Energy-saving method and system for multiple devices in a park based on deep learning model

Abstract

The present invention provides an energy-saving method and system for multiple devices in a park based on a deep learning model, including obtaining real-time energy consumption data of the device; preprocessing the energy consumption data; training the model using the preprocessed energy consumption data; formulating an energy-saving plan based on the model prediction and evaluation results; operating the device according to the energy-saving plan; and dynamically adjusting the energy-saving plan of the device according to external environmental changes and internal needs. The beneficial effects of the present invention are that through in-depth analysis of energy consumption data, energy consumption trends can be predicted more accurately, and effective energy-saving measures can be formulated accordingly; a variety of technical means such as early stopping method and regularization are used to prevent model overfitting, thereby ensuring the stability and reliability of the system; the dynamic adjustment mechanism enables the energy-saving plan to better adapt to changing environmental conditions and different usage requirements.

Description

Technical Field

[0001] The present invention belongs to the technical field of energy conservation and emission reduction, and in particular, relates to an energy-saving method and system for multiple devices in a park based on a deep learning model. Background Art

[0002] The increase in carbon emissions caused by global climate change and building energy consumption has led to an increasing focus on low-energy buildings worldwide. From "double control" of energy consumption to "double control" of carbon emissions, the construction industry, as a major energy consumer, is imperative to save energy and reduce carbon emissions. The energy consumption of air-conditioning systems accounts for a large proportion of building energy consumption. How to reduce the energy consumption of air-conditioning systems is of great significance to the overall carbon emission reduction of buildings and is a key issue that should be considered in air-conditioning design. In many areas of my country, the proportion of air-conditioning load in summer has exceeded 50%.

[0003] As the main components for supplying cold and warm air, the cold and hot source system usually includes chillers and heat pumps, etc., which provide the necessary cold and hot air according to the heat load demand of the building. The efficiency of these devices directly determines the overall energy efficiency of the air conditioning system, and its operation strategy, such as start and stop time and load regulation, often depends on external climate conditions and internal temperature settings. Energy consumption distribution covers the flow of energy from generation, distribution to final use of the entire system. In most commercial buildings, the energy consumption of the air conditioning system accounts for the main part of energy consumption. Unreasonable energy consumption peaks are usually manifested in the air conditioning system still running at full capacity during periods when such large-scale cold and hot supply is not needed, such as in the morning or evening when there are few people, or during non-business hours in commercial buildings. This phenomenon may be caused by improper control system settings or the preset temperature control strategy does not match the actual demand, resulting in a large amount of unnecessary energy consumption, increased operating costs and increased equipment wear. Summary of the invention

[0004] In order to solve the above technical problems, the present invention provides an energy-saving method and system for multiple devices in a park based on a deep learning model, which is particularly suitable for the energy-saving method of multiple devices in actual use in the park.

[0005] The technical solution adopted by the present invention is: in the first aspect, a method for energy saving of multiple devices in a park based on a deep learning model is provided, comprising:

[0006] Get real-time energy consumption data of equipment;

[0007] Preprocess the energy consumption data;

[0008] Use the preprocessed energy consumption data to train the model;

[0009] Formulate energy-saving plans based on model prediction and evaluation results;

[0010] Operate the equipment according to the energy-saving plan;

[0011] Dynamically adjust the energy-saving plan of equipment according to external environmental changes and internal needs.

[0012] Furthermore, training the model using the preprocessed energy consumption data includes the following steps:

[0013] Set minimization of overall energy consumption as the main optimization goal;

[0014] Build a deep learning-based neural network model and a decision tree-based ensemble learning model;

[0015] Divide the preprocessed energy consumption data, environmental data and equipment operation parameter data into training set, validation set and test set according to a certain ratio;

[0016] Use the training set to train the neural network model to capture long-term dependencies in time series data and extract features from multidimensional data;

[0017] Use the random forest model to classify and identify energy consumption patterns of different regions and types of equipment;

[0018] The encoding methods for different devices are represented, and a genetic algorithm is used to approach the optimal solution through multiple generations of evolution.

[0019] Furthermore, early stopping and regularization are used during training to prevent overfitting.

[0020] Furthermore, for multi-objective optimization problems, an algorithm based on Pareto optimality is used to find a set of non-inferior solutions.

[0021] In the second aspect, a multi-device energy-saving system for a park based on a deep learning model is provided, including:

[0022] An energy consumption module, used for consuming energy;

[0023] Energy consumption collection module, used to collect energy consumption data and usage demand data of energy consumption modules;

[0024] The energy-saving calculation module is used to receive the energy consumption data and usage demand data from the energy consumption collection module and calculate the solution information for minimizing the comprehensive energy consumption;

[0025] The device control module is used to receive the solution information from the energy-saving calculation module, control the energy consumption module to execute the solution information and visualize the information for the user.

[0026] Furthermore, the energy consumption collection module includes:

[0027] Equipment energy consumption collection unit, used to collect energy consumption data of energy consumption modules;

[0028] The usage demand collection unit is used to collect the user's demand data.

[0029] Furthermore, the device control module includes:

[0030] A control unit, used for controlling the energy consumption module to execute the scheme information according to the scheme information;

[0031] The visualization unit is used to visualize the received solution information on the user terminal.

[0032] According to a third aspect, an electronic device is provided, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so as to enable the at least one processor to execute the energy-saving method for multiple devices in a campus based on a deep learning model provided in the present disclosure.

[0033] In a fourth aspect, a non-transitory computer-readable storage medium storing computer instructions is provided, wherein the computer instructions are used to enable a computer to execute the energy-saving method for multiple devices in a campus based on a deep learning model provided in the present disclosure.

[0034] In a fifth aspect, a computer program product is provided, including a computer program / instruction, which, when executed by a processor, implements the energy-saving method for multiple devices in a campus based on a deep learning model provided in the present disclosure.

[0035] The advantages and positive effects of the present invention are: due to the adoption of the above-mentioned technical scheme, through in-depth analysis of energy consumption data, it is possible to more accurately predict energy consumption trends and formulate effective energy-saving measures accordingly; a variety of technical means such as early stopping method and regularization are used to prevent model overfitting, thereby ensuring the stability and reliability of the system; the dynamic adjustment mechanism enables the energy-saving solution to better adapt to changing environmental conditions and different usage requirements. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] Figure 1 This is a flow chart of a method for energy saving of multiple devices in a park based on a deep learning model according to an embodiment of the present invention.

[0037] Figure 2 Schematic diagram of a training model method according to an embodiment of the present invention

[0038] Figure 3 This is a schematic diagram of the structure of an energy-saving system for multiple devices in a park based on a deep learning model according to an embodiment of the present invention.

[0039] Figure 4 This is a schematic diagram of the structure of an energy consumption collection module according to an embodiment of the present invention.

[0040] Figure 5Schematic diagram of the structure of a device control module according to an embodiment of the present invention DETAILED DESCRIPTION

[0041] The present disclosure is described more fully below with reference to the accompanying drawings, in which exemplary embodiments of the present disclosure are described. The technical solutions in the embodiments of the present disclosure will be clearly and completely described below in conjunction with the drawings in the embodiments of the present disclosure. Obviously, the described embodiments are only part of the embodiments of the present disclosure, not all of the embodiments. Based on the embodiments in the present disclosure, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present disclosure.

[0042] like Figure 1 As shown, the present invention provides an energy-saving method for multiple devices in a park based on a deep learning model, comprising:

[0043] S100, obtaining real-time energy consumption data of the device;

[0044] The sensors or monitoring devices installed on each device, namely the energy consumption acquisition module 800, are used to regularly collect information such as the power consumption and working status of the device.

[0045] S200, preprocessing the energy consumption data;

[0046] Including but not limited to cleaning and organizing raw data, removing outliers, filling missing values, and standardizing or normalizing values.

[0047] S300, training a model using the preprocessed energy consumption data;

[0048] Using deep learning techniques, including but not limited to recurrent neural networks (RNN) or long short-term memory networks (LSTM), the model is trained using a large amount of historical energy consumption data, enabling it to accurately predict future energy consumption trends.

[0049] S400, formulate energy-saving plans based on model prediction and evaluation results;

[0050] Based on the model's prediction results and actual operational needs, design specific energy-saving measures, including but not limited to adjusting the equipment's working mode, optimizing the operating schedule, etc., to achieve the goal of reducing energy consumption.

[0051] S500, operate the equipment according to the energy-saving plan;

[0052] Apply the formulated energy-saving plan to the operation of actual equipment, and accurately control the behavior of the equipment through the automated control system to ensure the effective implementation of the plan.

[0053] S600, dynamically adjust the energy-saving plan of the equipment according to changes in the external environment and internal needs.

[0054] Energy saving can be flexibly adjusted according to changes in weather conditions, holiday arrangements and other factors to ensure energy saving effects while meeting user needs.

[0055] In one embodiment, if Figure 2 As shown, training the model using the preprocessed energy consumption data includes the following steps:

[0056] S301, setting minimization of overall energy consumption as the main optimization goal;

[0057] S302, constructing a neural network model based on deep learning and an integrated learning model based on a decision tree;

[0058] Neural network models based on deep learning include but are not limited to hybrid models combining long short-term memory networks (LSTM) and convolutional neural networks (CNN). LSTM is used to process time series energy consumption data and can capture long-term dependencies in the data, such as predicting future energy consumption fluctuations based on energy consumption trends over the past few days. CNN is used to extract features from multidimensional data such as environmental data and equipment operating parameters, such as extracting correlation features between temperature and equipment power from two-dimensional data. At the same time, an integrated learning model based on decision trees is established, including but not limited to random forests. Random forests are used to classify and identify energy consumption patterns in different areas and types of equipment in the park to determine whether the equipment is in normal operation, inefficient operation or failure.

[0059] S303, dividing the pre-processed energy consumption data, environmental data and equipment operation parameter data into a training set, a validation set and a test set according to a certain ratio;

[0060] S304, training the neural network model using the training set to capture long-term dependencies in the time series data and extract features from the multidimensional data;

[0061] S305, using a random forest model to classify and identify energy consumption patterns of different regions and different types of equipment;

[0062] S306 , encoding methods for different devices are represented, and a genetic algorithm is used to approach an optimal solution through multiple generations of evolution.

[0063] In one embodiment, early stopping and regularization are used during training to prevent overfitting.

[0064] In the model training phase, in order to ensure that the model has good generalization ability, strategies such as early stopping and regularization are adopted to effectively prevent overfitting. Early stopping means terminating training early when the performance on the validation set no longer improves; while regularization limits the model complexity by adding a penalty term to the loss function to prevent the model from overfitting the training data.

[0065] In one embodiment, for multi-objective optimization problems, a Pareto optimality-based algorithm is used to find a set of non-inferior solutions.

[0066] An algorithm based on Pareto optimality is used to solve the multi-objective conflict problem in energy-saving optimization. By constructing a multi-objective optimization model, a set of non-inferior solutions can be found among multiple conflicting objectives, that is, solutions to any one objective cannot be further improved without sacrificing other objectives.

[0067] like Figure 3 As shown, in order to facilitate the implementation of the energy-saving method provided by the present disclosure, the present disclosure also provides an energy-saving system for multiple devices in a park based on a deep learning model, including:

[0068] The energy consumption module 700 is used to consume energy;

[0069] Responsible for performing various tasks, including but not limited to lighting, air conditioning, office equipment, etc., and is the main source of energy consumption.

[0070] The energy consumption collection module 800 is used to collect energy consumption data and usage demand data of the energy consumption module 700;

[0071] The energy-saving calculation module 900 is used to receive the energy consumption data and the usage demand data from the energy consumption collection module 800, and calculate the scheme information for minimizing the comprehensive energy consumption;

[0072] The device control module 110 is used to receive the solution information from the energy-saving calculation module 900, control the energy consumption module 700 to execute the solution information and visualize the information for the user.

[0073] In one embodiment, if Figure 4 As shown, the energy consumption collection module includes:

[0074] The equipment energy consumption collection unit 801 is used to collect energy consumption data of the energy consumption module 700;

[0075] The user demand collection unit 802 is used to collect user demand data.

[0076] Record user usage habits and preferences, including but not limited to temperature settings, light intensity, etc. This information helps to develop energy-saving strategies that better meet user needs.

[0077] In one embodiment, if Figure 5 As shown, the device control module includes:

[0078] The control unit 111 is used to control the energy consumption module 700 to execute the scheme information according to the scheme information;

[0079] The visualization unit 112 is used to visualize the received solution information on the user terminal.

[0080] Based on the embodiments of the present disclosure, the present disclosure also provides an electronic device, a readable storage medium and a computer program product.

[0081] An electronic device includes at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the energy-saving method for multiple devices in a campus based on a deep learning model provided in the present disclosure.

[0082] Electronic devices are intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframes, and other suitable computers. Electronic devices may also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present disclosure described and / or claimed herein.

[0083] A non-transitory computer-readable storage medium storing computer instructions, wherein the computer instructions are used to enable a computer to execute the energy-saving method for multiple devices in a campus based on a deep learning model provided by the present disclosure.

[0084] Various embodiments of the present disclosure may be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0085] A computer program product includes a computer program / instruction, which, when executed by a processor, provides an energy-saving method for multiple devices in a campus based on a deep learning model.

[0086] The program code for implementing the method of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that the program code, when executed by the processor or controller, enables the functions / operations specified in the flow chart and / or block diagram to be implemented. The program code may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0087] In the context of the present disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0088] The embodiments of the present invention are described in detail above, but the contents described are only preferred embodiments of the present invention and cannot be considered to limit the scope of implementation of the present invention. All equivalent changes and improvements made within the scope of the present invention should still fall within the scope of the patent coverage of the present invention.

Claims

1. A multi-device energy-saving method for a park based on a deep learning model, characterized in that: include: Get real-time energy consumption data of equipment; Preprocess the energy consumption data; Use the preprocessed energy consumption data to train the model; Formulate energy-saving plans based on model prediction and evaluation results; Operate the equipment according to the energy-saving plan; Dynamically adjust the energy-saving plan of equipment according to external environmental changes and internal needs.

2. The energy-saving method for multiple devices in a park based on a deep learning model according to claim 1 is characterized in that: Training the model using preprocessed energy consumption data includes the following steps: Set minimization of overall energy consumption as the main optimization goal; Build a deep learning-based neural network model and a decision tree-based ensemble learning model; Divide the preprocessed energy consumption data, environmental data and equipment operation parameter data into training set, validation set and test set according to a certain ratio; Use the training set to train the neural network model to capture long-term dependencies in time series data and extract features from multidimensional data; Use the random forest model to classify and identify energy consumption patterns of different regions and types of equipment; The encoding methods for different devices are represented, and a genetic algorithm is used to approach the optimal solution through multiple generations of evolution.

3. The energy-saving method for multiple devices in a park based on a deep learning model according to claim 2 is characterized in that: Early stopping and regularization are used during training to prevent overfitting.

4. The energy-saving method for multiple devices in a park based on a deep learning model according to claim 2 is characterized in that: For multi-objective optimization problems, an algorithm based on Pareto optimality is used to find a set of non-inferior solutions.

5. A multi-device energy-saving system for a park based on a deep learning model, characterized in that: include: An energy consumption module, used for consuming energy; Energy consumption collection module, used to collect energy consumption data and usage demand data of energy consumption modules; The energy-saving calculation module is used to receive the energy consumption data and usage demand data from the energy consumption collection module and calculate the solution information for minimizing the comprehensive energy consumption; The device control module is used to receive the solution information from the energy-saving calculation module, control the energy consumption module to execute the solution information and visualize the information for the user.

6. The energy-saving system for multiple devices in a park based on a deep learning model according to claim 5 is characterized in that: The energy consumption collection module includes: Equipment energy consumption collection unit, used to collect energy consumption data of energy consumption modules; The usage demand collection unit is used to collect the user's demand data.

7. The energy-saving system for multiple devices in a park based on a deep learning model according to claim 5 is characterized in that: The equipment control module includes: A control unit, used for controlling the energy consumption module to execute the scheme information according to the scheme information; The visualization unit is used to visualize the received solution information on the user terminal.

8. An electronic device comprising: at least one processor; as well as a memory communicatively connected to at least one processor; wherein, The memory stores instructions that can be executed by at least one processor. The instructions are executed by at least one processor so that the at least one processor can execute the method according to any one of claims 1 to 4.

9. A non-transitory computer-readable storage medium storing computer instructions, wherein: The computer instructions are used to make a computer execute the method according to any one of claims 1 to 4.

10. A computer program product comprising a computer program / instructions, which, when executed by a processor, implement the steps of the method according to any one of claims 1 to 4.

Images