Comprehensive energy optimization management platform
By designing a comprehensive energy optimization management platform with integrated multi-module, the problem of ineffective energy distribution in traditional platforms is solved, and more efficient and reasonable energy distribution and power consumption structure optimization is achieved, reducing energy waste and carbon emissions.
Patent Information
- Application Number
- CN202510162846.3
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-02-14
- Publication Date
- 2025-05-30
AI Technical Summary
The traditional comprehensive energy optimization management platform lacks an efficient energy distribution mechanism, resulting in energy waste and inefficient use, and the inability to make detailed planning based on the specific plant situation, resulting in a lack of guidance in energy optimization management.
A comprehensive energy optimization management platform was designed, including the main control module, the energy optimization management module, the temperature and humidity control module, the load prediction module and the photovoltaic energy storage module. Through the collaborative work of these modules, efficient and reasonable distribution of energy can be achieved, and detailed planning will be made according to the specific situation of the factory.
It achieves more efficient, more reasonable and more plant-based adaptability in energy distribution, reduces energy waste, improves energy use efficiency, and provides stable cold and heat through phase change energy storage technology to achieve the purpose of saving energy and reducing carbon emissions.
Smart Images
Figure CN120069324A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of integrated energy optimization management, and more specifically to an integrated energy optimization management platform. Background Art
[0002] An integrated energy optimization management platform is an integrated management system that helps enterprises or organizations improve energy utilization efficiency, reduce energy costs, and achieve energy conservation and emission reduction goals by centrally managing and optimizing energy use.
[0003] Specifically, such a platform can integrate various energy data, devices, and operation processes. It aggregates the energy consumption data in the unit through the Internet, various metering instruments, etc., and completely, accurately, and timely accesses it to the cloud platform. These data can be transmitted from one end to multiple platforms, such as provincial and municipal platforms, while ensuring the authenticity, continuity, and security of the data.
[0004] Traditional platforms lack an efficient energy distribution mechanism, resulting in energy waste and low utilization efficiency. At the same time, they cannot make detailed plans according to the specific plant conditions, making the optimization management of energy lack guidance. Therefore, an integrated energy optimization management platform is proposed to solve the above-mentioned problems. Summary of the Invention
[0005] (I) Technical Problems to be Solved In view of the deficiencies of the prior art, the present invention provides an integrated energy optimization management platform, which has the advantages of more efficient, more reasonable, and more plant-adaptable energy distribution on the platform, and solves the problems that traditional platforms lack an efficient energy distribution mechanism, resulting in energy waste and low utilization efficiency, and at the same time cannot make detailed plans according to the specific plant conditions, making the optimization management of energy lack guidance.
[0006] (II) Technical Solutions To achieve the above-mentioned purpose of more efficient, more reasonable, and more plant-adaptable energy distribution, the present invention provides the following technical solutions: an integrated energy optimization management platform, including a main control module, an energy optimization management module, a temperature and humidity control module, a load prediction module, and a photovoltaic energy storage module; Among them, the main control module controls the energy optimization management module, the temperature and humidity control module, the load prediction module, and the photovoltaic energy storage module to ensure the coordinated operation of each module; The energy optimization management module conducts preliminary energy distribution based on the electricity demand of the equipment according to the difference in electricity consumption in different seasons. The temperature and humidity control module balances the temperature in the plant area through a dehumidification device to avoid the situation where the relative humidity increases after the plant area temperature decreases. The load prediction module further optimizes energy distribution through the prediction of electric load, cooling load, and heating load. The photovoltaic energy storage module adjusts the electricity consumption through phase change energy storage technology to further achieve energy-saving effects.
[0007] Preferably, the energy allocated by the energy optimization management module includes photovoltaic power generation, power grid, energy storage, and natural gas, and the plant equipment includes welding equipment, commissioning equipment, air conditioning system, fan device, air drying equipment, and gas boiler.
[0008] Preferably, the energy optimization management module further includes an equipment energy demand module, an energy distribution module, and an energy-saving strategy module. The equipment energy demand module classifies and allocates energy using a linear programming algorithm based on data of energy consumption of equipment in the working area and non-working area of the plant.
[0009] Preferably, the objective function of the linear programming algorithm is to minimize the cost of purchasing electricity and gas, and the constraint conditions are power constraints of electricity, heat, cold, and gas, as well as the constraints of the unit itself.
[0010] Preferably, the temperature and humidity control module further includes a temperature prediction module and a dehumidification module. The temperature prediction module uses an autoregressive integrated moving average model based on the historical temperature and humidity conditions in Zhuzhou area and the results of environmental trend analysis to perform time series analysis on historical climate data, predict the future temperature and humidity change trend, generate the prediction model results, and adjust the temperature and humidity of the plant through a condensation dehumidification module and an adsorption dehumidification module. Preferably, the load prediction module further includes an electric load prediction module, a cooling load prediction module, and a heating load prediction module.
[0011] Preferably, the heating load and cooling load are mainly provided by the air conditioning system. The summer load is mainly composed of electric load and cooling load, and the winter load is mainly composed of electric load and heating load.
[0012] Preferably, the load prediction module predicts the energy distribution based on a deep learning model by setting a cross-entropy loss function and constraint conditions to further optimize the energy distribution results.
[0013] Preferably, the energy storage module includes a phase change heat storage module and a phase change cold storage module. Due to the large price difference in electricity, the battery can be used to store electricity when the electricity price difference is low and discharge when the electricity price is high. Introducing a large-capacity phase change energy storage technology can utilize phase change materials to store cold and heat in combination with valley electricity, industrial waste heat, abandoned wind and light, etc., to provide stable cold and heat for the town.
[0014] (III) Beneficial effects
[0015] Compared with the prior art, the present invention provides a comprehensive energy optimization management platform, which has the following beneficial effects: Compared with the prior art, the present invention provides a comprehensive energy optimization management platform, which has the following beneficial effects: 1. The integrated energy optimization management platform controls the energy optimization management module, temperature and humidity control module, load forecasting module, and photovoltaic energy storage module through the main control module. The multiple modules work together synergistically, making the energy distribution of the integrated energy optimization management platform more reasonable and efficient, thereby achieving the goals of energy conservation, carbon emission reduction, and optimizing the electricity consumption structure.
[0016] 2. The integrated energy optimization management platform introduces a large-capacity phase change energy storage technology, which can utilize phase change materials to store cold and heat by combining off-peak electricity, industrial waste heat, abandoned wind and light, etc., providing stable cold and heat for the town. BRIEF DESCRIPTION OF THE DRAWINGS
[0017] Figure 1 It is a schematic diagram of the integrated energy optimization management platform system of the present invention; Figure 2 It is a schematic diagram of the energy system topology of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS
[0018] 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 only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.
[0019] Please refer to Figure 1-2 , the integrated energy optimization management platform includes a main control module, an energy optimization management module, a temperature and humidity control module, a load forecasting module, and a photovoltaic energy storage module; Among them, the main control module controls the energy optimization management module, temperature and humidity control module, load forecasting module, and photovoltaic energy storage module, thereby ensuring the coordinated operation of each module; The energy optimization management module conducts preliminary energy distribution based on the electricity consumption requirements of the equipment and according to the differences in seasonal electricity consumption. The temperature and humidity control module balances the temperature in the plant area through a dehumidification device to avoid the situation where the relative humidity increases after the temperature in the plant area decreases. The load forecasting module further optimizes the energy distribution through the prediction of electrical load, cooling load, and heating load. The photovoltaic energy storage module adjusts the electricity consumption through phase change energy storage technology to further achieve the energy-saving effect.
[0020] In Figure 1 and Figure 2 , the energy optimization management module further includes an equipment energy demand module, an energy distribution module, and an energy-saving strategy module. The equipment energy demand module classifies and allocates energy using a linear programming algorithm based on the data of energy consumption of equipment in the working area and non-working area of the plant area.
[0021] In Figure 1 andFigure 2 Among them, the objective function of the linear programming algorithm is to minimize the electricity and gas purchase costs, and the constraints are the power constraints of electricity, heat, cold, and gas, as well as the constraints of the unit itself.
[0022] Specifically, the constraints of the unit itself are that the welding equipment and the fan device require stable power supply, and the load of the debugging equipment fluctuates significantly and has a large power. Through the initial distribution of electric energy, the basic electricity consumption of each electrical equipment is ensured.
[0023] In Figure 1 and Figure 2 Among them, the temperature and humidity control module also includes a temperature prediction module and a dehumidification module. The temperature prediction module adopts the autoregressive integrated moving average model based on the historical temperature and humidity conditions in Zhuzhou area and the analysis results of the environmental trend, conducts time series analysis on the historical climate data, predicts the future temperature and humidity change trend, generates the prediction model results, and adjusts the temperature and humidity in the plant area through the condensation dehumidification module and the adsorption dehumidification module.
[0024] Specifically, through the prediction of temperature and humidity in different seasons, it is possible to allocate electricity consumption more precisely according to the power consumption in different seasons during the electricity distribution, making the distribution of energy more efficient, thereby avoiding waste of electricity.
[0025] In Figure 1 and Figure 2 Among them, the load prediction module also includes an electric load prediction module, a cooling load prediction module, and a heating load prediction module.
[0026] Specifically, by setting the electric load prediction module, the cooling load prediction module, and the heating load prediction module, the electricity, cooling, and heating loads are predicted separately, so as to ensure the refined distribution of different electricity consumption types, further improve the optimal distribution of energy, improve the distribution efficiency, and effectively reduce energy waste at the same time.
[0027] In Figure 1 and Figure 2 Among them, the heating load and the cooling load are mainly provided by the air conditioning system. The summer load is mainly the electric load and the cooling load, and the winter load is mainly the electric load and the heating load.
[0028] In Figure 1 and Figure 2 Among them, the load prediction module predicts the energy distribution based on the deep learning model by setting the cross-entropy loss function and the constraints, further optimizing the energy distribution result.
[0029] Specifically, the deep learning model is a CNN energy distribution prediction model. The CNN (Convolutional Neural Network) energy distribution prediction model mainly includes the following structures: input layer, convolutional layer, pooling layer, and fully connected layer.
[0030] Among them, the input layer: This is the starting point of the CNN, responsible for receiving raw data, such as time series data related to energy distribution, sensor data, etc. These data may need to be preprocessed, such as normalization, size adjustment, etc., for subsequent network processing; The convolutional layer: The convolutional layer is the core part of the CNN. It extracts features from the input data through a series of learnable filters (convolution kernels). These filters can detect specific patterns or structures in the data. For energy distribution prediction, it may include patterns such as seasonal changes and daily changes in energy use. After the convolution operation, a non-linear activation function, such as ReLU, is usually introduced to increase the expressive power of the model; The pooling layer: The pooling layer is located after the convolutional layer, used to reduce the dimension of the data, prevent overfitting, and further extract important features. Common pooling operations include max pooling and average pooling, which can extract the maximum or average value in the feature map, thereby retaining key information and reducing the computational amount; The fully connected layer: The fully connected layer summarizes the features extracted by all previous layers and outputs a prediction result. Each neuron in this layer is connected to all neurons in the previous layer, acting as a classifier or regressor. For energy distribution prediction, the fully connected layer may output one or more prediction values, such as future energy demand, distribution ratio, etc.
[0031] Through the CNN energy distribution model, the refinement degree of energy distribution is further improved, thus achieving the effect of comprehensive energy optimization.
[0032] In Figure 1 and Figure 2 the energy storage module includes a phase change heat storage module and a phase change cold storage module. Due to the large electricity price difference, the battery can be used to store electricity when the electricity price difference is low and discharge when the electricity price is high. Introducing a large-capacity phase change energy storage technology can utilize phase change materials to store cold and heat in combination with off-peak electricity, industrial waste heat, abandoned wind and light, etc., to provide stable cold and heat for the town.
[0033] Specifically as follows: Table (1) Table (2) It can be concluded from the above table that after the energy system optimization, the electricity and gas purchase costs of the factory area are significantly reduced.
[0034] Table (3)
[0035] The above table compares the condensing industrial dehumidifier and the adsorption industrial dehumidifier. The factory area can choose the appropriate dehumidification equipment according to the cost and funds.
[0036] In summary, for the integrated energy optimization management platform, during its operation, the energy consumption of electrical equipment is first monitored through the equipment energy demand module, and the energy is initially distributed through the energy distribution module. Then, through the temperature and humidity prediction module, time series analysis is performed on climate data to predict the climate. Based on the prediction results, the power distribution is further refined. Next, through the load prediction module, based on the CNN model, the electrical load is predicted. At the same time, the RMSprop optimization method is used to adjust the weights and biases of the CNN model to further improve the prediction accuracy. Finally, through the energy storage module, the phase change energy storage technology is introduced to discharge energy storage during peak electricity consumption periods to further maintain stable electricity consumption, thus achieving the comprehensive optimization of energy.
[0037] In addition, the self-generated power device in the factory area is a photovoltaic power generation unit, with a photovoltaic installation capacity of 7.5 MW in the first phase and 11 MW in the second phase. In summer, the photovoltaic power generation time is long but the peak value is low; in winter, the photovoltaic power generation time is short but the power generation peak value is high.
[0038] Moreover, the summer operation analysis shows that the load mainly consists of electrical load and cooling load. During the peak electricity price period, the energy storage system discharges, and the heating load and cooling load are mainly provided by the air conditioning system. The winter operation analysis shows that the load mainly consists of electrical load and heating load. During the peak electricity price period, the energy storage system discharges, and the heating load and cooling load are mainly provided by the air conditioning system.
[0039] It should be noted that in this article, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the term "comprising", "including" or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, method, article or device comprising a series of elements not only includes those elements, but also includes other elements not expressly listed, or elements inherent to such process, method, article or device. Without further limitation, an element defined by the statement "comprising an..." does not exclude the existence of additional identical elements in the process, method, article or device comprising the element.
[0040] Although the embodiments of the present invention have been shown and described, it will be understood by those of ordinary skill in the art that various changes, modifications, substitutions and variations can be made to these embodiments without departing from the principles and spirit of the present invention, and the scope of the present invention is defined by the appended claims and their equivalents.
Claims
1. Comprehensive energy optimization management platform, including main control module, energy optimization management module, temperature and humidity control module, load forecasting module and photovoltaic energy storage module; in, The main control module controls the energy optimization management module, temperature and humidity control module, load prediction module and photovoltaic energy storage module to ensure that the modules work in coordination; The energy optimization management module makes preliminary energy allocation based on the power demand of the equipment and the difference in seasonal power consumption. The temperature and humidity control module balances the temperature in the factory through a dehumidification device to avoid the increase in relative humidity after the temperature in the factory drops. The load prediction module further optimizes energy allocation by predicting the electrical load, cooling load and heating load. The photovoltaic energy storage module adjusts power consumption through phase change energy storage technology to further achieve energy-saving effects.
2. The comprehensive energy optimization management platform according to claim 1 is characterized by: The energy allocated by the energy optimization management module includes photovoltaic power generation, power grid, energy storage and natural gas, and the factory equipment includes welding equipment, debugging equipment, air conditioning system, fan device, air drying equipment and gas boiler.
3. The comprehensive energy optimization management platform according to claim 1 is characterized in that: The energy optimization management module also includes an equipment energy demand module, an energy allocation module and an energy-saving strategy module. The equipment energy demand module classifies and allocates energy demand based on the data of energy consumption of equipment in the working area and non-working area of the factory, using a linear programming algorithm.
4. The comprehensive energy optimization management platform according to claim 2 is characterized by: The objective function of the linear programming algorithm is to minimize the cost of purchasing electricity and gas, and the constraints are the power constraints of electricity, heat, cooling, gas and the unit's own constraints.
5. The comprehensive energy optimization management platform according to claim 1 is characterized by: The temperature and humidity control module also includes a temperature prediction module and a dehumidification module. The temperature prediction module adopts the results of environmental trend analysis based on the historical temperature and humidity conditions in Zhuzhou area and adopts an autoregressive integral sliding average. The average model is used to conduct time series analysis on historical climate data, predict future temperature and humidity trends, generate prediction model results, and adjust the temperature and humidity of the factory area through the condensation dehumidification module and the adsorption dehumidification module.
6. The comprehensive energy optimization management platform according to claim 1 is characterized by: The load prediction module also includes an electric load prediction module, a cooling load prediction module and a heating load prediction module.
7. The comprehensive energy optimization management platform according to claim 1 is characterized by: The heat load and the cold load are mainly provided by the air conditioning system, the summer load is mainly composed of the electric load and the cold load, and the winter load is mainly composed of the electric load and the heat load.
8. The comprehensive energy optimization management platform according to claim 1 is characterized by: The load forecasting module predicts energy distribution based on the deep learning model by setting a cross-extraction loss function and constraints, and further optimizes the energy distribution results.
9. The comprehensive energy optimization management platform according to claim 1 is characterized by: The energy storage module includes a phase change heat storage module and a phase change cold storage module. Due to the large difference in electricity prices, batteries can be used to store electricity when the electricity price difference is low and discharge it when the electricity price is high. By introducing large-capacity phase change energy storage technology, phase change materials can be used to store cold and heat in combination with off-peak electricity, industrial waste heat, abandoned wind and solar power, etc., to provide stable cooling and heating for towns.