Energy consumption prediction and optimization system and method based on artificial intelligence

Abstract

The invention discloses an energy consumption prediction and optimization system and method based on artificial intelligence, and relates to the technical field of energy consumption prediction and optimization, and the method comprises the following steps: calculating the energy consumption intensity indexes of all devices in different time periods, and forming a time segment set of historical energy consumption abnormity of the devices; generating a candidate scheduling strategy, for any strategy, obtaining an equipment calling sequence and energy consumption switching time between equipment, and when the scheduling time of the equipment falls into a historical energy consumption abnormal paragraph set, calculating the actual operation energy consumption of the equipment in an abnormal time period; traversing the equipment calling time in the strategy to calculate the actual total energy consumption and the number of times exceeding the predicted energy consumption, calculating the energy efficiency matching value of each candidate strategy, and generating a strategy recommendation sequence; and selecting the strategy with the highest energy efficiency matching value from the strategy recommendation sequence as a preferred execution scheme, collecting real-time energy consumption data after execution, calculating an energy consumption deviation rate, comparing the energy consumption deviation rate with a threshold value, and judging the effectiveness of the strategy, so that energy consumption prediction and optimization are realized.

Description

Technical Field

[0001] The present invention relates to the technical field of energy consumption prediction and optimization, and specifically to an energy consumption prediction and optimization system and method based on artificial intelligence. Background Art

[0002] As the scale of commercial facilities continues to expand, companies are increasingly demanding refined energy management. As a key cost factor in commercial operations, the optimization of equipment energy consumption affects the company's operations, green development goals, and the scientific nature of its business decisions.

[0003] However, traditional energy management methods have gradually exposed the following problems when dealing with complex equipment systems, multi-period energy consumption fluctuations, and intelligent optimization needs: First, the identification of historical energy consumption anomalies is delayed and lacks systematicity. During the operation of commercial facilities, equipment often experiences energy consumption anomalies due to load fluctuations, equipment aging, or improper scheduling. Traditional management methods rely on manual inspections or post-event statistics, which cannot capture the changes in the energy consumption intensity of each device in different time periods in real time, resulting in long-term energy waste and difficulty in tracing. Second, equipment scheduling strategies lack intelligence and dynamic adaptability. Traditional energy scheduling is mostly based on fixed rules and does not combine the historical energy efficiency performance of equipment with real-time demand. In peak and valley electricity price scenarios, equipment starts and stops only based on time nodes, without considering the actual energy efficiency of different equipment in specific time periods. Third, the policy evaluation and optimization mechanism lacks closed-loop feedback. In traditional energy management, there is a lack of real-time energy efficiency monitoring and dynamic adjustment mechanisms after policy execution. The actual energy consumption deviation rate exceeds expectations. The manual troubleshooting cycle is long and the adjustment is delayed, which cannot trigger policy switching or equipment maintenance in a timely manner, resulting in a gradual decline in energy efficiency optimization effects. Summary of the Invention

[0004] The purpose of the present invention is to provide an energy consumption prediction and optimization system and method based on artificial intelligence to solve the problems raised in the prior art.

[0005] To achieve the above objectives, the present invention provides the following technical solution: an energy consumption prediction and optimization method based on artificial intelligence, the method comprising the following steps:

[0006] Obtain historical data of commercial facilities and equipment specified by the user, generate a historical data set, calculate the energy consumption intensity index of each device in different time periods, construct an energy consumption intensity change graph, mark the abnormal time periods when the historical energy consumption intensity is lower than the preset threshold, and form a time segment set of historical energy consumption abnormalities of the equipment;

[0007] Generate candidate scheduling strategies based on user-specified device information and real-time energy consumption requirements. For any strategy, obtain the device call sequence and the energy consumption switching time between devices. When the device's scheduling time falls into its historical energy consumption anomaly period, calculate the device's actual operating energy consumption during the anomaly period.

[0008] Traverse the device call time in the strategy to calculate the actual total energy consumption and the number of times the predicted energy consumption is exceeded, calculate the energy efficiency matching value of each candidate strategy, generate a set of energy efficiency matching values ​​and sort them from high to low to obtain a strategy recommendation sequence;

[0009] The strategy with the highest energy efficiency matching value is selected from the strategy recommendation sequence as the preferred execution plan. The real-time energy consumption data after execution is collected to calculate the energy consumption deviation rate, which is then compared with the threshold to determine the effectiveness of the strategy.

[0010] Obtain historical data of commercial facilities and equipment specified by the user, generate a historical data set, calculate the energy consumption intensity index of each device in different time periods, construct an energy consumption intensity change graph, mark the abnormal time periods when the historical energy consumption intensity is lower than the preset threshold, and form a time segment set of historical energy consumption abnormalities of the equipment. The specific steps include:

[0011] Obtain the historical data of commercial facilities and equipment specified by the user and generate a historical data set E = {E1, E2, ..., E n}; where E1, E2, ..., E n It represents the historical data of the 1st, 2nd, ..., nth equipment, where n represents the total number of commercial facilities and equipment specified by the user. The historical data information of any commercial facility equipment is E a , the historical data information includes: the load rate of device a in the jth time period, the energy consumption value of device a in the jth time period, and the operating status of device a in the jth time period;

[0012] Calculate the energy consumption intensity index of device a in the jth time period. The calculation formula is as follows: η aj =C aj / (P aj *T j ); where η aj represents the energy consumption intensity of device i in the jth time period, C aj represents the energy consumption value of device a in the jth time period, P aj represents the load rate of device i in the jth time period, T j represents the duration of the jth time period;

[0013] The historical data information of the target device is traversed to obtain the energy consumption intensity index of different devices in different time periods. The energy consumption intensity index is used as the vertical coordinate and a two-dimensional plane coordinate system is constructed to form a diagram of the energy consumption intensity change of the device. According to the diagram of the energy consumption intensity change, the time period when the historical energy consumption intensity is lower than the preset threshold is marked to form a time segment set Q of the device's historical energy consumption anomaly. a ={Q a1 ,Q a2 ,...,Q aM '}, where Qa1 ,Q a2 ,...,Q aM ' indicates that the energy consumption intensity of device a is abnormal in the 1st, 2nd, ..., M' time periods, and M' indicates the total number of time periods in which abnormal energy consumption efficiency is detected.

[0014] Generate candidate scheduling strategies based on user-specified device information and real-time energy consumption requirements. For any strategy, obtain the device call sequence and the energy consumption switching time between devices. When the device's scheduling time falls into its historical energy consumption anomaly period, calculate the device's actual operating energy consumption during the anomaly period. The specific steps include:

[0015] Based on the device information and real-time energy consumption requirements specified by the user, equipment scheduling planning is performed to generate candidate scheduling strategies. Any scheduling strategy is selected and recorded as S k , according to strategy S k The calling sequence D(k,i) of the devices and the energy consumption switching time T(k,i) between the devices are obtained respectively, where T(k,i) represents the energy consumption switching time according to the strategy S k The energy consumption adjustment time required to switch from the i-1th device to the i-th device, D(k,i) represents the energy consumption adjustment time required to switch from the i-1th device to the i-th device according to the strategy S k The i-th called device;

[0016] When the device D(k,i) is in the time period In the historical energy consumption abnormal section set Q D(k,i) ={Q D(k,i),1 ,Q D(k,i),2 ,...Q D(k,i),M '} (i.e., the scheduling time falls into the historical low efficiency or high load period of the device), the actual operating energy consumption of the device D(k,i) is calculated as C k,i =η D (k,i),j '*P D(k,i),j’ *T j’ ; Among them, η D (k,i),j ' represents the energy consumption intensity of device D(k,i) in the j'th abnormal time period, P D(k,i),j’ represents the load rate of device D(k,i) in the j'th abnormal time period, t0 represents the starting time point of the policy execution, T j’ Indicates the duration of the j'th abnormal time period.

[0017] Traverse the device call time in the strategy to calculate the actual total energy consumption and the number of times the predicted energy consumption is exceeded, calculate the energy efficiency matching value of each candidate strategy, generate a set of energy efficiency matching values ​​and sort them from high to low to obtain a strategy recommendation sequence. The specific steps include:

[0018] Traversal strategy S kThe calling time of all devices in the system is used to calculate the actual total energy consumption C k,N , and count the number of times it exceeds the predicted energy consumption K(C k,i >C pred,i ), where C pred,i Indicates device D k,i The predicted energy consumption value, C k,i Indicates device D k,i The actual energy consumption value;

[0019] Calculation strategy S k The energy efficiency matching value is defined as follows: F k =1-K(C k,i >C pred,i ) / N; where K(C k,i >C pred,i ) represents the cumulative number of times the actual energy consumption of the devices in the strategy exceeds the predicted value, and N represents the total number of devices called by the strategy;

[0020] Traverse all generated candidate strategies S1, S2, ..., S R , get the energy efficiency matching value of each strategy, and get the set F={F1,F2,...,F R}, R represents the total number of candidate strategies generated, F1, F2, ..., F R Indicates the candidate strategies generated 1, 2, ..., R, sorts the obtained set F from high to low, and generates a strategy recommendation sequence F' = {F'1, F'2, ..., F' R}, where F'1>F'2>...>F' R , F'1, F'2, ..., F' R represents the 1st, 2nd, ..., Rth generated candidate strategies after sorting.

[0021] The strategy with the highest energy efficiency matching value is selected from the strategy recommendation sequence as the preferred execution plan. The real-time energy consumption data after execution is collected to calculate the energy consumption deviation rate. The energy consumption deviation rate is compared with the threshold to determine the effectiveness of the strategy. The specific steps include:

[0022] Select the strategy with the highest energy efficiency matching value from the strategy recommendation sequence as the preferred execution plan;

[0023] Collect the real-time energy consumption data after the strategy is executed, compare it with the predicted value, and calculate the energy consumption deviation rate, which is defined as follows: Z = |C real -C pred | / C pred *100%; among which, C real represents the real-time energy consumption data after the strategy is executed, C pred represents the energy consumption forecast value, and Z represents the energy consumption deviation rate;

[0024] Set the energy consumption deviation rate threshold Z0. When Z≤Z0, the strategy is determined to be effective and the current strategy is maintained. When Z>Z0, the strategy is determined to be unsatisfactory and the strategy switching mechanism is triggered. The suboptimal scoring strategy F'2 is selected from the strategy recommendation sequence and updated as the current execution plan. The monitoring and switching process is repeated until any of the following conditions is met: the energy consumption deviation rate threshold Z≤Z0, the strategy is successfully executed; all strategies are tried and fail to meet the standard, and an alarm is triggered.

[0025] An artificial intelligence-based energy consumption prediction and optimization system is applied to an artificial intelligence-based energy consumption prediction and optimization method described in any one of claims 1 to 5. The system includes: a data acquisition module, a candidate strategy generation module, a strategy evaluation and ranking module, and a strategy execution and feedback module. The data acquisition module is used to calculate the energy consumption intensity index of each device in different time periods to form a time segment set of historical energy consumption anomalies of the device; the candidate strategy generation module is used to generate candidate scheduling strategies. For any strategy, the device call sequence and the energy consumption switching time between devices are obtained. When the scheduling time of the device falls into its historical energy consumption anomaly segment set, the actual operating energy consumption of the device in the abnormal time period is calculated; the strategy evaluation and ranking module is used to traverse the device call time in the strategy to calculate the actual total energy consumption and the number of times the predicted energy consumption is exceeded, calculate the energy efficiency matching value of each candidate strategy, and generate a strategy recommendation sequence; the strategy execution and feedback module is used to select the strategy with the highest energy efficiency matching value from the strategy recommendation sequence as the preferred execution plan, collect real-time energy consumption data after execution to calculate the energy consumption deviation rate, and determine the effectiveness of the strategy after comparing it with the threshold.

[0026] The data acquisition module includes a data acquisition unit, an energy consumption intensity calculation unit and an abnormal period marking unit. The data acquisition unit is used to obtain historical data of user-specified devices and generate a historical data set; the energy consumption intensity calculation unit is used to calculate the energy consumption intensity index of each device in different time periods through a formula; the abnormal period marking unit is used to construct an energy consumption intensity change graph, compare it with a preset threshold, mark the abnormal time period where the energy consumption intensity is lower than the threshold, and generate an abnormal time segment set.

[0027] The candidate strategy generation module includes a strategy planning unit and an abnormal energy consumption calculation unit. The strategy planning unit is used to generate candidate scheduling strategies based on the device information and real-time energy consumption requirements specified by the user. Each strategy includes a device call sequence and switching time. The abnormal energy consumption calculation unit is used to calculate the actual operating energy consumption when the device scheduling time in the strategy falls into its abnormal time segment set.

[0028] The policy evaluation and sorting module includes an energy consumption statistics unit, an energy efficiency matching calculation unit and a policy sorting unit. The energy consumption statistics unit is used to traverse the call time of all devices in the policy, calculate the actual total energy consumption, and count the number of times the actual energy consumption exceeds the predicted value; the energy efficiency matching calculation unit is used to calculate the energy efficiency matching value of the policy; the policy sorting unit is used to sort the energy efficiency matching value set from high to low to generate a policy recommendation sequence.

[0029] The strategy execution and feedback module includes a strategy execution unit, a real-time monitoring unit and a strategy optimization unit. The strategy execution unit is used to select the strategy with the highest energy efficiency matching value from the recommended sequence as the preferred option; the real-time monitoring unit is used to collect real-time energy consumption data after the strategy is executed, and compare it with the predicted value to calculate the energy consumption deviation rate; the strategy optimization unit is used to set the energy consumption deviation rate threshold, compare the energy consumption deviation amount with the preset threshold, and determine the effectiveness of the strategy.

[0030] Compared with the prior art, the present invention has the following beneficial effects:

[0031] 1. Through multi-dimensional analysis of historical energy consumption data of equipment, combined with multiple indicators such as load rate, energy consumption value, and operating status, the energy consumption intensity index is calculated and a change chart is constructed. Unlike the single total energy consumption analysis in the existing technology, this invention captures the energy efficiency change trends and abnormal fluctuations of equipment in different time periods, realizes accurate marking of historical energy consumption abnormal periods and multi-dimensional comprehensive evaluation, thereby improving the ability to identify energy consumption anomalies;

[0032] 2. The present invention introduces an intelligent candidate strategy generation and evaluation module, which combines historical abnormal period data of the equipment and real-time energy consumption demand factors to dynamically generate multiple scheduling strategies and calculate energy efficiency matching values. Unlike the static fixed rule scheduling in the existing technology, the present invention automatically adjusts the calling sequence and switching time according to the energy efficiency performance of the equipment and the real-time load to ensure the efficiency and adaptability of the strategy, and at the same time quantifies the ranking through energy efficiency matching values. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] Fig. 1 This is a flow chart of an energy consumption prediction and optimization method based on artificial intelligence according to the present invention;

[0034] Fig. 2 This is a structural diagram of an energy consumption prediction and optimization system based on artificial intelligence in the present invention. DETAILED DESCRIPTION

[0035] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only 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 ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0036] In the embodiment: Figs. 1-2 As shown, the present invention provides a technical solution, an energy consumption prediction and optimization method based on artificial intelligence, which includes the following steps:

[0037] Obtain historical data of commercial facilities and equipment specified by the user, generate a historical data set, calculate the energy consumption intensity index of each device in different time periods, construct an energy consumption intensity change graph, mark the abnormal time periods when the historical energy consumption intensity is lower than the preset threshold, and form a time segment set of historical energy consumption abnormalities of the equipment;

[0038] Generate candidate scheduling strategies based on user-specified device information and real-time energy consumption requirements. For any strategy, obtain the device call sequence and energy consumption switching time between devices. When a device's scheduling time falls into its historical energy consumption anomaly section set, calculate the device's actual operating energy consumption during the anomaly period.

[0039] Traverse the device call time in the strategy to calculate the actual total energy consumption and the number of times the predicted energy consumption is exceeded, calculate the energy efficiency matching value of each candidate strategy, generate a set of energy efficiency matching values ​​and sort them from high to low to obtain a strategy recommendation sequence;

[0040] The strategy with the highest energy efficiency matching value is selected from the strategy recommendation sequence as the preferred execution plan. The real-time energy consumption data after execution is collected to calculate the energy consumption deviation rate, which is then compared with the threshold to determine the effectiveness of the strategy.

[0041] Obtain historical data of commercial facilities and equipment specified by the user, generate a historical data set, calculate the energy consumption intensity index of each device in different time periods, construct an energy consumption intensity change graph, mark the abnormal time periods when the historical energy consumption intensity is lower than the preset threshold, and form a time segment set of historical energy consumption abnormalities of the equipment. The specific steps include:

[0042] Obtain the historical data of commercial facilities and equipment specified by the user and generate a historical data set E = {E1, E2, ..., E n}; where E1, E2, ..., E n It represents the historical data of the 1st, 2nd, ..., nth equipment, where n represents the total number of commercial facilities and equipment specified by the user. The historical data information of any commercial facility equipment is E a,The historical data information includes: the load rate of device a in the jth time period, the energy consumption value of device a in the jth time period, and the ,operation status of device a in the jth time period;

[0043] Calculate the energy consumption intensity index of device a in the jth time period. The calculation formula is as follows: η aj =C aj / (P aj *T j ); where η aj represents the energy consumption intensity of device i in the jth time period, C aj represents the energy consumption value of device a in the jth time period, P aj represents the load rate of device i in the jth time period, T j represents the duration of the jth time period;

[0044] The historical data information of the target device is traversed to obtain the energy consumption intensity index of different devices in different time periods. The energy consumption intensity index is used as the vertical coordinate and a two-dimensional plane coordinate system is constructed to form a diagram of the energy consumption intensity change of the device. According to the diagram of the energy consumption intensity change, the time period when the historical energy consumption intensity is lower than the preset threshold is marked to form a time segment set Q of the device's historical energy consumption anomaly. a ={Q a1 ,Q a2 ,...,Q aM '}, where Q a1 ,Q a2 ,...,Q aM ' indicates that the energy consumption intensity of device a is abnormal in the 1st, 2nd, ..., M' time periods, and M' indicates the total number of time periods in which abnormal energy consumption efficiency is detected.

[0045] Specifically, in a supermarket, the equipment includes air conditioners (4 units, each with a rated power of 50kW), lighting systems (total power of 80kW), refrigerators (20 units, each with a power of 2kW), and charging piles (5 units, each with a power of 60kW). The peak power period is 9:00-21:00, and the off-peak period is 21:00-9:00 the next day.

[0046] Collect equipment operation data from the supermarket over the past 30 days to generate a historical data set. For example, for equipment 1, Air Conditioner 1: during the time period of 8:00-8:30, the load factor was 0.6, the energy consumption was 30 kWh, and the operating state was cooling; during the time period of 9:00-9:30, the load factor was 0.9, the energy consumption was 45 kWh, and the operating state was full-load cooling; during the time period of 12:00-12:30, the load factor was 0.7, the energy consumption was 42 kWh, and the operating state was cooling;

[0047] Taking 8:00-8:30 as an example, the time period is 0.5 hours, and the energy consumption intensity index η is calculated according to the formula 11 =100kW, the preset threshold is 80kW, and energy consumption intensity less than the threshold is marked as abnormal. For example, the energy consumption intensity index of device 1 from 12:00 to 12:30 is 120kW, which is normal. The energy consumption intensity index of device 2 from 14:00 to 14:30 is 4kW. At this time, the energy consumption intensity index is lower than the threshold and is marked as abnormal.

[0048] Generate candidate scheduling strategies based on user-specified device information and real-time energy consumption requirements. For any strategy, obtain the device call sequence and the energy consumption switching time between devices. When the device's scheduling time falls into its historical energy consumption anomaly period, calculate the device's actual operating energy consumption during the anomaly period. The specific steps include:

[0049] Based on the device information and real-time energy consumption requirements specified by the user, equipment scheduling planning is performed to generate candidate scheduling strategies. Any scheduling strategy is selected and recorded as S k , according to strategy S k The calling sequence D(k,i) of the devices and the energy consumption switching time T(k,i) between the devices are obtained respectively, where T(k,i) represents the energy consumption switching time according to the strategy S k The energy consumption adjustment time required to switch from the i-1th device to the i-th device, D(k,i) represents the energy consumption adjustment time required to switch from the i-1th device to the i-th device according to the strategy S k The i-th called device;

[0050] When the device D(k,i) is in the time period In the historical energy consumption abnormal section set Q D(k,i) ={Q D(k,i),1 ,Q D(k,i),2 ,...Q D(k,i),M '} (i.e., the scheduling time falls into the historical low efficiency or high load period of the device), the actual operating energy consumption of the device D(k,i) is calculated as C k,i =η D (k,i),j '*P D(k,i),j’ *T j’ ; Among them, η D (k,i),j ' represents the energy consumption intensity of device D(k,i) in the j'th abnormal time period, P D(k,i),j’ represents the load rate of device D(k,i) in the j'th abnormal time period, t0 represents the starting time point of the policy execution, T j’ Indicates the duration of the j'th abnormal time period.

[0051] Specifically, for real-time load (peak power period 9:00-21:00): air conditioners must maintain cooling with a load factor greater than or equal to 0.8; refrigerators must operate at all times with a load factor greater than or equal to 0.9; charging piles must prioritize valley charging, with peak discharge power less than or equal to 30kW / pile. Three candidate strategies are generated based on user-specified device information and real-time energy consumption requirements.

[0052] Freezer 2 falls into the abnormal period from 14:00 to 14:30, and the actual energy consumption is calculated to be 1.4 (if the energy consumption in normal operation is 0.9). Since the energy consumption intensity is low during the abnormal period, the actual energy consumption is higher, and the strategy needs to be adjusted to avoid it).

[0053] Traverse the device call time in the strategy to calculate the actual total energy consumption and the number of times the predicted energy consumption is exceeded, calculate the energy efficiency matching value of each candidate strategy, generate a set of energy efficiency matching values ​​and sort them from high to low to obtain a strategy recommendation sequence. The specific steps include:

[0054] Traversal strategy S k The calling time of all devices in the system is used to calculate the actual total energy consumption C k,N , and count the number of times it exceeds the predicted energy consumption K(C k,i >C pred,i ), where C pred,i Indicates device D k,i The predicted energy consumption value, C k,i Indicates device D k,i The actual energy consumption value;

[0055] Calculation strategy S k The energy efficiency matching value is defined as follows: F k =1-K(C k,i >C pred,i ) / N; where K(C k,i >C pred,i ) represents the cumulative number of times the actual energy consumption of the devices in the strategy exceeds the predicted value, and N represents the total number of devices called by the strategy;

[0056] Traverse all generated candidate strategies S1, S2, ..., S R , get the energy efficiency matching value of each strategy, and get the set F={F1,F2,...,F R}, R represents the total number of candidate strategies generated, F1, F2, ..., F R Indicates the candidate strategies generated 1, 2, ..., R, sorts the obtained set F from high to low, and generates a strategy recommendation sequence F' = {F'1, F'2, ..., F' R}, where F'1>F'2>...>F' R , F'1, F'2, ..., F' Rrepresents the 1st, 2nd, ..., Rth generated candidate strategies after sorting.

[0057] Specifically, the actual total energy consumption and the number of over-prediction are calculated. For strategy S1, the peak lighting energy consumption is 480kWh (the predicted value is 500kWh, not overspent), the charging pile is not in operation, there is no overspending, and the number of over-prediction is 0; for strategy S2, the air-conditioning load rate is reduced, resulting in insufficient cooling effect, the actual energy consumption over-prediction value is 3, and the number of over-prediction is 3; for strategy S3, the energy consumption over-prediction value of the refrigerator during abnormal period is 1, and the number of over-prediction is 1. The energy efficiency matching value of each strategy is calculated, and the generated candidate strategies are sorted from high to low according to the calculated energy efficiency matching value of each strategy to generate a strategy recommendation sequence.

[0058] The strategy with the highest energy efficiency matching value is selected from the strategy recommendation sequence as the preferred execution plan. The real-time energy consumption data after execution is collected to calculate the energy consumption deviation rate. The energy consumption deviation rate is compared with the threshold to determine the effectiveness of the strategy. The specific steps include:

[0059] Select the strategy with the highest energy efficiency matching value from the strategy recommendation sequence as the preferred execution plan;

[0060] Collect the real-time energy consumption data after the strategy is executed, compare it with the predicted value, and calculate the energy consumption deviation rate, which is defined as follows: Z = |C real -C pred | / C pred *100%; among which, C real represents the real-time energy consumption data after the strategy is executed, C pred represents the energy consumption forecast value, and Z represents the energy consumption deviation rate;

[0061] Set the energy consumption deviation rate threshold Z0. When Z≤Z0, the strategy is determined to be effective and the current strategy is maintained. When Z>Z0, the strategy is determined to be unsatisfactory and the strategy switching mechanism is triggered. The suboptimal scoring strategy F'2 is selected from the strategy recommendation sequence and updated as the current execution plan. The monitoring and switching process is repeated until any of the following conditions is met: the energy consumption deviation rate threshold Z≤Z0, the strategy is successfully executed; all strategies are tried and fail to meet the standard, and an alarm is triggered.

[0062] Specifically, execute the preferred strategy S1, collect real-time energy consumption data after the strategy is executed, and compare it with the predicted value. The energy consumption deviation rate is calculated to be 1.05%, and the energy consumption deviation rate threshold is set to 5%. At this time, the energy consumption deviation rate is less than or equal to the energy consumption deviation rate threshold. The strategy is determined to be effective and execution is maintained.

[0063] An artificial intelligence-based energy consumption prediction and optimization system is applied to an artificial intelligence-based energy consumption prediction and optimization method described in any one of claims 1-5. The system includes: a data acquisition module, a candidate strategy generation module, a strategy evaluation and ranking module, and a strategy execution and feedback module. The data acquisition module is used to calculate the energy consumption intensity index of each device in different time periods to form a time segment set of historical energy consumption anomalies of the device; the candidate strategy generation module is used to generate candidate scheduling strategies. For any strategy, the device call sequence and the energy consumption switching time between devices are obtained. When the scheduling time of the device falls into its historical energy consumption anomaly segment set, the actual operating energy consumption of the device in the abnormal time period is calculated; the strategy evaluation and ranking module is used to traverse the device call time in the strategy to calculate the actual total energy consumption and the number of times the predicted energy consumption is exceeded, calculate the energy efficiency matching value of each candidate strategy, and generate a strategy recommendation sequence; the strategy execution and feedback module is used to select the strategy with the highest energy efficiency matching value from the strategy recommendation sequence as the preferred execution plan, collect real-time energy consumption data after execution to calculate the energy consumption deviation rate, and determine the effectiveness of the strategy after comparing it with the threshold.

[0064] The data acquisition module includes a data acquisition unit, an energy consumption intensity calculation unit and an abnormal period marking unit. The data acquisition unit is used to obtain historical data of the user-specified device and generate a historical data set; the energy consumption intensity calculation unit is used to calculate the energy consumption intensity index of each device in different time periods through a formula; the abnormal period marking unit is used to construct an energy consumption intensity change graph, compare it with the preset threshold, mark the abnormal time period where the energy consumption intensity is lower than the threshold, and generate an abnormal time segment set.

[0065] The candidate strategy generation module includes a strategy planning unit and an abnormal energy consumption calculation unit. The strategy planning unit is used to generate candidate scheduling strategies based on the device information and real-time energy consumption requirements specified by the user. Each strategy contains the device call sequence and switching time; the abnormal energy consumption calculation unit is used to calculate the actual operating energy consumption when the device scheduling time in the strategy falls into its abnormal time segment set.

[0066] The policy evaluation and ranking module includes an energy consumption statistics unit, an energy efficiency matching calculation unit and a policy ranking unit. The energy consumption statistics unit is used to traverse the call time of all devices in the policy, calculate the actual total energy consumption, and count the number of times the actual energy consumption exceeds the predicted value; the energy efficiency matching calculation unit is used to calculate the energy efficiency matching value of the policy; the policy ranking unit is used to sort the energy efficiency matching value set from high to low to generate a policy recommendation sequence.

[0067] The strategy execution and feedback module includes a strategy execution unit, a real-time monitoring unit and a strategy optimization unit. The strategy execution unit is used to select the strategy with the highest energy efficiency matching value from the recommended sequence as the preferred option; the real-time monitoring unit is used to collect real-time energy consumption data after the strategy is executed, and compare it with the predicted value to calculate the energy consumption deviation rate; the strategy optimization unit is used to set the energy consumption deviation rate threshold, compare the energy consumption deviation amount with the preset threshold, and determine the effectiveness of the strategy.

[0068] It will be apparent to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above and that the invention can be embodied in other specific forms without departing from the spirit or essential characteristics of the invention. Therefore, the embodiments should be considered in all respects as illustrative and non-restrictive, and the scope of the invention is defined by the appended claims, not the foregoing description, and all variations within the meaning and range of equivalents of the claims are intended to be included therein. Any reference sign in a claim should not be construed as limiting the claim to which it relates.

Claims

1. An energy consumption prediction and optimization method based on artificial intelligence, characterized by: The method comprises the following steps: Obtain historical data of commercial facilities and equipment specified by the user, generate a historical data set, calculate the energy consumption intensity index of each device in different time periods, construct an energy consumption intensity change graph, mark the abnormal time periods when the historical energy consumption intensity is lower than the preset threshold, and form a time segment set of historical energy consumption abnormalities of the equipment; Generate candidate scheduling strategies based on user-specified device information and real-time energy consumption requirements. For any strategy, obtain the device call sequence and energy consumption switching time between devices. When a device's scheduling time falls into its historical energy consumption anomaly section set, calculate the device's actual operating energy consumption during the anomaly period. Traverse the device call time in the strategy to calculate the actual total energy consumption and the number of times the predicted energy consumption is exceeded, calculate the energy efficiency matching value of each candidate strategy, generate a set of energy efficiency matching values ​​and sort them from high to low to obtain a strategy recommendation sequence; The strategy with the highest energy efficiency matching value is selected from the strategy recommendation sequence as the preferred execution plan. The real-time energy consumption data after execution is collected to calculate the energy consumption deviation rate, which is then compared with the threshold to determine the effectiveness of the strategy.

2. The energy consumption prediction and optimization method based on artificial intelligence according to claim 1, characterized in that: Obtain historical data of commercial facilities and equipment specified by the user, generate a historical data set, calculate the energy consumption intensity index of each device in different time periods, construct an energy consumption intensity change graph, mark the abnormal time periods when the historical energy consumption intensity is lower than the preset threshold, and form a time segment set of historical energy consumption abnormalities of the equipment. The specific steps include: Obtain the historical data of commercial facilities and equipment specified by the user and generate a historical data set E = {E1, E2, ..., E n }; where E1, E2, ..., E n It represents the historical data of the 1st, 2nd, ..., nth equipment, where n represents the total number of commercial facilities and equipment specified by the user. The historical data information of any commercial facility equipment is E a , the historical data information includes: the load rate of device a in the jth time period, the energy consumption value of device a in the jth time period, and the operating status of device a in the jth time period; Calculate the energy consumption intensity index of device a in the jth time period. The calculation formula is as follows: η aj =C aj / (P aj *T j ); where η aj represents the energy consumption intensity of device i in the jth time period, C aj represents the energy consumption value of device a in the jth time period, P aj represents the load rate of device i in the jth time period, T j represents the duration of the jth time period; The historical data information of the target device is traversed to obtain the energy consumption intensity index of different devices in different time periods. The energy consumption intensity index is used as the vertical coordinate and a two-dimensional plane coordinate system is constructed to form a diagram of the energy consumption intensity change of the device. According to the diagram of the energy consumption intensity change, the time period when the historical energy consumption intensity is lower than the preset threshold is marked to form a time segment set Q of the device's historical energy consumption anomaly. a ={Q a1 ,Q a2 ,...,Q aM '}, where Q a1 ,Q a2 ,...,Q aM ' indicates that the energy consumption intensity of device a is abnormal in the 1st, 2nd, ..., M' time periods, and M' indicates the total number of time periods in which abnormal energy consumption efficiency is detected.

3. The energy consumption prediction and optimization method based on artificial intelligence according to claim 2, characterized in that: Generate candidate scheduling strategies based on user-specified device information and real-time energy consumption requirements. For any strategy, obtain the device call sequence and the energy consumption switching time between devices. When the device's scheduling time falls into its historical energy consumption anomaly period, calculate the device's actual operating energy consumption during the anomaly period. The specific steps include: Based on the device information and real-time energy consumption requirements specified by the user, equipment scheduling planning is performed to generate candidate scheduling strategies. Any scheduling strategy is selected and recorded as S k , according to strategy S k The calling sequence D(k,i) of the devices and the energy consumption switching time T(k,i) between the devices are obtained respectively, where T(k,i) represents the energy consumption switching time according to the strategy S k The energy consumption adjustment time required to switch from the i-1th device to the i-th device, D(k,i) represents the energy consumption adjustment time required to switch from the i-1th device to the i-th device according to the strategy S k The i-th called device; When the device D(k,i) is in the time period In the historical energy consumption abnormal section set Q D(k,i) ={Q D(k,i),1 ,Q D(k,i),2 ,...Q D(k,i),M '}, the actual operating energy consumption of computing device D(k,i) is C k,i =η D (k,i),j '*P D(k,i),j’ *T j’ ; Among them, η D (k,i),j ' represents the energy consumption intensity of device D(k,i) in the j'th abnormal time period, P D(k,i),j’ represents the load rate of device D(k,i) in the j'th abnormal time period, t0 represents the starting time point of the policy execution, T j’ Indicates the duration of the j'th abnormal time period.

4. The energy consumption prediction and optimization method based on artificial intelligence according to claim 3, characterized in that: Traverse the device call time in the strategy to calculate the actual total energy consumption and the number of times the predicted energy consumption is exceeded, calculate the energy efficiency matching value of each candidate strategy, generate a set of energy efficiency matching values ​​and sort them from high to low to obtain a strategy recommendation sequence. The specific steps include: Traversal strategy S k The calling time of all devices in the system is used to calculate the actual total energy consumption C k,N , and count the number of times it exceeds the predicted energy consumption K(C k,i >C pred,i ), where C pred,i Indicates device D k,i The predicted energy consumption value, C k,i Indicates device D k,i The actual energy consumption value; Calculation strategy S k The energy efficiency matching value is defined as follows: F k =1-K(C k,i >C pred,i ) / N; where K(C k,i >C pred,i ) represents the cumulative number of times the actual energy consumption of the devices in the strategy exceeds the predicted value, and N represents the total number of devices called by the strategy; Traverse all generated candidate strategies S1, S2, ..., S R , get the energy efficiency matching value of each strategy, and get the set F={F1,F2,...,F R }, R represents the total number of candidate strategies generated, F1, F2, ..., F R Indicates the candidate strategies generated 1, 2, ..., R, sorts the obtained set F from high to low, and generates a strategy recommendation sequence F' = {F'1, F'2, ..., F' R }, where F'1>F'2>...>F' R , F'1, F'2, ..., F' R represents the 1st, 2nd, ..., Rth generated candidate strategies after sorting.

5. The energy consumption prediction and optimization method based on artificial intelligence according to claim 4, characterized in that: The strategy with the highest energy efficiency matching value is selected from the strategy recommendation sequence as the preferred execution plan. The real-time energy consumption data after execution is collected to calculate the energy consumption deviation rate. The energy consumption deviation rate is compared with the threshold to determine the effectiveness of the strategy. The specific steps include: Select the strategy with the highest energy efficiency matching value from the strategy recommendation sequence as the preferred execution plan; Collect the real-time energy consumption data after the strategy is executed, compare it with the predicted value, and calculate the energy consumption deviation rate, which is defined as follows: Z = |C real -C pred | / C pred *100%; among which, C real represents the real-time energy consumption data after the strategy is executed, C pred represents the energy consumption forecast value, and Z represents the energy consumption deviation rate; Set the energy consumption deviation rate threshold Z0. When Z≤Z0, the strategy is determined to be effective and the current strategy is maintained. When Z>Z0, the strategy is determined to be unsatisfactory and the strategy switching mechanism is triggered. The suboptimal scoring strategy F'2 is selected from the strategy recommendation sequence and updated as the current execution plan. The monitoring and switching process is repeated until any of the following conditions is met: the energy consumption deviation rate threshold Z≤Z0, the strategy is successfully executed; all strategies are tried and fail to meet the standard, and an alarm is triggered.

6. An artificial intelligence-based energy consumption prediction and optimization system, applied to the artificial intelligence-based energy consumption prediction and optimization method according to any one of claims 1 to 5, characterized in that: The system includes: a data acquisition module, a candidate strategy generation module, a strategy evaluation and ranking module, and a strategy execution and feedback module. The data acquisition module is used to calculate the energy consumption intensity index of each device in different time periods to form a time segment set of historical energy consumption anomalies of the device; the candidate strategy generation module is used to generate candidate scheduling strategies. For any strategy, the device call sequence and the energy consumption switching time between devices are obtained. When the scheduling time of the device falls into its historical energy consumption anomaly segment set, the actual operating energy consumption of the device in the abnormal time period is calculated; the strategy evaluation and ranking module is used to traverse the device call time in the strategy to calculate the actual total energy consumption and the number of times the predicted energy consumption is exceeded, calculate the energy efficiency matching value of each candidate strategy, and generate a strategy recommendation sequence; the strategy execution and feedback module is used to select the strategy with the highest energy efficiency matching value from the strategy recommendation sequence as the preferred execution plan, collect real-time energy consumption data after execution to calculate the energy consumption deviation rate, and determine the effectiveness of the strategy after comparing it with the threshold.

7. The artificial intelligence-based energy consumption prediction and optimization system according to claim 6, characterized in that: The data acquisition module includes a data acquisition unit, an energy consumption intensity calculation unit and an abnormal period marking unit. The data acquisition unit is used to obtain historical data of user-specified devices and generate a historical data set; the energy consumption intensity calculation unit is used to calculate the energy consumption intensity index of each device in different time periods through a formula; the abnormal period marking unit is used to construct an energy consumption intensity change graph, compare it with a preset threshold, mark the abnormal time period where the energy consumption intensity is lower than the threshold, and generate an abnormal time segment set.

8. The artificial intelligence-based energy consumption prediction and optimization system according to claim 7, characterized in that: The candidate strategy generation module includes a strategy planning unit and an abnormal energy consumption calculation unit. The strategy planning unit is used to generate candidate scheduling strategies based on the device information and real-time energy consumption requirements specified by the user. Each strategy includes a device call sequence and switching time. The abnormal energy consumption calculation unit is used to calculate the actual operating energy consumption when the device scheduling time in the strategy falls into its abnormal time segment set.

9. The artificial intelligence-based energy consumption prediction and optimization system according to claim 8, characterized in that: The policy evaluation and sorting module includes an energy consumption statistics unit, an energy efficiency matching calculation unit, and a policy sorting unit. The energy consumption statistics unit is used to traverse the call time of all devices in the policy, calculate the actual total energy consumption, and count the number of times the actual energy consumption exceeds the predicted value; The energy efficiency matching calculation unit is used to calculate the energy efficiency matching value of the strategy; the strategy sorting unit is used to sort the energy efficiency matching value set from high to low to generate a strategy recommendation sequence.

10. The artificial intelligence-based energy consumption prediction and optimization system according to claim 9, characterized in that: The strategy execution and feedback module includes a strategy execution unit, a real-time monitoring unit and a strategy optimization unit. The strategy execution unit is used to select the strategy with the highest energy efficiency matching value from the recommendation sequence as the preferred solution; The real-time monitoring unit is used to collect real-time energy consumption data after the strategy is executed, and compare it with the predicted value to calculate the energy consumption deviation rate; the strategy optimization unit is used to set the energy consumption deviation rate threshold, compare the energy consumption deviation amount with the preset threshold, and determine the effectiveness of the strategy.

Images