Smart park energy saving control system and method

Abstract

The invention belongs to the technical field of energy-saving control, and provides a smart park energy-saving control system and method. The method comprises the following steps: dividing each device in a park into a plurality of device groups in advance, wherein each device group is configured to have different regulation and control priorities; equipment operation data fed back by the sensing devices corresponding to the equipment are received, the energy demand quantity of the park in the target future time period is predicted according to the equipment operation data, and the total energy demand quantity of the park in the current attention period is predicted based on the energy demand quantity; calculating a difference value between the total energy demand quantity and the estimated total energy demand quantity, screening out a plurality of target equipment groups from each equipment group according to the difference value and the regulation priority, and optimizing the operation strategy of each equipment in each target equipment group based on the difference value. The difference value between the actual total energy demand quantity of the park and the estimated total energy demand quantity is lower than a preset difference value. According to the invention, the interference to core services is reduced as much as possible while the overall energy-saving effect of the park is improved.

Description

Technical Field

[0001] This invention relates to the field of energy-saving control technology, and more specifically, to a smart park energy-saving control system and method. Background Technology

[0002] In today's era that emphasizes sustainable development, energy conservation control in industrial parks is crucial. Currently, most parks primarily rely on specific rules to implement energy-saving operations on specific equipment. For example, some parks only set fixed on / off times for lighting equipment or regulate air conditioning systems according to preset temperature ranges. While this approach can achieve some energy savings for certain equipment, it has significant limitations.

[0003] This is mainly reflected in the fact that energy-saving control based on specific rules and specific equipment lacks a holistic consideration of the overall energy usage of the park. The park contains numerous and complex pieces of equipment, and the energy consumption of each piece of equipment is interconnected and influences each other. Simply controlling the energy consumption of individual pieces of equipment cannot optimize energy allocation as a whole, making it difficult to maximize the park's energy efficiency.

[0004] In summary, existing energy-saving control methods for industrial parks can no longer meet the growing demand for energy conservation, and there is an urgent need for a new method that can control energy conservation across the entire industrial park. Summary of the Invention

[0005] To address the aforementioned technical problems, this invention provides a smart park energy-saving control method, system, electronic device, computer storage medium, and computer program product to solve these problems.

[0006] This invention discloses a smart park energy-saving control method, the method comprising the following steps: pre-dividing the equipment in the park into several equipment groups, each equipment group being configured with a different control priority; receiving equipment operation data fed back by the sensors corresponding to each equipment, predicting the energy demand of the park in a target future period based on the equipment operation data, and predicting the total energy demand of the park in the current monitoring period based on the energy demand; wherein the target future period is located within the current monitoring period; calculating the difference between the total energy demand and the estimated total energy demand, selecting several target equipment groups from each equipment group based on the difference and the control priority, and optimizing the operation strategy of each equipment in each target equipment group based on the difference, so that the difference between the actual total energy demand and the estimated total energy demand of the park is lower than a preset difference.

[0007] In some embodiments, the step of pre-dividing the devices in the park into several device groups, with each device group configured with a different control priority, includes: obtaining device attribute information for each device in the park, the device attribute information including device function type, energy consumption level, device operation association level, business importance level, and operating time pattern; grouping devices with similar function types, similar energy consumption levels, similar device operation association levels, and similar operating time patterns into the same device group according to the device attribute information; and determining the control priority of each device group according to the highest business importance level, specifically, the higher the business importance level, the lower the control priority of the corresponding device group.

[0008] In some embodiments, predicting the energy demand of the park in a target future period based on the equipment operation data includes: acquiring historical operation data of each of the devices corresponding to the equipment operation data, and integrating the historical operation data into target historical operation data; wherein, the equipment operation data includes the device's own operation data and corresponding environmental parameters, and the historical operation data includes the device's own historical operation data and corresponding historical environmental parameters; removing abnormal and missing data from the equipment operation data, performing normalization processing, and using a convolutional network to extract features from the processed equipment operation data and the target historical operation data to obtain real-time operation features and historical operation features, respectively; inputting the real-time operation features and the historical operation features into an ARIMA model to obtain the energy demand predicted by the ARIMA model; wherein, the amount of historical operation data acquired for each device is determined by: determining the energy consumption fluctuation range based on the equipment operation data of each device, and obtaining the corresponding amount of historical operation data based on the deployment and operation time of the device and the energy consumption fluctuation range.

[0009] In some embodiments, the step of predicting the total energy demand of the park within the current monitoring period based on the energy demand includes: calculating the actual total energy consumption from the start time of the current monitoring period to the current time; calculating the historical average energy consumption of each future time period within the current monitoring period, excluding the target future time period, based on the historical energy consumption of the park in each time period; and calculating the total energy demand of the park within the current monitoring period based on the actual total energy consumption, the energy demand, and each of the historical average energy consumptions.

[0010] In some embodiments, the step of selecting a number of target device groups from each of the device groups based on the difference and the control priority includes: determining the number of control groups based on the difference and a preset relationship, and selecting the device groups of the number of control groups as the target device groups in descending order of the control priority.

[0011] This invention also discloses a smart park energy-saving control system. The system includes a processor and a memory. The processor executes computer code in the memory to: pre-divide the devices in the park into several device groups, each device group being configured with a different control priority; receive device operation data fed back by sensors corresponding to each device; predict the energy demand of the park in a target future period based on the device operation data; predict the total energy demand of the park in the current monitoring period based on the energy demand; wherein the target future period is located within the current monitoring period; calculate the difference between the total energy demand and the estimated total energy demand; select several target device groups from the device groups based on the difference and the control priority; and optimize the operation strategy of each device in each target device group based on the difference, so that the difference between the actual total energy demand and the estimated total energy demand of the park is lower than a preset difference.

[0012] In some embodiments, the step of pre-dividing the devices in the park into several device groups, with each device group configured with a different control priority, includes: obtaining device attribute information for each device in the park, the device attribute information including device function type, energy consumption level, device operation association level, business importance level, and operating time pattern; grouping devices with similar function types, similar energy consumption levels, similar device operation association levels, and similar operating time patterns into the same device group according to the device attribute information; and determining the control priority of each device group according to the highest business importance level, specifically, the higher the business importance level, the lower the control priority of the corresponding device group.

[0013] In some embodiments, predicting the energy demand of the park in a target future period based on the equipment operation data includes: acquiring historical operation data of each of the devices corresponding to the equipment operation data, and integrating the historical operation data into target historical operation data; wherein, the equipment operation data includes the device's own operation data and corresponding environmental parameters, and the historical operation data includes the device's own historical operation data and corresponding historical environmental parameters; removing abnormal and missing data from the equipment operation data, performing normalization processing, and using a convolutional network to extract features from the processed equipment operation data and the target historical operation data to obtain real-time operation features and historical operation features, respectively; inputting the real-time operation features and the historical operation features into an ARIMA model to obtain the energy demand predicted by the ARIMA model; wherein, the amount of historical operation data acquired for each device is determined by: determining the energy consumption fluctuation range based on the equipment operation data of each device, and obtaining the corresponding amount of historical operation data based on the deployment and operation time of the device and the energy consumption fluctuation range.

[0014] In some embodiments, the step of predicting the total energy demand of the park within the current monitoring period based on the energy demand includes: calculating the actual total energy consumption from the start time of the current monitoring period to the current time; calculating the historical average energy consumption of each future time period within the current monitoring period, excluding the target future time period, based on the historical energy consumption of the park in each time period; and calculating the total energy demand of the park within the current monitoring period based on the actual total energy consumption, the energy demand, and each of the historical average energy consumptions.

[0015] In some embodiments, the step of selecting a number of target device groups from each of the device groups based on the difference and the control priority includes: determining the number of control groups based on the difference and a preset relationship, and selecting the device groups of the number of control groups as the target device groups in descending order of the control priority.

[0016] The present invention also discloses an electronic device comprising: at least one processor, a memory, and a computer program stored in the memory and executable on the at least one processor, the processor executing the computer program to implement the method as described in any of the preceding claims.

[0017] The present invention also discloses a computer storage medium storing a computer program that is executed by a processor to implement the methods described in any of the preceding methods.

[0018] The present invention also discloses a computer program product that, when run on an electronic device, causes the electronic device to execute in order to implement the method described in any of the preceding methods.

[0019] The beneficial effects of the present invention are as follows: the present invention's solution scientifically groups the equipment and reasonably sets the control priority, giving priority to energy-saving control of equipment with low importance but high control priority. While achieving energy-saving control of the entire park, it can also minimize the impact on the park's core business. Attached Figure Description

[0020] To more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings used in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of the present invention and should not be regarded as a limitation on the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0021] Figure 1 This is a flowchart illustrating a smart park energy-saving control method disclosed in an embodiment of the present invention.

[0022] Figure 2 This is a schematic diagram illustrating the specific implementation process of step S01 disclosed in the embodiments of the present invention.

[0023] Figure 3 This is a schematic diagram of the process for predicting the energy demand of a park in a target future period based on equipment operation data, as disclosed in an embodiment of the present invention. Detailed Implementation

[0024] The following specific embodiments illustrate the implementation of this application. Those skilled in the art can easily understand other advantages and effects of this application from the content disclosed in this specification. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments in this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0025] Furthermore, the technical features involved in the different embodiments of this application described below can be combined with each other as long as they do not conflict with each other.

[0026] like Figure 1 As shown in the figure, an embodiment of the present invention discloses a smart park energy-saving control method, the method including the following steps: S01, the various devices in the park are pre-divided into several device groups, and each device group is configured with a different control priority.

[0027] The numerous complex devices in the park are divided into different equipment groups according to certain rules, and a control priority is set for each equipment group so that targeted control can be carried out according to the priority in subsequent energy-saving control.

[0028] Taking a comprehensive industrial park as an example, the equipment is divided into core production equipment, auxiliary production equipment, office equipment, and public facilities equipment. The public facilities and office equipment groups are given the highest control priority because their direct impact on the park's core business is relatively small; the auxiliary production equipment group has the next highest priority; and the core production equipment group plays a crucial role in the park's production and operation, thus receiving the lowest control priority. For example, in an electronics manufacturing park, public facilities equipment such as lighting equipment, although necessary daily, have no direct impact on product production and therefore have a high control priority; while chip manufacturing equipment directly determines product output and quality, and therefore has a low control priority.

[0029] S02, receiving equipment operation data fed back by the sensing devices corresponding to each of the devices, predicting the energy demand of the park in the target future period based on the equipment operation data, and predicting the total energy demand of the park in the current monitoring period based on the energy demand; wherein, the target future period is located within the current monitoring period.

[0030] Each piece of equipment within the park is equipped with sensors that detect its operational data. This data includes the equipment's own operating data and corresponding environmental parameters. Equipment operating data includes, for example, power consumption (power, voltage, current, number of devices started, etc.) and water flow, while environmental parameters include, for example, temperature, humidity, light intensity, and air quality. These sensors use wireless data communication technologies (such as LoRaWAN, NB-IoT, Wi-Fi, or Zigbee) via the Internet of Things (IoT) to feed back the operational data to the execution end of this invention, such as an artificial intelligence algorithm platform deployed in the cloud or on a local server. The AI ​​algorithm platform uses data analysis and prediction models to calculate the park's energy demand during a target future period (e.g., 14:00-16:00), and based on this, further predicts the park's total energy demand during the current monitoring period, providing a data foundation for subsequent energy-saving control. For example, analysis revealed that during the summer hours of 2:00 PM to 4:00 PM, as outdoor temperatures rise, the energy demand for air conditioning increases significantly. Combined with energy demand forecasts for other types of equipment, the total energy demand of the park during the current monitoring period of 6:00 AM to 12:00 AM on the same day was calculated.

[0031] S03, calculate the difference between the total energy demand and the estimated total energy demand, select several target equipment groups from each of the equipment groups based on the difference and the control priority, and optimize the operation strategy of each equipment in each of the target equipment groups based on the difference, so that the difference between the actual total energy demand and the estimated total energy demand of the park is lower than a preset difference.

[0032] Staff can pre-determine the total energy demand of the park during the current monitoring period, based on factors such as historical experience and manual adjustment values ​​considering operating costs. The difference between the actual predicted total energy demand and the pre-estimated total energy demand is calculated. Based on this difference and the control priority of each equipment group, target equipment groups requiring adjustment are selected. The operating strategies of the equipment within these target groups are then optimized to ensure the difference between the two is lower than the preset difference, thereby achieving overall energy conservation for the entire park.

[0033] For example, if a park estimates its total energy demand for the day at 10,000 kWh, and the actual predicted demand is 12,000 kWh, the difference is 2,000 kWh. With this 1,000 kWh difference preset, office equipment and public facilities equipment are designated as target equipment groups, and energy-saving control is implemented on the equipment within them. For office equipment, the performance of some computers can be reduced during non-critical business hours to decrease energy consumption; for public facilities equipment, such as lighting equipment, brightness can be appropriately reduced or some lights can be turned off in well-lit areas.

[0034] The solution of this invention scientifically groups the equipment and reasonably sets the control priority, giving priority to energy-saving control to equipment with low importance but high control priority. While achieving energy-saving control of the entire park, it can also minimize the impact on the core business of the park.

[0035] In some embodiments, such as Figure 2 As shown, the process of pre-dividing the equipment within the park into several equipment groups, with each equipment group configured with different control priorities, includes: acquiring equipment attribute information for each piece of equipment within the park, the equipment attribute information including equipment function type, energy consumption level, equipment operation association level, business importance level, and operating time pattern; grouping equipment with similar function types, similar energy consumption levels, similar equipment operation association levels, and similar operating time patterns into the same equipment group based on the equipment attribute information; and determining the control priority of each equipment group based on the highest business importance level, specifically, the higher the business importance level, the lower the control priority of the corresponding equipment group.

[0036] In this embodiment of the invention, comprehensive data on equipment attributes within the park is collected, including multiple dimensions such as equipment function type, energy consumption level, equipment operation correlation level, business importance level, and operation time pattern. This data can be manually determined by staff (mainly equipment function type) or automatically obtained by analysis equipment based on relevant information of each device (mainly energy consumption level, equipment operation correlation level, business importance level, and operation time pattern).

[0037] Then, based on the acquired equipment attribute information, equipment with similar attributes is grouped into the same equipment group. This grouping facilitates unified management and control of equipment, improving the efficiency and targeting of energy-saving control. For example, in a logistics park, all lighting equipment (with similar functional types) can be grouped together. These devices have relatively low and stable energy consumption levels, low operational correlation levels (mainly operating independently), and their operating time patterns are likely to be at night or when there is insufficient light. Similarly, forklifts of the same type (with similar functional types, energy consumption levels, operational correlation levels, and operating time patterns) can be grouped together. They mainly work collaboratively during cargo handling periods, facilitating unified control of their operating power and working time.

[0038] This invention determines the control priority of each equipment group based on the highest business importance level within the group. The higher the business importance level, the lower the control priority of the corresponding equipment group, ensuring its stable operation and preventing energy-saving measures from impacting core business operations. For example, in a logistics park, the goods sorting equipment group has a high business importance level and a low control priority; when energy demand discrepancies require adjustment, its normal operation will be prioritized. Conversely, the landscape lighting equipment group in the park has a low business importance level and a high control priority; during energy-saving adjustments, its brightness can be reduced or some lights can be turned off first.

[0039] In some embodiments, such as Figure 3As shown, the step of predicting the energy demand of the park in a target future period based on the equipment operation data includes: acquiring historical operation data of each of the equipment corresponding to the equipment operation data, and integrating the historical operation data into target historical operation data; wherein, the equipment operation data includes the equipment's own operation data and corresponding environmental parameters, and the historical operation data includes the equipment's own historical operation data and corresponding historical environmental parameters; removing abnormal and missing data from the equipment operation data, then performing normalization processing, and using a convolutional network to extract features from the processed equipment operation data and the target historical operation data to obtain real-time operation features and historical operation features respectively; inputting the real-time operation features and the historical operation features into an ARIMA model to obtain the energy demand predicted by the ARIMA model; wherein, the amount of historical operation data acquired for each of the equipment is determined in the following way: determining the energy consumption fluctuation range based on the equipment operation data of each of the equipment, and obtaining the corresponding amount of historical operation data based on the deployment and operation time of the equipment and the energy consumption fluctuation range.

[0040] In this embodiment of the invention, the equipment operation data includes the current operation data of each device. Based on this, historical operation data corresponding to the current operation data is obtained, and this historical data is integrated into target historical operation data. Equipment operation data includes the device's own operation data (such as power, speed, etc.) and environmental parameters (such as temperature, humidity, etc.), and historical operation data is similarly analyzed. For example, for a large air conditioning unit in a park, its own operation data includes the current cooling capacity, compressor speed, etc., and the environmental parameter is the current indoor and outdoor temperature. Its historical operation data covers information such as cooling capacity, compressor speed, and corresponding indoor and outdoor temperatures at different time periods in the past. After integrating this historical data, a historical dataset on the relationship between the operation and energy consumption of the air conditioning unit can be formed, providing a reference for prediction.

[0041] First, abnormal and missing data are removed from the above-mentioned equipment operation data to ensure data reliability. Then, normalization processing is performed to make different types of data comparable. Next, a convolutional network is used to extract features from the preprocessed equipment operation data and the target historical operation data. The convolutional network can automatically learn the spatial and temporal features in the equipment operation data, obtaining real-time operation features and historical operation features respectively. For example, for air conditioning equipment, it can extract features such as the correlation between temperature changes and cooling capacity adjustments, and the impact of different seasonal environmental parameters on energy consumption from a large amount of operation data and historical data.

[0042] The ARIMA model has the ability to predict time series data. It can effectively predict future energy demand based on the trends and patterns of historical data and combined with current real-time characteristics, thereby obtaining the predicted energy demand of the park in the target future period (e.g., the next two hours).

[0043] Furthermore, while the ARIMA model itself has already been trained, another improvement of this invention is that it also simultaneously inputs historical operating features corresponding to the target historical operating data into the ARIMA model for reference and guidance. Regarding the amount of historical operating data acquired, this invention sets it to be dynamic. Specifically, based on the operating data of the corresponding device during the current time period (e.g., 10:00-12:00) (i.e., the data corresponding to that device in the device's operating data), the energy consumption fluctuation range of the device is determined, such as the fluctuation range of actual power and current. A larger energy consumption fluctuation range indicates poorer operational stability of the device, thus requiring more historical operating data to provide the ARIMA model with more and richer reference feature information; otherwise, the settings are reversed, and the specifics will not be elaborated further. Meanwhile, this invention also considers the deployment runtime of the equipment, which refers to the cumulative actual runtime of the equipment since it was installed in the park. Based on this deployment runtime, a roughly negatively correlated optimization coefficient can be obtained. This optimization coefficient is used to appropriately correct the energy consumption fluctuation range calculated above. For example, the optimization coefficient is 1.3 for deployment runtime below 50 hours, 1.2 for deployment runtime between 50 and 200 hours, and 1.0 for deployment runtime above 200 hours. In other words, the longer the deployment runtime of the equipment, the more stable its operation and the more obvious its operating pattern. Therefore, a smaller optimization coefficient is set, reducing the degree of adjustment to the energy consumption fluctuation range, and thus obtaining less historical operating data for the equipment. This allows the amount of historical operating characteristics data used for ARIMA model reference to be controlled within a reasonable range.

[0044] In some embodiments, the step of predicting the total energy demand of the park within the current monitoring period based on the energy demand includes: calculating the actual total energy consumption from the start time of the current monitoring period to the current time; calculating the historical average energy consumption of each future time period within the current monitoring period, excluding the target future time period, based on the historical energy consumption of the park in each time period; and calculating the total energy demand of the park within the current monitoring period based on the actual total energy consumption, the energy demand, and each of the historical average energy consumptions.

[0045] In this embodiment of the invention, based on statistics of the actual electricity consumption of the park, the total actual energy consumption from the start of the current monitoring period to the present moment can be determined. For the remaining future time periods, the energy demand for the target future time period has already been predicted, while for other future time periods, it can be calculated based on the historical energy consumption statistics of the park for each time period. Therefore, the total energy demand of the park within the current monitoring period can be predicted.

[0046] It should be noted that the current monitoring period can be preset, such as 12 hours or one week, but the future time period must be included in the current monitoring period, which is an hourly segment within each current monitoring period.

[0047] In some embodiments, the step of selecting a number of target device groups from each of the device groups based on the difference and the control priority includes: determining the number of control groups based on the difference and a preset relationship, and selecting the device groups of the number of control groups as the target device groups in descending order of the control priority.

[0048] In this embodiment of the invention, a preset relationship between the number of control groups and the difference is established in advance. For example, the difference corresponds to three intervals from low to high. The higher the interval to which the difference belongs, the more control groups there are. For example, if the interval to which the difference belongs is a high-level interval, then the corresponding number of control groups is 3 groups. If the interval to which the difference belongs is a low-level interval, then the corresponding number of control groups is 1 group.

[0049] Furthermore, after identifying the target equipment groups that need to participate in this round of energy-saving control, the operating strategies of each piece of equipment within each target equipment group can be optimized in the manner described above to achieve energy-saving goals. This could include reducing the performance of some computers, decreasing the brightness of landscape lighting, optimizing the number of handling machines involved, or optimizing their collaborative handling strategies for greater energy efficiency. Ultimately, this ensures that by the end of the current monitoring period, the difference between the actual total energy demand and the estimated total energy demand of the park is lower than a preset difference.

[0050] This invention also discloses a smart park energy-saving control system. The system includes a processor and a memory. The processor executes computer code in the memory to: pre-divide the devices in the park into several device groups, each device group being configured with a different control priority; receive device operation data fed back by sensors corresponding to each device; predict the energy demand of the park in a target future period based on the device operation data; predict the total energy demand of the park in the current monitoring period based on the energy demand; wherein the target future period is located within the current monitoring period; calculate the difference between the total energy demand and the estimated total energy demand; select several target device groups from the device groups based on the difference and the control priority; and optimize the operation strategy of each device in each target device group based on the difference, so that the difference between the actual total energy demand and the estimated total energy demand of the park is lower than a preset difference.

[0051] This invention also discloses an electronic device, comprising: at least one processor, a memory, and a computer program stored in the memory and executable on the at least one processor, wherein the processor executes the computer program to implement the method described in the foregoing embodiments.

[0052] This invention also discloses a computer storage medium storing a computer program that is executed by a processor to implement the methods described in the foregoing embodiments.

[0053] This invention also discloses a computer program product that, when run on an electronic device, causes the electronic device to execute the method described in the foregoing embodiments.

[0054] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0055] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the invention patent. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this patent application should be determined by the appended claims.

Claims

1. A smart park energy-saving control method, characterized in that, The method includes the following steps: pre-dividing the equipment in the park into several equipment groups, each equipment group being configured with a different control priority; receiving equipment operation data fed back by the sensors corresponding to each equipment, predicting the energy demand of the park in a target future period based on the equipment operation data, and predicting the total energy demand of the park in the current monitoring period based on the energy demand; wherein the target future period is located within the current monitoring period; calculating the difference between the total energy demand and the estimated total energy demand, selecting several target equipment groups from each equipment group based on the difference and the control priority, and optimizing the operation strategy of each equipment in each target equipment group based on the difference, so that the difference between the actual total energy demand and the estimated total energy demand of the park is lower than a preset difference.

2. The smart park energy-saving control method according to claim 1, characterized in that: The process of pre-dividing the equipment within the park into several equipment groups, with each equipment group configured with different control priorities, includes: acquiring equipment attribute information for each piece of equipment within the park, the equipment attribute information including equipment function type, energy consumption level, equipment operation association level, business importance level, and operating time pattern; grouping equipment with similar function types, similar energy consumption levels, similar equipment operation association levels, and similar operating time patterns into the same equipment group based on the equipment attribute information; and determining the control priority of each equipment group based on the highest business importance level, specifically, the higher the business importance level, the lower the control priority of the corresponding equipment group.

3. The smart park energy-saving control method according to claim 2, characterized in that: The step of predicting the energy demand of the park in a target future period based on the equipment operation data includes: acquiring historical operation data of each of the equipment corresponding to the equipment operation data, and integrating the historical operation data into target historical operation data; wherein, the equipment operation data includes the equipment's own operation data and corresponding environmental parameters, and the historical operation data includes the equipment's own historical operation data and corresponding historical environmental parameters; removing abnormal and missing data from the equipment operation data, then performing normalization processing, and using a convolutional network to extract features from the processed equipment operation data and the target historical operation data to obtain real-time operation features and historical operation features respectively; inputting the real-time operation features and the historical operation features into an ARIMA model to obtain the energy demand predicted by the ARIMA model; wherein, the amount of historical operation data acquired for each of the equipment is determined by: determining the energy consumption fluctuation range based on the equipment operation data of each of the equipment, and obtaining the corresponding amount of historical operation data based on the deployment and operation time of the equipment and the energy consumption fluctuation range.

4. The smart park energy-saving control method according to claim 3, characterized in that: The method of predicting the total energy demand of the park within the current monitoring period based on the energy demand includes: calculating the actual total energy consumption from the start time of the current monitoring period to the current time; calculating the historical average energy consumption of each future time period within the current monitoring period, excluding the target future time period, based on the historical energy consumption of the park in each time period; and calculating the total energy demand of the park within the current monitoring period based on the actual total energy consumption, the energy demand, and the historical average energy consumption.

5. The smart park energy-saving control method according to claim 4, characterized in that: The step of selecting several target equipment groups from each of the equipment groups based on the difference and the control priority includes: determining the number of control groups based on the difference and a preset relationship, and selecting the equipment groups of the number of control groups as the target equipment groups in descending order of the control priority.

6. A smart park energy-saving control system, the system comprising a processor and a memory, characterized in that: The processor executes computer code in the memory to: pre-divide the devices in the park into several device groups, each device group being configured with a different control priority; receive device operation data fed back by sensors corresponding to each device, predict the energy demand of the park in a target future period based on the device operation data, and predict the total energy demand of the park in the current monitoring period based on the energy demand; wherein the target future period is located within the current monitoring period; calculate the difference between the total energy demand and the estimated total energy demand, select several target device groups from the device groups based on the difference and the control priority, and optimize the operation strategy of each device in each target device group based on the difference, so that the difference between the actual total energy demand and the estimated total energy demand of the park is lower than a preset difference.

7. The smart park energy-saving control system according to claim 6, characterized in that: The process of pre-dividing the equipment within the park into several equipment groups, with each equipment group configured with different control priorities, includes: acquiring equipment attribute information for each piece of equipment within the park, the equipment attribute information including equipment function type, energy consumption level, equipment operation association level, business importance level, and operating time pattern; grouping equipment with similar function types, similar energy consumption levels, similar equipment operation association levels, and similar operating time patterns into the same equipment group based on the equipment attribute information; and determining the control priority of each equipment group based on the highest business importance level, specifically, the higher the business importance level, the lower the control priority of the corresponding equipment group.

8. An electronic device, comprising: At least one processor, a memory, and a computer program stored in the memory and executable on the at least one processor, characterized in that: the processor executes the computer program to implement the method as claimed in any one of claims 1-5.

9. A computer storage medium, wherein the computer-readable storage medium stores a computer program, characterized in that: The computer program is executed by a processor to implement the method as described in any one of claims 1-5.

10. A computer program product, characterized in that: When a computer program product is run on an electronic device, it causes the electronic device to perform the method as described in any one of claims 1-5.

Images