Optical storage and charging cooperative off-network control method based on energy router

Abstract

The invention discloses an optical storage and charging cooperative off-network control method based on an energy router, and relates to the technical field of optical storage and charging cooperative control, and the method comprises the steps: collecting energy router grid-connected point off-network control data and environmental parameters in real time, carrying out the preprocessing of the collected data, and storing the processed data into a time sequence database; constructing a multi-level prediction model to predict load, power generation and power grid condition data, and dynamically updating system operation parameters according to a prediction result; according to the off-network control data, performing intelligent off-network pre-judgment to switch a system operation mode, and performing off-network operation optimization control; and continuously monitoring the state of the power grid, recovering grid-connected operation after the bus voltage is stable, and carrying out optical storage and charging collaborative off-grid control based on the energy router. According to the invention, long-time off-grid operation of the DC micro-grid is realized, and the power supply reliability and the equipment safety of off-grid operation are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of photovoltaic storage and charging coordinated control, and in particular to a photovoltaic storage and charging coordinated off-grid control method based on an energy router. Background Art

[0002] With the rapid development of renewable energy technology and the advancement of smart grid technology, energy routers, as key equipment connecting renewable energy generation and the user side, play an increasingly important role in modern power systems. Energy routers connect DC devices such as photovoltaics (PV), energy storage (ESS) and charging piles (EVCharger) through DC bus distribution, forming an efficient DC microgrid system. This configuration can not only realize the localization of clean energy consumption, but also significantly improve energy utilization efficiency. In addition, through intelligent control strategies, energy routers can supply electricity to charging piles during peak hours, achieve the effect of peak shaving and valley filling, and further improve the economic benefits of the system. In the event of a power grid outage, the energy storage system can provide emergency power supply, ensure continuous power supply to critical loads, and enhance the power supply reliability of the DC microgrid.

[0003] Although the application of energy routers and their supporting photovoltaic storage and charging systems in modern power systems has made significant progress, there are still some technical challenges that need to be solved. First, the management and protection mechanism of the energy storage system is not perfect. In particular, when the power generation or power consumption exceeds the design capacity of the energy storage system, overcharging or over-discharging is prone to occur, which in turn causes failure or damage to the energy storage unit. Secondly, the existing energy management strategies often lack effective monitoring and response mechanisms for real-time environmental parameters and grid status, resulting in low system operation efficiency. In addition, the traditional off-grid control method relies on a fixed threshold to determine when to switch from grid-connected mode to off-grid mode. This method lacks flexibility and cannot make optimal adjustments based on actual load changes and power generation conditions. Finally, due to the lack of effective data collection and prediction methods, it is difficult for the system to accurately predict future load demand and power generation, which limits its adaptability and stability in complex power environments. Summary of the invention

[0004] In view of the problems existing in the existing photovoltaic storage and charging coordinated off-grid control method based on energy router, the present invention is proposed. Therefore, the problem to be solved by the present invention is how to provide a photovoltaic storage and charging coordinated off-grid control method based on energy router.

[0005] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0006] In the first aspect, the present invention provides a photovoltaic storage and charging coordinated off-grid control method based on an energy router, which includes real-time collection of off-grid control data and environmental parameters of the energy router grid-connected point, preprocessing the collected data, and storing the processed data in a time series database; constructing a multi-level prediction model to predict load, power generation and grid status data, and dynamically updating system operating parameters according to the prediction results; intelligent off-grid prediction and switching of system operation modes according to off-grid control data, and off-grid operation optimization control; continuous monitoring of the grid status, and restoration of grid-connected operation after the bus voltage is stable, and photovoltaic storage and charging coordinated off-grid control based on the energy router.

[0007] As a preferred solution of the off-grid control method of photovoltaic storage and charging coordinated based on energy router described in the present invention, the off-grid control data includes grid connection point voltage, photovoltaic power, charging pile power and energy storage power; the environmental parameters include temperature, humidity, light intensity and wind speed.

[0008] As a preferred solution of the photovoltaic storage and charging coordinated off-grid control method based on energy router described in the present invention, the multi-level prediction model construction includes the following steps: using a multi-layer LSTM network to process the time series data of the off-grid control data; performing spatial correlation modeling, using a graph convolutional neural network to process the grid topology and user distribution information; constructing a multi-task learning framework to simultaneously predict load, power generation and grid status, and share the underlying feature extraction layer; introducing time and space attention to capture the impact of key time periods and regions; combining the outputs of multiple models for integrated learning, and outputting the predicted value through weighted average.

[0009] As a preferred solution of the off-grid control method of photovoltaic storage and charging based on energy router described in the present invention, the off-grid operation optimization control includes the following steps: setting the prediction time domain and control interval, obtaining state variables and control variables; setting off-grid operation optimization control constraints and objective functions to minimize energy costs, maximize renewable energy utilization, and minimize power fluctuations; using unsupervised learning algorithms to dynamically classify loads, and dynamically calculate load priorities based on user preferences, energy efficiency and system status; using adaptive load control strategies to dispatch and control loads, real-time power quality monitoring, using high-speed data acquisition systems to calculate total harmonic distortion indicators in real time, and using wavelet transforms for harmonic analysis to dynamically adjust filtering parameters; constructing a collaborative control strategy to coordinate reactive power compensation and dynamic voltage regulation for energy storage systems and photovoltaic inverters; using the SOCliity language to write energy trading smart contracts, and dynamically adjusting prices according to supply and demand relationships; performing fault detection and location, and using transfer learning technology to perform online fine-tuning of control strategies.

[0010] As a preferred solution of the off-grid control method for photovoltaic storage and charging based on energy router described in the present invention, the pricing mechanism of the smart contract adopts a dynamic marginal pricing model, which is expressed as follows:

[0011] P t =P base +k(D t -S t ) / S t

[0012] Among them, P t is the electricity price at time t, P base is the basic electricity price, D t is the demand, S t is the supply, k is the adjustment coefficient; the fault detection adopts an abnormality detection model based on a deep signal network, and the calculation formula of the reconstruction error is:

[0013]

[0014] Among them, x is the input data and x' is the reconstructed data.

[0015] As a preferred solution of the photovoltaic storage and charging coordinated off-grid control method based on the energy router described in the present invention, the photovoltaic storage and charging coordinated off-grid control based on the energy router includes the following steps: periodically collecting the primary side voltage of the energy router grid connection point to judge the voltage condition, when the voltage is not equal to 0, continue to the next round of collection; when the voltage is equal to 0, it means that the energy router is powered off, the circuit breaker of the energy router grid connection point is opened, the energy storage operation mode is switched to the constant voltage mode, the DC microgrid bus voltage is stabilized by the energy storage, and the off-grid operation is started; periodically collecting off-grid control data, if the voltage is greater than the minimum allowable voltage, the energy router resumes power supply, and the DC microgrid is in In normal operation, the energy storage operation mode is switched to constant power mode, the energy router grid-connected point circuit breaker is closed, the energy router stabilizes the DC microgrid bus voltage, and the grid-connected operation is restored; if the voltage is below the minimum allowable voltage, the control power of the photovoltaic and charging piles is calculated according to the energy storage port power and the current power, and the control instructions are sent to the corresponding devices and the off-grid control data is re-collected for secondary judgment; the control power of the photovoltaic and charging piles is calculated, and classified control is performed according to the energy storage SOC and power status, the energy storage operation mode is switched to constant power mode, the energy router grid-connected point circuit breaker is closed, the energy router stabilizes the DC microgrid bus voltage, and the grid-connected operation is restored.

[0016] As a preferred solution of the off-grid control method of photovoltaic storage and charging based on energy router described in the present invention, the classification control according to energy storage SOC and power state includes the following steps: when the minimum power SOC L<Current SOC of energy storage<Maximum power SOC H Or the current SOC of the energy storage is greater than SOC H And P c ≤0 or the current SOC of energy storage is less than SOC H And P c >0, the photovoltaic and charging piles maintain the current power; when the current SOC of the energy storage is greater than SOC H And P c >0, reduce the photovoltaic power generation power, increase the charging power of the charging pile, and recalculate the energy storage power so that the energy storage power meets P c ≤0, calculate the photovoltaic setting power and charging pile setting power; when the current SOC of the energy storage is less than SOC H And P c ≤0, increase the photovoltaic power generation power, reduce the charging power of the charging pile, and recalculate the energy storage power so that the energy storage power meets P c >0, the photovoltaic setting power and charging pile setting power are calculated; if the energy storage power P c <Energy storage rated power P e , the calculated photovoltaic setting power and charging pile setting power are directly issued; if the energy storage power P c ≥ Rated power of energy storage P e When the photovoltaic power setting value and the charging pile power setting value are adjusted, the energy storage power is recalculated to make the energy storage power P c < Rated power of energy storage P e After that, the calculated photovoltaic setting power and charging pile setting power are sent down.

[0017] The classification control according to the energy storage SOC and power state includes the following steps: when the current SOC of the energy storage is within the normal range, the photovoltaic and charging piles maintain the current power; when the current SOC of the energy storage is too high and the energy storage power is discharging, the photovoltaic and charging piles maintain the current power; when the current SOC of the energy storage is too high and the energy storage power is charging, the photovoltaic power generation power is reduced and the charging power of the charging pile is increased so that the energy storage power meets the discharging condition; when the current SOC of the energy storage is too low and the energy storage power is charging, the photovoltaic and charging piles maintain the current power; when the current SOC of the energy storage is too low and the energy storage power is discharging, the photovoltaic power generation power is increased and the charging power of the charging pile is reduced so that the energy storage power meets the charging condition; if the energy storage power exceeds the rated power, the photovoltaic and charging pile power setting values ​​are adjusted to make the energy storage power lower than the rated power.

[0018] In the second aspect, the present invention provides a photovoltaic storage and charging coordinated off-grid control system based on an energy router, which includes: an acquisition module, used to collect off-grid control data and environmental parameters of the energy router grid-connected point in real time, pre-process the collected data, and store the processed data in a time series database; a construction module, used to construct a multi-level prediction model to predict load, power generation and grid status data, and dynamically update system operation parameters according to the prediction results; an optimization module, used to perform intelligent off-grid prediction and switching of system operation modes according to off-grid control data, and perform off-grid operation optimization control; a control module, used to continuously monitor the grid status and resume grid-connected operation after the bus voltage is stable, and perform photovoltaic storage and charging coordinated off-grid control based on the energy router.

[0019] In a third aspect, the present invention provides a computer device including a memory and a processor, wherein the memory stores a computer program, wherein: when the processor executes the computer program, the steps of a photovoltaic storage and charging coordinated off-grid control method based on an energy router are implemented.

[0020] In a fourth aspect, the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein: when the computer program is executed by a processor, the steps of a photovoltaic storage and charging coordinated off-grid control method based on an energy router are implemented.

[0021] The beneficial effects of the present invention are that by controlling the power of photovoltaics and charging piles, the charging and discharging of energy storage is indirectly controlled, so that the energy storage capacity is always kept within an appropriate range, thereby improving the sustainability of off-grid operation; through the coordinated control of photovoltaics and charging piles, the power of the energy storage port does not exceed the rated power at all times, so that the DC microgrid can operate off-grid for a long time, thereby improving the power supply reliability and equipment safety of off-grid operation. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. 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 creative work.

[0023] Figure 1 This is a flow chart of the off-grid control method for photovoltaic storage and charging coordination based on energy router.

[0024] Figure 2 This is the architecture diagram of the off-grid control system for photovoltaic storage and charging coordination based on energy router. DETAILED DESCRIPTION

[0025] In order to make the above-mentioned purposes, features and advantages of the present invention more understandable, the specific implementation methods of the present invention are described in detail below in conjunction with the drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present invention, but not all of them. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in the art without creative work should fall within the scope of protection of the present invention.

[0026] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0027] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive with other embodiments.

[0028] Example 1

[0029] Reference Figure 1 , which is the first embodiment of the present invention, and provides a photovoltaic storage and charging coordinated off-grid control method based on an energy router, comprising:

[0030] S1: collect off-grid control data and environmental parameters of energy router grid-connected points in real time, pre-process the collected data, and store the processed data in a time series database;

[0031] Specifically, off-grid control data includes grid connection point voltage, photovoltaic power, charging pile power and energy storage power; environmental parameters include temperature, humidity, light intensity and wind speed. The collected data is subjected to outlier detection and smoothing; the processed data is stored in a time series database.

[0032] S2: Build a multi-level prediction model to predict load, power generation and grid status data, and dynamically update system operation parameters based on the prediction results;

[0033] Specifically, time series data processing is performed using a multi-layer LSTM network, with inputs including historical load, weather data, and calendar features; the LSTM network structure is:

[0034] h t =tanh(W h ·[h (t-1) ,x t ]+b h )

[0035]

[0036] y t =o t ⊙tanh(c t )

[0037] Among them, h t is the hidden state, c t is the unit state, x t is the input, W h is the weight matrix, b h is the bias vector, f t 、i t , o t They are forget gate, input gate and output gate respectively, ⊙ represents Hadamard product;

[0038] Spatial correlation modeling: Use graph convolutional neural network (GCN) to process power grid topology and user distribution information; one convolution operation of GCN is defined as:

[0039]

[0040] Among them, H (l) is the node feature matrix of the lth layer, is the adjacency matrix with self-loops added, D is the degree matrix, and W (l) is the learnable weight matrix, σ is the activation function;

[0041] Build a multi-task learning framework to simultaneously predict load, generation, and grid status, sharing the underlying feature extraction layer;

[0042] Introducing time and space attention to capture the impact of key periods and regions, the calculation formula is:

[0043] α t =softmax(v T tanh(W1h t +W2s (t-1) )

[0044] c t =∑α t h t

[0045] Among them, α t is the attention weight, h t is the encoder hidden state, s (t-1) is the state of the decoder at the previous moment, W1, W2 and v T is a learnable parameter;

[0046] Combine the outputs of multiple models for ensemble learning and output the predicted value through weighted average.

[0047] S3: Intelligent off-grid prediction and switching of system operation mode are performed according to off-grid control data, and off-grid operation optimization control is performed;

[0048] Set the prediction time domain: 1 hour, control interval: 1 minute; obtain state variables: energy storage SOC, bus voltage, power of each device; control variables: energy storage charging and discharging power, photovoltaic power limit, controllable load power;

[0049] Set constraints: equipment power limit, energy storage SOC range, voltage stability requirements; objective function: minimize energy cost, maximize renewable energy utilization, minimize power fluctuation, defined as:

[0050] minJ=∑(w1C t +w2(1-η t )+w3ΔP t )

[0051] Among them, C t is the energy cost at time t, η t is the utilization rate of renewable energy, ΔP t is the power fluctuation, w1, w2, w3 are the weight coefficients.

[0052] Use deep reinforcement learning to learn long-term optimization strategies. State space: including current SOC, load level, power generation, time, etc. Action space: energy storage charging and discharging strategy, load response strategy, photovoltaic power regulation Reward function: comprehensive consideration of energy utilization efficiency, system stability and user comfort

[0053] Perform load classification and priority assessment, and use unsupervised learning algorithms to dynamically classify loads;

[0054] Based on user preferences, energy efficiency and system status, load priorities are dynamically calculated using the analytic hierarchy process.

[0055] Build an adaptive load control strategy. For critical loads: ensure 100% power supply and enable backup power supply when necessary; for adjustable loads: implement demand-side response, such as automatic adjustment of air-conditioning temperature; for delayed loads: intelligently dispatch according to predicted energy surplus.

[0056] Design incentive electricity price plans to encourage users to actively participate in demand response, provide real-time energy usage feedback and suggestions, and display them through mobile apps.

[0057] Design a multi-stage load shedding solution, which is automatically executed according to the system frequency and voltage conditions; achieve rapid load shedding in milliseconds to protect key equipment and energy storage systems.

[0058] Real-time power quality monitoring, using a high-speed data acquisition system with a sampling rate of no less than 20kHz; real-time calculation of total harmonic distortion (TH), voltage fluctuation, flicker, unbalance and other indicators. The calculation formula for total harmonic distortion is:

[0059]

[0060] Among them, V h is the effective value of the hth harmonic voltage, and V1 is the effective value of the fundamental voltage;

[0061] Use wavelet transform to perform harmonic analysis, implement adaptive active filtering, and dynamically adjust filtering parameters.

[0062] Construct a coordinated control strategy to coordinate reactive power compensation and dynamic voltage regulation between the energy storage system and the photovoltaic inverter:

[0063] Realize dynamic voltage regulation with a response time of <10ms; use a fuzzy controller to dynamically adjust the regulation strategy according to load characteristics and voltage deviation. The constant voltage mode uses a PI controller, and the discrete form expression is:

[0064] u(k)=K p e(k)+K i ∑(i)

[0065] Among them, u(k) is the control output, e(k) is the voltage error, K p and K i are the proportional and integral coefficients respectively;

[0066] Carry out smart contracts and use the SOCliity language to write energy trading smart contracts; implement automatic pricing mechanisms and dynamically adjust prices based on supply and demand. The pricing mechanism of smart contracts adopts a dynamic marginal pricing model:

[0067] P t =P base +k(D t -S t ) / S t

[0068] Among them, P t is the electricity price at time t, P base is the basic electricity price, D t is the demand, S t is the supply, k is the adjustment coefficient;

[0069] Adopt the proof-of-stake mechanism to reduce energy consumption; design a reputation-based node selection algorithm to improve system reliability.

[0070] Establish a real-time bidding mechanism to match energy transactions every 5 minutes; realize peer-to-peer energy transactions and support micropayments.

[0071] Build self-repair and fault-tolerant mechanisms for fault detection and diagnosis, use deep signal networks for fault pattern recognition, and achieve fault detection and location.

[0072] A self-healing control algorithm based on a multi-agent system is designed to achieve automatic reconstruction of the distribution network topology and minimize the fault impact area. Fault detection uses an anomaly detection model based on a deep signal network, and the reconstruction error calculation formula is:

[0073]

[0074] Among them, x is the input data and x' is the reconstructed data.

[0075] Implement redundant design and hot standby switching of key components, use model predictive control of the fault-tolerant version of the MP, and consider the possibility of component failure.

[0076] Use transfer learning technology to quickly adapt to new system configurations, achieve online fine-tuning of control strategies, and improve system robustness.

[0077] S4: Continuously monitor the grid status and resume grid-connected operation after the bus voltage stabilizes, and perform off-grid control of photovoltaic storage and charging coordinated based on energy routers.

[0078] The primary voltage of the energy router grid connection point is collected periodically to determine the voltage condition. When the voltage is not equal to 0, the next round of collection will be continued;

[0079] When the voltage is equal to 0, it means that the energy router is out of power. The circuit breaker at the energy router grid connection point is opened, and the energy storage operation mode is switched to the constant voltage mode. The energy storage stabilizes the DC microgrid bus voltage and starts off-grid operation.

[0080] The off-grid control data is collected periodically. If the voltage is greater than the minimum allowable voltage, the energy router resumes power supply, the DC microgrid is in normal operation, the energy storage operation mode is switched to the constant power mode, the energy router grid-connected point circuit breaker is closed, and the energy router stabilizes the DC microgrid bus voltage and resumes grid-connected operation;

[0081] If the voltage is below the minimum allowable voltage, the control power of the photovoltaic and charging piles is calculated based on the energy storage port power and the current power, and the control command is sent to the corresponding device and the off-grid control data is collected again for a second judgment;

[0082] Calculate the control power of photovoltaic and charging piles, perform classified control according to energy storage SOC and power status, switch the energy storage operation mode to constant power mode, close the circuit breaker at the energy router grid connection point, stabilize the DC microgrid bus voltage by the energy router, and restore grid connection operation.

[0083] When the current SOC of the energy storage is within the normal range, the photovoltaic and charging piles maintain the current power. When the current SOC of the energy storage is too high and the energy storage power is discharging, the photovoltaic and charging piles maintain the current power. The calculation formula of the energy storage SOC is:

[0084] SOC t =SOC (t-1) +(η c P c Δt-P d Δt / η d ) / E rated

[0085] Among them, SOC t is the SOC at time t, η c and η d are the charging and discharging efficiencies, P c and P d are charging and discharging power respectively, Δt is the time interval, E rated is the rated capacity;

[0086] When the current SOC of the energy storage is greater than the minimum power SOC L And less than the maximum power SOC H When the photovoltaic and charging pile maintain the current power, the photovoltaic setting power P' g =P g , charging pile set power P' z =P z ;

[0087] When the current SOC of the energy storage is greater than SOC H And P c ≤0, the photovoltaic and charging pile maintain the current power, and the photovoltaic setting power P' g =P g , charging pile set power P' z =P z ;

[0088] When the current SOC of the energy storage is greater than SOC H And P c >0, reduce the photovoltaic power generation power and increase the charging power of the charging pile so that the energy storage power meets P c ≤0, calculate the photovoltaic set power P' g and charging pile set power P' 桩 ;

[0089] When the current SOC of the energy storage is less than SOC H And P c >0, the photovoltaic and charging pile maintain the current power, and the photovoltaic setting power P' g =P g , charging pile set power P' z =P z ;

[0090] When the current SOC of the energy storage is less than SOC H And P c ≤0, increase the photovoltaic power generation power and reduce the charging power of the charging pile to make the energy storage power meet P c >0, calculate the photovoltaic set power P' g and charging pile set power P' z ;

[0091] If the energy storage power P c Less than the energy storage rated power P e , then send the P' calculated in the above steps g and P' z , if P c Greater than or equal to the energy storage rated power P e , then adjust the power setting values ​​of photovoltaic power generation and charging pile so that P c <P e Then send the photovoltaic and charging pile power setting value P' g and P' z ; The adjustment formula is:

[0092] P′ g =P g -min(P c , P g )

[0093] P′ z =P z +min(P c , P g )

[0094] Among them, P′ g and P′ z are the new set powers of photovoltaic and charging pile, P g and P z are the current power of photovoltaic and charging pile, P c Charging power for energy storage.

[0095] Furthermore, this embodiment also provides a photovoltaic storage and charging coordinated off-grid control system based on an energy router, including: an acquisition module, used to collect off-grid control data and environmental parameters of the energy router grid-connected point in real time, pre-process the collected data, and store the processed data in a time series database; a construction module, used to build a multi-level prediction model to predict load, power generation and grid status data, and dynamically update system operation parameters according to the prediction results; an optimization module, used to perform intelligent off-grid prediction and switching of system operation modes according to off-grid control data, and perform off-grid operation optimization control; a control module, used to continuously monitor the grid status and resume grid-connected operation after the bus voltage is stable, and perform photovoltaic storage and charging coordinated off-grid control based on the energy router.

[0096] This embodiment also provides a computer device, which is applicable to the case of a photovoltaic storage and charging coordinated off-grid control method based on an energy router, including: a memory and a processor; the memory is used to store computer executable instructions, and the processor is used to execute computer executable instructions to implement all or part of the steps of the method described in the embodiment of the present invention as proposed in the above embodiment.

[0097] This embodiment also provides a storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the method in any optional implementation of the above embodiment is executed. The storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, disk or optical disk.

[0098] The storage medium proposed in this embodiment and the data storage method proposed in the above embodiment belong to the same inventive concept. The technical details not fully described in this embodiment can be found in the above embodiment, and this embodiment has the same beneficial effects as the above embodiment.

[0099] From the above, it can be seen that this method indirectly controls the charging and discharging of energy storage by controlling the power of photovoltaics and charging piles, so that the energy storage capacity is always kept within an appropriate range, thereby improving the sustainability of off-grid operation; through the coordinated control of photovoltaics and charging piles, the power of the energy storage port does not exceed the rated power at all times, so that the DC microgrid can operate off-grid for a long time, thereby improving the power supply reliability and equipment safety of off-grid operation.

[0100] Example 2

[0101] Referring to Table 1, which is the second embodiment of the present invention, this embodiment provides a photovoltaic storage and charging coordinated off-grid control method based on an energy router. In order to verify the beneficial effects of the present invention, scientific demonstration is carried out through economic benefit calculation and simulation experiments.

[0102] Table 1 Test data table

[0103]

[0104] As can be seen from the table, the average system response time of this method is faster and has higher prediction accuracy than the existing technical solutions. By controlling the power of photovoltaics and charging piles, the charging and discharging of energy storage is indirectly controlled, so that the energy storage capacity is always kept within an appropriate range, thereby improving the sustainability of off-grid operation; through the coordinated control of photovoltaics and charging piles, the power of the energy storage port does not exceed the rated power, so that the DC microgrid can operate off-grid for a long time, improving the power supply reliability and equipment safety of off-grid operation.

[0105] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A photovoltaic storage and charging coordinated off-grid control method based on an energy router, characterized by: include, Collect the off-grid control data and environmental parameters of the energy router grid-connected point in real time, pre-process the collected data, and store the processed data in the time series database; Construct a multi-level prediction model to predict load, power generation and grid status data, and dynamically update system operating parameters based on the prediction results; Intelligent off-grid prediction and switching of system operation modes are performed based on off-grid control data, and off-grid operation optimization control is performed; The grid status is continuously monitored and grid-connected operation is restored after the bus voltage stabilizes, and off-grid control of photovoltaic storage and charging coordination is carried out based on the energy router.

2. The off-grid control method for photovoltaic storage and charging based on energy router according to claim 1 is characterized in that: The off-grid control data includes grid connection point voltage, photovoltaic power, charging pile power and energy storage power; the environmental parameters include temperature, humidity, light intensity and wind speed.

3. The off-grid control method for photovoltaic storage and charging based on energy router according to claim 2 is characterized in that: The construction of the multi-level prediction model includes the following steps: Use a multi-layer LSTM network to process the time series data of off-grid control data; Perform spatial correlation modeling and use graph convolutional neural networks to process power grid topology and user distribution information; Build a multi-task learning framework to simultaneously predict load, generation, and grid status, sharing the underlying feature extraction layer; Introducing temporal and spatial attention to capture the impact of critical periods and regions; Combine the outputs of multiple models for ensemble learning and output the predicted value through weighted average.

4. The off-grid control method for photovoltaic storage and charging based on energy router according to claim 3 is characterized in that: The off-grid operation optimization control comprises the following steps: Set the prediction time domain and control interval, and obtain state variables and control variables; Set off-grid operation optimization control constraints and objective functions to minimize energy costs, maximize renewable energy utilization, and minimize power fluctuations; Use unsupervised learning algorithms to dynamically classify loads and dynamically calculate load priorities based on user preferences, energy efficiency, and system status; Use adaptive load control strategy to dispatch and control loads, monitor power quality in real time, use high-speed data acquisition system to calculate total harmonic distortion index in real time, use wavelet transform to perform harmonic analysis and dynamically adjust filter parameters; Construct a collaborative control strategy to coordinate reactive power compensation and dynamic voltage regulation between the energy storage system and the photovoltaic inverter; Use the SOCliity language to write smart contracts for energy transactions and dynamically adjust prices based on supply and demand; Perform fault detection and location, and use transfer learning technology to perform online fine-tuning of control strategies.

5. The off-grid control method for photovoltaic storage and charging based on energy router according to claim 4 is characterized in that: The pricing mechanism of the smart contract adopts a dynamic marginal pricing model, which is expressed as: P t =P base +k(D t -S t ) / S t Among them, P t is the electricity price at time t, P base is the basic electricity price, D t is the demand, S t is the supply, k is the adjustment coefficient; The fault detection adopts an anomaly detection model based on a deep signal network, and the calculation formula of the reconstruction error is: Among them, x is the input data and x' is the reconstructed data.

6. The off-grid control method for photovoltaic storage and charging based on energy router according to claim 5 is characterized in that: The off-grid control of photovoltaic storage and charging coordination based on energy router includes the following steps: The primary voltage of the energy router grid connection point is collected periodically to determine the voltage condition. When the voltage is not equal to 0, the next round of collection will be continued; When the voltage is equal to 0, it means that the energy router is out of power. The circuit breaker at the energy router grid connection point is opened, and the energy storage operation mode is switched to the constant voltage mode. The energy storage stabilizes the DC microgrid bus voltage and starts off-grid operation. The off-grid control data is collected periodically. If the voltage is greater than the minimum allowable voltage, the energy router resumes power supply, the DC microgrid is in normal operation, the energy storage operation mode is switched to the constant power mode, the energy router grid-connected point circuit breaker is closed, and the energy router stabilizes the DC microgrid bus voltage and resumes grid-connected operation; If the voltage is below the minimum allowable voltage, the control power of the photovoltaic and charging piles is calculated based on the energy storage port power and the current power, and the control command is sent to the corresponding device and the off-grid control data is collected again for a second judgment; Calculate the control power of photovoltaic and charging piles, perform classified control according to energy storage SOC and power status, switch the energy storage operation mode to constant power mode, close the circuit breaker at the energy router grid connection point, stabilize the DC microgrid bus voltage by the energy router, and restore grid connection operation.

7. The off-grid control method for photovoltaic storage and charging based on energy router according to claim 6 is characterized in that: The classification control according to the energy storage SOC and power state includes the following steps: When the minimum power SOC L <Current SOC of energy storage<Maximum power SOC H Or the current SOC of the energy storage is greater than SOC H And P c ≤0 or the current SOC of energy storage is less than SOC H And P c >0, the photovoltaic and charging piles maintain the current power; When the current SOC of the energy storage is greater than SOC H And P c >0, reduce the photovoltaic power generation power, increase the charging power of the charging pile, and recalculate the energy storage power so that the energy storage power meets P c ≤0, the photovoltaic set power and charging pile set power are calculated; When the current SOC of the energy storage is less than SOC H And P c ≤0, increase the photovoltaic power generation power, reduce the charging power of the charging pile, and recalculate the energy storage power so that the energy storage power meets P c >0, the photovoltaic setting power and charging pile setting power are calculated; If the energy storage power P c <Energy storage rated power P e When the calculated photovoltaic power setting and charging pile power setting are sent directly; If the energy storage power P c ≥ Rated power of energy storage P e When the photovoltaic power setting value and the charging pile power setting value are adjusted, the energy storage power is recalculated so that the energy storage power P c < Rated power of energy storage P e After that, the calculated photovoltaic set power and charging pile set power are issued.

8. A photovoltaic storage and charging coordinated off-grid control system based on an energy router, based on the photovoltaic storage and charging coordinated off-grid control method based on an energy router according to any one of claims 1 to 7, characterized in that: include, The acquisition module is used to collect the off-grid control data and environmental parameters of the energy router grid connection point in real time, pre-process the collected data, and store the processed data in the time series database; The construction module is used to construct a multi-level prediction model to predict load, power generation and grid status data, and dynamically update system operation parameters based on the prediction results; The optimization module is used to perform intelligent off-grid prediction and switch the system operation mode according to the off-grid control data, and perform off-grid operation optimization control; The control module is used to continuously monitor the grid status and resume grid-connected operation after the bus voltage stabilizes, and to perform off-grid control of photovoltaic storage and charging coordination based on the energy router.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the off-grid control method for photovoltaic storage and charging coordination based on an energy router are implemented in any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the photovoltaic storage and charging coordinated off-grid control method based on an energy router according to any one of claims 1 to 7 are implemented.

Images