Energy management method and device of new energy power system and storage medium

Abstract

The invention discloses an energy management method and device of a new energy power system and a storage medium. The method comprises the steps that basic data are acquired, and the basic data comprise the load demand of a target power system, the renewable energy power generation amount and meteorological data; performing prediction based on a preset model and the basic data to obtain a prediction result, the prediction result including a predicted load demand and a predicted power generation amount; generating a target scheduling strategy based on the prediction result; and adjusting the energy supply operation of the target power system based on the target scheduling strategy. The technical problem of supply and demand imbalance of the new energy power system caused by new energy fluctuation is solved.

Description

Technical Field

[0001] The present invention relates to the technical field of new energy power systems, and in particular to an energy management method, device and storage medium for a new energy power system. Background Art

[0002] In the context of new energy power systems, renewable energy (such as wind and solar energy) is gradually replacing traditional fossil energy with its advantages of cleanliness and low carbon, becoming an important part of the power system. However, due to the volatility and unpredictability of wind and solar energy, the stability and reliability of the power system face severe challenges. The output of new energy power generation fluctuates with weather conditions and sunshine changes, resulting in an imbalance between supply and demand, making it difficult for the dispatch of traditional power systems to adapt to the access of new energy power generation. This uncertainty makes the power system prone to frequency fluctuations, voltage instability and other problems in actual operation, which in turn affects power supply security and grid stability. To address the above problems, energy storage systems and demand response have been introduced as effective auxiliary means. Energy storage systems can balance supply and demand fluctuations and alleviate the impact of unstable output of new energy by charging when there is surplus power and discharging when there is a shortage of power. Demand response guides users to change their electricity habits through real-time electricity prices and user-side equipment control, thereby reducing loads during peak hours and increasing loads during valley hours. However, traditional energy storage system management and demand response control still have shortcomings in dealing with the volatility and complexity of new energy power systems. The lack of accurate prediction methods and intelligent management strategies leads to problems such as low efficiency of energy storage resources and poor overall economic efficiency of the system.

[0003] However, in the new energy power system, the access of renewable energy (such as wind power and solar energy) increases the uncertainty and volatility of the system. Since its power generation is greatly affected by meteorological conditions, the supply and demand balance of the power system faces challenges. In the existing technology, the power system usually lacks accurate load demand and power generation prediction means, making it difficult for the dispatching scheme to achieve high efficiency and stability when dealing with new energy fluctuations. In addition, as an important regulation means of the new energy power system, although the energy storage system can balance supply and demand through charging and discharging behavior, the traditional energy storage management method fails to achieve dynamic response and intelligent balance of economy and life, resulting in low utilization and economic benefits of the energy storage system. Demand response also fails to intelligently control the user's electricity consumption behavior, making it difficult to effectively balance the load during peak load periods; at the same time, in the existing power system, energy storage and load management are mostly decentralized local control, lacking a global collaborative optimization mechanism, and unable to take into account the supply and demand balance of local energy storage units and the global power grid, resulting in unreasonable resource allocation and reduced overall economy and flexibility of the system. In addition, the existing fault diagnosis means are not sufficient to monitor and predict potential faults in real time, making the system lack of preventive and intelligent processing when dealing with faults.

[0004] To address the above-mentioned problems, no effective solution has been proposed yet. Summary of the invention

[0005] The embodiments of the present invention provide an energy management method, device and storage medium for a new energy power system, so as to at least solve the technical problem of imbalance between supply and demand of the new energy power system caused by fluctuation of new energy.

[0006] According to one aspect of an embodiment of the present invention, there is provided an energy management method for a new energy power system, comprising: acquiring basic data, the basic data comprising: load demand of a target power system, renewable energy power generation and meteorological data; performing prediction based on a preset model and the basic data to obtain prediction results, the prediction results comprising: predicted load demand and predicted power generation; generating a target scheduling strategy based on the prediction results; and adjusting the energy supply operation of the target power system based on the target scheduling strategy.

[0007] Furthermore, prediction is performed based on the preset model and the basic data to obtain a prediction result, including: predicting based on the first preset model in the preset model and the basic data to obtain a first result; predicting based on the second preset model in the preset model and the basic data to obtain a second result; predicting based on the third preset model in the preset model and the basic data to obtain a third result; determining the prediction result based on the first result, the second result and the third result.

[0008] Furthermore, based on the prediction results, a target scheduling strategy is generated, including: constructing an objective function based on the predicted load demand and the predicted power generation; solving the objective function based on a preset algorithm to obtain a power supply decision quantity; and generating a target scheduling strategy based on the power supply decision quantity.

[0009] Furthermore, based on the target scheduling strategy, the energy supply operation of the target power system is adjusted, including: generating a charging and discharging strategy for the energy storage system in the target power system based on the prediction results; and adjusting the energy supply operation of the target power system based on the target scheduling strategy and the charging and discharging strategy.

[0010] Furthermore, based on the prediction results, a charging and discharging strategy for the energy storage system in the target power system is generated, including: defining the state space of the energy storage system based on the real-time electricity price, the charging and discharging state of the energy storage system and the prediction results; defining the action space of the energy storage system based on the action parameters of the energy storage system, wherein the action parameters include: charging state, discharging state and holding state; generating a charging and discharging control model of the energy storage system based on the state space and the action space; obtaining optimization target parameters, wherein the optimization target parameters include: economic target and life management target; generating a charging and discharging strategy based on the charging and discharging control model and the optimization target parameters.

[0011] Furthermore, based on the prediction results, a target scheduling strategy is generated, including: obtaining historical electricity consumption information of the target object; constructing an electricity consumption behavior prediction model of the target object based on the historical electricity consumption information; and generating a target scheduling strategy based on the electricity consumption behavior prediction model, the prediction results and the real-time electricity price.

[0012] Furthermore, based on the prediction results, a target scheduling strategy is generated, including: obtaining local prediction results, the local prediction results are prediction results of energy storage units of the energy storage system in the target power system; based on the local prediction results, generating local scheduling strategies for each energy storage unit; obtaining status information of each energy storage unit; and generating a target scheduling strategy based on the status information of each energy storage unit, the power supply strategy of the target power system, and the prediction results.

[0013] Furthermore, based on the prediction results, a target scheduling strategy is generated, including: obtaining local prediction results, the local prediction results being the predicted load demand and predicted power generation of the energy storage units of the energy storage system in the target power system; generating a local scheduling strategy for each energy storage unit based on the local prediction results; obtaining status information of each energy storage unit; and generating a target scheduling strategy based on the local scheduling strategy of each energy storage unit, the status information of each energy storage unit, and the prediction results.

[0014] According to another aspect of an embodiment of the present invention, an energy management device for a new energy power system is also provided, including: an acquisition module, which acquires basic data, and the basic data include: load demand of a target power system, renewable energy power generation and meteorological data; a prediction module, which performs prediction based on a preset model and basic data to obtain prediction results, and the prediction results include: predicted load demand and predicted power generation; a generation module, which generates a target scheduling strategy based on the prediction results; and a scheduling module, which adjusts the energy supply operation of the target power system based on the target scheduling strategy.

[0015] According to another aspect of an embodiment of the present invention, a computer-readable storage medium is provided. The computer-readable storage medium includes a stored executable program, wherein when the executable program is running, the device where the computer-readable storage medium is located is controlled to execute the methods in various embodiments of the present invention.

[0016] According to another aspect of an embodiment of the present invention, a computer program product is provided, including a computer program. When the computer program is executed by a processor, the method in each embodiment of the present invention is implemented.

[0017] In an embodiment of the present invention, by predicting the supply and demand of the new energy power system, intelligent optimization of the control of the target power system is achieved, thereby achieving the purpose of improving the adaptability of the target power system, thereby achieving the technical effect of improving the economy of the new energy power system, and further solving the technical problem of imbalance in supply and demand of the new energy power system caused by new energy fluctuations. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] The drawings described herein are used to provide a further understanding of the present invention and constitute a part of this application. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the drawings:

[0019] Figure 1 is a flow chart of an optional energy management method for a new energy power system according to one embodiment of the present invention;

[0020] Figure 2 is a flow chart of an optional energy management method for a new energy power system according to one embodiment of the present invention;

[0021] Figure 3 It is a structural block diagram of an optional energy management device for a new energy power system according to one embodiment of the present invention. DETAILED DESCRIPTION

[0022] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0023] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0024] According to an embodiment of the present invention, an embodiment of an energy management method for a new energy power system is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although the logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0025] The method embodiment can be executed in an electronic device or a similar computing device including a memory and a processor. Taking running on a new energy power system terminal as an example, the new energy power system terminal may include one or more processors (processors may include but are not limited to central processing units (CPU), graphics processing units (GPU), digital signal processing (DSP) chips, microprocessors (MCU), programmable logic devices (Field Programmable Gate Array, FPGA), neural network processors (Neural-network Processor Unit, NPU), tensor processors (Tensor Processing Unit, TPU), artificial intelligence (Artificial Intelligence, AI) type processors and other processing devices) and a memory for storing data. Optionally, the above-mentioned new energy power system terminal may also include a transmission device, an input and output device, and a display device for communication functions. It can be understood by those skilled in the art that the above-mentioned structural description is only for illustration, and it does not limit the structure of the above-mentioned new energy power system terminal. For example, the new energy power system terminal may also include more or fewer components than the above-mentioned structural description, or have a configuration different from the above-mentioned structural description.

[0026] The memory can be used to store computer programs, for example, software programs and modules of application software, such as the corresponding computer program of the energy management method of the new energy power system in the embodiment of the present invention. The processor executes various functional applications and data processing by running the computer program stored in the memory, that is, the energy management method of the new energy power system mentioned above is realized. The memory may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory may further include a memory remotely arranged relative to the processor, and these remote memories can be connected to the mobile terminal via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and a combination thereof.

[0027] The transmission device is used to receive or send data via a network. The specific example of the above network may include a wireless network provided by a communication provider of the mobile terminal. In one example, the transmission device includes a network adapter (Network Interface Controller, referred to as NIC), which can be connected to other network devices through a base station so as to communicate with the Internet. In one example, the transmission device can be a radio frequency (Radio Frequency, referred to as RF) module, which is used to communicate with the Internet wirelessly.

[0028] The display device may be, for example, a touch screen type liquid crystal display (LCD) and a touch display (also referred to as a "touch screen" or "touch display screen"). The liquid crystal display may enable a user to interact with a user interface of a mobile terminal. In some embodiments, the mobile terminal has a graphical user interface (GUI), and a user may interact with the GUI by finger contacts and / or gestures on a touch-sensitive surface, wherein the human-computer interaction functions here may optionally include the following interactions: creating web pages, drawing, word processing, making electronic documents, games, video conferencing, instant messaging, sending and receiving emails, call interfaces, playing digital videos, playing digital music and / or web browsing, etc. The executable instructions for executing the above human-computer interaction functions are configured / stored in a computer program product or readable storage medium executable by one or more processors.

[0029] Figure 1 is a method according to an embodiment of the present invention, such as Figure 1 As shown, the method comprises the following steps:

[0030] Step S10, obtaining basic data, the basic data including: load demand of the target power system, renewable energy power generation and meteorological data.

[0031] In step S10, the basic data includes the load demand of the target power system, the power generation of renewable energy (such as wind power, solar energy) and related meteorological data. The load demand data reflects the power demand of the system in a specific time period, which is usually estimated based on historical power consumption data and user behavior patterns. The power generation of renewable energy depends on meteorological data, such as wind speed, solar radiation intensity, etc. These basic data can be obtained through real-time monitoring systems such as sensor networks, smart meters, weather stations, and historical databases. The accuracy and real-time nature of the data directly affect the reliability of subsequent predictions and scheduling decisions.

[0032] Step S12, performing prediction based on the preset model and basic data to obtain prediction results, the prediction results including: predicted load demand and predicted power generation.

[0033] In step S12, the obtained basic data is analyzed using a preset prediction model to generate predicted load demand and (renewable energy) predicted power generation. The selection of the prediction model should be based on factors such as data characteristics, prediction accuracy requirements and computing resources. For example, the long short-term memory network (LSTM) is suitable for processing time series data, can capture long-term dependencies, and is suitable for long-term prediction of load demand and power generation. Support vector machines (SVM) and time series models (such as ARIMA) are suitable for processing nonlinear relationships and short-term fluctuation predictions, respectively. The prediction results provide future prediction-based information for subsequent scheduling decisions, allowing the system to plan and adjust in advance to cope with the volatility of renewable energy and changes in load demand.

[0034] Step S14, generating a target scheduling strategy based on the prediction results.

[0035] In step S14, the generation of the target scheduling strategy may involve optimization algorithms, such as dynamic programming, genetic algorithms, particle swarm optimization, etc., which can help determine the optimal resource allocation plan to minimize operating costs, maximize renewable energy utilization, or ensure supply and demand balance. The output of the scheduling strategy is usually the power supply decision at every moment, including purchasing electricity from the power grid, generating electricity through renewable energy, charging and discharging operations of energy storage units, etc., to meet the predicted load demand.

[0036] Step S16: adjusting the energy supply operation of the target power system based on the target dispatching strategy.

[0037] In step S16, the charging and discharging state of the energy storage unit is adjusted according to the dispatching strategy, the operation of renewable energy power generation equipment is controlled, and the purchase and sale of electricity is managed. By implementing the dispatching strategy, the system can accurately match supply and demand, reduce operating costs, improve the utilization rate of renewable energy, and ensure the stable operation of the power system. During the execution process, it is also necessary to monitor the real-time status of the system to ensure the adaptability and effectiveness of the strategy, and make dynamic adjustments when necessary to deal with forecast deviations or emergencies.

[0038] Based on steps S10 to S16, by predicting the supply and demand of the new energy power system, the intelligent optimization of the control of the target power system is realized, and the efficient, stable and economic operation of the new energy power system is realized, which is an important part of modern smart grid and energy Internet technology. In the face of the uncertainty of renewable energy and the increasingly complex power market environment, this prediction-based energy management method can significantly improve the adaptability and economy of the system, and provide technical support for the realization of green and low-carbon energy transformation.

[0039] As an optional implementation, prediction is performed based on a preset model and basic data to obtain prediction results, including:

[0040] Step S201, performing prediction based on a first preset model in the preset models and basic data to obtain a first result.

[0041] In step S201, the first preset model can be a long short-term memory network (LSTM). LSTM is a special recurrent neural network (RNN) that is good at processing time series data and capturing long-term and short-term dependencies, and is suitable for predicting the long-term trend of load demand and power generation in the power system. In this step, the LSTM model will learn the characteristics and laws of the time series through training based on the input basic data (including historical load data, power generation data, meteorological data, etc.), so as to predict the load demand and power generation in a certain period of time in the future. The prediction result, as the first result, reflects the long-term trend of the power system and provides a basis for subsequent scheduling decisions.

[0042] Step S202: performing prediction based on a second preset model in the preset model and basic data to obtain a second result.

[0043] In step S202, the second preset model may be a support vector machine (SVM). SVM is excellent in processing nonlinear relationships and classification problems, and can capture seasonal changes and periodic patterns in power system data. The SVM model can process medium-term changes in weather and load, such as changes in load and power generation within a week or a month, and the prediction result, as the second result, reflects the fluctuation and change trend of the power system within a specific period.

[0044] Step S203: performing prediction based on a third preset model in the preset models and the basic data to obtain a third result.

[0045] In step S203, the third preset model can use a time series analysis method, such as an ARIMA model, for short-term prediction. The ARIMA model (autoregressive integrated moving average model) can handle random fluctuations in power load and power generation in the short term, and is suitable for predicting the load demand and power generation of the power system in the next few hours or a day. Through the ARIMA model, an accurate prediction of the power system in the short term can be obtained, which, as the third result, provides direct support for real-time scheduling and control.

[0046] Step S204, determining a prediction result based on the first result, the second result and the third result.

[0047] In step S204, the prediction results (first result, second result and third result) obtained in steps S201 to S203 are fused to determine the final prediction result. The fusion method can be a weighted average, in which the prediction results of each model are assigned different weights according to their prediction accuracy and reliability in a specific time period. The determination of the weight can be based on the performance evaluation results of historical predictions. For example, if the LSTM model performs best in long-term predictions, then in the weighted average, the prediction results of the LSTM model will be assigned a higher weight. The fused prediction results comprehensively consider the long-term trend, medium-term fluctuations and short-term fluctuations of the power system, providing comprehensive and accurate data support for subsequent energy management and scheduling decisions.

[0048] Preferably, the prediction value calculation formula of the weighted average method is:

[0049]

[0050] Among them, w1 is the weight of the long short-term memory network (the first preset model), w2 is the weight of the support vector machine (the second preset model), and w3 is the weight of the time series model.

[0051] Based on steps S201 to S204, multi-model fusion prediction can improve the accuracy of power system load and power generation prediction, provide a more reliable dispatch basis for new energy power systems, help achieve effective energy management and supply and demand balance, and reduce system operating costs caused by prediction errors. This prediction mechanism is an important part of realizing intelligent dispatch and optimized operation in new energy power systems.

[0052] Optionally, based on the prediction results, a target scheduling strategy is generated, including:

[0053] Step S211, constructing an objective function based on the predicted load demand and the predicted power generation;

[0054] In step S211, the objective function is used to quantify the goal of system operation, such as minimizing operating costs, maximizing renewable energy utilization, etc. In a new energy power system, the objective function usually includes the following key elements:

[0055] a. Forecast of load demand and power generation: The system obtains the predicted values ​​of load demand and power generation in the future time period through multi-model fusion prediction. These predicted values ​​will be used as the input of the objective function to guide the formulation of scheduling strategies.

[0056] b. Renewable energy use cost: Consider the use cost of renewable energy, which may include the marginal cost of renewable energy power generation, the charging and discharging cost of energy storage systems, etc. Incorporating these cost factors into the objective function will help the system to reasonably utilize renewable energy in scheduling decisions and reduce operating costs.

[0057] c. Scheduling time period and adjustment parameters: The scheduling time period in the objective function specifies the duration of the scheduling decision, such as one day, one week, etc. The adjustment parameters are used to adjust the relative importance of different objectives in the objective function to ensure that the scheduling strategy can comprehensively consider economy and stability.

[0058] Furthermore, the objective function is:

[0059]

[0060] Among them, D t To predict load demand, S t is the predicted power generation of (renewable energy), T is the scheduling time period, α is the adjustment parameter, C RE (t) is the cost of using renewable energy.

[0061] Step S212, solving the objective function based on a preset algorithm to obtain a power supply decision quantity;

[0062] In step S212, once the objective function is determined, an appropriate optimization algorithm is used to solve the objective function to obtain the optimal power supply decision quantity within the forecast period. The power supply decision quantity refers to the power that the power supply should output at each time point to meet the system load demand and achieve optimal economy.

[0063] Furthermore, in the renewable energy power system, the dynamic programming algorithm is an effective solution method. The dynamic programming algorithm can handle optimization problems with time series characteristics. By decomposing the problem into multiple stages, the optimal strategy for each stage is gradually solved, and finally the optimal power supply decision quantity S in the entire forecast time period is obtained. t *. The dynamic programming algorithm takes into account the impact of decisions made at each time point on subsequent time points, ensuring the consistency and optimality of the power supply strategy in the time series.

[0064] Step S213, generating a target scheduling strategy based on the power supply decision quantity.

[0065] In step S213, based on the power supply decision quantity S t *, the system generates a specific target scheduling strategy. This includes converting power supply decision quantities into control instructions for different power sources (such as renewable energy, energy storage systems, and traditional power generation units), as well as suggestions for adjusting the operating status of user-side equipment. The generation of the target scheduling strategy needs to take into account the following points:

[0066] a. Resource scheduling: Based on the power supply decision volume, the output of renewable energy, energy storage systems and traditional power generation resources is scheduled to meet load demand while maximizing the utilization of renewable energy and reducing operating costs.

[0067] b. Demand response: Based on real-time electricity prices and user behavior predictions, signals are sent to users to guide them to increase electricity consumption during low electricity price periods and reduce electricity consumption during peak periods to balance system load and reduce peak load.

[0068] c. Energy storage optimization: For energy storage systems, the charge and discharge status of the energy storage unit at each time point is adjusted according to the charge and discharge strategy and power supply decision quantity to achieve a balance between economy and battery life.

[0069] d. System stability: Ensure that the target dispatch strategy does not cause excessive fluctuations or pressure on the power system, maintain the voltage and frequency stability of the power grid, and ensure the safe operation of the power system.

[0070] Based on steps S211 to S213, the output of the target dispatch strategy will guide the actual operation of the power system within the forecast time window, including the power supply decision S at each moment. t *, the charging and discharging control signals of the energy storage system, the operating status of the user's smart devices, and possible power trading decisions to achieve supply and demand balance and economic optimization, ensuring the efficient, environmentally friendly and economical operation of the new energy power system.

[0071] Optionally, based on the target dispatching strategy, adjusting the energy supply operation of the target power system includes:

[0072] Step S221: generating a charging and discharging strategy for the energy storage system in the target power system based on the prediction result.

[0073] In step S221, the results of load demand forecasting and power generation forecasting are combined with real-time electricity price information to generate a charging and discharging strategy for the energy storage system. The forecast results provide an expectation of the supply and demand of the power system in the future, while the real-time electricity price reflects the economic signals of the current market. Combining this information, the system can intelligently decide when the energy storage system is charged, when it is discharged, and the power of charging or discharging, so as to achieve the dual goals of economy and system stability.

[0074] Furthermore, the generation of charging and discharging strategies will take into account the following points:

[0075] Supply and demand balance: Based on the predicted load demand and power generation, the global control layer will analyze the supply and demand relationship in the future period and determine whether the energy storage system needs to participate in regulation to balance the total demand and total power supply. For example, if it is predicted that demand will exceed supply in a certain period in the future, the global control layer will instruct the energy storage system to charge in advance so that it can discharge during the peak demand period to supplement the shortage of the power grid.

[0076] Economic optimization: When formulating charging and discharging strategies, the global control layer calculates the economic benefits of energy storage operations. This means charging as much as possible during low electricity price periods and discharging during high electricity price periods to maximize the benefits of the energy storage system from electricity price fluctuations. At the same time, the costs of charging and discharging operations, such as battery loss and operating expenses, are also taken into account to maximize net benefits.

[0077] System stability: The global control layer also needs to ensure that the charging and discharging strategies do not cause excessive fluctuations or pressure on the power system and maintain the voltage and frequency stability of the power grid.

[0078] Resource coordination: The global control layer takes into account the total capacity and distribution of all energy storage units to ensure that the charging and discharging strategy can fully utilize all available energy storage resources and achieve optimal allocation of system resources.

[0079] Furthermore, the generation of the charge and discharge strategy may include the following steps:

[0080] a. Define the state space: including the current state of charge (SOC) of the energy storage system, the real-time electricity price, and the predicted load demand and power generation.

[0081] b. Define the action space: the charging and discharging state of the energy storage system, including charging state, discharging state and holding state.

[0082] c. Construct a reward function: With economy and battery life as the goals, reward or penalize the energy storage system's actions in a specific state to ensure that the strategy can both reduce operating costs and extend the battery's service life.

[0083] d. Apply optimization algorithms: such as deep reinforcement learning, genetic algorithms, or particle swarm optimization algorithms to solve the optimal charging and discharging strategy in state space and action space.

[0084] Step S222: adjusting the energy supply operation of the target power system based on the target scheduling strategy and the charging and discharging strategy.

[0085] In step S222, based on the target scheduling strategy and the charging and discharging strategy of the energy storage system, the energy supply operation of the entire power system is adjusted to achieve supply and demand balance and optimal economic efficiency. Specifically, it includes the following aspects:

[0086] a. Adjust power distribution: Depending on the target dispatch strategy, the system may need to obtain or reduce power output from different power sources (such as wind, solar, and traditional power plants) to match the predicted load demand.

[0087] b. Execute charging and discharging strategies: The energy storage system will dynamically adjust the charging and discharging status according to the generated charging and discharging strategies to ensure charging when electricity prices are low and discharging at peak times, reducing dependence on traditional power sources while extending battery life.

[0088] c. Manage demand-side response: Through real-time electricity prices and user electricity consumption behavior predictions, the system can send signals to users to guide them to increase electricity consumption when electricity prices are low and reduce electricity consumption during peak hours, thereby achieving load management and demand response.

[0089] d. Implement control instructions: The system dispatch control module makes real-time adjustments to various components in the power system, including power generation units, energy storage systems, and user-side equipment, based on the control instructions generated by the strategy, to ensure that the entire system operates according to the optimal strategy.

[0090] Based on steps S221 to S222, the target power system can intelligently respond to the predicted load demand and power generation changes, manage the energy storage system to optimize the economy and battery life, and finally achieve efficient, economical and environmentally friendly operation of the entire system. By implementing the prediction-based charging and discharging strategy and dispatching strategy, the power system can more flexibly respond to market demand fluctuations, improve the utilization rate of renewable energy, reduce operating costs, and ensure the stability and reliability of the power grid.

[0091] Optionally, based on the prediction result, a charging and discharging strategy of the energy storage system in the target power system is generated, including:

[0092] Step S231, defining the state space of the energy storage system based on the real-time electricity price, the charging and discharging state of the energy storage system and the prediction result;

[0093] In step S231, a space describing the current and possible future states of the energy storage system is constructed based on the real-time state and prediction results of the energy storage system. The definition of the state space depends on the key state parameters of the energy storage system, which include at least:

[0094] Real-time electricity price: reflects the price of electricity in the current electricity market and is used to guide the energy storage system to perform charging and discharging operations at a time when cost-effectiveness is high.

[0095] State of Charge (SOC): Indicates the current energy level stored in the energy storage system and is an important basis for determining charging and discharging operations.

[0096] Predict load demand: Based on the results of multi-model fusion prediction, predict the power demand in the future time period.

[0097] Forecasting power generation: Also based on the forecasting model, the future power generation of renewable energy is predicted to balance supply and demand.

[0098] The state space is a collection of all possible states of the energy storage system, which provides a comprehensive view for the formulation of charging and discharging strategies. In the state space, the energy storage system may be at different SOC levels, and the changes in real-time electricity prices, load demand, and power generation also constitute the dynamic elements of the state space. The construction of the state space is the basis of intelligent decision-making, which provides a possible state set for the subsequent generation of charging and discharging strategies.

[0099] Step S232, defining an action space of the energy storage system based on action parameters of the energy storage system, wherein the action parameters include: a charging state, a discharging state, and a holding state.

[0100] In step S232, the action space describes the operations that the energy storage system can perform in any given state, including:

[0101] State of charge: The energy storage system purchases electricity from the grid and stores it as chemical energy or other forms of energy.

[0102] Discharge state: The energy storage system sells electricity to the grid, converting the stored energy into electrical energy.

[0103] Maintaining state: The energy storage system maintains the current charge and discharge state unchanged, neither charging nor discharging.

[0104] The definition of the action space provides an operational guide for the generation of subsequent charging and discharging strategies, ensuring that the execution of the strategy is both logical and can effectively avoid the negative impact of frequent charging and discharging on battery life.

[0105] Step S233: generating a charge and discharge control model of the energy storage system based on the state space and the action space.

[0106] In step S233, the charge and discharge control model is constructed using the definitions of the state space and the action space. The control model can use various advanced algorithms, such as deep reinforcement learning, genetic algorithm, particle swarm optimization, etc., to intelligently select operations in the action space according to the changes in state parameters to achieve the optimal balance between economy and battery life. The learning process of the control model may involve the analysis of historical data, and the optimal charge and discharge strategy under different states is learned through a large number of trial and error.

[0107] Step S234, obtaining optimization target parameters, wherein the optimization target parameters include: economic target and life management target.

[0108] In step S234, the optimization target parameters define the ultimate goal of the charge and discharge strategy, including at least:

[0109] Economic goal: pursue minimizing operating costs or maximizing profits, ensuring that the charging and discharging operations of the energy storage system can charge when electricity prices are low and discharge when electricity prices are high, thereby reducing overall operating costs.

[0110] Life management goal: Extend the service life of the energy storage system and reduce maintenance and replacement costs by limiting the depth and frequency of charge and discharge.

[0111] These parameters will be input into the charge and discharge control model as a guide for the model to seek the optimal strategy.

[0112] Step S235: generating a charge and discharge strategy based on the charge and discharge control model and the optimization target parameters.

[0113] In step S235, based on the charge and discharge control model and the optimization target parameters, a specific charge and discharge strategy is generated through the model solving process. The strategy will guide the charge and discharge operation of the energy storage system under different conditions, ensuring that the long-term health of the battery is taken into account while meeting the economic goals, so that the energy storage system can achieve intelligent and efficient resource management in a complex and changing market environment.

[0114] Based on steps S231 to S235, the new energy power system can intelligently generate a charging and discharging strategy for the energy storage system based on prediction information and optimization objectives, ensuring that the system can flexibly and efficiently dispatch energy when responding to renewable energy fluctuations and load changes, thereby achieving the dual goals of economic operation and environmental protection.

[0115] Optionally, the method further includes the following steps:

[0116] Step S236, constructing a reward function based on the optimization target parameters and state parameters.

[0117] In step S236, under the deep reinforcement learning framework, the reward function is the key to guiding the learning of the agent. The construction of the reward function is based on the optimization target parameters and state parameters, and the revenue (such as electricity sales revenue) and cost (such as electricity purchase cost) of the energy storage system and the battery aging cost are converted into reward signals for evaluating and providing feedback on the effect of the energy storage system after performing a certain action. A high reward indicates that the action is beneficial to achieving the optimization goal; conversely, a low reward or penalty indicates a disadvantage. By correctly defining the reward function, the model can be guided to learn a charging and discharging strategy that meets the optimization goal.

[0118] Furthermore, the reward function is:

[0119] R t =p t ·P out (t)-Cop (t)·a t -λ·ΔSOH(t);

[0120] Among them, P t is the electricity price, P out (t) is the output power, C op (t) is the operating cost, λ is the battery aging cost factor, and ΔSOH(t) is the battery life change.

[0121] Step S237, optimizing the charge and discharge control model based on the reward function.

[0122] In step S237, after the reward function is defined, the charge and discharge control model is trained and optimized through the reward function to find a strategy that can maximize the cumulative reward under a given state space and action space. This usually involves an iterative optimization process. In each round, the model tries different charge and discharge strategies, evaluates their effects based on the reward function, and then adjusts the model parameters in order to obtain higher rewards in future decisions. Through repeated training and optimization, the charge and discharge control model can learn a set of complex charge and discharge strategies that take into account future market changes and battery health conditions, and realize intelligent and efficient management of energy storage systems.

[0123] Based on steps S236 to S237, the new energy power system can intelligently generate a charging and discharging strategy for the energy storage system based on prediction information and optimization objectives, ensuring that the system can flexibly and efficiently dispatch energy when responding to renewable energy fluctuations and load changes, thereby achieving the dual goals of economic operation and environmental protection.

[0124] Optionally, based on the prediction results, a target scheduling strategy is generated, including:

[0125] Step S241, obtaining the historical electricity usage information of the target object.

[0126] In step S241, historical electricity consumption data of a target object (such as a household, enterprise or community) is collected. Such data generally include hourly or daily electricity consumption over a period of time (such as weeks or months) in the past.

[0127] Step S242: Based on the historical electricity usage information, a power usage behavior prediction model of the target object is constructed in response to the historical electricity usage information of the target object.

[0128] In step S242, the historical electricity consumption data collected in step S241 is used to construct an electricity consumption behavior prediction model using machine learning or deep learning algorithms. This may include the use of time series analysis, support vector machines (SVM), deep neural networks (DNN), or other models suitable for processing electricity data. The model is designed to learn the periodicity, seasonality, and relationship with other factors (such as weather, electricity prices, etc.) of the target object's electricity consumption pattern, so as to predict the target object's future electricity demand.

[0129] Step S243, generating a target scheduling strategy based on the electricity consumption behavior prediction model, prediction results and real-time electricity prices.

[0130] In step S243, the prediction results of the power consumption behavior prediction model are combined with the power generation prediction, load demand prediction results and real-time electricity price information obtained by multi-model fusion prediction to generate the optimal scheduling strategy for the target object. The target scheduling strategy is intended to guide the target object on how to adjust the power consumption in different electricity price periods to reduce electricity costs, balance supply and demand, and optimize resource utilization. For example, the system may recommend increasing the use of adjustable loads during low electricity price periods and reducing unnecessary power consumption during peak electricity price periods.

[0131] Based on steps S241 to S243, based on the user's historical electricity consumption information and real-time market conditions, the target scheduling strategy is intelligently generated to guide users to optimize their electricity consumption behavior, while ensuring the balance of supply and demand in the power system, achieving efficient allocation of resources and reducing operating costs. It is an important part of improving system operating efficiency and user satisfaction in smart grids and energy Internet.

[0132] Optionally, the method further includes the following steps:

[0133] Step S244: determining the operating status of the user's smart device based on the user's power usage behavior prediction result.

[0134] In step S244, based on the prediction results of the user's electricity consumption behavior prediction model, the optimal operating state of the user-side smart devices (such as electric vehicle charging piles, smart home devices, smart air conditioners, etc.) is determined. In this step, the system analyzes the predicted user load demand and real-time electricity prices to determine which smart devices can be operated or charged at the current electricity price to reduce the user's total electricity cost while ensuring the stable operation of the power system.

[0135] Step S245: Based on the operating status of the user's smart device, control the operation of the user's smart device.

[0136] In step S245, according to the optimal operating state of the user's smart device, the system automatically adjusts the operating or charging state of the device through the communication interface with the smart device. For example, when it is predicted that the user's electricity demand is low during the low electricity price period, the system will recommend or automatically control the charging time of the electric vehicle to be adjusted to this period to make full use of the low-priced electricity. At the same time, when it is predicted that the electricity demand during peak hours is too high, the system will reduce the power consumption of certain non-emergency devices accordingly, such as automatically adjusting the air conditioning temperature, delaying the heating of the water heater, etc., so as to avoid overloading the power grid and achieve a balance between supply and demand.

[0137] Based on steps S244 to S245, the user's electricity consumption behavior can be intelligently predicted, and the operation of smart devices can be controlled accordingly to achieve demand-side response, balance electricity supply and demand, reduce operating costs, and improve user experience and the overall efficiency of the power system.

[0138] Furthermore, based on the prediction results, a target scheduling strategy is generated, including:

[0139] Step S251, obtaining a local prediction result, where the local prediction result is a predicted load demand and predicted power generation of an energy storage unit of an energy storage system in a target power system.

[0140] In step S251, the predicted load demand and predicted power generation of each energy storage unit in the future period are obtained. The local prediction results are based on factors such as specific meteorological conditions, historical load data, and electricity price fluctuations at the location of the energy storage unit. The local prediction results provide a basis for autonomous control and economic dispatch of the energy storage unit.

[0141] Step S252: Generate a local dispatch strategy for each energy storage unit based on the local prediction results.

[0142] In step S252, each energy storage unit independently generates its local dispatch strategy based on the local prediction results. The local dispatch strategy takes into account the state of charge (SOC) of the energy storage unit, the predicted load demand and power generation, and the real-time electricity price, aiming to achieve the economic operation of the energy storage unit itself and extend the battery life.

[0143] Step S253, obtaining status information of each energy storage unit.

[0144] In step S253, the status information of each energy storage unit is obtained in real time, including but not limited to: Current state of charge (SOC): reflects the level of electricity stored in the energy storage unit. Health status: monitors the health status of the energy storage unit, including the degree of battery aging. Operation status: charging, discharging or holding status. This status information is crucial for the global control layer to formulate a comprehensive scheduling strategy.

[0145] Step S254, generating a target scheduling strategy based on the local scheduling strategy of each energy storage unit, the status information of each energy storage unit, and the prediction results.

[0146] In step S254, the global control layer integrates the local dispatching strategies and status information of all energy storage units, combines the global forecast results (including but not limited to load demand, renewable energy generation, electricity price forecast, etc.), and generates a target dispatching strategy. This strategy aims to achieve global optimization, ensure the balance of supply and demand of the entire power system, and take into account both economy and energy storage system life management. It includes the following steps:

[0147] a. Resource integration: The global control layer evaluates the charging and discharging capabilities and status of all energy storage units, and determines which units participate in charging and which participate in discharging to balance the total load demand.

[0148] b. Collaborative optimization: Based on the prediction results and local scheduling strategies, the global control layer coordinates the charging and discharging behaviors of each energy storage unit to avoid global resource waste or supply and demand imbalance caused by local optimization.

[0149] c. Economic dispatch: The global control layer considers the economy of the entire system and minimizes operating costs by optimizing charging and discharging strategies while ensuring the reliability of power supply.

[0150] d. Fault prevention: Using digital twin technology and fault diagnosis models, the global control layer monitors the operating status of the energy storage system, prevents potential faults, and ensures stable operation of the system.

[0151] Based on steps S251 to S254, the multi-level control architecture can realize the autonomous optimization of local energy storage units and the coordinated dispatch of the global power system, and improve the economic operation efficiency and reliability of the new energy power system. This hierarchical control strategy effectively solves the challenges brought by the volatility and uncertainty of new energy and is a key component in smart grid management.

[0152] Figure 2 is a flow chart of another energy management method for a new energy power system according to one embodiment of the present invention. Figure 2 As shown, the method comprises the following steps:

[0153] Step S201, performing prediction based on a first preset model in the preset models and basic data to obtain a first result;

[0154] Step S202, performing prediction based on a second preset model in the preset model and basic data to obtain a second result;

[0155] Step S203, performing prediction based on a third preset model in the preset models and the basic data to obtain a third result;

[0156] Step S204, determining a prediction result based on the first result, the second result and the third result.

[0157] Step S211, constructing an objective function based on the predicted load demand and the predicted power generation;

[0158] Step S212, solving the objective function based on a preset algorithm to obtain a power supply decision quantity;

[0159] Step S213, generating a target scheduling strategy based on the power supply decision quantity.

[0160] Step S221, generating a charging and discharging strategy for the energy storage system in the target power system based on the prediction result;

[0161] Step S222: adjusting the energy supply operation of the target power system based on the target scheduling strategy and the charging and discharging strategy.

[0162] Step S231, defining the state space of the energy storage system based on the real-time electricity price, the charging and discharging state of the energy storage system and the prediction result;

[0163] Step S232, defining an action space of the energy storage system based on action parameters of the energy storage system, wherein the action parameters include: a charging state, a discharging state, and a holding state;

[0164] Step S233, generating a charge and discharge control model of the energy storage system based on the state space and the action space;

[0165] Step S234, obtaining optimization target parameters, wherein the optimization target parameters include: economic target and life management target;

[0166] Step S235: generating a charge and discharge strategy based on the charge and discharge control model and the optimization target parameters.

[0167] Step S241, obtaining historical electricity usage information of the target object;

[0168] Step S242, based on the historical electricity usage information, constructing a power usage behavior prediction model of the target object in response to the historical electricity usage information of the target object;

[0169] Step S243, generating a target scheduling strategy based on the electricity consumption behavior prediction model, prediction results and real-time electricity prices.

[0170] Step S244, determining the operating status of the user's smart device based on the user's power consumption behavior prediction result;

[0171] Step S245: Based on the operating status of the user's smart device, control the operation of the user's smart device.

[0172] Step S251, obtaining a local prediction result, where the local prediction result is a predicted load demand and predicted power generation of an energy storage unit of an energy storage system in a target power system;

[0173] Step S252, generating a local dispatching strategy for each energy storage unit based on the local prediction result;

[0174] Step S253, obtaining status information of each energy storage unit;

[0175] Step S254, generating a target scheduling strategy based on the local scheduling strategy of each energy storage unit, the status information of each energy storage unit, and the prediction results.

[0176] Based on the above steps S201 to S254, in an embodiment of the present invention, by predicting the supply and demand of the new energy power system and intelligently optimizing the charging and discharging control of the energy storage system, demand response is achieved by combining the prediction of user-side electricity consumption behavior and intelligent device control, and local and global coordinated optimization is achieved through a multi-level control architecture, thereby improving the ability to cope with load fluctuations, thereby improving the economy, stability and technical effects of the new energy power system, and further solving the technical problem of imbalance in supply and demand of the new energy power system caused by new energy fluctuations.

[0177] Through the description of the above implementation methods, those skilled in the art can clearly understand that the method according to the above embodiment can be implemented by means of software plus a necessary general hardware platform, and of course can also be implemented by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present invention, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, a magnetic disk, or an optical disk), and includes a number of instructions for enabling a terminal device (which can be a mobile phone, a computer, a server, or a network device, etc.) to execute the methods described in each embodiment of the present invention.

[0178] According to an embodiment of the present invention, an embodiment of an energy management device for a new energy power system is provided. It should be noted that the device can be used to execute the energy management method for the new energy power system.

[0179] In an embodiment of the present invention, an energy management device for a new energy power system is also provided, which is used to implement the above-mentioned embodiments and preferred implementation modes, and will not be repeated hereafter. As used below, the term "module" can implement a combination of software and / or hardware for a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, the implementation of hardware, or a combination of software and hardware, is also possible and conceivable.

[0180] Figure 31 is a structural block diagram of an energy management device for a new energy power system according to one embodiment of the present invention. Figure 3 As shown, the device comprises:

[0181] The acquisition module 301 is used to acquire basic data, including: load demand of the target power system, renewable energy power generation and meteorological data;

[0182] Prediction module 302, prediction module 302 is used to make predictions based on a preset model and basic data to obtain prediction results, the prediction results include: predicted load demand and predicted power generation;

[0183] A generation module 303, the generation module 303 is used to generate a target scheduling strategy based on the prediction result;

[0184] The scheduling module 304 is used to adjust the energy supply operation of the target power system based on the target scheduling strategy.

[0185] Optionally, the prediction module 302 is also used to make predictions based on a first preset model and basic data in the preset model to obtain a first result; make predictions based on a second preset model and basic data in the preset model to obtain a second result; make predictions based on a third preset model and basic data in the preset model to obtain a third result; determine the prediction result based on the first result, the second result and the third result.

[0186] Optionally, the generation module 303 is also used to construct an objective function based on the predicted load demand and the predicted power generation; solve the objective function based on a preset algorithm to obtain a power supply decision quantity; and generate a target scheduling strategy based on the power supply decision quantity.

[0187] Optionally, the generation module 303 is further used to generate a charging and discharging strategy for the energy storage system in the target power system based on the prediction results; the scheduling module 304 is further used to adjust the energy supply operation of the target power system based on the target scheduling strategy and the charging and discharging strategy.

[0188] Optionally, the generation module 303 is also used to define the state space of the energy storage system based on the real-time electricity price, the charging and discharging state of the energy storage system and the prediction results; define the action space of the energy storage system based on the action parameters of the energy storage system, wherein the action parameters include: charging state, discharging state and holding state; generate a charging and discharging control model of the energy storage system based on the state space and the action space; obtain optimization target parameters, wherein the optimization target parameters include: economic target and life management target; generate a charging and discharging strategy based on the charging and discharging control model and the optimization target parameters.

[0189] Optionally, the generation module 303 is also used to obtain local prediction results, which are the predicted load demand and predicted power generation of the energy storage units of the energy storage system in the target power system; based on the local prediction results, generate a local scheduling strategy for each energy storage unit; obtain status information of each energy storage unit; and generate a target scheduling strategy based on the local scheduling strategy of each energy storage unit, the status information of each energy storage unit, and the prediction results.

[0190] It should be noted that the above modules can be implemented by software or hardware. For the latter, it can be implemented in the following ways, but not limited to: the above modules are all located in the same processor; or the above modules are located in different processors in any combination.

[0191] According to one embodiment of the present invention, there is also provided an electronic device, comprising: a memory storing an executable program; and a processor for running the program, wherein the program executes the energy management method of the new energy power system when running.

[0192] Optionally, in this embodiment, the processor may be configured to perform the following steps through a computer program:

[0193] Step S10, obtaining basic data, the basic data including: load demand of the target power system, renewable energy power generation and meteorological data;

[0194] Step S12, performing prediction based on the preset model and basic data to obtain prediction results, the prediction results including: predicted load demand and predicted power generation;

[0195] Step S14, generating a target scheduling strategy based on the prediction results;

[0196] Step S16: adjusting the energy supply operation of the target power system based on the target dispatching strategy.

[0197] According to one embodiment of the present invention, a computer-readable storage medium is also provided, which includes a stored executable program, wherein when the executable program is running, the device where the storage medium is located is controlled to execute the above-mentioned energy management method of the new energy power system.

[0198] Optionally, in this embodiment, the storage medium may be configured to store a computer program for performing the following steps:

[0199] Step S10, obtaining basic data, the basic data including: load demand of the target power system, renewable energy power generation and meteorological data;

[0200] Step S12, performing prediction based on the preset model and basic data to obtain prediction results, the prediction results including: predicted load demand and predicted power generation;

[0201] Step S14, generating a target scheduling strategy based on the prediction results;

[0202] Step S16: adjusting the energy supply operation of the target power system based on the target dispatching strategy.

[0203] Optionally, in this embodiment, the above-mentioned storage medium may include but is not limited to: a USB flash drive, a read-only memory (ROM), a random access memory (RAM), a mobile hard disk, a magnetic disk or an optical disk, and other media that can store computer programs.

[0204] According to one embodiment of the present invention, a computer program product is also provided, including a computer program, which implements the above-mentioned energy management method of the new energy power system when executed by a processor.

[0205] Optionally, in this embodiment, the computer program product may be configured as a computer program for executing the following steps:

[0206] Step S10, obtaining basic data, the basic data including: load demand of the target power system, renewable energy power generation and meteorological data;

[0207] Step S12, performing prediction based on the preset model and basic data to obtain prediction results, the prediction results including: predicted load demand and predicted power generation;

[0208] Step S14, generating a target scheduling strategy based on the prediction results;

[0209] Step S16: adjusting the energy supply operation of the target power system based on the target dispatching strategy.

[0210] An embodiment of the present application further provides a computer program product, including a computer program, which implements the methods in various embodiments of the present invention when executed by a processor.

[0211] An embodiment of the present application further provides a computer program product, including a non-volatile computer-readable storage medium, wherein the non-volatile computer-readable storage medium is used to store a computer program, and when the computer program is executed by a processor, the method in each embodiment of the present invention is implemented.

[0212] The embodiments of the present application further provide a computer program, which implements the methods in the above-mentioned embodiments of the present invention when executed by a processor.

[0213] In the above embodiments of the present invention, 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.

[0214] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the device embodiments described above are only schematic. For example, the division of the units can be a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of units or modules, which can be electrical or other forms.

[0215] 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 units. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0216] 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.

[0217] 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 storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, magnetic disk or optical disk and other media that can store program codes.

[0218] 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 principle of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. An energy management method for a new energy power system, characterized in that: include: Acquiring basic data, the basic data including: load demand of the target power system, renewable energy power generation and meteorological data; Perform prediction based on the preset model and the basic data to obtain prediction results, the prediction results including: predicted load demand and predicted power generation; Based on the prediction results, generating a target scheduling strategy; Based on the target scheduling strategy, the energy supply operation of the target power system is adjusted.

2. The method according to claim 1, characterized in that Performing prediction based on the preset model and the basic data to obtain the prediction result includes: Perform prediction based on a first preset model in the preset models and the basic data to obtain a first result; Perform prediction based on a second preset model in the preset models and the basic data to obtain a second result; Perform prediction based on a third preset model in the preset models and the basic data to obtain a third result; The prediction result is determined based on the first result, the second result and the third result.

3. The method according to claim 1 or 2, characterized in that: Based on the prediction result, generating the target scheduling strategy includes: constructing an objective function based on the predicted load demand and the predicted power generation; Solving the objective function based on a preset algorithm to obtain a power supply decision quantity; Based on the power supply decision quantity, the target scheduling strategy is generated.

4. The method according to claim 1 or 2, characterized in that: Based on the target scheduling strategy, adjusting the energy supply operation of the target power system includes: Based on the prediction result, generating a charging and discharging strategy for the energy storage system in the target power system; Based on the target scheduling strategy and the charging and discharging strategy, the energy supply operation of the target power system is adjusted.

5. The method according to claim 4, characterized in that Generating the charging and discharging strategy of the energy storage system in the target power system based on the prediction result includes: Based on the real-time electricity price, the charging and discharging state of the energy storage system and the prediction result, define the state space of the energy storage system; Based on the action parameters of the energy storage system, defining the action space of the energy storage system, wherein the action parameters include: charging state, discharging state and holding state; Based on the state space and the action space, generating a charge and discharge control model of the energy storage system; Obtaining optimization target parameters, wherein the optimization target parameters include: an economic target and a life management target; The charge and discharge strategy is generated based on the charge and discharge control model and the optimization target parameter.

6. The method according to claim 5, characterized in that Based on the prediction result, generating the target scheduling strategy includes: Obtain historical electricity consumption information of the target object; Based on the historical electricity usage information, constructing an electricity usage behavior prediction model for the target object; The target scheduling strategy is generated based on the electricity consumption behavior prediction model, the prediction result and the real-time electricity price.

7. The method according to claim 1, characterized in that Based on the prediction results, a target scheduling strategy is generated, including: Acquire a local prediction result, wherein the local prediction result is a predicted load demand and a predicted power generation of an energy storage unit of an energy storage system in the target power system; Based on the local prediction results, generating a local scheduling strategy for each of the energy storage units; Acquiring status information of each of the energy storage units; Based on the local scheduling strategy of each of the energy storage units, the status information of each of the energy storage units, and the prediction results, a target scheduling strategy is generated.

8. An energy management device for a new energy power system, characterized in that: include: An acquisition module, for acquiring basic data, wherein the basic data includes: load demand of a target power system, power generation of renewable energy, and meteorological data; A prediction module performs prediction based on a preset model and the basic data to obtain a prediction result, wherein the prediction result includes: predicted load demand and predicted power generation; A generation module generates a target scheduling strategy based on the prediction result; The scheduling module adjusts the energy supply operation of the target power system based on the target scheduling strategy.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a stored executable program, wherein when the executable program is executed, the device where the storage medium is located is controlled to execute the method according to any one of claims 1 to 7.

10. A computer program product, characterized in that The invention comprises a computer program which, when executed by a processor, implements the method according to any one of claims 1 to 7.

Images