Multi-source collaborative energy storage peak regulation heat supply optimization method and related device

Abstract

The invention discloses a multi-source collaborative energy storage peak regulation heat supply optimization method and a related device. The method comprises the following steps: acquiring meteorological data, historical load data, an electricity price signal and an equipment state in real time; according to the meteorological data, the historical load data, the electricity price signal and the equipment state, utilizing an LSTM neural network to predict the load and the electricity price in the future 72 hours; according to the predicted load and electricity price in the future 72 hours, an optimal scheduling scheme is generated through a reinforcement learning-fuzzy control hybrid algorithm; a scheduling instruction is generated according to the optimal scheduling scheme, the scheduling instruction is executed through the Internet of Things equipment, and the method and the related device can improve the stability of energy supply.

Description

Technical Field

[0001] The present invention belongs to the technical field of integrated energy systems, and relates to a multi-source collaborative energy storage peak shaving and heat supply optimization method and related devices. Background Art

[0002] With the increasing global emphasis on energy conservation, emission reduction and sustainable development, the heating industry is facing an urgent need to transform from the traditional high-energy consumption and high-pollution mode to a green and efficient mode. Against this background, many problems have emerged in traditional heating systems, such as:

[0003] Traditional heating systems mostly rely on a single energy source, such as fossil fuels like coal and natural gas. On the one hand, the excessive reliance on these limited resources not only faces the risk of unstable energy supply, but also makes it difficult to control the heating cost due to resource price fluctuations. On the other hand, the large-scale combustion of fossil fuels is one of the main sources of carbon emissions, causing serious environmental pollution and not meeting the current environmental protection requirements. According to statistics, the waste heat utilization rate of traditional heating systems is generally low, only about 65%, and a large amount of energy is wasted during production and transmission;

[0004] In terms of energy storage, traditional heating systems mostly use a single energy storage medium, such as hot water tanks. Such energy storage methods have a low energy density and are difficult to meet the large-scale and long-term energy storage requirements. Moreover, the single energy storage medium has poor adaptability and cannot flexibly cope with the heating load fluctuations under different working conditions. When emergencies or load peaks occur, the stability and reliability of heating are often unable to be guaranteed;

[0005] From the perspective of control strategies, traditional heating systems mostly rely on fixed rules for control. In the face of complex and changeable meteorological conditions, user load changes and real-time electricity price fluctuations, this fixed strategy lacks flexibility and self-adaptability and is difficult to achieve the optimal operation of the system. For example, it is unable to dynamically adjust the energy conversion and storage strategies according to the real-time electricity price, missing the opportunity to reduce costs by using low-price electricity, and it is also difficult to accurately control the heating parameters according to meteorological changes, resulting in energy waste or unqualified heating quality. In the current situation of increasing energy transformation and environmental protection pressure, the defects of traditional heating systems in energy utilization, energy storage and control are becoming more and more prominent, leading to unstable energy supply. Summary of the Invention

[0006] The purpose of the present invention is to overcome the above-mentioned disadvantages of the prior art, and provide a multi-source collaborative energy storage peak shaving and heat supply optimization method and related devices, which can improve the stability of energy supply.

[0007] To achieve the above object, the present invention discloses a multi-source collaborative energy storage peak shaving and heat supply optimization method, including:

[0008] Obtain meteorological data, historical load data, electricity price signals, and equipment status in real time;

[0009] According to the meteorological data, historical load data, electricity price signals, and equipment status, use the LSTM neural network to predict the load and electricity price for the next 72 hours;

[0010] According to the predicted load and electricity price for the next 72 hours, generate an optimal scheduling plan through a hybrid algorithm of reinforcement learning and fuzzy control;

[0011] Generate a scheduling instruction according to the optimal scheduling plan and execute the scheduling instruction through Internet of Things devices.

[0012] Furthermore, the process of generating the optimal scheduling plan through the hybrid algorithm of reinforcement learning and fuzzy control is as follows:

[0013] Generate an optimal scheduling plan based on the deep Q-network model and the fuzzy control rule base.

[0014] The present invention discloses a multi-source collaborative energy storage peak shaving and heat supply system, including a multi-source energy input module, a composite energy storage unit, a dynamic energy flow network, an intelligent decision-making and control module, and a virtual power plant operation platform. Among them, the intelligent decision-making and control module is connected to the multi-source energy input module, the composite energy storage unit, and the virtual power plant operation platform through the dynamic energy flow network. Among them, the intelligent decision-making and control module is used to implement the optimal method for energy storage peak shaving and heat supply with multi-source collaboration.

[0015] Furthermore, the multi-source energy input module includes a geothermal energy collection device, an industrial waste heat recovery device, a biomass boiler, and a wind-solar power generation component, and the geothermal energy collection device, the industrial waste heat recovery device, the biomass boiler, and the wind-solar power generation component are connected in parallel.

[0016] Furthermore, the composite energy storage unit includes a thermochemical energy storage TCES module and a phase change material energy storage PCM module. Among them, the thermochemical energy storage TCES module and the phase change material energy storage PCM module are connected in series and coupled through a cascaded heat exchanger.

[0017] Furthermore, the working temperature range of the thermochemical energy storage TCES module is 200 - 500 °C, and the working temperature range of the phase change material energy storage PCM module is 50 - 150 °C.

[0018] Furthermore, the intelligent decision-making and control module includes:

[0019] A prediction sub-module that predicts the heat load and electricity price for the next 72 hours based on the LSTM neural network;

[0020] An optimization sub-module that uses the ε-constraint method to solve the multi-objective optimization problem, and the objective function includes: Among them,

[0021] Let λ be the carbon emission weight coefficient, π(t) be the electricity price at time t, and γ grid and γ biomass be the carbon emission factors of the power grid and biomass energy respectively;

[0022] The execution sub-module dynamically adjusts the operating parameters of the heat pump, boiler and energy storage system through Internet of Things devices.

[0023] Furthermore, the multi-source energy input module is configured with a waste heat grade improvement device.

[0024] The present invention discloses a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the steps of the multi-source collaborative energy storage peak shaving and heating optimization method are implemented.

[0025] The present invention discloses a computer-readable storage medium storing a computer program, and when the computer program is executed by a processor, the steps of the multi-source collaborative energy storage peak shaving and heating optimization method are implemented.

[0026] The present invention has the following beneficial effects:

[0027] When the multi-source collaborative energy storage peak shaving and heating optimization method and related devices of the present invention are specifically operated, through the multi-source energy input module, geothermal energy, industrial waste heat, biomass energy and wind-solar power generation components are integrated, significantly improving the diversity and complementarity of energy utilization, changing the situation that the traditional heating system overly relies on a single energy source, realizing the collaborative utilization of multiple energy sources, effectively improving the energy utilization efficiency, reducing the dependence on a single energy source, and ensuring the stability of energy supply.

[0028] By setting up a composite energy storage unit and adopting a cascaded design of a thermochemical energy storage and a phase change material energy storage module, the energy storage efficiency and flexibility are greatly improved. The cascaded heat exchange efficiency of the thermochemical energy storage and the phase change material energy storage module is ≥92%, the energy density is increased by 3 times, and the modular design facilitates the flexible expansion and upgrade of the system. The expansion of a 10MW system can be completed within 4 hours, changing the situation of low energy density and poor adaptability of traditional single energy storage media, being able to better cope with the fluctuations of heating load, ensuring efficient storage and release of energy under different working conditions, and enhancing the stability and reliability of the entire heating system;

[0029] By setting up an intelligent decision-making control module and applying a hybrid algorithm of reinforcement learning and fuzzy control, the response speed and decision-making accuracy of the system are significantly improved. It can receive meteorological data, load forecasting, and electricity price signals in real time, quickly generate an optimal scheduling plan, with the system response speed increased by 40%, and the multi-objective optimization solution time ≤ 30 seconds. It changes the lag of the traditional fixed-rule control strategy, enabling the system to make timely adjustments according to the complex and changeable operating environment, effectively improving the economy, environmental protection, and reliability of the heating system operation;

[0030] By setting up a virtual power plant operation platform and integrating a blockchain intelligent contract system, the energy trading mode is optimized, the trading cost is reduced, and decentralized trading settlement between multiple energy suppliers and users is achieved. The trading cost is reduced by 35%, and automatic settlement is carried out every 15 minutes. It changes the problems of cumbersome traditional energy trading processes and high trust costs, improves trading efficiency and transparency, and enhances the competitiveness and profitability of the system in participating in the electricity market trading;

[0031] By setting up a two-way energy flow network, configuring a temperature-adaptive heat pump-absorption chiller coupling device and a power-thermal conversion strategy based on real-time electricity prices, two-way flexible conversion and storage of energy are realized. In summer, it can reverse refrigerate and store cold energy, and preferentially convert electric energy into thermal energy for storage during off-peak electricity price periods, with a conversion efficiency ≥ 85%. It changes the one-way and single conversion mode of the traditional energy flow network, improves the flexibility and economy of energy utilization, can better adapt to the energy demand changes in different seasons and different electricity price periods, and enhances the comprehensive energy utilization efficiency. Brief Description of the Drawings

[0032] The accompanying drawings forming a part of this invention are used to provide a further understanding of the invention. The schematic embodiments of the invention and their descriptions are used to explain the invention and do not constitute an improper limitation of the invention. In the drawings:

[0033] Figure 1 It is a flowchart of the method of the present invention. Detailed Embodiments

[0034] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are some, but not all, of the embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0035] In the description of the present invention, it should be understood that the terms "include" and "comprise" indicate the presence of the described features, wholes, steps, operations, elements, and / or components, but do not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components, and / or their combinations.

[0036] It should also be understood that the terms used in the specification of the present invention are merely for the purpose of describing specific embodiments and are not intended to limit the present invention. As used in the specification of the present invention and the appended claims, unless the context clearly indicates otherwise, the singular forms "a", "an" and "the" are intended to include the plural forms.

[0037] It should be further understood that the term "and / or" used in the specification of the present invention and the appended claims refers to any combination and all possible combinations of one or more of the associated listed items, and includes these combinations. For example, A and / or B can represent three cases: A exists alone, A and B exist simultaneously, and B exists alone. In addition, the character " / " in the present invention generally represents an "or" relationship between the contextually related objects.

[0038] It should be understood that although the terms first, second, third, etc. may be used in the embodiments of the present invention to describe preset ranges, etc., these preset ranges should not be limited to these terms. These terms are only used to distinguish the preset ranges from each other. For example, without departing from the scope of the embodiments of the present invention, the first preset range may also be referred to as the second preset range, and similarly, the second preset range may also be referred to as the first preset range.

[0039] Depending on the context, the word "if" as used herein can be interpreted as "when" or "while" or "in response to determining" or "in response to detecting". Similarly, depending on the context, the phrase "if determined" or "if detected (stated condition or event)" can be interpreted as "when determined" or "in response to determining" or "when detected (stated condition or event)" or "in response to detecting (stated condition or event)".

[0040] To make the objectives, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are some, but not all, of the embodiments of the present invention. Generally, the components described and shown in the drawings herein can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present invention provided in the drawings is not intended to limit the scope of the claimed present invention, but merely represents selected embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the scope of protection of the present invention.

[0041] Various structural schematic diagrams according to the disclosed embodiments of the present invention are shown in the accompanying drawings. These figures are not drawn to scale, where for the purpose of clear expression, certain details are enlarged and certain details may be omitted. The shapes of various regions and layers shown in the figures, as well as their relative sizes and positional relationships, are merely exemplary. In practice, there may be deviations due to manufacturing tolerances or technical limitations, and those skilled in the art can design regions / layers with different shapes, sizes, and relative positions according to actual needs.

[0042] Embodiment 1

[0043] Reference Figure 1 , the multi-source collaborative energy storage peak shaving and heating optimization method of the present invention includes the following steps:

[0044] 1) Data collection and preprocessing. Specifically, meteorological data, historical load data, electricity price signals, and equipment status are obtained in real time;

[0045] 2) Load and electricity price prediction; according to the collected data, the load and electricity price for the next 72 hours are predicted using an LSTM neural network, with an error rate ≤ 5%;

[0046] 3) Multi-objective optimization decision-making; according to the predicted load and electricity price for the next 72 hours, an optimal scheduling plan is generated through a hybrid algorithm of reinforcement learning - fuzzy control. The optimal scheduling plan includes the charging and discharging timings of the energy storage system, the output distribution ratio of multiple heat sources, and the operation mode switching of heat pumps and chillers;

[0047] 4) Dynamic execution and feedback; according to the optimal scheduling plan, a scheduling instruction is generated, the scheduling instruction is executed through Internet of Things devices, and the parameters are corrected in real time using adaptive PID control.

[0048] In step 3), the hybrid algorithm of reinforcement learning - fuzzy control includes:

[0049] Deep Q-network model:

[0050] State space S = {T out , L(t), SOC(t), π(t)}, action space A = {ΔP heat , ΔP cool , ΔP gril}, and the reward function is

[0051] where α + β + γ = 1, C base is the historical benchmark operating cost, E base is the historical benchmark carbon emission, and Rel(t) is the heating reliability index based on redundant heat source configuration;

[0052] Fuzzy control rule base:

[0053] The input variables are humidity H and wind speed V, and the output is the heating compensation coefficient K. The membership function adopts a Gaussian distribution, that is:

[0054] Generate K through the Mamdani inference rule and correct the actual heating quantity Q actual = Q set ·K.

[0055] In step 3), in the multi-objective optimization decision-making process, the carbon emission is:

[0056]

[0057] Among them, p i (t) is the output of the i-th type of energy, and γ i is the corresponding carbon emission factor;

[0058] The heating reliability is ensured by the redundant heat source configuration formula where η j is the efficiency of the j-th redundant heat source, and S j is its capacity;

[0059] The operating cost formula C op = C grid + C fuel + C main , including the electricity purchase cost, fuel cost and equipment maintenance cost.

[0060] In step 4), when the deviation between the actual load and the predicted value exceeds 10%, the rolling optimization mechanism is triggered; the SOC state of charge of the energy storage system is maintained in the range of 30%-80% to ensure flexibility.

[0061] Embodiment 2

[0062] The multi-source collaborative energy storage peak shaving and heating system described in this embodiment includes:

[0063] A multi-source energy input module that integrates a geothermal energy collection device, an industrial waste heat recovery device, a biomass boiler and a wind-solar power generation module, and realizes energy complementarity through a multi-energy flow coupling interface;

[0064] A composite energy storage unit that includes a thermochemical energy storage TCES module and a phase change material energy storage PCM module. Among them, the thermochemical energy storage TCES module uses metal hydride heat storage technology, and the phase change material energy storage PCM module selects fatty acid-based phase change materials. The two are coupled in series through a cascaded heat exchanger, and the heat transfer efficiency is ≥92%;

[0065] A dynamic energy flow network, consisting of a two-way heat exchange pipe network, power electronic converters, and intelligent valves, supports the bidirectional flow of energy among distributed heat sources, power grids, and energy storage systems;

[0066] An intelligent decision-making and control module, equipped with a hybrid algorithm of reinforcement learning and fuzzy control, receives meteorological data, load forecasts, and electricity price signals in real time and generates an optimal scheduling strategy;

[0067] A virtual power plant operation platform, integrating a blockchain intelligent contract system, realizes decentralized trading and settlement among multiple energy suppliers and users.

[0068] In this embodiment, the composite energy storage unit adopts a modular design:

[0069] Each module is a movable container structure, internally integrating a TCES reaction bed, a PCM heat storage box, and a heat exchange system;

[0070] The operating temperature range of the thermochemical energy storage TCES module is 200 - 500 °C, and the operating temperature range of the phase change material energy storage PCM module is 50 - 150 °C;

[0071] The modules are quickly spliced and expanded through a standardized interface, and the expansion time ≤ 4 h.

[0072] In this embodiment, the intelligent decision-making and control module includes:

[0073] A prediction sub-module, based on the LSTM neural network, predicts the heat load and electricity price fluctuations in the next 72 hours, with an error rate ≤ 5%;

[0074] An optimization sub-module, using the ε-constraint method to solve the multi-objective optimization problem, and the objective function includes: Among them,

[0075] λ is the carbon emission weight coefficient, π(t) is the electricity price at time t, and γ grid and γ biomass are the carbon emission factors of the power grid and biomass energy respectively;

[0076] An execution sub-module, dynamically adjusts the operating parameters of heat pumps, boilers, and energy storage systems through Internet of Things devices.

[0077] In this embodiment, the dynamic energy flow network is configured with:

[0078] A temperature adaptive heat pump-absorption chiller coupling device, supports reverse refrigeration in summer and stores cold energy, with a refrigeration COP ≥ 4.5;

[0079] A power-heat conversion strategy based on real-time electricity prices, preferentially converts electric energy into heat energy for storage during off-peak electricity price periods, with a conversion efficiency ≥ 85%.

[0080] In this embodiment, the virtual power plant operation platform includes:

[0081] A blockchain-based smart contract system to achieve the immutability and automatic settlement of transaction data, with a transaction confirmation time ≤ 5 min;

[0082] A day-ahead market bidding module to formulate the next-day energy trading plan according to the load forecasting results, with a bidding capacity error rate ≤ 3%;

[0083] A real-time balancing market response module to perform rapid power regulation in response to grid dispatching instructions, with a regulation rate ≥ 10% of the rated power / min.

[0084] In this embodiment, the multi-source energy input module is configured with a waste heat grade improvement device:

[0085] Industrial waste heat is raised to the available range of the TCES module through a multi-stage heat pump, with a temperature rise of 25 - 35°C per stage;

[0086] The biomass energy boiler is coupled with the phase change material energy storage PCM module to achieve efficient recovery of low-temperature waste heat, with a recovery efficiency ≥ 75%.

[0087] Embodiment 3

[0088] The multi-source collaborative energy storage peak shaving and heat supply system of the present invention includes:

[0089] 1. A multi-source energy input module:

[0090] 1.1. Geothermal energy collection: Drill a well 1800 meters deep vertically in the selected area, install a Φ219mm double U-shaped HDPE buried pipe heat exchanger, ensure that the pipe material has good thermal conductivity and corrosion resistance, and make the heat transfer medium flow in the pipe through a circulation pump to extract geothermal energy at a flow rate of 60 m 3 / h, achieving a water temperature difference of 12°C at the inlet and outlet, effectively increasing the geothermal extraction rate to 78%, and matching with a water source heat pump unit to make full use of the extracted geothermal energy for heating, with a heating capacity of 6.2 MW and a coefficient of performance COP of 4.5, greatly improving the energy utilization efficiency;

[0091] 1.2. Industrial waste heat recovery: For the high-temperature flue gas in the hot rolling process of the steel plant, a three-stage GEAM75-B plate heat exchanger is used for waste heat recovery. In the first-stage heat exchange, the 380°C high-temperature flue gas exchanges heat with the heat transfer oil, raising the temperature of the heat transfer oil from 180°C to 280°C, with a heat exchange efficiency of up to 85% in this process; in the second-stage heat exchange stage, the heat transfer oil transfers heat to the 80°C water, raising the water temperature to 150°C, with a heat exchange efficiency of 90%; in the third-stage heat exchange, the waste heat is used to drive the Yuanda BZQ1000 absorption chiller to generate 1000 kW of cooling capacity, realizing the cascade utilization of waste heat;

[0092] 1.3 Biomass energy boiler: A circulating fluidized bed boiler is selected, using straw pelletized fuel with a calorific value of 16 MJ / kg and an ash content of ≤3% to ensure efficient combustion of the fuel and low pollution emissions. The designed evaporation capacity of the boiler is 29 t / h, the steam temperature is maintained at 130 °C, and the pressure is 1.6 MPa. The supporting bag filter can control the emission concentration within 25 mg / m 3 , meeting the environmental protection standards;

[0093] 1.4 Wind-solar power generation components: Distributed monocrystalline silicon photovoltaic arrays are arranged. Through precise calculation and installation, the inclination angle of the photovoltaic panels is set at 35° to obtain the best lighting conditions, with an annual power generation of up to 2.8 GWh. At the same time, 5 wind turbines are installed, with the hub height set at 100 m to effectively utilize wind energy resources, and the annual power generation is 3.2 GWh. To balance the intermittency of wind-solar power generation, a 10 MW / 20 MWh lithium battery pack is configured, with a charge-discharge efficiency of 92% to ensure the stability of power supply.

[0094] 2. Composite energy storage unit:

[0095] 2.1 Thermal chemical energy storage TCES module: LaNi5 metal hydride with a purity of 99.9% is used as the heat storage material and made into particles with a particle size of 0.5 - 1.0 mm to ensure good reaction activity and heat storage performance. The reaction bed is made of 316L stainless steel and lined with an enamel anti-corrosion layer to ensure the long-term stable operation of the equipment in high-temperature and high-pressure environments. A seamless steel pipe with a total length of 1200 m and a diameter of Φ32×3 mm is built-in as the heat exchange coil for efficient heat transfer. A hydrogen storage tank with a volume of 50 m 3 and a design pressure of 3.5 MPa is equipped to store the hydrogen generated by the reaction. Under the 200 - 500 °C cycling condition, the heat storage density of this module can reach 1.5 kWh / kg. When charging with 300 °C heat transfer oil at a flow rate of 50 m 3 / h, it only takes 2 hours to complete the charging process;

[0096] 2.2 Phase change material energy storage PCM module: The phase change material palmitic acid with a purity of 99% and expanded graphite are compounded in a mass ratio of 9:1 to improve the thermal conductivity and stability of the material. The heat storage tank is designed as a cuboid structure with dimensions L×W×H = 5 m×2 m×2 m, made of aluminum material with a wall thickness of 5 mm. A serpentine heat exchange coil made of Φ25×2 mm copper tubes is arranged inside to increase the heat exchange area. The outside of the box is wrapped with a 50 mm thick nano-aerogel felt insulation layer with a thermal conductivity of ≤0.015 W / (m·K) to effectively reduce heat loss. The phase change temperature of this module is stable at 63 °C (±2 °C), and the heat storage capacity of each heat storage tank is 150 kWh, with a charge-discharge rate of up to 100 kW;

[0097] Cascade coupling: The outlet of the thermochemical energy storage (TCES) module is connected to the inlet of the phase change material energy storage (PCM) module through a Φ159mm stainless steel pipe to achieve their cascade coupling. When the TCES module releases heat, the heat transfer oil with an outlet temperature of 300°C enters the inlet of the PCM module after being cooled to 180°C through a plate heat exchanger to ensure temperature matching. The hot water with an outlet temperature of 65°C from the TCES module serves as the low-temperature heat source of the heat pump unit to achieve efficient heat transfer and utilization. The cascade heat exchange efficiency is ≥92%.

[0098] 3. Dynamic energy flow network:

[0099] 3.1 Bidirectional heat exchange pipe network: Seamless steel pipes (φ219×8mm) are selected as the pipe network materials to ensure sufficient strength and pressure resistance. The design pressure is 2.5MPa. The outside of the pipe network is wrapped with a polyurethane foam insulation layer with a thickness of 80mm and a thermal conductivity of ≤0.024W / (m·K) to effectively reduce heat loss during transmission. Electric control valves are installed at key nodes of the pipe network. The regulation accuracy of the valves can reach ±1%, and the heat medium flow can be accurately controlled according to system requirements.

[0100] 3.2 Heat pump-absorption chiller coupling device: A water source heat pump unit with a heating capacity of 5MW and a coefficient of performance (COP) of 4.2 is adopted, and a lithium bromide absorption chiller with a refrigerating capacity of 3MW and a COP of 1.2 is supported. When the real-time electricity price is lower than 0.3 yuan / kWh, the system automatically switches to the refrigeration mode to achieve flexible conversion and storage of electricity, heat, and cold.

[0101] 4. Intelligent decision-making control module:

[0102] 4.1 Prediction sub-module: An LSTM neural network model is constructed. The input layer receives the historical load data of the previous 7 days and the current meteorological data, including temperature, humidity, and wind speed. Three hidden layers are set inside the network, with 128 neurons in each layer, and a fully connected layer is added to integrate information. The output layer predicts the load and electricity price every 15 minutes for the next 72h. The Adam optimizer is used, and the learning rate is set to 0.001. The root mean square error is used as the loss function. After 500 training cycles with a batch size of 64, after training, the RMSE of the heat load prediction is ≤3%, the mean absolute percentage error is ≤4.2%, the RMSE of the electricity price prediction is ≤5%, and the MAPE is ≤6.8%, with high prediction accuracy.

[0103] 4.2. Optimization Sub - module: The ε - constraint method is used to solve the multi - objective optimization problem. With the minimum operation cost as the main objective, the carbon emission constraint ε = 0.8 kg / kWh and the heating reliability constraint ε = 1.2 are set. The CPLEX 22.1 solver is adopted, the optimization period is set to 15 minutes, and the solving time ≤ 30S. It can quickly generate the optimal scheduling plan that meets the multi - objective requirements;

[0104] 4.3. Execution Sub - module: An Internet of Things control system based on the OPC UA 1.04 communication protocol is established to ensure that the data transmission delay ≤ 150ms and its IO response time ≤ 10ms, and it can execute control instructions quickly and accurately.

[0105] 5. Virtual Power Plant Operation Platform:

[0106] 5.1. Blockchain System: Build the underlying architecture based on Hyperledger Fabric 2.2. The organizational structure includes 3 energy suppliers, 1 grid company, and 1 aggregator. The PBFT consensus algorithm is adopted, 4 nodes are set, and the fault tolerance rate is 25%. To ensure the stability and reliability of the system, Solidity is used to write smart contracts to realize the automatic execution of power purchase agreements, the transaction confirmation time ≤ 3 minutes, and the settlement period is 15 minutes;

[0107] 5.2. Market Response Module: In the day - ahead market bidding, according to the load forecasting results, formulate the trading plan for the next day. The bidding capacity is 95% of the forecast load, and a 5% adjustment margin is reserved to cope with the fluctuations of the actual load. The bidding price is based on marginal cost pricing, with the valley price increased by 10% and the peak price decreased by 15%. In the real - time balancing market, a 20MW flywheel energy storage system is configured, and the response time ≤ 100ms, which can quickly adjust the power to meet the real - time needs of the power grid.

[0108] Example Four

[0109] A computer device includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the steps of the multi-source collaborative energy storage peak shaving and heating optimization method are implemented. For example, it includes: obtaining meteorological data, historical load data, electricity price signals, and equipment status in real time; using an LSTM neural network to predict the load and electricity price for the next 72 hours based on the meteorological data, historical load data, electricity price signals, and equipment status; generating an optimal scheduling plan through a hybrid algorithm of reinforcement learning and fuzzy control according to the predicted load and electricity price for the next 72 hours; generating a scheduling instruction according to the optimal scheduling plan and executing the scheduling instruction through an Internet of Things device. Among them, the memory may include internal memory, such as high-speed random access memory, and may also include non-volatile memory, such as at least one disk memory, etc.; the processor, network interface, and memory are interconnected through an internal bus, which can be an Industry Standard Architecture bus, a Peripheral Component Interconnect standard bus, an Extended Industry Standard Architecture bus, etc. The bus can be divided into an address bus, a data bus, a control bus, etc. The memory is used to store programs. Specifically, the program may include program code, and the program code includes computer operation instructions. The memory may include internal memory and non-volatile memory and provide instructions and data to the processor.

[0110] Embodiment Five

[0111] A computer-readable storage medium stores a computer program. When the computer program is executed by a processor, the steps of the multi-source collaborative energy storage peak shaving and heating optimization method are implemented. For example, it includes: obtaining meteorological data, historical load data, electricity price signals, and equipment status in real time; using an LSTM neural network to predict the load and electricity price for the next 72 hours based on the meteorological data, historical load data, electricity price signals, and equipment status; generating an optimal scheduling plan through a hybrid algorithm of reinforcement learning and fuzzy control according to the predicted load and electricity price for the next 72 hours; generating a scheduling instruction according to the optimal scheduling plan and executing the scheduling instruction through an Internet of Things device. Specifically, the computer-readable storage medium includes, but is not limited to, for example, volatile memory and / or non-volatile memory. The volatile memory may include random access memory (RAM) and / or cache memory, etc. The non-volatile memory may include read-only memory (ROM), hard disk, flash memory, optical disc, magnetic disk, etc.

[0112] Those skilled in the art should understand that the embodiments of the present application can be provided as a method, a system, or a computer program product. Therefore, the present application can take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present application can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0113] The present application is described with reference to the flowcharts and / or block diagrams of methods, apparatuses (systems), and computer program products according to the embodiments of the present application. It should be understood that each flow and / or block in the flowchart and / or block diagram, and the combination of flows and / or blocks in the flowchart and / or block diagram, can be realized by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to generate a machine, such that the instructions executed by the processor of the computer or other programmable data processing devices generate means for realizing the functions specified in Figure 1 one or more of the processes or multiple processes and / or blocks Figure 1 one or more of the blocks or multiple blocks.

[0114] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, such that the instructions stored in the computer-readable memory generate a manufactured article including instruction means that realizes the functions specified in Figure 1 one or more of the processes or multiple processes and / or blocks Figure 1 one or more of the blocks or multiple blocks.

[0115] These computer program instructions can also be loaded onto a computer or other programmable data processing device, such that a series of operation steps are executed on the computer or other programmable device to generate a computer-implemented process, and thus the instructions executed on the computer or other programmable device provide steps for realizing the functions specified in Figure 1 one or more of the processes or multiple processes and / or blocks Figure 1 one or more of the blocks or multiple blocks.

[0116] After considering the specification and the disclosure of the invention, those skilled in the art will readily think of other embodiments of the present invention. The present application is intended to cover any variations, uses, or adaptations of the present invention, which follow the general principles of the present invention and include the common general knowledge or conventional technical means in the technical field not disclosed in the present invention. The specification and the embodiments are only regarded as exemplary, and the true scope and spirit of the present invention are pointed out by the following claims.

[0117] It should be understood that the present invention is not limited to the exact structures described above and shown in the drawings, and various modifications and changes can be made without departing from its scope. The scope of the present invention is only limited by the appended claims.

[0118] The above are only the preferred embodiments of the present invention and do not impose any limitation on the present invention. Any simple modifications, changes, and equivalent structural changes made to the above embodiments according to the technical essence of the present invention still fall within the scope of protection of the technical solutions of the present invention.

Claims

1. A multi-source collaborative energy storage peak shaving and heating optimization method, characterized in that Including: Obtain meteorological data, historical load data, electricity price signals, and equipment status in real time; According to the meteorological data, historical load data, electricity price signals, and equipment status, use the LSTM neural network to predict the load and electricity price for the next 72 hours; According to the predicted load and electricity price for the next 72 hours, generate an optimal scheduling plan through a hybrid algorithm of reinforcement learning - fuzzy control; Generate a scheduling instruction according to the optimal scheduling plan and execute the scheduling instruction through Internet of Things devices.

2. The multi-source collaborative energy storage peak shaving and heating optimization method according to claim 1, wherein, The process of generating the optimal scheduling plan through the hybrid algorithm of reinforcement learning - fuzzy control is as follows: Generate an optimal scheduling plan based on the deep Q network model and the fuzzy control rule base.

3. A multi-source collaborative energy storage peak shaving and heating supply system, characterized in that, Including a multi-source energy input module, a composite energy storage unit, a dynamic energy flow network, an intelligent decision-making and control module, and a virtual power plant operation platform. Among them, the intelligent decision-making and control module is connected to the multi-source energy input module, the composite energy storage unit, and the virtual power plant operation platform through the dynamic energy flow network. Among them, the intelligent decision-making and control module is used to implement the multi-source collaborative energy storage peak shaving and heating optimization method described in claim 1 or 2.

4. The multi-source collaborative energy storage peak shaving and heat supply system according to claim 3, characterized in that The multi-source energy input module includes a geothermal energy collection device, an industrial waste heat recovery device, a biomass boiler, and a wind-solar power generation component. The geothermal energy collection device, the industrial waste heat recovery device, the biomass boiler, and the wind-solar power generation component are connected in parallel.

5. The multi-source collaborative energy storage peak shaving and heat supply system according to claim 3, characterized in that The composite energy storage unit includes a thermochemical energy storage TCES module and a phase change material energy storage PCM module. Among them, the thermochemical energy storage TCES module and the phase change material energy storage PCM module are connected in series and coupled through a cascade heat exchanger.

6. The multi-source collaborative energy storage peak shaving and heat supply system according to claim 3, wherein, The operating temperature range of the thermochemical energy storage TCES module is 200 - 500 °C, and the operating temperature range of the phase change material energy storage PCM module is 50 - 150 °C.

7. The multi-source collaborative energy storage peak shaving and heat supply system according to claim 3, wherein The intelligent decision-making and control module includes: A prediction sub-module that predicts the heat load and electricity price for the next 72 hours based on the LSTM neural network; Optimization sub-module, using the ε-constraint method to solve the multi-objective optimization problem, the objective functions include: Among them, λ is the carbon emission weight coefficient, π(t) is the electricity price at time t, γ grid and γ biomass are the carbon emission factors of the power grid and biomass energy respectively; An execution sub-module that dynamically adjusts the operating parameters of the heat pump, boiler, and energy storage system through Internet of Things devices.

8. The multi-source collaborative energy storage peak shaving and heat supply system according to claim 3, wherein, The multi-source energy input module is configured with a waste heat grade improvement device.

9. A computer device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the multi-source collaborative energy storage peak shaving and heating optimization method described in any one of claims 1 - 2.

10. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, it implements the steps of the multi-source collaborative energy storage peak shaving and heating optimization method described in any one of claims 1 - 2.

Images