User-side energy storage discharge control method, computer equipment and energy storage control system

Abstract

The invention provides a method and a computer program product for user side energy storage discharge control, computer equipment and an energy storage control system, the method comprises the following steps: setting a strategy execution period and prediction periods, the strategy execution period comprising a plurality of prediction periods; in each prediction period, performing power prediction by using a neural network algorithm model; in each prediction period, performing load prediction by using a neural network algorithm model; generating a discharge control strategy in the strategy execution period according to the load prediction and the power prediction in each prediction period; and controlling the charging and discharging operation in the strategy execution period by using the discharging control strategy. According to the technical scheme provided by the invention, a refined energy storage discharge control method can be formulated, and user revenue maximization is realized.

Description

Technical Field

[0001] The present invention relates to the field of photovoltaic energy storage technology, and in particular to a method and computer program product, computer equipment and energy storage control system for user-side energy storage discharge control. Background Art

[0002] As the user-side energy storage market is developing rapidly, it has become an important growth point in the energy storage industry. The rapid development of user-side energy storage has benefited from technological progress, cost reduction, policy support and market demand growth. With the deepening of power market reform and the continuous innovation of energy storage technology, it is expected that the user-side energy storage market will continue to maintain a rapid development trend.

[0003] With the decline in prices of industrial and commercial energy storage equipment and the improvement of technical performance, the user-side energy storage market is growing rapidly, especially in Zhejiang, Jiangsu, Guangdong and other places. The revenue model of user-side energy storage is mainly based on the arbitrage of peak-valley electricity price differences, as well as various supplementary benefits such as demand-side response and distributed photovoltaic consumption. User-side energy storage mainly reduces electricity costs by arbitrage by utilizing the difference in peak-valley electricity prices. Especially in areas with large peak-valley electricity price differences, user-side energy storage projects have better profitability.

[0004] The current technical problem is that the revenue source of user-side energy storage is relatively single, relying mainly on arbitrage of peak-valley electricity price differences. The decline in industrial and commercial electricity prices and the narrowing of the peak-valley price difference will further affect its profitability.

[0005] To this end, a technical solution is needed to maximize benefits by formulating a refined energy storage discharge control method. Summary of the invention

[0006] The present invention aims to provide a method and computer program product, computer equipment and energy storage control system for user-side energy storage discharge control, which can formulate a refined energy storage discharge control method to maximize user benefits.

[0007] According to one aspect of the present invention, a method for controlling energy storage discharge at a user side is provided, the method comprising:

[0008] Setting a method execution cycle and a prediction cycle, wherein the method execution cycle includes a plurality of prediction cycles;

[0009] In each of the prediction cycles, a neural network algorithm model is used to perform power prediction;

[0010] In each of the forecasting cycles, a neural network algorithm model is used to perform load forecasting;

[0011] Generating a discharge control strategy within the strategy execution cycle according to the load forecast and the power forecast within each of the forecast cycles;

[0012] The discharge control strategy is applied to control the charge and discharge operations within the strategy execution cycle.

[0013] According to some embodiments, in each of the prediction cycles, a neural network algorithm model is applied to perform power prediction, including:

[0014] According to the prediction cycle, similar days in historical data are selected as samples based on meteorological factors such as the season of the day to be predicted, the daily weather type, the daily maximum temperature, the daily minimum temperature, and humidity, and the like, to train the neural network algorithm model;

[0015] The neural network model performs power prediction according to the meteorological data of the day to be measured to obtain a power prediction result.

[0016] According to some embodiments, in each of the forecasting cycles, a neural network algorithm model is applied to perform load forecasting, including:

[0017] According to the prediction cycle, similar day samples in the historical data are screened out based on the month, week type, daily maximum temperature, and daily minimum temperature of the day to be tested, and the neural network algorithm model is trained;

[0018] The neural network model performs load forecasting according to the meteorological data of the day to be measured to obtain a load forecasting result.

[0019] According to some embodiments, generating a discharge control strategy within the strategy execution cycle according to the load forecast and the power forecast within each of the forecast cycles includes:

[0020] Calculating the difference between the power forecast result and the load forecast result within the same forecast period;

[0021] summing the differences of the prediction periods contained in the strategy execution period to obtain a first prediction result of the strategy execution period;

[0022] The control strategy is generated according to the first prediction result.

[0023] According to some embodiments, generating the control strategy according to the first prediction result includes:

[0024] According to the energy storage installed capacity of the user-side energy storage system, a first charge and discharge judgment threshold is set;

[0025] According to the relationship between the first prediction result and the first charge and discharge judgment threshold, discharge is performed according to the peak shaving and valley filling time period configured for the user-side energy storage system.

[0026] According to some embodiments, the method further includes: configuring a peak shaving and valley filling time period, and controlling the discharge power to be a difference between 0.9 times the energy storage installed capacity and the first prediction result divided by one hour.

[0027] According to some embodiments, the method further comprises:

[0028] Protection strategy, determine whether the user-side energy storage system is in a normal state, and perform fault processing if a fault occurs.

[0029] According to another aspect of the present invention, a computer program product is provided, characterized in that it comprises: a computer program, and when the computer program is executed by a processor, it implements any of the methods described above.

[0030] According to another aspect of the present invention, there is provided a computing device, comprising:

[0031] Processor; and

[0032] A memory storing a computer program, which, when executed by the processor, enables the processor to execute any of the methods described above.

[0033] According to another aspect of the present invention, there is provided a non-transitory computer-readable storage medium having computer-readable instructions stored thereon, and when the instructions are executed by a processor, the processor is caused to execute any of the above methods.

[0034] According to another aspect of the present invention, there is provided an energy storage control system, which, when in operation, executes the discharge control method as described in any one of the above items.

[0035] According to an embodiment of the present invention, the discharge control method in the scheme of the present invention performs accurate playback point control on the user-side energy storage system by applying the protection strategy and the control strategy generated by the energy storage charge and discharge power calculation module to maximize user benefits. By applying the neural network algorithm model to accurately predict power and load, energy storage and release are performed more effectively, energy waste is reduced, overall energy utilization efficiency is improved, and the grid demand is better responded to.

[0036] According to some embodiments, the scheme of the present invention obtains a precise control strategy through the neural network calculation model, thereby controlling the energy storage device to perform charging and discharging operations, realizing peak shaving and valley filling of the grid load, optimizing the operation of the power system, reducing unnecessary charging and discharging operations, extending battery life, reducing operation and maintenance costs, and improving the economic benefits of user-side energy storage projects.

[0037] It is to be understood that the foregoing general description and the following detailed description are exemplary only and are not restrictive of the invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings required for describing the embodiments are briefly introduced below.

[0039] Figure 1 A flow chart of a method for controlling energy storage discharge at a user side according to an example embodiment is shown.

[0040] Figure 2 A schematic diagram of the architecture of a user-side energy storage system according to an example embodiment is shown.

[0041] Figure 3 A simple flow chart of a method for controlling energy storage discharge at a user side according to an example embodiment is shown.

[0042] Figure 4 A schematic diagram of a method for calculating the energy storage charging and discharging power of a user-side energy storage system according to an example embodiment is shown.

[0043] Figure 5 A block diagram of a computing device according to an example embodiment of the invention is shown. DETAILED DESCRIPTION

[0044] Example embodiments will now be described more fully with reference to the accompanying drawings. However, example embodiments can be implemented in many forms and should not be construed as limited to the embodiments set forth herein; rather, these embodiments are provided so that the present invention will be comprehensive and complete and fully convey the concepts of the example embodiments to those skilled in the art. The same reference numerals in the figures represent the same or similar parts, and thus their repeated description will be omitted.

[0045] In addition, the described features, structures or characteristics may be combined in one or more embodiments in any suitable manner. In the following description, many specific details are provided to provide a full understanding of the embodiments of the present invention. However, those skilled in the art will appreciate that the technical solution of the present invention can be practiced without one or more of the specific details, or other methods, components, devices, steps, etc. may be adopted. In other cases, known methods, devices, implementations or operations are not shown or described in detail to avoid blurring various aspects of the present invention.

[0046] The block diagrams shown in the accompanying drawings are merely functional entities and do not necessarily correspond to physically independent entities. That is, these functional entities may be implemented in software form, or in one or more hardware modules or integrated circuits, or in different networks and / or processor devices and / or microcontroller devices.

[0047] The flowcharts shown in the accompanying drawings are only exemplary and do not necessarily include all the contents and operations / steps, nor must they be executed in the order described. For example, some operations / steps can be decomposed, and some operations / steps can be combined or partially combined, so the actual execution order may change according to actual conditions.

[0048] It should be understood that although the terms first, second, third, etc. may be used herein to describe various components, these components should not be limited by these terms. These terms are used to distinguish one component from another component. Therefore, the first component discussed below can be referred to as the second component without departing from the teachings of the present inventive concept. As used herein, the term "and / or" includes any one of the associated listed items and all combinations of one or more.

[0049] The user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in the present invention are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with the relevant laws, regulations and standards of relevant countries and regions, and provide corresponding operation entrances for users to choose to authorize or refuse.

[0050] Those skilled in the art will appreciate that the drawings are merely schematic diagrams of example embodiments, and the modules or processes in the drawings are not necessarily necessary for implementing the present invention, and therefore cannot be used to limit the protection scope of the present invention.

[0051] As national policies encourage the development of user-side energy storage, such as the "Notice on Further Improving the Work of Power Grid Enterprises Purchasing Power on Behalf of Others", industrial and commercial users are encouraged to directly participate in the electricity market and use energy storage systems to reduce electricity costs. National standards, industry standards and local standards related to new energy storage are gradually being improved, pushing user-side energy storage from disorderly development to an orderly development stage. The global user-side energy storage market is also growing. In 2021, user-side energy storage accounted for a certain proportion of the world's new energy storage installed capacity, and global installed capacity is expected to increase significantly in 2026. In China's newly commissioned electrochemical energy storage in 2021, user-side energy storage accounted for a relatively high proportion, especially benefiting from the construction of distributed photovoltaics in China.

[0052] User-side energy storage mainly reduces electricity costs by arbitrage by taking advantage of the difference between peak and valley electricity prices. In particular, user-side energy storage projects are more profitable in areas with large differences in peak and valley electricity prices. The current technical problem is that the revenue source of user-side energy storage is relatively single, and it mainly relies on arbitrage between peak and valley electricity prices. The decline in industrial and commercial electricity prices and the narrowing of the peak and valley price difference will further affect its profitability. It is necessary to use highly accurate power and load forecasts, combined with peak and valley electricity prices to formulate refined energy storage discharge control methods to improve energy storage revenue. Therefore, the accuracy of combining power forecasts and load forecasts is crucial for the scheduling of energy storage systems, but the imperfection of forecasting technology leads to reduced operating efficiency of energy storage systems and affects revenue. Power forecasting and load forecasting technologies may be affected by many factors, such as weather changes, uncertainty in user electricity behavior, etc., which increases the difficulty of forecasting.

[0053] To this end, the present invention proposes a discharge control method and energy storage control system for user-side energy storage taking into account power and load forecasting, and maximizes benefits by formulating a refined energy storage discharge control method. According to the embodiment, through accurate power and load forecasting, user-side energy storage can more effectively store and release energy, reduce energy waste, improve overall energy utilization efficiency, help user-side energy storage systems better respond to grid demand, and achieve peak shaving and valley filling of grid loads through the charging and discharging operations of energy storage equipment, thereby optimizing the operation of the power system. Accurate prediction can reduce unnecessary charging and discharging operations, extend battery life, reduce operation and maintenance costs, and improve the economic benefits of user-side energy storage projects.

[0054] Before describing the embodiments of the present invention, some terms or concepts involved in the embodiments of the present invention are explained.

[0055] Exemplary embodiments of the present invention are described below with reference to the accompanying drawings.

[0056] Figure 1 A flow chart of a method for controlling energy storage discharge at a user side according to an example embodiment is shown.

[0057] See also Figure 1 According to an example embodiment, a method for controlling energy storage discharge at a user side is provided, the method comprising:

[0058] In S101 , a policy execution cycle and a prediction cycle are set, wherein the policy execution cycle includes a plurality of prediction cycles.

[0059] According to some embodiments, a prediction cycle is set, and the prediction cycle is used for the power prediction and the load prediction. A strategy execution cycle is set, and the method cyclically executes the discharge control strategy in each set strategy execution cycle.

[0060] In S103, in each prediction cycle, a neural network algorithm model is applied to perform power prediction.

[0061] According to some embodiments, in each of the prediction cycles, a neural network algorithm model is applied to perform power prediction. The power prediction uses the prediction week as the time interval, and selects similar day samples in the historical data based on meteorological factors such as the season of the day to be predicted, the day's weather type, the day's maximum temperature, the day's minimum temperature, and humidity, trains the neural network, and finally inputs the meteorological data of the day to be tested to obtain the prediction result.

[0062] In S105, in each of the prediction cycles, a neural network algorithm model is applied to perform load prediction.

[0063] According to some embodiments, in each of the forecasting cycles, a neural network algorithm model is applied to perform load forecasting. The load forecasting uses the forecasting week as the time interval, selects similar day samples in historical data based on the month, week type, daily maximum temperature, and daily minimum temperature of the day to be tested, trains the neural network, and finally inputs the month, week type, and meteorological data of the day to be tested to obtain the forecast result.

[0064] In S107, a discharge control strategy within the strategy execution cycle is generated according to the load prediction and the power prediction within each prediction cycle.

[0065] According to some embodiments, the charge and discharge conditions of the strategy execution cycle are evaluated based on the load forecast and the power forecast in each forecast cycle, thereby generating a discharge control strategy in the strategy execution cycle. The discharge control strategy needs to consider the unit price of electricity in each time period to maximize user benefits.

[0066] In S109, the discharge control strategy is applied to control the charge and discharge operations within the strategy execution period.

[0067] According to some embodiments, the discharge control strategy is applied to control the charge and discharge operations within the strategy execution cycle. In each strategy execution cycle, load forecasting and power forecasting are performed through a neural network calculation model, and a refined discharge control strategy is generated based on the load forecasting and power forecasting to reduce energy consumption and improve user benefits.

[0068] According to some embodiments, the method of the present invention utilizes advanced data analysis techniques, such as neural network algorithms, to predict power demand and user load in the future, thereby formulating a more intelligent and efficient discharge control method, which can minimize energy costs without affecting users' daily electricity needs and help smooth the grid load curve.

[0069] Figure 2A schematic diagram of the architecture of a user-side energy storage system according to an example embodiment is shown.

[0070] See also Figure 2 According to an example embodiment, a user-side energy storage system is shown in the figure. Generally, the user-side energy storage system includes an energy storage device, a power storage converter (PCS), a battery management system (BMS), an energy management system (EMS), and an energy storage charging and discharging power calculation module.

[0071] According to some embodiments, in general, a user side energy storage system (User Side Energy Storage System) refers to a system installed on the user side for storing electrical energy and releasing it when needed. This system plays an important role in balancing the load of the power grid, improving the utilization rate of renewable energy, and reducing electricity bills. Among them, the energy storage device is the core component of the energy storage system, which is composed of multiple independent energy storage units, usually composed of a group of batteries, which can be lithium-ion batteries, lead-acid batteries, sodium-sulfur batteries, etc. The energy storage device is responsible for storing electrical energy and releasing it back to the power grid or directly for users to use when needed. The power storage converter (Power Conversion System, PCS) is a key device connecting the energy storage device to the power grid. It can realize the conversion between direct current (DC) and alternating current (AC). When charging, it converts the alternating current from the power grid into direct current suitable for battery storage. When discharging, it performs the opposite process and converts the direct current stored in the battery into usable alternating current. The Battery Management System (BMS) is used to monitor the status of the battery, including parameters such as voltage, current, and temperature, to ensure safe operation of the battery, prevent overcharging and over-discharging, balance the power of each single cell in the battery pack, and extend the battery life. The Energy Management System (EMS) is the brain of the entire energy storage system. It is responsible for collecting data from the BMS and other sensors, and controlling the operation of the PCS according to the user's settings and the needs of the power grid. Through EMS, users can achieve multiple functions such as peak load reduction, demand management, and backup power supply.

[0072] According to some embodiments, the method of discharge control in the scheme of the present invention is used in the energy storage charging and discharging power calculation module to calculate the best discharge control strategy to maximize the economic benefits of the energy storage system or meet specific service goals. For example, it can decide when to purchase electricity from the grid for charging, or when to sell excess electricity to the grid, and control the various components to work together, so that the user-side energy storage system can improve energy utilization efficiency while reducing the user's energy costs and promoting sustainable development.

[0073] According to some embodiments, within each of the prediction cycles, a neural network algorithm model is applied to perform power prediction, including: according to the prediction cycle, similar days in historical data are selected as samples based on meteorological factors such as the season of the day to be predicted, the daily weather type, the daily maximum temperature, the daily minimum temperature, and humidity, and the neural network algorithm model is trained; the neural network model performs power prediction based on the meteorological data of the day to be measured to obtain a power prediction result.

[0074] According to some embodiments, within each of the prediction cycles, a neural network algorithm model is applied to perform load prediction, including: according to the prediction cycle, similar day samples in historical data are screened out based on the month, week type, daily maximum temperature, and daily minimum temperature of the day to be measured, and the neural network algorithm model is trained; the neural network model performs load prediction based on the meteorological data of the day to be measured to obtain a load prediction result.

[0075] According to some embodiments, an accurate and effective prediction model is a prerequisite for the discharge control method to achieve optimal scheduling. Since distributed power generation output and load power consumption have great uncertainty, especially photovoltaic output, which is greatly affected by factors such as weather, etc., accurate photovoltaic output and load power consumption prediction can transform uncertainty problems into deterministic problems. The system can guide energy storage charging and discharging according to the prediction results and participate in power grid exchange reasonably. The neural network algorithm is selected as the main algorithm of the prediction module for photovoltaic and load prediction, and the prediction period of photovoltaic output power prediction is set to T (T can be 15mins-1h). The season of the day to be predicted, the weather type of the day, the maximum temperature of the day, the minimum temperature of the day, the humidity and other meteorological factors are used to screen out similar daily samples in the historical data, train the neural network calculation model, and finally input the meteorological data of the day to be tested to obtain the prediction results. The load prediction prediction period is T (T can be 15mins-1h). The month, week type, maximum temperature of the day, and minimum temperature of the day to be tested are used to screen out similar daily samples in the historical data, train the neural network, and finally input the month, week type and meteorological data of the day to be tested to obtain the prediction results.

[0076] According to some embodiments, a discharge control strategy within the strategy execution cycle is generated based on the load forecast and the power forecast within each of the forecast cycles, including: calculating the difference between the power forecast result and the load forecast result within the same forecast cycle; summing the differences of the forecast cycles included in the strategy execution cycle to obtain a first forecast result of the strategy execution cycle; and generating the control strategy based on the first forecast result.

[0077] According to some embodiments, the energy storage charging and discharging power calculation module combines the functions of power prediction and load prediction, taking the generation of control strategies in the time period of 8:00-11:00 in the morning under different weather and different power load conditions as an example. On the one hand, more electricity is discharged during the peak period (9:00-11:00), and on the other hand, all electricity (DoD is 90%) is ensured to be discharged between 8:00-11:00.

[0078] Electricity load level: The electricity load from 8:00 to 11:00 directly determines the space for photovoltaic power generation and energy storage discharge; Photovoltaic power generation level: Photovoltaic output varies greatly in different seasons and under different weather conditions. According to the current load level, when photovoltaic power generation reaches a peak, depending on the photovoltaic installed capacity, it will be almost impossible to fully discharge from 9:00 to 11:00, or even impossible to discharge. It will also be difficult to fully discharge from 8:00 to 11:00.

[0079] According to the above analysis, in order to maximize the benefits, it is necessary to predict the power consumption from 8:00 to 11:00 in advance, and predict the power generation of photovoltaic power from 8:00 to 11:00. According to the comparison between the two, determine the discharge strategy from 8:00 to 11:00. The specific steps are as follows: First, according to the load forecast (Load) and photovoltaic power generation forecast (PV) from 9:00 to 11:00, calculate the difference between the load forecast and the photovoltaic power generation forecast. Assuming that the forecast period of the load forecast and the photovoltaic forecast is set to 15 minutes, the specific steps are as follows:

[0080]

[0081] The above-mentioned differences every 15 minutes are added together to obtain the first prediction result.

[0082] According to some embodiments, the control strategy is generated according to the first prediction result, including: setting a first charge and discharge judgment threshold according to the energy storage installed capacity of the user-side energy storage system; and discharging according to the peak shaving and valley filling time period configured for the user-side energy storage system according to the relationship between the first prediction result and the first charge and discharge judgment threshold.

[0083] Continuing with the above example, the first charge and discharge judgment threshold is set according to the load forecast and power forecast deviation and the energy storage installed capacity (Q). Generally speaking, it can be set to Q*0.9*0.98*1.2, where Q is the energy storage installed capacity. Q*0.9 represents: the maximum dischargeable capacity of the energy storage, which is equivalent to the actual installed capacity of 200 kWh of energy storage, but each time due to battery protection, each discharge will not be completely discharged, only 90% of the electricity will be discharged, that is, the installed capacity multiplied by 0.9, which is an empirical value, which can be configured and adjusted by the system; considering that both the load forecast and the photovoltaic power forecast have deviations, the average accuracy level of the load forecast is 98%, and the average accuracy level of the photovoltaic forecast is 80%, so when considering the forecast deviation, consider the case where the load forecast is smaller by *0.98 and the power forecast is larger by *1.2. 0.98 and 1.2 are both estimated empirical values, which are configurable by the system.

[0084] If the added value is greater than or equal to the first charge and discharge judgment threshold, Q*0.9*0.98*1.2 (taking into account the load forecast and power forecast deviations), then discharge at 9:00-11:00; if it is less than Q*0.9*0.98*1.2, the remaining power will be discharged at 8:00-9:00.

[0085] Figure 3 A simple flow chart of a method for controlling energy storage discharge at a user side according to an example embodiment is shown.

[0086] See also Figure 3 , the figure shows a simple flow chart of a method for controlling energy storage discharge at a user side according to an example embodiment, the method also includes: a protection strategy for limiting the charging and discharging power.

[0087] According to some embodiments, the discharge control method is an overall strategy that combines the protection strategy with the charge and discharge control strategy. First, determine whether the system is in a normal state according to the protection strategy. If an alarm occurs, process the PCS and BMS according to the requirements of the alarm level. When normal operating conditions are met, start the energy storage charge and discharge power calculation module that combines power prediction and load prediction, and work according to the control strategy. According to the set cycle time, cycle the protection strategy process and monitor the EMS dispatch instruction process.

[0088] Specifically, the method also includes: a protection strategy to determine whether the user-side energy storage system is in a normal state, and to perform fault processing if a fault occurs. Wherein, determining whether the user-side energy storage system is in a normal state includes: determining whether a critical fault occurs in the user-side energy storage system. If a critical fault occurs in the user-side energy storage system, the energy storage converter (PCS) is controlled to shut down, and a command is sent to the battery management system (BMS) and the energy management system EMS to control the BMS to disconnect the DC circuit breaker; determining whether a serious fault occurs in the user-side energy storage system. If a serious fault occurs in the user-side energy storage system, the PCS is controlled to shut down; determining whether a minor fault occurs in the user-side energy storage system. If a minor fault occurs in the user-side energy storage system, the PCS is controlled to standby.

[0089] According to some embodiments, first, the protection strategy is activated and started to ensure the safety of the energy storage system and its related components to avoid equipment damage or safety accidents due to abnormal conditions. Before actual operation, the operating status of the energy storage system is checked to confirm whether all components (such as batteries, PCS, BMS, etc.) are working properly. If an abnormality is found, further operations may be suspended until the problem is resolved.

[0090] According to some embodiments, if the system confirms that everything is normal, the energy storage charge and discharge power calculation module is started to determine the best discharge control strategy. The energy storage charge and discharge power calculation module calculates the most appropriate charge and discharge power based on factors such as the current energy storage state, load and power demand forecast.

[0091] According to some embodiments, the energy storage charging and discharging power calculation module will use an integrated neural network algorithm model to perform power forecasting and load forecasting. Neural network is an artificial intelligence technology that imitates the structure of human brain neurons. It can learn historical data patterns and make predictions based on them. The neural network algorithm model will predict future power demand and supply based on historical power consumption data, weather forecasts, electricity price information and other factors, and formulate the optimal discharge control strategy accordingly.

[0092] According to some embodiments, based on the generated discharge control strategy, the energy management system (EMS) will guide the PCS to perform specific charging and discharging operations, including charging when the electricity price is low and discharging when the electricity price is high or the grid pressure is large, so as to achieve the goals of peak load shaving, saving electricity costs, and improving grid stability. In the scheme of the present invention, advanced prediction technology and automatic control system are used to dynamically adjust the working state of the energy storage device, so as to achieve the goals of energy saving and emission reduction, cost reduction, and improving grid service quality.

[0093] According to some embodiments, the protection strategy includes: limiting the energy storage charging and discharging power based on the PCS rated power and the maximum power allowed by the BMS for charging and discharging. The protection strategy is to limit the energy storage charging and discharging power based on the PCS rated power of the energy storage charging and discharging and the maximum power allowed by the BMS for charging and discharging, wherein the single PCS power = min(P pcs额i , P bms限制值i ), accumulating and summing each individual energy storage unit in the energy storage device

[0094] According to some embodiments, the discharge control method further includes a secondary discharge strategy, wherein the actual discharge power at a certain moment needs to be based on the external grid load's consumption of photovoltaic power generation, and the remaining power is supplemented by energy storage. 表总 <0 (i.e., reverse discharge), the charging and discharging power of the energy storage is 0, i.e., P 副 =0; the final power given to the energy storage is 0; on the contrary, if P 表总 >0; the charging and discharging power of the energy storage is

[0095] Figure 4 A schematic diagram of a method for calculating the energy storage charging and discharging power of a user-side energy storage system according to an example embodiment is shown.

[0096] See also Figure 4 , according to the schematic diagram of the calculation method of the energy storage charging and discharging power of the user-side energy storage system in the example embodiment, the discharge control method also includes: configuring a peak shaving and valley filling time period, and controlling the discharge power to be the difference between 0.9 times the energy storage installed capacity and the first prediction result divided by one hour.

[0097] First, according to the load forecast (Load) and photovoltaic power generation power forecast (PV) from 9:00 to 11:00, the difference between the load forecast and the photovoltaic power generation power forecast is calculated, and the forecast period is 15 minutes. The difference obtained every 15 minutes is added to obtain a first forecast result (Q1). According to the energy storage installed capacity of the user-side energy storage system, a first charge and discharge judgment threshold (Q2) is set. In this example, Q2=Q*0.9*0.98*1 is set. According to the relationship between the first forecast result and the first charge and discharge judgment threshold, discharge is performed according to the peak shaving and valley filling time period configured by the user-side energy storage system, and the corresponding power P main=(0.9*Q-Q1) / 1h.

[0098] According to some embodiments, the protection strategy limits the energy storage charging and discharging power based on the PCS rated power of the energy storage charging and discharging and the maximum power allowed by the BMS for charging and discharging. The single PCS power = min(P pcs额i , P bms限制值i), accumulating and summing each individual energy storage unit in the energy storage device n is the number of energy storage units. The auxiliary discharge strategy is that the actual discharge power at a certain moment needs to be based on the external grid load's consumption of photovoltaic power generation, and the remaining power is supplemented by energy storage.

[0099] According to some embodiments, the solution of the present invention can be applied to the design of an energy storage control system. When the energy storage control system executes the discharge control method as described in any of the above items to optimize the scheduling strategy, through accurate power prediction and load prediction, energy management and optimization of the scheduling strategy can be more effectively performed to achieve reasonable allocation and use of electric energy.

[0100] According to some embodiments, the energy storage charging and discharging power calculation module described in the solution of the present invention is combined with power and load forecasting, and the user-side energy storage can better participate in demand side response (DSM), and guide users to use more electricity during low electricity price periods through incentives, thereby reducing electricity demand during peak hours. Prediction technology can help the energy storage system perceive grid load changes in advance, adjust the charging and discharging plan in time, reduce grid load fluctuations, and improve the stability and reliability of the power system. Accurate load forecasting helps the user-side energy storage system reduce unnecessary charging and discharging operations, reduce operating costs, and improve economic benefits. The use of advanced neural network algorithm models, including artificial intelligence and machine learning technologies, can improve the accuracy of power forecasting and load forecasting, and provide more accurate data support for the operation of the energy storage system. By integrating intelligent control technology, the user-side energy storage system can automatically respond to the prediction results, achieve self-regulation and optimization, and improve the intelligence level of the system.

[0101] According to some embodiments, the scheme of the present invention can more effectively store and release energy through accurate power and load forecasting, reduce energy waste, and improve overall energy utilization efficiency. Prediction technology helps the user-side energy storage system to better respond to grid demand, and through the charging and discharging operations of energy storage equipment, it can realize peak load shaving and valley filling of grid load and optimize the operation of the power system. Accurate prediction can reduce unnecessary charging and discharging operations, extend battery life, reduce operation and maintenance costs, and improve the economic benefits of user-side energy storage projects.

[0102] According to some embodiments, the application of power prediction technology in the solution of the present invention helps to better integrate new energy sources such as wind energy and solar energy. User-side energy storage can store excess new energy power generation, reduce wind and solar power abandonment, and promote the efficient use of new energy.

[0103] According to some embodiments, the accuracy of the control strategy is improved through load forecasting and power forecasting in the solution of the present invention, and the user-side energy storage system can achieve more intelligent energy management.

[0104] Those skilled in the art can clearly understand that the technical solution of the present invention can be implemented with the help of software and / or hardware. "Unit" and "module" in this specification refer to software and / or hardware that can independently complete or cooperate with other components to complete specific functions, where the hardware can be, for example, a field programmable gate array, an integrated circuit, etc.

[0105] Figure 5 A block diagram of a computing device according to an example embodiment of the invention is shown.

[0106] like Figure 5 As shown, computing device 30 includes processor 12 and memory 14. Computing device 30 may also include bus 22, network interface 16, and I / O interface 18. Processor 12, memory 14, network interface 16, and I / O interface 18 may communicate with each other via bus 22.

[0107] The processor 12 may include one or more general-purpose CPUs (Central Processing Units, processors), microprocessors, or application-specific integrated circuits, etc., for executing relevant program instructions. According to some embodiments, the computing device 30 may also include a high-performance graphics card (GPU) 20 for accelerating the processor 12.

[0108] The memory 14 may include a machine system readable medium in the form of a volatile memory, such as a random access memory (RAM), a read-only memory (ROM) and / or a cache memory. The memory 14 is used to store one or more programs including instructions and data. The processor 12 can read the instructions stored in the memory 14 to execute the above-mentioned method according to the embodiment of the present invention.

[0109] The computing device 30 may also communicate with one or more networks via the network interface 16. The network interface 16 may be a wireless network interface.

[0110] The bus 22 may include an address bus, a data bus, a control bus, etc. The bus 22 provides a path for exchanging information between components.

[0111] It should be noted that, for the above-mentioned method embodiments, for the sake of simplicity, they are all described as a series of action combinations, but those skilled in the art should know that the present invention is not limited by the described order of actions, because according to the present invention, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also know that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by the present invention.

[0112] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0113] In the several embodiments provided by the present invention, it should be understood that the disclosed devices can be implemented in other ways. For example, the device embodiments described above are only schematic, such as the division of units, which is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some service interfaces, and the indirect coupling or communication connection of devices or units can be electrical or other forms.

[0114] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0115] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0116] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable memory. Based on this understanding, the technical solution of the present invention is essentially or the part that contributes to the prior art or the whole or part of the technical solution can be embodied in the form of a software product, which is stored in a memory and includes several instructions for a computer device (which can be a personal computer, server or network device, etc.) to perform all or part of the steps of the methods of various embodiments of the present invention.

[0117] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0118] The exemplary embodiments of the present invention are specifically shown and described above. It should be understood that the present invention is not limited to the detailed structures, configurations or implementations described herein; on the contrary, the present invention is intended to cover various modifications and equivalent configurations included in the spirit and scope of the appended clauses.

Claims

1. A method for controlling energy storage discharge at a user side, characterized in that: The method comprises: Setting a strategy execution cycle and a prediction cycle, wherein the strategy execution cycle includes a plurality of prediction cycles; In each of the prediction cycles, a neural network algorithm model is used to perform power prediction; In each of the forecasting cycles, a neural network algorithm model is used to perform load forecasting; Generating a discharge control strategy within the strategy execution cycle according to the load forecast and the power forecast within each of the forecast cycles; The discharge control strategy is applied to control the charge and discharge operations within the strategy execution cycle.

2. The method according to claim 1, characterized in that In each of the prediction cycles, a neural network algorithm model is applied to perform power prediction, including: According to the prediction cycle, similar days in historical data are selected as samples based on meteorological factors such as the season of the day to be predicted, the daily weather type, the daily maximum temperature, the daily minimum temperature, and humidity, and the like, to train the neural network algorithm model; The neural network model performs power prediction according to the meteorological data of the day to be measured to obtain a power prediction result.

3. The method according to claim 1, characterized in that In each of the forecasting cycles, a neural network algorithm model is applied to perform load forecasting, including: According to the prediction cycle, similar day samples in the historical data are screened out based on the month, week type, daily maximum temperature, and daily minimum temperature of the day to be tested, and the neural network algorithm model is trained; The neural network model performs load forecasting according to the meteorological data of the day to be measured to obtain a load forecasting result.

4. The method according to claim 1, characterized in that: Generating a discharge control strategy within the strategy execution cycle according to the load forecast and the power forecast within each forecast cycle, including: Calculating the difference between the power forecast result and the load forecast result within the same forecast period; summing the differences of the prediction periods contained in the strategy execution period to obtain a first prediction result of the strategy execution period; The control strategy is generated according to the first prediction result.

5. The method according to claim 4, characterized in that Generate a case number based on the first prediction result: The control strategy includes: According to the energy storage installed capacity of the user-side energy storage system, a first charge and discharge judgment threshold is set; According to the relationship between the first prediction result and the first charge and discharge judgment threshold, discharge is performed according to the peak shaving and valley filling time period configured for the user-side energy storage system.

6. The method according to claim 1, characterized in that Also includes: Configure the peak shaving and valley filling time period and control the discharge power to be the difference between 0.9 times the energy storage installed capacity and the first prediction result divided by one hour.

7. The method according to claim 1, characterized in that The method further comprises: Protection strategy, determine whether the user-side energy storage system is in a normal state, and perform fault processing if a fault occurs.

8. A computer program product, characterized in that include: A computer program, wherein when the computer program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

9. A computing device, characterized in that include: processor; as well as A memory storing a computer program, which, when executed by the processor, enables the processor to perform the method according to any one of claims 1 to 7.

10. An energy storage control system, characterized in that: When the energy storage control system is in operation, the method according to any one of claims 1 to 7 is executed.

Images