Smart park load regulation and control method, system and device and storage medium

Abstract

The invention relates to the technical field of load regulation and control, in particular to a smart park load regulation and control method, system and device and a storage medium. The method comprises the following steps: acquiring energy use data, environment data and power limiting demand data of a smart park; calculating a load regulation demand of power limitation according to load data and power limitation demand data in the energy use data; according to the energy use data and the environment data, adopting a pre-trained neural network model to predict an adjustable load; determining an actual adjustable load based on the relationship between the predicted adjustable load and the load regulation demand; and generating a load regulation instruction according to the actual adjustable load and executing the load regulation instruction. According to the invention, through data mining and analysis, a better load regulation and control scheme is provided, and the energy load management level and the operation efficiency of the smart park are effectively improved.

Description

Technical Field

[0001] The present invention relates to the field of load control technology, and in particular to a smart park load control method, system, equipment and storage medium. Background Art

[0002] With the rapid development of smart cities, smart parks, as an important part of cities, are receiving increasing attention for their energy management and load regulation technologies. Existing technologies mainly rely on traditional energy management systems to regulate loads through preset thresholds and rules, but this approach often lacks real-time and flexibility, and is difficult to cope with complex and changing park energy needs. Summary of the invention

[0003] In view of this, the present invention provides a smart park load control method, system, device and storage medium to solve the problem in the prior art that smart park load control is difficult to cope with the complex and changeable park energy demand.

[0004] In a first aspect, the present invention provides a load control method for a smart park, the method comprising: obtaining energy usage data, environmental data and power restriction demand data of the smart park, the energy usage data including load data; calculating the load control demand for power restriction based on the load data and the power restriction demand data; predicting an adjustable load using a pre-trained neural network model based on the energy usage data and the environmental data; determining the actual adjustable load based on the relationship between the predicted adjustable load and the load control demand; generating and executing a load control instruction based on the actual adjustable load.

[0005] In the present invention, the load control demand of power restriction is calculated through load data and power restriction demand data, the adjustable load is predicted based on energy usage data and environmental data, and the load control demand and the predicted adjustable load are compared and analyzed to determine the actual adjustable load for regulation. Therefore, this method provides a better load control scheme through data mining and analysis, which effectively improves the energy load management level and operation efficiency of the smart park.

[0006] In an optional embodiment, a pre-trained neural network model is used to predict the adjustable load according to the energy usage data and the environmental data, including: dividing the smart park into multiple areas according to the function of the smart park; using a preset algorithm to extract high-power equipment, power curve, current curve, voltage curve, ambient temperature, and power necessity data in each area based on the energy usage data and the environmental data as feature data; inputting the feature data into the pre-trained neural network model to obtain a predicted adjustable load, and the neural network is trained based on the difference between the predicted adjustable load and the actual adjustable load as a loss function, wherein the loss function is expressed by the following formula:

[0007] loss = (yp-y)(yp-y)

[0008] Where yp represents the predicted controllable load, and y represents the actual controllable load.

[0009] In an optional embodiment, a load control instruction is generated and executed according to the actual adjustable load, including: using a table lookup method to divide the load into uncontrollable load, adjustable load and disconnectable load according to the necessity of the power consumption nature; generating a first load control instruction for controlling the uncontrollable load, a second load control instruction for controlling the disconnectable load and a third load control instruction for controlling the adjustable load according to the actual adjustable load; executing the first load control instruction, the second load control instruction and the third load control instruction in sequence, and monitoring the total load of the smart park during the execution of each load control instruction, and stopping execution when the change in the total load meets the demand of the actual adjustable load.

[0010] In this embodiment, the load is divided into uncontrollable load, adjustable load and disconnectable load according to the nature of electricity consumption, and different control instructions are generated according to the load type, thereby achieving precise control of different types of loads.

[0011] In an optional embodiment, a first load control instruction, a second load control instruction and a third load control instruction are executed in sequence, including: monitoring the operating status of an uncontrollable load based on the first load control instruction and a preset time interval; controlling the disconnection of an adjustable load based on the second load control instruction; and adjusting the power supply strategy of the adjustable load based on the third load control instruction.

[0012] In an optional embodiment, the power supply strategy of the adjustable load is adjusted based on the third load control instruction, including: controlling the charging and discharging time of the energy storage box, controlling the air conditioning temperature, controlling the street light switch and controlling the power supply of the administrative area in sequence based on the third load control instruction.

[0013] In an optional embodiment, controlling the air conditioning temperature includes: obtaining an air conditioning turnable area and an air conditioning adjustable area; sending a control instruction to the air conditioning to turn off the air conditioning in the air conditioning turnable area and to increase the air conditioning temperature in the air conditioning adjustable area; after the control instruction is sent, if it is monitored that the air conditioning controlled to be turned off is in operation, obtaining feedback information; when no feedback information is received, resending the control instruction; when the received feedback information includes information that the air conditioning is locked, sending an unlocking command to the air conditioning and then sending the control instruction; when the received feedback information includes information that the control fails, analyzing the feedback information to determine the cause of the failure, and resending the control instruction after solving the problem in the cause of the failure.

[0014] In this embodiment, when the temperature of the air conditioner is controlled, if it is monitored that the air conditioner that should be turned off is still in operation, analysis can be performed based on the type of feedback information received to ensure accurate control of the air conditioner.

[0015] In an optional embodiment, the load data includes the total load of the smart park, the power limitation demand data includes the maximum load value allowed by power limitation, and the load control demand for power limitation is calculated using the following formula: load control demand for power limitation = total load - maximum load value allowed by power limitation × first preset value.

[0016] In an optional embodiment, the pre-trained neural network model includes: an input layer, a hidden layer, and an output layer;

[0017] The input layer includes input energy usage data and environmental data;

[0018] The hidden layer includes m neurons. The input of each neuron is the weighted sum of the outputs of all neurons in the previous layer, plus the bias term. The input and output of the jth neuron in the hidden layer are expressed by the following formulas:

[0019] [Z_j=\sum_{i=1}^{X}W1_{ij}\cdotA_i+b1_j]

[0020] Among them, X represents the number of data features input to the input layer, W1 represents the weight matrix from the input layer to the hidden layer, and b1 represents the bias vector of the hidden layer;

[0021] [A1_j=f(Z_j)]

[0022] Where f is the activation function;

[0023] The output layer consists of n neurons. The input of each neuron is the weighted sum of the outputs of all neurons in the hidden layer, plus the bias term. The input and output of the kth neuron in the output layer can be expressed as:

[0024] [Z_k=\sum_{j=1}^{m}W2_{jk}\cdotA1_j+b2_k]

[0025] Among them, W2 represents the weight matrix from the hidden layer to the output layer, and b2 represents the bias vector of the output layer;

[0026] [Y_k=g(Z_k)]

[0027] Among them, g represents the activation function of the output layer, and Y_k represents the predicted number of controllable loads.

[0028] In a second aspect, the present invention provides a smart park load control system, the system comprising: a data acquisition module for acquiring energy usage data, environmental data and power restriction demand data of the smart park, the energy usage data including load data; a demand calculation module for calculating the load control demand for power restriction based on the load data and the power restriction demand data; a prediction module for predicting an adjustable load based on the energy usage data and environmental data using a pre-trained neural network model; an actual adjustable determination module for determining the actual adjustable load based on the relationship between the predicted adjustable load and the load control demand; and a control execution module for generating and executing a load control instruction based on the actual adjustable load.

[0029] In a third aspect, the present invention provides a computer device, comprising: a memory and a processor, the memory and the processor are communicatively connected to each other, computer instructions are stored in the memory, and the processor executes the smart park load control method of the first aspect or any corresponding embodiment thereof by executing the computer instructions.

[0030] In a fourth aspect, the present invention provides a computer-readable storage medium having computer instructions stored thereon, the computer instructions being used to enable a computer to execute the smart park load control method of the first aspect or any corresponding embodiment thereof.

[0031] In a fifth aspect, the present invention provides a computer program product, comprising computer instructions, which are used to enable a computer to execute the smart park load control method of the first aspect or any corresponding embodiment thereof. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] In order to more clearly illustrate the specific implementation methods of the present invention or the technical solutions in the prior art, the drawings required for use in the specific implementation methods or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some implementation methods of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0033] Figure 1 is a flow chart of a method for controlling load in a smart park according to an embodiment of the present invention;

[0034] Figure 2 is a schematic diagram of air conditioning control feedback according to an embodiment of the present invention;

[0035] Figure 3 is a structural block diagram of a smart park load control system according to an embodiment of the present invention;

[0036] Figure 4is a structural block diagram of another smart park load control system according to an embodiment of the present invention;

[0037] Figure 5 It is a schematic diagram of the hardware structure of a computer device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0038] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0039] According to an embodiment of the present invention, an embodiment of a smart park load control method is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0040] In this embodiment, a smart park load control method is provided, which can be used for electronic devices such as computers, mobile phones, tablet computers, etc. Figure 1 is a flow chart of a load control method for a smart park according to an embodiment of the present invention. Figure 1 As shown, the process includes the following steps:

[0041] Step S101, obtain the energy usage data, environmental data and power restriction demand data of the smart park, and the energy usage data includes load data. Specifically, various sensors and electricity meters can be deployed at various locations in the smart park to obtain various data. For example, various sensors and electricity meters can be deployed at key locations in the smart park, such as workshops, energy storage systems, street lights, office areas, and dormitories, to collect energy usage data such as current, voltage, power, and environmental data such as temperature and humidity. The collected data can be preprocessed first, and the preprocessing process specifically includes data cleaning, missing value and outlier processing, etc., and then the data can be processed by simple calculations, such as drawing relevant curves, calculating load data, etc.

[0042] After relevant preprocessing, the collected energy usage data and environmental data can be encrypted and stored locally, and the stored data can also be backed up to the cloud regularly. In addition, for power restriction demand data, when power restriction measures need to be implemented, relevant data such as power restriction time, maximum load, and impact range can be obtained from relevant measures.

[0043] Step S102, calculate the load control demand for power restriction based on the load data and the power restriction demand data. The load control demand for power restriction indicates the load that needs to be regulated when power restriction is implemented. Specifically, the load control demand can be determined based on the total load of the park in the load data and the maximum load in the power restriction demand data.

[0044] Step S103, predicting the adjustable load using a pre-trained neural network model based on the energy usage data and environmental data. Specifically, when training the neural network, the historically stored energy usage data and environmental data can be obtained from the local or cloud, and the historical adjustable load corresponding to the power restriction at the historical moment can also be obtained. These historical data are used as the input and output of the neural network model for training. During training, the back propagation algorithm can also be used to update the model's weights, biases and other parameters. Afterwards, based on the trained model, the energy usage data and environmental data obtained at the current moment can be input to obtain the predicted adjustable load.

[0045] Step S104, determining the actual adjustable load based on the relationship between the predicted adjustable load and the load regulation demand. Specifically, after the adjustable load is predicted, it is compared and analyzed with the load regulation demand to determine whether the predicted adjustable load can meet the load regulation demand. If it can, the predicted adjustable load can be used as the actual adjustable load. If it cannot, it is necessary to further return to re-analyze the energy usage data and re-predict.

[0046] Step S105, generating and executing a load control instruction according to the actual controllable load. Specifically, after determining the actual controllable load, a load control instruction can be generated and executed for the equipment in the smart park, and during the execution process, the load in the smart park is monitored in real time to ensure that the regulated load reaches the actual controllable load.

[0047] The load control method for a smart park provided in an embodiment of the present invention calculates the load control demand for power restriction through load data and power restriction demand data, predicts the controllable load based on energy usage data and environmental data, and compares and analyzes the load control demand and the predicted controllable load to determine the actual controllable load for control. Therefore, the method provides a better load control scheme through data mining and analysis, effectively improving the energy load management level and operation efficiency of the smart park.

[0048] In this embodiment, a method for controlling load in a smart park is provided, and the process includes the following steps:

[0049] Step S201, obtaining energy usage data, environmental data, power restriction demand data and historical data of the smart park, wherein the energy usage data includes load data. Figure 1 Step S101 of the illustrated embodiment will not be described in detail here.

[0050] Step S202: Calculate the load regulation demand of power restriction according to the load data and the power restriction demand data. The load regulation demand of power restriction is calculated using the following formula:

[0051] The load control demand for power restriction=total load-maximum load value allowed by power restriction×first preset value.

[0052] Specifically, when calculating the load control demand, the load fluctuation needs to be considered. Therefore, the maximum load value allowed by power restriction is first multiplied by the first preset value, which can be 90% or 95%. Then, the load allowed by power restriction is subtracted from the current total load of the smart park, thereby obtaining the load control demand for power restriction. That is, under the current total load, the current total load can be adjusted according to the load control demand to make the current total load reach the load allowed by power restriction. However, in actual situations, it is also necessary to consider the actual power consumption of the current smart park, such as energy usage, to determine the actual controllable load for control, and it is impossible to control directly according to the load control demand.

[0053] Step S203, predicting the adjustable load using a pre-trained neural network model according to the energy usage data and environmental data;

[0054] Specifically, the above step S203 includes:

[0055] Step S2031, the smart park is divided into multiple areas according to the functions of the smart park; specifically, in the smart park, there are multiple building areas including workshops, office areas, dormitories, etc., and the power consumption of different building areas is also different. At the same time, corresponding electric energy meters and gateways are usually installed in different building areas, and the gateway is used to collect the power consumption data of the electric energy meter. Therefore, the smart park can be divided into regions according to the gateways in the smart park, for example, different gateways are used to divide different areas.

[0056] Step S2032, using a preset algorithm, extracting high-power-consuming devices, power curves, current curves, voltage curves, ambient temperature, and power necessity data in each area as feature data based on the energy usage data and environmental data; wherein high-power-consuming devices refer to devices whose power consumption is greater than a threshold. Specifically, the electric energy consumed by each device can be obtained from the energy usage data, and compared with the threshold to determine the high-power-consuming devices. Specifically, the electric energy consumed by the device can usually be queried from the data collected by the electric energy meter. For example, the data collected by the electric energy meter can be classified according to the communication address of the electric energy meter and the pre-stored device archive of the connection relationship between the electric energy meter and the device, so as to determine the electric energy consumed by different devices.

[0057] The power curve, current curve, and voltage curve can be determined by analyzing and calculating the energy usage data using relevant technologies. The ambient temperature can be determined from the environmental data. The electricity necessity data can be determined by analyzing historical data. The historical data can be energy usage data and environmental data at historical moments obtained locally or in the cloud. During the analysis, a machine learning algorithm can be used to analyze the historical data and predict the available maximum load data for each area. The available maximum load data can be understood as the equipment that can be load-controlled in each area. For example, if a certain equipment has no production tasks and does not need to work, it can be idle, and it can be used as a load control device. After obtaining the available maximum load data, a greedy algorithm can be used to analyze the load control demand and the available maximum load data to obtain the electricity necessity data.

[0058] Step S2033, input the characteristic data into the pre-trained neural network model to obtain the predicted adjustable load, and the neural network is trained based on the difference between the predicted adjustable load and the actual adjustable load as the loss function. Wherein, when training the neural network, the weight of each characteristic data can be generated according to the degree of influence of the characteristic data on the adjustable load, and the characteristic data and the weight can be multiplied and then used as the input of the neural network. At the same time, before the historical control load corresponding to the historical moment when the power restriction was implemented is used as the model output for training, the historical control load can also be assigned a difference random value to simulate the sample change in the actual data. The loss function used in training can be expressed as: loss = (yp-y)(yp-y), where yp represents the predicted adjustable load and y represents the historical actual control load. Therefore, the loss value calculated by this formula can be used to determine the adjustable load of each area during training.

[0059] In an optional embodiment, the pre-trained neural network model includes: an input layer, a hidden layer, and an output layer;

[0060] The input layer includes input energy usage data and environmental data;

[0061] The hidden layer includes m neurons. The input of each neuron is the weighted sum of the outputs of all neurons in the previous layer, plus the bias term. The input and output of the jth neuron in the hidden layer are expressed by the following formulas:

[0062] [Z_j=\sum_{i=1}^{X}W1_{ij}\cdotA_i+b1_j]

[0063] Among them, X represents the number of data features input to the input layer, W1 represents the weight matrix from the input layer to the hidden layer, and b1 represents the bias vector of the hidden layer;

[0064] [A1_j=f(Z_j)]

[0065] Where f is the activation function;

[0066] The output layer consists of n neurons. The input of each neuron is the weighted sum of the outputs of all neurons in the hidden layer, plus the bias term. The input and output of the kth neuron in the output layer can be expressed as:

[0067] [Z_k=\sum_{j=1}^{m}W2_{jk}\cdotA1_j+b2_k]

[0068] Among them, W2 represents the weight matrix from the hidden layer to the output layer, and b2 represents the bias vector of the output layer;

[0069] [Y_k=g(Z_k)]

[0070] Among them, g represents the activation function of the output layer, and Y_k represents the predicted number of controllable loads.

[0071] In practical applications, if the input layer includes six characteristic data, such as the state or number of high-power equipment, the characteristic value of the power curve (such as the average value, peak value, etc.), the characteristic value of the current curve, the characteristic value of the voltage curve, the ambient temperature, and the evaluation value of the necessity of electricity (such as the degree of urgency, priority, etc.), then X is 6. In addition, when training the neural network model, the backpropagation algorithm can be used to adjust the weights W1, W2 and the biases b1, b2 by minimizing the loss function (such as the mean square error MSE). The training process includes the steps of forward propagation calculation output, calculation of loss, backpropagation calculation gradient, updating weights and biases, etc. Step S204, determine the actual adjustable load based on the relationship between the predicted adjustable load and the load regulation demand. In an optional implementation, when the predicted adjustable load does not meet the load regulation demand, it can return to step S3022, re-analyze and determine the necessity data for electricity consumption, and re-predict.

[0072] Step S205: Generate and execute a load control instruction based on the actual controllable load. Figure 1 Step S105 of the illustrated embodiment will not be described in detail here.

[0073] In this embodiment, a method for controlling load in a smart park is provided, and the method comprises the following steps:

[0074] Step S301, obtaining energy usage data, environmental data, power restriction demand data and historical data of the smart park, wherein the energy usage data includes load data; for details, see Figure 1 Step S101 of the illustrated embodiment will not be described in detail here.

[0075] Step S302: Calculate the load regulation demand for power restriction based on the load data and the power restriction demand data; see Figure 1 Step S102 of the illustrated embodiment will not be described in detail here.

[0076] Step S303: predict the controllable load using a pre-trained neural network model based on the energy usage data and environmental data; see Figure 1 Step S103 of the illustrated embodiment will not be described in detail here.

[0077] Step S304: Determine the actual adjustable load based on the relationship between the predicted adjustable load and the load adjustment demand. Figure 1 Step S104 of the illustrated embodiment will not be described in detail here.

[0078] Step S305: generating and executing a load control instruction according to the actual controllable load.

[0079] Specifically, the above step S305 includes:

[0080] Step S3051, using the table lookup method, the load is divided into uncontrollable load, adjustable load and disconnectable load according to the necessity of the nature of electricity consumption; specifically, the uncontrollable load means the load that cannot be regulated, including security, power generation, etc. Adjustable load means the load that can be adjusted, such as energy storage box, workshop air conditioner, administrative building electricity and other loads. When adjusting its load, the strategy of energy storage box charging and discharging, air conditioning temperature, and administrative building electricity consumption can be modified. Disconnectable load means the load that can be powered off, for example, unnecessary public equipment such as central courtyard logo lights and billboards can be powered off. In actual applications, different loads can be divided based on the necessity of electricity consumption and formed in a table. When it is necessary to regulate the load of a smart park, it can be queried in the table based on the load therein to determine whether it is an uncontrollable load, an adjustable load or a disconnectable load.

[0081] Step S3052, generating a first load control instruction for controlling an uncontrollable load, a second load control instruction for controlling a disconnectable load, and a third load control instruction for controlling an adjustable load according to the actual adjustable load; specifically, when generating load control instructions, corresponding load control instructions can be generated for different types of loads respectively, so as to control different types of loads.

[0082] Step S3053, sequentially execute the first load control instruction, the second load control instruction, and the third load control instruction. In the process of executing each load control instruction, monitor the total load of the smart park, and stop executing when the change of the total load meets the demand of the actual adjustable load. Specifically, in the process of executing the load control instruction, it is necessary to monitor the total load of the smart park in real time, and stop executing the load control instruction when the change of the total load meets the demand of the actual adjustable load.

[0083] In an optional implementation manner, the above step S3053 includes:

[0084] Step a1, monitor the operating status of the uncontrollable load based on the first load control instruction and the preset time interval; specifically, after the first load control instruction is generated, the data of the uncontrollable load such as security monitoring, workshop emergency order production, etc. can be collected and the operating status can be monitored every preset time such as fifteen minutes according to the first load control instruction to ensure its normal operation and issue an alarm information notification when an abnormal situation occurs.

[0085] Step a2, based on the second load control instruction, control the disconnection of the disconnectable load; specifically, after generating the second load control instruction, the power supply to the disconnectable load such as the central courtyard logo lights, billboards, fountains and other non-essential facilities in the park can be cut off according to the second load control instruction to reduce the power load.

[0086] Step a3, adjusting the power supply strategy of the adjustable load based on the third load control instruction. Specifically, for the regulation of the adjustable load, the power supply strategy can be adjusted in the order of controlling the charging and discharging time of the energy storage box, controlling the air conditioning temperature, controlling the street light switch, and controlling the power supply of the administrative area. Among them, for the energy storage box, different power supply strategies can be adopted according to different electricity price periods in different seasons. For example, you can use the low electricity price during the valley period to save costs, and discharge during the power restriction period to use the equipment with large power consumption in the production workshop, reduce the power load of the park, and reduce the scope of impact caused by power restriction.

[0087] In an optional implementation, in order to control the air conditioner temperature, a control system can be added to all air conditioner outdoor units in the smart park, the air conditioner communication protocol can be coordinated, and the front-end machine can collect the device status information of all air conditioners at a preset interval, such as 15 minutes, to control all air conditioners in the smart park. Among them, when controlling the air conditioner temperature, it can be implemented according to the following process:

[0088] Step b1, obtaining the air conditioning shutoff area and the air conditioning adjustable area.

[0089] Step b2, sending a control instruction to the air conditioner to turn off the air conditioner in the air conditioner-disabled area and to increase the air conditioner temperature in the air conditioner-adjustable area.

[0090] Step b3, after the control instruction is sent, if it is monitored that the air conditioner controlled to be turned off is in operation, feedback information is obtained.

[0091] Step b4: when no feedback information is received, resend the control instruction.

[0092] Step b5: When the received feedback information includes information that the air conditioner is locked, an unlock command is sent to the air conditioner and then a control instruction is sent.

[0093] Step b6: when the received feedback information includes information about control failure, the feedback information is analyzed to determine the cause of the failure, and the control instruction is resent after the problem in the cause of the failure is resolved.

[0094] Specifically, for the production workshop, the air conditioner needs to be turned on to ensure the normal operation of the production. Therefore, in actual situations, all areas outside the production environment can be regarded as air-conditioning disconnectable areas, and the air conditioners in this area can be turned off. For the air conditioners in the production environment (air-conditioning adjustable areas), the specified range of ambient temperatures of all in-production workshops can be obtained, and the air-conditioning temperature can be raised but not higher than the specified production temperature by issuing control instructions.

[0095] At the same time, if Figure 2As shown, after the control command is issued, if it is found through monitoring that the air conditioner that should be turned off is still running, the feedback information of the air conditioner can be obtained through the control system to determine the reason why it is still running. Among them, when there is no feedback within the first preset time such as 1 minute after the control command is issued, there may be network fluctuations, and the control command is issued again. If there is still no feedback after sending the control command three times, the system administrator is notified to check; if the received feedback information includes the information that the air conditioner is locked, the unlock command frame is sent first, and the control command is sent again after the air conditioner is unlocked; when the received feedback information includes feedback information such as communication address error and control failure, the cause of control failure can be analyzed and the control command can be re-issued through frame data analysis and machine model learning. In addition, after the control command is issued, it is necessary to monitor the load information of the air conditioner in real time to determine whether the load is reduced. If the load is reduced, it is determined that the control command is executed successfully.

[0096] In an optional implementation, when controlling the switch of street lights, the total load change of the smart park after controlling the air-conditioning temperature can be used to determine whether to turn the street lights on and off at intervals, turn them off completely, or use other control methods such as turning off each area, wherein, when controlling the street lights, the switch of the street lights can be controlled by the control terminal, and control instructions can be broadcast to the relevant street lights; manual control can also be used, which is not limited in this embodiment. After controlling the street lights, if the actual adjustable load has not been reached, the power supply of the administrative area can be further adjusted. For example, a power restriction message can be sent to all personnel through the relevant system of the smart park, and the administrative areas that can be powered off can be counted, and the power supply of the relevant areas can be cut off.

[0097] The load control method for a smart park provided by the embodiment of the present invention can optimize resource allocation, improve operating efficiency, reduce energy consumption, and provide users with a more convenient and energy-saving experience through intelligent monitoring and load control. Therefore, the method has broad application prospects and significant promotion value. For example, it can be applied to smart city projects, smart shopping mall projects, smart campus projects, etc.

[0098] In this embodiment, a smart park load control system is also provided, which is used to implement the above-mentioned embodiments and preferred implementation modes, and the descriptions that have been made will not be repeated. As used below, the term "module" can be a combination of software and / or hardware that implements a predetermined function. Although the system described in the following embodiments is preferably implemented in software, the implementation of hardware, or a combination of software and hardware, is also possible and conceivable.

[0099] This embodiment provides a smart park load control system. Figure 3 As shown, including:

[0100] The data collection module 31 is used to obtain energy usage data, environmental data and power restriction demand data of the smart park, wherein the energy usage data includes load data;

[0101] A demand calculation module 32, configured to calculate the load regulation demand for power restriction according to the load data and the power restriction demand data;

[0102] A prediction module 33, for predicting adjustable loads using a pre-trained neural network model based on the energy usage data and environmental data;

[0103] An actual adjustable determination module 34, configured to determine the actual adjustable load based on the relationship between the predicted adjustable load and the load regulation demand;

[0104] The control execution module 35 is used to generate and execute a load control instruction according to the actual controllable load.

[0105] The further functional description of each of the above modules and units is the same as that of the above corresponding embodiments and will not be repeated here.

[0106] In an optional embodiment, if Figure 4 As shown in the figure, the system includes a data acquisition module, an intelligent analysis module, a control execution module and a user interaction interface. The data acquisition module is used to deploy various sensors and front-end machines such as smart meters in key locations in the park, such as workshops, energy storage systems, street lights, office areas, dormitories, etc., to collect real-time data such as current, voltage, power, load, temperature, humidity, etc., and monitor the overall energy usage and environmental conditions of the park. The collected data can be processed by data cleaning, data backup, and file management.

[0107] The intelligent analysis module includes a demand calculation module, a prediction module, and an actual adjustable determination module, which are used for big data analysis and the formulation of control strategies. Specifically, the intelligent analysis module can obtain the data collected by the data acquisition module, perform data classification, load demand analysis, predict the adjustable load, and the effect and evaluation, and generate load control instructions (i.e., control strategies).

[0108] The control execution module includes a regulation execution module, which can issue the formulated load regulation instructions. In the process of executing the instructions, it monitors the operating status of the uncontrollable load and generates alarm data when there is an abnormality. When controlling the air-conditioning temperature, it receives feedback information and generates an alarm when the feedback information includes control failure information. In addition, it can also issue power restriction notices and determine the administrative areas where power outages occur.

[0109] The user interaction interface is used for graphical display. The interface includes the comprehensive homepage, strategy formulation page, power restriction demand page, load display page and exception management page. All functional modules are displayed in the comprehensive homepage. The functions of the intelligent analysis module can be realized in the strategy formulation page, the current power restriction information is displayed in the power restriction demand page, the current analyzed and calculated load data is displayed in the load display page, and the abnormal alarm information of the control process is displayed in the exception management page.

[0110] The embodiment of the present invention also provides a computer device having the above Figure 3 The smart park load control system shown.

[0111] See also Figure 5 , Figure 5 is a schematic diagram of the structure of a computer device provided by an optional embodiment of the present invention, such as Figure 5 As shown, the computer device includes: one or more processors 10, memory 20, and interfaces for connecting various components, including high-speed interfaces and low-speed interfaces. Various components utilize different buses to communicate with each other, and can be installed on a common mainboard or installed in other ways as required. The processor can process the instructions executed in the computer device, including instructions stored in the memory or on the memory to display the graphical information of the GUI on an external input / output system (such as, a display device coupled to the interface). In some optional embodiments, if necessary, multiple processors and / or multiple buses can be used together with multiple memories and multiple memories. Similarly, multiple computer devices can be connected, and each device provides part of the necessary operations (for example, as a server array, a group of blade servers, or a multi-processor system). Figure 5 A processor 10 is taken as an example.

[0112] The processor 10 may be a central processing unit, a network processor or a combination thereof. The processor 10 may further include a hardware chip. The hardware chip may be a dedicated integrated circuit, a programmable logic device or a combination thereof. The programmable logic device may be a complex programmable logic device, a field programmable gate array, a general purpose array logic or any combination thereof.

[0113] The memory 20 stores instructions executable by at least one processor 10, so that at least one processor 10 executes the method shown in the above embodiment.

[0114] The memory 20 may include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function; the data storage area may store data created by the use of a computer device based on the presentation of a small program landing page, etc. In addition, the memory 20 may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some optional embodiments, the memory 20 may optionally include a memory remotely arranged relative to the processor 10, and these remote memories may be connected to the computer device via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0115] The memory 20 may include a volatile memory, such as a random access memory; the memory may also include a non-volatile memory, such as a flash memory, a hard disk or a solid state drive; the memory 20 may also include a combination of the above types of memory.

[0116] The computer device further comprises a communication interface 30 for the computer device to communicate with other devices or a communication network.

[0117] The embodiment of the present invention also provides a computer-readable storage medium. The method according to the embodiment of the present invention can be implemented in hardware, firmware, or can be implemented as a computer code that can be recorded in a storage medium, or can be implemented as a computer code that is originally stored in a remote storage medium or a non-temporary machine-readable storage medium and will be stored in a local storage medium through a network download, so that the method described herein can be stored in such software processing on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. Among them, the storage medium can be a magnetic disk, an optical disk, a read-only storage memory, a random access memory, a flash memory, a hard disk or a solid-state hard disk, etc.; further, the storage medium can also include a combination of the above types of memories. It can be understood that a computer, a processor, a microprocessor controller, or programmable hardware includes a storage component that can store or receive software or computer code. When the software or computer code is accessed and executed by a computer, a processor, or hardware, the method shown in the above embodiment is implemented.

[0118] A part of the present invention may be applied as a computer program product, such as a computer program instruction, which, when executed by a computer, can call or provide the method and / or technical solution according to the present invention through the operation of the computer. Those skilled in the art should understand that the existence of the computer program instruction in a computer-readable medium includes, but is not limited to, a source file, an executable file, an installation package file, etc., and accordingly, the way in which the computer program instruction is executed by the computer includes, but is not limited to: the computer directly executes the instruction, or the computer compiles the instruction and then executes the corresponding compiled program, or the computer reads and executes the instruction, or the computer reads and installs the instruction and then executes the corresponding installed program. Here, the computer-readable medium may be any available computer-readable storage medium or communication medium accessible to the computer.

[0119] Although the embodiments of the present invention have been described in conjunction with the accompanying drawings, those skilled in the art may make various modifications and variations without departing from the spirit and scope of the present invention, and such modifications and variations are all within the scope defined by the appended claims.

Claims

1. A load control method for a smart park, characterized in that: The method comprises: Obtaining energy usage data, environmental data, and power restriction demand data of the smart park, wherein the energy usage data includes load data; Calculate the load regulation demand for power restriction according to the load data and the power restriction demand data; Predicting controllable loads using a pre-trained neural network model based on the energy usage data and environmental data; Determining the actual adjustable load based on the relationship between the predicted adjustable load and the load adjustment demand; A load control instruction is generated and executed according to the actual controllable load.

2. The method according to claim 1, characterized in that Based on the energy usage data and environmental data, a pre-trained neural network model is used to predict the adjustable load, including: Dividing the smart park into multiple areas according to the functions of the smart park; Using a preset algorithm, based on the energy usage data and environmental data, extracting high-power equipment, power curve, current curve, voltage curve, ambient temperature, and power necessity data in each area as feature data; The characteristic data is input into a pre-trained neural network model to obtain a predicted adjustable load. The neural network is trained based on the difference between the predicted adjustable load and the actual adjustable load as a loss function, wherein the loss function is expressed by the following formula: loss = (yp-y)(yp-y) Where yp represents the predicted controllable load, and y represents the actual controllable load.

3. The method according to claim 1, characterized in that Generating and executing a load control instruction according to the actual controllable load includes: By using the table lookup method, the load is divided into uncontrollable load, adjustable load and interruptible load according to the necessity of the nature of electricity consumption; Generate a first load control instruction for controlling an uncontrollable load, a second load control instruction for controlling a disconnectable load, and a third load control instruction for controlling an adjustable load according to the actual controllable load; Execute the first load control instruction, the second load control instruction and the third load control instruction in sequence. During the execution of each load control instruction, monitor the total load of the smart park. When the change in the total load meets the demand of the actual adjustable load, stop the execution.

4. The method according to claim 1, characterized in that: Executing the first load control instruction, the second load control instruction and the third load control instruction in sequence, including: Monitoring the operating state of the uncontrollable load based on the first load regulation instruction and a preset time interval; Controlling the disconnectable load to be disconnected based on the second load regulation instruction; The power supply strategy of the adjustable load is adjusted based on the third load control instruction.

5. The method according to claim 4, characterized in that The power supply strategy for adjusting the adjustable load based on the third load control instruction includes: Based on the third load control instruction, the charging and discharging time of the energy storage box, the air conditioning temperature, the street light switch and the power supply of the administrative area are controlled in sequence.

6. The method according to claim 5, characterized in that Control air conditioning temperature, including: Get the air conditioner disconnectable area and air conditioner adjustable area; Send control instructions to the air conditioner to turn off the air conditioner in the air conditioner-disabled area and increase the air conditioner temperature in the air conditioner-adjustable area; After the control command is sent, if it is detected that the air conditioner controlled to be turned off is in operation, feedback information is obtained; When no feedback information is received, resend the control instruction; When the received feedback information includes information that the air conditioner is locked, an unlock command is sent to the air conditioner and then a control command is sent; When the received feedback information includes information of control failure, the feedback information is analyzed to determine the cause of the failure, and the control instruction is resent after the problem in the cause of the failure is solved.

7. The method according to claim 1, characterized in that The load data includes the total load of the smart park, the power restriction demand data includes the maximum load value allowed by power restriction, and the load regulation demand of power restriction is calculated using the following formula: The load control demand for power restriction=total load-maximum load value allowed by power restriction×first preset value.

8. The method according to claim 1, characterized in that The pre-trained neural network model includes: input layer, hidden layer and output layer; The input layer includes input energy usage data and environmental data; The hidden layer includes m neurons. The input of each neuron is the weighted sum of the outputs of all neurons in the previous layer, plus the bias term. The input and output of the jth neuron in the hidden layer are expressed by the following formulas: [Z_j=\sum_{i=1}^{X}W1_{ij}\cdotA_i+b1_j] Among them, X represents the number of data features input to the input layer, W1 represents the weight matrix from the input layer to the hidden layer, and b1 represents the bias vector of the hidden layer; [A1_j=f(Z_j)] Where f is the activation function; The output layer consists of n neurons. The input of each neuron is the weighted sum of the outputs of all neurons in the hidden layer, plus the bias term. The input and output of the kth neuron in the output layer can be expressed as: [Z_k=\sum_{j=1}^{m}W2_{jk}\cdotA1_j+b2_k] Among them, W2 represents the weight matrix from the hidden layer to the output layer, and b2 represents the bias vector of the output layer; [Y_k=g(Z_k)] Among them, g represents the activation function of the output layer, and Y_k represents the predicted number of controllable loads.

9. A smart park load control system, characterized in that: The system comprises: A data acquisition module, used to acquire energy usage data, environmental data, and power restriction demand data of the smart park, wherein the energy usage data includes load data; A demand calculation module, used for calculating the load regulation demand for power restriction according to the load data and the power restriction demand data; A prediction module, for predicting adjustable loads using a pre-trained neural network model based on the energy usage data and environmental data; An actual adjustable determination module, used to determine the actual adjustable load based on the relationship between the predicted adjustable load and the load regulation demand; The control execution module is used to generate and execute load control instructions according to the actual controllable load.

10. A computer device, characterized in that: include: A memory and a processor, wherein the memory and the processor are communicatively connected to each other, computer instructions are stored in the memory, and the processor executes the smart park load control method according to any one of claims 1 to 8 by executing the computer instructions.

11. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a computer to execute the smart park load control method according to any one of claims 1 to 8.

Images