Dynamic energy optimization scheduling method and system for temporarily built optical storage system

Abstract

The invention aims to provide a dynamic energy optimization scheduling method and system for a temporarily-built optical storage system, and belongs to the technical field of temporarily-built optical storage system control, and the method comprises the steps: obtaining the photovoltaic power generation power, the energy storage charge state and the load demand in real time, judging the power balance state, and controlling the cooperative operation of each unit according to the power balance state. When photovoltaic power generation is sufficient, redundant electric energy is stored in the energy storage unit; if not enough, energy storage and electricity supplementation are preferentially carried out, and the diesel generator is started if not enough. The system also combines historical data and a neural network to predict a future scheduling strategy, and optimizes an energy storage charging and discharging plan. In addition, non-critical loads are identified through the intelligent electric meter, and the power supply priority is dynamically adjusted. The system improves the operation efficiency and stability of the optical storage system, prolongs the service life of equipment, and is suitable for temporary building facility power supply scenes.

Description

Technical Field

[0001] The present invention relates to the technical field of control of a temporary photovoltaic storage system, and in particular to a dynamic energy optimization scheduling method and system for a temporary photovoltaic storage system. Background Art

[0002] Photovoltaic energy storage systems are often used to provide power in temporary buildings to reduce reliance on diesel generators. However, due to the large fluctuations in electricity load in temporary buildings and the significant impact of weather on photovoltaic power generation, existing energy scheduling strategies for photovoltaic storage systems often struggle to achieve efficient and stable operation.

[0003] Traditional scheduling methods for photovoltaic storage systems typically use fixed threshold control. For example, when photovoltaic power generation is lower than the load demand, the diesel generator is directly started to supplement the power. This approach has two major problems: first, it does not fully consider the real-time charge state of the energy storage unit, which may lead to over-discharge of energy storage or frequent start-up and shutdown of the diesel generator, reducing the life of the equipment; second, it lacks dynamic management of load priorities. When the power supply is tight, critical loads may be mistakenly cut off, affecting the normal operation of temporary buildings. In addition, the photovoltaic arrays of temporary buildings often have unstable output due to factors such as construction obstruction and dust coverage. Existing methods do not effectively integrate real-time monitoring data and prediction algorithms, making it difficult to achieve forward-looking energy scheduling.

[0004] Therefore, how to design a dynamic optimization energy scheduling method based on the real-time matching of photovoltaic power generation, energy storage status and load demand has become a technical problem that needs to be urgently solved in temporary building photovoltaic storage systems. Summary of the Invention

[0005] The purpose of the present invention is to overcome the deficiencies in the prior art and to provide a method, system, electronic equipment and computer storage medium for dynamic energy optimization scheduling of a temporary solar-storage system.

[0006] A first aspect of the present invention provides a dynamic energy optimization scheduling method for a temporary solar-storage system, comprising: Obtain the real-time power generation of the photovoltaic power generation unit, the current state of charge of the energy storage unit, and the power demand of the load unit; Determining a power balance state according to a difference between the real-time generated power and the power demand, the power balance state including a first state and a second state, wherein the first state is that the photovoltaic generated power is greater than or equal to the power demand, and the second state is that the photovoltaic generated power is less than the power demand; When in the first state, controlling the photovoltaic power generation unit to supply power to the load unit and storing the remaining electric energy in the energy storage unit; When in the second state, determining whether the current state of charge of the energy storage unit is higher than a preset threshold, and if so, controlling the energy storage unit to supply power to the load unit; If the current state of charge is not higher than the preset threshold, the diesel generator is started to supply power.

[0007] Furthermore, obtaining the real-time generated power includes: The DC side output parameters are collected through the current sensor and voltage sensor of the photovoltaic array; The real-time generated power is calculated based on the DC side output parameters, and a sliding average filtering algorithm is used to eliminate instantaneous fluctuations.

[0008] Furthermore, controlling the energy storage unit to supply power to the load unit includes: Calculating the sustainable power supply time according to the remaining capacity of the energy storage unit and the shortfall power of the load unit; When the sustainable power supply time is less than a preset time threshold, the power supply priority of non-critical loads is lowered.

[0009] Furthermore, the identification of non-critical loads includes: A preset load classification table including priority marks for air conditioning equipment, lighting equipment, and construction equipment; The current of each branch is collected by a smart meter, and the load to be cut off is determined by matching the load classification table.

[0010] Furthermore, the starting of the diesel generator includes: Calculate the optimal output power of the diesel generator, where the dynamic adjustment coefficient ranges from 0.8 to 1.2; The speed of the diesel generator is adjusted according to the optimal output power.

[0011] Furthermore, it also includes: Establishing a historical output curve and a historical load curve of the photovoltaic power generation unit; Based on the historical output curve and the historical load curve, a neural network model is used to predict the photovoltaic and energy storage coordinated scheduling strategy for future time periods.

[0012] Furthermore, the scheduling strategy for predicting future time periods includes: Inputting weather forecast data into the neural network model to obtain a photovoltaic output forecast value; According to the difference between the photovoltaic output forecast value and the load forecast value, the charging and discharging plan of the energy storage unit is adjusted in advance.

[0013] A second aspect of the present invention provides a dynamic energy optimization scheduling system for a temporary solar-storage system, used in any of the above methods, comprising: Data acquisition module, used to obtain real-time operating parameters of photovoltaic power generation units, energy storage units and load units; A state judgment module, used to determine the power balance state of the system according to the real-time operating parameters; A scheduling execution module is used to control the coordinated operation of the photovoltaic power generation unit, the energy storage unit and the diesel generator according to the power balance state.

[0014] The data acquisition module specifically includes: Photovoltaic monitoring submodule, used to collect group cascade output parameters and detect shadow occlusion; An energy storage management submodule, configured to calculate the state of charge and health status of the energy storage unit in real time; The communication module adopts wireless networking technology to connect the distributed sensors, and the transmission period of the communication module is dynamically adjusted according to the change rate of the load unit.

[0015] A third aspect of the present invention provides an electronic device comprising: at least one processor, a memory, and a computer program stored in the memory and executable on the at least one processor, wherein the processor executes the computer program to implement any of the methods described above.

[0016] A fourth aspect of the present invention provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and the computer program is executed by a processor to implement any of the above methods.

[0017] In summary, compared with the prior art, the solution of the present invention obtains the real-time power generation of the photovoltaic power generation unit, the current state of charge of the energy storage unit, and the power demand of the load unit, and determines the power balance state based on the difference between the real-time power generation and the power demand. When in the first state, the photovoltaic power generation unit is controlled to supply power to the load unit, and the remaining electric energy is stored in the energy storage unit. When in the second state, it is determined whether the current state of charge of the energy storage unit is higher than the preset threshold. If it is higher, the energy storage unit is controlled to supply power to the load unit, otherwise the diesel generator is started to supply power. The solution of the present invention can dynamically match energy demand and supply by monitoring the operating status of each unit in real time, thereby achieving the effect of improving the energy utilization efficiency of the temporary photovoltaic storage system, extending the service life of the equipment, and reducing operating costs. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments of the present invention and, together with the description, serve to explain the principles of the present invention.

[0019] The present invention can be more clearly understood from the following detailed description with reference to the accompanying drawings, in which: Figure 1 This is an overall flow chart of a dynamic energy optimization scheduling method for a temporary solar-storage system provided by an embodiment of the present invention; Figure 2 This is a detailed flow chart for creating a data acquisition process for a dynamic energy optimization scheduling method for a temporary solar-storage system provided by an embodiment of the present invention; Figure 3 This is a detailed flow chart of the energy storage and power replenishment link of the dynamic energy optimization scheduling method for the temporary solar storage system provided by an embodiment of the present invention; Figure 4 This is a detailed flow chart of the diesel generator power supply link of the dynamic energy optimization scheduling method for the temporary solar storage system provided by an embodiment of the present invention; Figure 5 This is a detailed flow chart of the prediction and optimization steps of the dynamic energy optimization scheduling method for a temporary solar-storage system provided by an embodiment of the present invention: Figure 6 This is a diagram of the dynamic energy optimization scheduling system architecture of the temporary solar storage system provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0020] The technical solution of the present invention is described in detail below through the accompanying drawings and specific embodiments. It should be understood that the embodiments of the present application and the specific features in the embodiments are detailed descriptions of the technical solution of the present application, rather than limitations of the technical solution of the present application. In the absence of conflict, the technical features in the embodiments of the present application and the embodiments can be combined with each other. The following embodiments are only used to more clearly illustrate the technical solution of the present invention and are not intended to limit the scope of protection of the present invention.

[0021] The term "and / or" in this document simply describes a relationship between related objects, indicating that three possible relationships exist. For example, "A and / or B" can mean: A exists alone, A and B exist simultaneously, or B exists alone. Additionally, the character " / " in this document generally indicates an "or" relationship between the related objects.

[0022] It should be understood that although the terms first, second, third, etc. may be used to describe ... in the embodiments of the present application, these ... should not be limited to these terms. These terms are only used to distinguish .... For example, without departing from the scope of the embodiments of the present application, the first ... may also be referred to as the second ..., and similarly, the second ... may also be referred to as the first .... Depending on the context, the words "if" and "if" as used herein can be interpreted as "at the time of ..." or "when ..." or "in response to determination" or "in response to detection". Similarly, depending on the context, the phrases "if it is determined" or "if (the stated condition or event) is detected" can be interpreted as "when it is determined" or "in response to determination" or "when (the stated condition or event) is detected" or "in response to detection (the stated condition or event)". It should also be noted that the terms "include", "comprising" or any other variants thereof are intended to cover non-exclusive inclusion, so that a product or system including a series of elements includes not only those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such product or system. Without further constraints, an element defined by the phrase "comprises a . . . " does not preclude the existence of additional identical elements in the product or system that includes the element.

[0023] See Figure 1 As shown, an embodiment of the present invention discloses a dynamic energy optimization scheduling method for a temporary photovoltaic storage system, the method comprising the following steps: Get the real-time power generation of photovoltaic power generation units in temporary construction areas , the current state of charge of the energy storage unit , and the power demand of the load unit ; According to the real-time power generation With the electricity demand The power balance state is determined by the difference between the first state and the second state, wherein the first state is , the second state is ; When in the first state, the photovoltaic power generation unit is controlled to supply power to the load unit and the remaining electric energy is stored in the energy storage unit. The calculation formula of the remaining electric energy is: ; When in the second state, determine the current Is it higher than the preset threshold? If it is higher than, the energy storage unit is controlled to supply power to the load unit, and the power supply is ,in is the maximum discharge power of the energy storage unit; if the current Not higher than the preset threshold , then start the diesel generator to supply power.

[0024] As an embodiment, controlling the energy storage unit to supply power to the load unit includes: Calculating the sustainable power supply time according to the remaining capacity of the energy storage unit and the shortfall power of the load unit; When the sustainable power supply time is less than the preset time threshold, load hierarchical control is performed: Obtaining a preset load priority table, wherein the priority table divides loads into critical loads, important loads, and general loads; Priority should be given to ensuring power supply to critical loads, and rotational shutdown control should be implemented for general loads.

[0025] By real-time monitoring of photovoltaic power generation and load demand and establishing a dual-state judgment mechanism, precise scheduling of photovoltaic storage system energy is achieved, effectively improving energy utilization efficiency.

[0026] Further, if Figure 2 As shown, the real-time power generation is obtained The method includes: collecting DC side output parameters through the current sensor and voltage sensor of the photovoltaic array; calculating the real-time power generation according to the DC side output parameters. , and uses a sliding average filtering algorithm to eliminate instantaneous fluctuations. Using a sliding average filtering algorithm to process photovoltaic power generation data can significantly reduce the impact of power fluctuations caused by sudden weather changes or equipment shading, and improve stability. The sliding average filtering algorithm includes: Set the time window length to N sampling periods, N ≥ 3; Calculate the average power of the current moment and the previous N-1 moments as the output value after filtering; When it is detected that the fluctuation amplitude of M consecutive sampling points exceeds the set threshold, the length of the time window is dynamically reduced, M ≥ 2; When it is detected that the power change rate is lower than the set threshold value for a predetermined time, the length of the time window is expanded.

[0027] Optionally, the sliding average filtering process further includes: Set up an outlier detection mechanism. When a single sample value deviates from the current window average by more than 3 standard deviations, it is replaced by the previous valid value. Physical constraints are imposed on the filtered data to ensure that the output value does not exceed the rated power of the PV unit and is not less than zero.

[0028] Specifically, if Figure 3 As shown, the control of the energy storage unit to supply power to the load unit includes: according to the remaining capacity of the energy storage unit and the shortfall power of the load unit , calculate the sustainable power supply time ; When the sustainable power supply time Less than the preset time threshold When power is insufficient, the power supply priority of non-critical loads is lowered. By calculating the sustainable power supply time of the energy storage system and combining it with load priority management, the power supply strategy is intelligently adjusted when there is a power shortage, which not only ensures the power supply of critical loads but also avoids excessive discharge of the energy storage system.

[0029] Furthermore, the identification of non-critical loads includes: a pre-set load classification table, which contains priority tags for air-conditioning equipment, lighting equipment, and construction equipment; collecting currents from each branch through a smart meter, matching the load classification table to determine the load to be cut off, and based on the preset load classification table and real-time monitoring data, intelligent hierarchical management of power loads is achieved, ensuring that the operation of important equipment is prioritized when power supply is tight.

[0030] Specifically, if Figure 4 As shown, the starting of the diesel generator includes: calculating the optimal output power of the diesel generator ,in is the dynamic adjustment coefficient and ; Adjusting the speed of the diesel generator according to the optimal output power reduces unnecessary fuel consumption and equipment wear while maintaining the power supply reliability of the system.

[0031] Further, if Figure 5 As shown, the method further includes: establishing a historical output curve of the photovoltaic power generation unit and load history curve Based on the historical output curve and the load history curve , a neural network model is used to predict the photovoltaic and storage coordinated scheduling strategy in the future period, and the prediction model is trained using historical data to achieve accurate prediction of energy supply and demand in the future period, providing forward-looking guidance for system scheduling.

[0032] As an embodiment, an LSTM neural network is used to predict the photovoltaic and energy storage coordinated scheduling strategy for future time periods. The LSTM neural network includes: Input layer, receives historical power series data with a time step of T, T ≥ 24; The first LSTM layer contains 128 neurons and the activation function is tanh; The second LSTM layer contains 64 neurons and the activation function is tanh; Fully connected layer, converting the LSTM layer output into predicted power values; Output layer, outputs the power forecast sequence for the next 24 hours; Use mean square error as the loss function and Adam optimizer for model training; Preferably, the training of the LSTM neural network further includes: The input historical power data is standardized so that its mean is 0 and its variance is 1; Add a Dropout layer between the LSTM layers, and set the dropout rate to 0.2; Use early stopping to prevent overfitting and terminate training when the validation set loss does not decrease for 5 consecutive epochs; Optionally, weather forecast data is used as additional input features, including irradiance, cloud cover and temperature forecast values ​​for the next 24 hours, and an attention mechanism is used to weight the weather forecast features to optimize the power prediction sequence.

[0033] As an embodiment, the scheduling strategy for predicting future time periods includes: inputting weather forecast data into the neural network prediction model, preferably into the LSTM neural network, to obtain the photovoltaic output prediction value ;according to and load forecast value The difference between the two is used to adjust the charge and discharge plan of the energy storage unit in advance, and the scheduling strategy is optimized in combination with weather forecast data, which effectively addresses the uncertainty of photovoltaic power generation and improves the system's adaptability to weather changes.

[0034] As an example, Figure 6 As shown, the present invention provides a dynamic energy optimization scheduling system for a temporary photovoltaic storage system, including: a data acquisition module for acquiring real-time operating parameters of a photovoltaic power generation unit, an energy storage unit and a load unit; a state judgment module for determining the system power balance state according to the real-time operating parameters; a scheduling execution module for controlling the coordinated operation of the photovoltaic power generation unit, the energy storage unit and the diesel generator according to the power balance state; the scheduling execution module includes a first control unit and a second control unit, the first control unit is used to perform energy storage charging operations when photovoltaic power generation is in excess, and the second control unit is used to perform energy storage discharging or diesel engine start-stop operations when power generation is insufficient.

[0035] The data acquisition module includes: Photovoltaic monitoring submodule, used to collect group cascade IV curve and detect shadow occlusion; Energy storage management submodule, used to calculate the energy storage unit in real time and state of health SOH; The communication module uses LoRa wireless networking technology to connect distributed sensors; the transmission period of the communication module is dynamically adjusted according to the change rate of the load unit.

[0036] The present invention also discloses an electronic device, comprising: at least one processor, a memory, and a computer program stored in the memory and executable on the at least one processor, wherein the processor executes the computer program to implement the method described in any one of the aforementioned embodiments.

[0037] The present invention also discloses a computer-readable storage medium, which stores a computer program. The computer program is executed by a processor to implement the method as described in any of the above embodiments, and has functional modules and beneficial effects corresponding to the execution method.

[0038] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the technical principles of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. A dynamic energy optimization scheduling method for a temporary solar-storage system, characterized in that: include: Obtain the real-time power generation of the photovoltaic power generation unit, the current state of charge of the energy storage unit, and the power demand of the load unit; Determining a power balance state according to a difference between the real-time generated power and the power demand, the power balance state including a first state and a second state, wherein the first state is that the photovoltaic generated power is greater than or equal to the power demand, and the second state is that the photovoltaic generated power is less than the power demand; When in the first state, controlling the photovoltaic power generation unit to supply power to the load unit and storing the remaining electric energy in the energy storage unit; When in the second state, determining whether the current state of charge of the energy storage unit is higher than a preset threshold, and if so, controlling the energy storage unit to supply power to the load unit; If the current state of charge is not higher than the preset threshold, the diesel generator is started to supply power.

2. The dynamic energy optimization scheduling method for a temporary solar-storage system according to claim 1 is characterized in that: The obtaining of real-time generated power includes: The DC side output parameters are collected through the current sensor and voltage sensor of the photovoltaic array; The real-time generated power is calculated based on the DC side output parameters, and a sliding average filtering algorithm is used to eliminate instantaneous fluctuations.

3. The dynamic energy optimization scheduling method for a temporary solar-storage system according to claim 1 is characterized in that: Controlling the energy storage unit to supply power to the load unit includes: Calculating the sustainable power supply time based on the remaining capacity of the energy storage unit and the shortfall power of the load unit; When the sustainable power supply time is less than a preset time threshold, the power supply priority of non-critical loads is reduced.

4. The dynamic energy optimization scheduling method for a temporary solar-storage system according to claim 3 is characterized in that: The identification of non-critical loads includes: A preset load classification table including priority marks for air conditioning equipment, lighting equipment, and construction equipment; The current of each branch is collected by a smart meter, and the load to be cut off is determined by matching the load classification table.

5. The dynamic energy optimization scheduling method for a temporary solar-storage system according to claim 1, characterized in that: The starting diesel generator comprises: Calculate the optimal output power of the diesel generator, where the dynamic adjustment coefficient ranges from 0.8 to 1.2; The speed of the diesel generator is adjusted according to the optimal output power.

6. The dynamic energy optimization scheduling method for a temporary solar-storage system according to claim 1, characterized in that: Also includes: Establishing a historical output curve and a historical load curve of the photovoltaic power generation unit; Based on the historical output curve and the historical load curve, a neural network model is used to predict the photovoltaic and energy storage coordinated scheduling strategy for future time periods.

7. The dynamic energy optimization scheduling method for a temporary solar-storage system according to claim 6, characterized in that: The scheduling strategy for predicting future time periods includes: Inputting weather forecast data into the neural network model to obtain a photovoltaic output forecast value; According to the difference between the photovoltaic output forecast value and the load forecast value, the charging and discharging plan of the energy storage unit is adjusted in advance.

8. A dynamic energy optimization scheduling system for a temporary solar-storage system, used in the method according to any one of claims 1 to 7, characterized in that: include: Data acquisition module, used to obtain real-time operating parameters of photovoltaic power generation units, energy storage units and load units; A state judgment module, used to determine the power balance state of the system according to the real-time operating parameters; a scheduling execution module, configured to control the coordinated operation of the photovoltaic power generation unit, the energy storage unit, and the diesel generator according to the power balance state; The data acquisition module specifically includes: Photovoltaic monitoring submodule, used to collect group cascade output parameters and detect shadow occlusion; An energy storage management submodule, configured to calculate the state of charge and health status of the energy storage unit in real time; The communication module adopts wireless networking technology to connect the distributed sensors, and the transmission period of the communication module is dynamically adjusted according to the change rate of the load unit.

9. An electronic device comprising: At least one processor, a memory, and a computer program stored in the memory and executable on the at least one processor, wherein the processor executes the computer program to implement the method according to any one of claims 1 to 7.

10. A computer-readable storage medium storing a computer program, characterized in that: The computer program is executed by a processor to implement the method according to any one of claims 1 to 7.

Images