old equipment in energy-consuming units; energy-saving equipment suppliers replace old equipment or use the energy-consuming units' sites to build new photovoltaic power generation systems, etc., and the electricity saved or generated thereby is called redundant electricity, which is transmitted to energy storage equipment; if the redundant electricity is sufficient for the energy-consuming units' production and use, a microgrid is constructed using the nodes (energy storage equipment), and the energy-consuming units in the microgrid that can achieve self-sufficiency in electricity consumption are separated to construct an off-grid enclosure; the excess electricity in the off-grid enclosure can also be sold and traded through a sharing mechanism or energy sharing platform, and the generated income is shared by the energy-consuming units and the energy-saving equipment suppliers; if the redundant electricity is not enough for the energy-consuming units to use, the power system needs to be connected to the microgrid, and while supplying energy to the energy-consuming units, the power system needs to be peak-shaving and valley-flattening, and the energy-consuming units take out a corresponding proportion of the saved electricity bills as subsidies to distribute to the energy-saving equipment suppliers.

[0094] Figure 5 The following is a structural block diagram of an energy storage monitoring system based on artificial intelligence provided by an embodiment of the present invention. The energy storage monitoring system based on artificial intelligence 1 includes:

[0095] Establishing module 11, for establishing an energy contract template, embedding the use rights of energy-saving equipment, identifying energy-consuming units in the area, generating an energy management agreement, issuing the use rights of energy-saving equipment to the energy-consuming units, and establishing a revenue sharing mechanism;

[0096] The marking module 12 is used to transfer the redundant power flowing in the energy-saving device to the energy storage device, configure a one-to-one correspondence between the energy storage device and the energy-consuming unit, define the energy storage device as a node, extract the attributes of the node, determine the coverage of each node, aggregate all nodes, construct a microgrid, and mark the interfaces of the microgrid;

[0097] The judgment module 13 is used to traverse the load within the node, where the load is used to characterize the equipment that is currently consuming electricity, use a machine learning algorithm to predict the load change of the node, compare the changing load and redundant power, and determine whether there is a power gap in the microgrid. If so, the interface is opened to the power system.

[0098] Figure 6 The following is a structural block diagram of the energy storage monitoring system based on artificial intelligence provided by an embodiment of the present invention. The establishment module 11 includes:

[0099] A generating unit 111, configured to insert a label generated by an energy management protocol into the node;

[0100] A correction unit 112 is configured to determine a reward coefficient based on the power consumption of the energy-consuming unit and to correct the revenue sharing mechanism;

[0101] The acquisition unit 113 is used to calculate the current electricity consumption of the energy-consuming unit, perform energy consumption evaluation, and obtain the power consumption of the load;

[0102] A determination unit 114 is configured to identify improvement points based on the evaluation results, deploy the energy-saving equipment, and determine redundant power;

[0103] The issuing unit 115 is configured to integrate the redundant power and the preset exchange mechanism, calculate the revenue of the energy-consuming unit, and issue the revenue using the revenue sharing mechanism;

[0104] The refreshing unit 116 is configured to refresh the revenue according to changes in electricity prices in the power system.

[0105] Figure 7 The following is a structural block diagram of the energy storage monitoring system based on artificial intelligence provided by an embodiment of the present invention. The marking module 12 includes:

[0106] A construction unit 121 is configured to generate a scheduling architecture according to the power coordination strategy, and transfer the nodes into the scheduling architecture to construct a microgrid;

[0107] The pointing unit 122 is configured to determine an interface in the microgrid, wherein the interface includes an incoming line and an outgoing line, wherein the incoming line points to the power system, and the outgoing line points to the node.

[0108] Figure 8 The following is a structural block diagram of the energy storage monitoring system based on artificial intelligence provided by an embodiment of the present invention. The judgment module 13 includes:

[0109] A feedback unit 131 is configured to divide the microgrid, construct an off-grid encirclement circle, and determine a feedback amount of electricity, wherein no nodes in the off-grid encirclement circle have a power shortage;

[0110] The building unit 132 is used to build an outbound transmission link for feedback power according to the off-grid encirclement circle.

[0111] The establishment module 11 is mainly used to complete step S100, the marking module 12 is mainly used to complete step S200, and the judgment module 13 is mainly used to complete step S300;

[0112] The generating unit 111 is mainly used to complete step S101, the correcting unit 112 is mainly used to complete step S102, the acquiring unit 113 is mainly used to complete step S103, the determining unit 114 is mainly used to complete step S104, the issuing unit 115 is mainly used to complete step S105, and the refreshing unit 116 is mainly used to complete step S106;

[0113] The construction unit 121 is mainly used to complete step S201, and the construction unit 121 is mainly used to complete step S202;

[0114] The feedback unit 131 is mainly used to complete step S301, and the construction unit 132 is mainly used to complete step S302.

[0115] The technical features of the above-mentioned embodiments can be combined arbitrarily. In order to make the description concise, not all possible combinations of the technical features in the above-mentioned embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0116] The above-described embodiments merely illustrate several implementations of the present invention, and while their descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the present invention. It should be noted that a person skilled in the art would be able to make numerous variations and improvements without departing from the spirit of the present invention, all of which fall within the scope of protection of the present invention. Therefore, the scope of protection of the present invention shall be determined by the appended claims.

[0117] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. An energy storage monitoring method based on artificial intelligence, characterized in that: The method comprises: S100: Establish an energy contract template, embed the use rights of energy-saving equipment, identify energy-consuming units in the area, generate an energy management agreement, issue the use rights of energy-saving equipment to the energy-consuming units, and establish a profit-sharing mechanism. S100 includes: determining a reward coefficient based on the power consumption of the energy-consuming units and revising the profit-sharing mechanism; calculating the current power consumption of the energy-consuming units and performing energy consumption assessment to obtain the power consumption of the load; based on the assessment results, finding improvement points, deploying the energy-saving equipment, and determining redundant power; S200: Transmitting redundant power flowing through the energy-saving device to the energy storage device, configuring a one-to-one correspondence between the energy storage device and the energy-consuming unit, defining the energy storage device as a node, extracting node attributes, determining the coverage of each node, aggregating all nodes, constructing a microgrid, and marking interfaces of the microgrid; S300: Traverse the load within the node, where the load is used to characterize the equipment currently using electricity, use a machine learning algorithm to predict the load change of the node, compare the changing load with the redundant power, and determine whether there is a power gap in the microgrid. If so, open the interface to the power system.

2. The energy storage monitoring method based on artificial intelligence according to claim 1, characterized in that: The S100 includes: A tag generated by the energy management protocol is inserted into the node.

3. The energy storage monitoring method based on artificial intelligence according to claim 1 is characterized in that: The S100 further includes: Integrate the redundant electricity and the preset exchange mechanism to calculate the income of the energy-consuming unit, and distribute the income using the income sharing mechanism; The revenue is refreshed according to changes in electricity prices in the power system.

4. The energy storage monitoring method based on artificial intelligence according to claim 2, characterized in that: The S200 includes: Embedding a coordination strategy into the nodes to generate a scheduling architecture, and transferring the nodes into the scheduling architecture to construct a microgrid; An interface in the microgrid is determined, wherein the interface includes an incoming line and an outgoing line, the incoming line points to the power system, and the outgoing line points to the node.

5. The energy storage monitoring method based on artificial intelligence according to claim 4 is characterized in that: The S300 includes: The microgrid is divided into sections to construct off-grid encirclement circles, and feedback power is determined, wherein there is no power shortage at nodes in the off-grid encirclement circles; Based on the off-grid encirclement circle, a transmission link for feedback power is established.

6. The energy storage monitoring method based on artificial intelligence according to claim 3 is characterized in that: The method further comprises: Integrating the nodes and loads into a virtual power plant, and utilizing the virtual power plant to smooth the peaks and valleys of the power system based on the electricity price changes; Expand the nodes, establish an energy sharing platform, and integrate a pre-built redundant electricity trading mechanism.

7. An energy storage monitoring system based on artificial intelligence, characterized in that: The system comprises: Establish a module for creating energy contract templates, embedding the use rights of energy-saving equipment, identifying energy users in the region, generating energy management agreements, issuing use rights of energy-saving equipment to the energy users, and establishing a revenue sharing mechanism; The establishment module further includes: a correction unit, configured to determine a reward coefficient based on the power consumption of the energy-consuming unit and to correct the revenue sharing mechanism; an acquisition unit, configured to calculate the power consumption status of the energy-consuming unit, perform energy consumption evaluation, and obtain the power consumption of the load; and a determination unit, configured to identify improvement points based on the evaluation results, deploy the energy-saving equipment, and determine redundant power; a marking module for transferring the redundant power flowing through the energy-saving device to the energy storage device, configuring a one-to-one correspondence between the energy storage device and the energy-consuming unit, defining the energy storage device as a node, extracting the node attributes, determining the coverage of each node, aggregating all nodes, constructing a microgrid, and marking the interfaces of the microgrid; The judgment module is used to traverse the load within the node, where the load is used to characterize the equipment currently using electricity, use a machine learning algorithm to predict the load change of the node, compare the changing load with the redundant power, and determine whether there is a power gap in the microgrid. If so, open the interface to the power system.

8. The artificial intelligence-based energy storage monitoring system according to claim 7, characterized in that: The establishment module further includes: a generating unit, configured to insert a label generated by the energy management protocol into the node; a distribution unit, configured to integrate the redundant power and a preset exchange mechanism, calculate the revenue of the energy-consuming unit, and distribute the revenue using the revenue sharing mechanism; A refreshing unit is used to refresh the revenue according to the change of electricity price in the power system.

9. The artificial intelligence-based energy storage monitoring system according to claim 7, characterized in that: The marking module includes: A construction unit, configured to embed a coordination strategy into the node, generate a scheduling architecture, and transfer the node into the scheduling architecture to construct a microgrid; The pointing unit is used to determine an interface in the microgrid, wherein the interface includes an incoming line and an outgoing line, wherein the incoming line points to the power system and the outgoing line points to the node.

Images