A smart energy optimization control method and system for ports

Abstract

The present invention relates to the field of energy management technology, and discloses a smart energy optimization control method and system for ports, which collects energy from a target port area and obtains a historical energy consumption data set of energy; constructs a nonlinear regression model based on the historical energy consumption data set to predict the future energy consumption value of the energy; constructs a confidence interval based on the historical energy consumption data set; compares the future energy consumption value with the confidence interval to determine the abnormal energy consumption value; calculates an optimization coefficient for each data point of the abnormal energy consumption value, determines the abnormal point corresponding to the abnormal energy consumption value and the abnormal degree of the abnormal point according to the optimization coefficient; and performs optimization control on the abnormal point according to the abnormal degree of the abnormal point. The future energy consumption demand is predicted more accurately, and the accuracy of anomaly detection is improved. Not only is the abnormal energy consumption marked, but also the abnormal point is subdivided into a warning sub-interval, a normal sub-interval and a warning sub-interval through the optimization coefficient and sub-interval division, which helps to distinguish the severity of the abnormality.

Description

Technical Field

[0001] The present invention relates to the field of energy management technology, and in particular to a smart energy optimization control method and system for a port. Background Art

[0002] The existing technology obtains the energy consumption corresponding to each energy within a preset time interval, and compares the energy consumption corresponding to each energy in the target port area within the preset time interval with the reference energy consumption corresponding to each energy within the preset time interval to confirm abnormal energy consumption; then dynamically tracks the abnormal energy consumption to confirm the abnormal nodes, and optimizes the control and adjustment of the abnormal nodes, thereby realizing integrated monitoring and intelligent analysis of water, electricity, oil and gas in the target port area, effectively improving the accuracy of digital management and control of the port area's energy business.

[0003] Existing technologies are usually based on simple time series comparisons, that is, directly comparing current energy consumption with historical reference energy consumption, and lack consideration of complex external factors. However, in actual scenarios, many external factors (such as holidays, weather changes, equipment status, etc.) will affect energy consumption levels. If they are not taken into account, they may lead to false positives or missed abnormalities. Existing solutions may simply mark them out without further in-depth analysis of the impact of the abnormality, which is not conducive to subsequent optimization control. Summary of the invention

[0004] In order to solve the above technical problems, the present invention provides a smart energy optimization control method and system for ports to achieve the setting of confidence intervals and the optimization control of abnormal points.

[0005] The present invention provides a smart energy optimization control method for a port, comprising:

[0006] Step 1: Collect energy from the target port area and obtain a historical energy consumption dataset;

[0007] The historical energy consumption data set includes at least: a historical time period and historical energy consumption values ​​generated during the historical time period;

[0008] Step 2: Based on the historical energy consumption data set, a nonlinear regression model is constructed to predict the future energy consumption value of energy;

[0009] Step 3, construct confidence intervals based on the historical energy consumption dataset;

[0010] Step 31, calculating the average of the historical energy consumption values ​​according to the historical energy consumption values ​​generated in the historical time period;

[0011] Step 32, calculating the standard deviation of the historical energy consumption values ​​according to the mean value and the historical energy consumption values;

[0012] Step 33, obtaining the number of data points of historical energy consumption values ​​generated in the historical time period, and calculating the standard error of the mean based on the number of data points and the standard deviation;

[0013] Step 34, obtaining the influence weight of external factors on historical energy consumption;

[0014] Step 35, obtaining the upper limit value of the confidence interval and the lower limit value of the confidence interval according to the mean, standard deviation, standard error, and influence weight;

[0015] Step 4, compare the future energy consumption value with the confidence interval. When the future energy consumption value is greater than or equal to the lower limit of the confidence interval and less than or equal to the upper limit of the confidence interval, the future energy consumption value is determined to be a normal energy consumption value; when the future energy consumption value is less than the lower limit of the confidence interval, or greater than the upper limit of the confidence interval, the future energy consumption value is determined to be an abnormal energy consumption value;

[0016] Step 5, calculating the optimization coefficient for each data point of the abnormal energy consumption value, and determining the abnormal point corresponding to the abnormal energy consumption value and the abnormal degree of the abnormal point according to the optimization coefficient;

[0017] Step 6: Optimize the control of the abnormal point according to its abnormality degree.

[0018] Furthermore, the nonlinear regression model is:

[0019]

[0020] In the formula, y represents the future energy consumption value, , , , , c, d represent model parameters, represents the error term, Represents the historical energy consumption value in the tth time period.

[0021] Furthermore, the calculation formula of the standard error is:

[0022] ;

[0023] In the formula, represents the standard error, represents the standard deviation, n represents the number of data points of historical energy consumption values ​​generated in the historical time period, and W is the adjustment coefficient.

[0024] Furthermore, the influence weight of external factors on historical energy consumption is obtained, which specifically includes the following steps:

[0025] Step 341, obtaining external factors according to historical energy consumption values;

[0026] Step 342, obtaining external factor data of the historical energy consumption values ​​of the current data point and the previous data point;

[0027] Step 343, obtaining the change range of the external factor according to the external factor data of the historical energy consumption value of the current data point and the external factor data of the historical energy consumption value of the previous data point;

[0028] Step 344, obtaining an adjustment factor according to the change range;

[0029] Step 345, obtaining the influence weight according to the adjustment factor and the change range.

[0030] Furthermore, the energy consumption change of the data point with the largest change amplitude is used as the adjustment factor.

[0031] Furthermore, the calculation of the optimization coefficient includes:

[0032] Step 51, determining the energy consumption value of each data point in the abnormal energy consumption value according to the future energy consumption value;

[0033] Step 52, calculating the optimization coefficient of each data point in the abnormal energy consumption value according to the energy consumption value and the upper limit value of the confidence interval and the lower limit value of the confidence interval.

[0034] Furthermore, the calculation formula of the optimization coefficient is:

[0035] ;

[0036] In the formula, Represents the optimization coefficient of the i-th data point in the abnormal energy consumption value, Represents the energy consumption value of the i-th data point in the abnormal energy consumption value, represents the upper limit of the confidence interval, Represents the lower limit of the confidence interval.

[0037] Furthermore, the abnormal point corresponding to the abnormal energy consumption value and the abnormal degree of the abnormal point are determined according to the optimization coefficient, specifically including:

[0038] Step 53, divide the confidence interval into several sub-intervals on average; define the first x sub-intervals close to the lower limit of the confidence interval as warning sub-intervals, define the first y sub-intervals close to the upper limit of the confidence interval as warning sub-intervals, and define the sub-intervals of the confidence interval other than the warning sub-interval and the warning sub-interval as normal sub-intervals;

[0039] Step 54, comparing the optimization coefficient of each data point with each sub-interval, determining whether the optimization coefficient of each data point belongs to any one of the warning sub-interval, the normal sub-interval, and the warning sub-interval, and obtaining an abnormal point;

[0040] Step 55, obtaining the number of optimization coefficients in the warning sub-interval, the normal sub-interval, and the warning sub-interval, and determining the continuity of the energy consumption value of the data point in each of the warning sub-interval, the normal sub-interval, and the warning sub-interval;

[0041] Step 56, obtaining the severity of the abnormal point according to the continuity of the energy consumption value of the data point.

[0042] The present invention also provides a smart energy optimization control system for a port, which is used to execute the above-mentioned smart energy optimization control method for a port, and includes the following modules:

[0043] Historical energy consumption data set acquisition module: used to collect energy in the target port area and obtain the historical energy consumption data set;

[0044] Nonlinear regression model: connected with the historical energy consumption data set acquisition module to predict the future energy consumption value of energy;

[0045] Confidence interval construction module: connected with the historical energy consumption data set acquisition module, used to construct a confidence interval based on the historical energy consumption data set;

[0046] Abnormal energy consumption value judgment module: connected to the confidence interval construction module, used to compare the future energy consumption value with the confidence interval. When the future energy consumption value is greater than or equal to the lower limit of the confidence interval and less than or equal to the upper limit of the confidence interval, the future energy consumption value is determined to be a normal energy consumption value; when the future energy consumption value is less than the lower limit of the confidence interval, or greater than the upper limit of the confidence interval, the future energy consumption value is determined to be an abnormal energy consumption value;

[0047] Optimization coefficient calculation module: connected to the abnormal energy consumption value judgment module, used to calculate the optimization coefficient for each data point of the abnormal energy consumption value, and determine the abnormal point corresponding to the abnormal energy consumption value and the abnormal degree of the abnormal point according to the optimization coefficient;

[0048] Optimization control module: connected with the optimization coefficient calculation module, used to perform optimization control on the abnormal points according to the abnormality degree of the abnormal points.

[0049] The embodiments of the present invention have the following technical effects:

[0050] This application predicts future energy consumption values ​​through historical energy consumption data sets, determines abnormal energy consumption values ​​of future energy consumption values ​​based on confidence intervals, calculates optimization coefficients for each data point in the abnormal energy consumption values, and then obtains the severity of each abnormal point. Based on the severity, optimization control is performed to more accurately predict future energy consumption needs, and the influence of external factors and standard errors is taken into account to improve the accuracy of anomaly detection. Not only does it mark abnormal energy consumption, but it also subdivides abnormal points into early warning subintervals, normal subintervals, and warning subintervals through optimization coefficients and subinterval divisions, which helps to distinguish the severity of the anomaly and facilitates the targeted adoption of different optimization control measures. Through more accurate predictions and detailed exception handling, this application can help ports achieve efficient management and optimization control of energy use, reduce unnecessary energy waste, and improve overall energy efficiency.

[0051] This application involves the calculation process of the confidence interval by setting the standard error of the mean. The standard error directly affects the width of the confidence interval. The smaller the standard error, the narrower the confidence interval, which means that the estimate of the population mean is more certain; on the contrary, the larger the standard error, the wider the confidence interval. For a larger standard error, W is assigned 0.1 to reduce the standard error. When the standard error is smaller, W is assigned 1. This design makes the final calculated confidence interval more credible and improves the confidence accuracy of the confidence interval.

[0052] The present application determines the external factors that affect the energy consumption value through the change of the energy consumption value, and obtains the influence weight, quantifies the influence degree of various factors on the energy consumption value, reduces the error caused by uncertain factors, and thus improves the accuracy of the confidence interval. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] In order to more clearly illustrate the specific implementation methods of the present invention or the technical solutions in the prior art, the drawings required for use in the specific implementation methods or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some implementation methods of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0054] Figure 1 is a flow chart of a smart energy optimization control method for a port provided by an embodiment of the present invention;

[0055] Figure 2 It is a structural schematic diagram of a smart energy optimization control system for a port provided by an embodiment of the present invention;

[0056] Figure 3 It is a structural schematic diagram of an electronic device provided by the implementation of the present invention. DETAILED DESCRIPTION

[0057] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be described clearly and completely below. 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 creative work belong to the scope of protection of the present invention.

[0058] Figure 1 1 is a flow chart of a smart energy optimization control method for a port provided by an embodiment of the present invention. Figure 1 , specifically including:

[0059] Step 1: Collect energy from the target port area and obtain the historical energy consumption dataset.

[0060] The historical energy consumption data set includes at least: historical time periods and historical energy consumption values ​​generated during the historical time periods; it may also include temperature, humidity, whether it is a holiday, maintenance records, etc. This embodiment collects energy consumption data for a period of time, preferably setting the collection frequency to one day, and collecting historical energy consumption data every day within a period of time to form a historical energy consumption data set.

[0061] Step 2: Based on the historical energy consumption data set, a nonlinear regression model is constructed to predict the future energy consumption value of energy.

[0062] The nonlinear regression model is:

[0063]

[0064] In the formula, y represents the future energy consumption value, , , , , c, d represent model parameters, represents the error term, Represents the historical energy consumption value in the tth time period.

[0065] Initialize the model parameters, input the historical energy consumption values ​​generated in the historical time period and the next historical time period in the historical energy consumption data set into the nonlinear regression model, output the predicted value, and construct the loss function to calculate the error between the predicted value and the historical energy consumption value. If the error is not minimized, iteratively update the model parameters until the error is minimized or the maximum number of iterations is reached, indicating that the nonlinear regression model training is complete. Take the current model parameters as the optimal parameters and use the optimal parameters to predict the energy consumption value. Input the energy consumption value of the current time period into the trained nonlinear regression model to predict the energy consumption value of the future time period.

[0066] Step 3: Construct confidence intervals based on the historical energy consumption dataset.

[0067] Step 31, calculating the average of the historical energy consumption values ​​according to the historical energy consumption values ​​generated in the historical time period.

[0068] Step 32, calculating the standard deviation of the historical energy consumption values ​​according to the mean value and the historical energy consumption values.

[0069] Step 33, obtain the number of data points of historical energy consumption values ​​generated in the historical time period, and calculate the standard error of the mean based on the number of data points and the standard deviation:

[0070] ;

[0071] In the formula, represents the standard error, represents the standard deviation, n represents the number of data points of historical energy consumption values ​​generated in the historical time period, and W is the adjustment coefficient.

[0072] It is worth noting that the data point mentioned in this embodiment refers to the unit time point of each day in the historical time period or the future time period.

[0073] In this embodiment, the standard error of the mean participates in the calculation process of the confidence interval. The standard error directly affects the width of the confidence interval. The smaller the standard error, the narrower the confidence interval, which means that the estimate of the population mean is more certain. On the contrary, the larger the standard error, the wider the confidence interval. For a larger standard error, W is assigned 0.1 to reduce the standard error. When the standard error is smaller, W is assigned 1. This design makes the final calculated confidence interval more credible and improves the confidence accuracy of the confidence interval.

[0074] Step 34, obtaining the influence weight of external factors on historical energy consumption.

[0075] This step aims to identify and quantify the impact of external factors on energy consumption values. In this process, the impact weight is a key concept that reflects the degree of influence of external factors on changes in energy consumption values.

[0076] Step 341, obtaining external factors according to historical energy consumption values.

[0077] Based on the historical energy consumption values ​​in the historical time period, external factors that may cause changes in the energy consumption values ​​are identified, for example, temperature, humidity, whether each data point is a holiday, maintenance records, etc.

[0078] During holidays, the cargo throughput of the port may change, which will affect the operating time and energy consumption of related equipment, as well as the ship's entry and exit schedule, thereby affecting the port's operating efficiency and energy consumption. Whether it is a holiday is considered one of the external factors.

[0079] Step 342, obtaining external factor data of the historical energy consumption values ​​of the current data point and the previous data point.

[0080] Step 343, obtaining the variation range of the external factor according to the external factor data of the historical energy consumption value of the current data point and the external factor data of the historical energy consumption value of the previous data point.

[0081] Step 344, obtaining an adjustment factor according to the change range.

[0082] The energy consumption change of the data point with the largest change amplitude is used as the adjustment factor.

[0083] Step 345, obtaining the influence weight according to the adjustment factor and the change range.

[0084] Step 35, obtaining the upper limit value of the confidence interval and the lower limit value of the confidence interval according to the mean, standard deviation, standard error, and influence weight.

[0085] The lower limit of the confidence interval is:

[0086] ;

[0087] The upper limit of the confidence interval is:

[0088] ;

[0089] represents the lower limit of the confidence interval, represents the upper limit of the confidence interval, represents the mean, represents the standard deviation, m represents the first coefficient, m=3, represents the standard error, Represents the influence weight.

[0090] Based on the prior art that calculates the confidence interval by the mean and standard deviation, this embodiment also considers the influence weight and standard error, quantifies the larger standard error into a standard range, and by introducing the standard error and influence weight, the calculation of the confidence interval becomes more accurate. The standard error reflects the sampling error of the sample mean, while the influence weight considers the quality and reliability of the energy consumption value. The combination of these two factors enables the confidence interval to better reflect the true situation of the overall parameter.

[0091] Step 4, compare the future energy consumption value with the confidence interval. When the future energy consumption value is greater than or equal to the lower limit of the confidence interval and less than or equal to the upper limit of the confidence interval, the future energy consumption value is determined to be a normal energy consumption value; when the future energy consumption value is less than the lower limit of the confidence interval, or greater than the upper limit of the confidence interval, the future energy consumption value is determined to be an abnormal energy consumption value;

[0092] Step 5, calculating the optimization coefficient for each data point of the abnormal energy consumption value, and determining the abnormal point corresponding to the abnormal energy consumption value and the abnormal degree of the abnormal point according to the optimization coefficient;

[0093] Step 51, determining the energy consumption value of each data point in the abnormal energy consumption value according to the future energy consumption value;

[0094] Step 52, calculating the optimization coefficient of each data point in the abnormal energy consumption value according to the energy consumption value and the upper limit value of the confidence interval and the lower limit value of the confidence interval.

[0095] ;

[0096] In the formula, Represents the optimization coefficient of the i-th data point in the abnormal energy consumption value, Represents the energy consumption value of the i-th data point in the abnormal energy consumption value, represents the upper limit of the confidence interval, Represents the lower limit of the confidence interval.

[0097] The abnormal point corresponding to the abnormal energy consumption value and the abnormal degree of the abnormal point are determined according to the optimization coefficient, including:

[0098] Step 53, divide the confidence interval into several sub-intervals on average; define the first x sub-intervals close to the lower limit of the confidence interval as warning sub-intervals, define the first y sub-intervals close to the upper limit of the confidence interval as warning sub-intervals, and define the sub-intervals of the confidence interval other than the warning sub-interval and the warning sub-interval as normal sub-intervals.

[0099] The future energy consumption values ​​predicted by this embodiment and the corresponding optimization coefficients are shown in Table 1:

[0100] Table 1 Comparison table of future energy consumption values ​​predicted by this embodiment and corresponding optimization coefficients

[0101]

[0102] Exemplarily, the confidence interval of this embodiment is [80KW, 120KW]. This embodiment preferably divides the confidence interval [80KW, 120KW] into 10 sub-intervals, and the width of each sub-interval is 4KW. Exemplarily, the sub-intervals of this embodiment are [80KW, 84KW), [84KW, 88KW), ..., [116KW, 120KW]. In this embodiment, the first two sub-intervals close to the lower limit of the confidence interval are defined as warning sub-intervals, the first two sub-intervals close to the upper limit of the confidence interval are defined as warning sub-intervals, and the remaining sub-intervals are defined as normal sub-intervals. Therefore, the warning sub-interval is [80KW, 88KW), the warning sub-interval is [112KW, 120KW], and the normal sub-interval is [88KW, 112KW].

[0103] Step 54, compare the optimization coefficient of each data point with each sub-interval, determine whether the optimization coefficient of each data point belongs to any one of the warning sub-interval, the normal sub-interval, and the warning sub-interval, and obtain the abnormal point.

[0104] The subinterval to which the data point belongs is determined according to the optimization coefficient as shown in Table 2:

[0105] Table 2 Comparison table of subintervals to which data points belong based on optimization coefficients

[0106]

[0107] In this embodiment, the data points in the early warning sub-interval and the warning sub-interval are regarded as abnormal points.

[0108] Step 55, obtaining the number of optimization coefficients in the early warning sub-interval, the normal sub-interval, and the warning sub-interval, and determining the continuity of the energy consumption value of the data point in each of the early warning sub-interval, the normal sub-interval, and the warning sub-interval.

[0109] The number of optimization coefficients in the warning sub-interval, normal sub-interval, and warning sub-interval can be directly obtained from Table 2.

[0110] In the warning interval, the data points are concentrated in 2024-10-01, 2024-10-04, 2024-10-07 and 2024-10-10. The future energy consumption values ​​are continuous in 2024-10-01 and 2024-10-04, and isolated in 2024-10-07 and 2024-10-10. In the warning subinterval, the data points are concentrated in 2024-10-02, 2024-10-05, 2024-10-08 and 2024-10-11. The future energy consumption values ​​are continuous in 2024-10-02 and 2024-10-05, and continuous in 2024-10-08 and 2024-10-11.

[0111] Step 56, according to the continuity of the energy consumption value of the data point and the abnormal point, the severity of the abnormal point is obtained.

[0112] In this embodiment, the severity of the abnormal point in the warning subinterval is higher than the severity of the abnormal point in the early warning subinterval. Specifically, the severity of the abnormal point with continuous energy consumption value in the warning subinterval is the highest, and the severity of the abnormal point with discontinuous energy consumption value in the subinterval is second. The severity of the abnormal point with continuous energy consumption value in the early warning subinterval is second to the severity of the abnormal point with discontinuous energy consumption value in the warning subinterval, and the severity of the abnormal point with discontinuous energy consumption value in the early warning subinterval is second to the severity of the abnormal point with discontinuous energy consumption value in the interval.

[0113] Step 6: Optimize the control of the abnormal point according to its abnormality degree.

[0114] This embodiment executes a corresponding optimization control scheme according to the severity of the abnormal point.

[0115] For abnormal points with continuous energy consumption values, take immediate measures to reduce energy consumption, investigate the causes and optimize the energy management system. For abnormal points with discontinuous energy consumption values, record and investigate the causes, and take targeted measures, such as equipment maintenance, operation specification training, etc.

[0116] like Figure 2 As shown, this embodiment also discloses a smart energy optimization control system for a port, which is used to execute the above-mentioned smart energy optimization control method for a port, and includes the following modules:

[0117] Historical energy consumption data set acquisition module: used to collect energy in the target port area and obtain the historical energy consumption data set;

[0118] Nonlinear regression model: connected with the historical energy consumption data set acquisition module to predict the future energy consumption value of energy;

[0119] Confidence interval construction module: connected with the historical energy consumption data set acquisition module, used to construct a confidence interval based on the historical energy consumption data set;

[0120] Abnormal energy consumption value judgment module: connected to the confidence interval construction module, used to compare the future energy consumption value with the confidence interval. When the future energy consumption value is greater than or equal to the lower limit of the confidence interval and less than or equal to the upper limit of the confidence interval, the future energy consumption value is determined to be a normal energy consumption value; when the future energy consumption value is less than the lower limit of the confidence interval, or greater than the upper limit of the confidence interval, the future energy consumption value is determined to be an abnormal energy consumption value;

[0121] Optimization coefficient calculation module: connected to the abnormal energy consumption value judgment module, used to calculate the optimization coefficient for each data point of the abnormal energy consumption value, and determine the abnormal point corresponding to the abnormal energy consumption value and the abnormal degree of the abnormal point according to the optimization coefficient;

[0122] Optimization control module: connected with the optimization coefficient calculation module, used to perform optimization control on the abnormal points according to the abnormality degree of the abnormal points.

[0123] like Figure 3 As shown, this embodiment also provides an electronic device including one or more processors 501 and a memory 502 .

[0124] The processor 501 may be a central processing unit (CPU) or other forms of processing units having data processing capabilities and / or instruction execution capabilities, and may control other components in the electronic device 500 to perform desired functions.

[0125] The memory 502 may include one or more computer program products, and the computer program product may include various forms of computer-readable storage media, such as volatile memory and / or non-volatile memory. The volatile memory may include, for example, random access memory (RAM) and / or cache memory (cache), etc. The non-volatile memory may include, for example, read-only memory (ROM), hard disk, flash memory, etc. One or more computer program instructions may be stored on the computer-readable storage medium, and the processor 501 may run the program instructions to implement a smart energy optimization control method for a port in any embodiment of the present application described above and / or other desired functions. Various contents such as initial external parameters, thresholds, etc. may also be stored in the computer-readable storage medium.

[0126] In one example, the electronic device 500 may further include: an input device 503 and an output device 504, which are interconnected via a bus system and / or other forms of connection mechanisms (not shown). The input device 503 may include, for example, a keyboard, a mouse, etc. The output device 504 may output various information to the outside, including early warning prompt information, braking force, etc. The output device 504 may include, for example, a display, a speaker, a printer, a communication network and a remote output device connected thereto, etc.

[0127] Of course, to simplify, Figure 3 Only some of the components related to the present application in the electronic device 500 are shown, and components such as a bus, an input / output interface, etc. are omitted. In addition, according to specific application conditions, the electronic device 500 may also include any other appropriate components.

[0128] In addition to the above-mentioned methods and devices, an embodiment of the present application may also be a computer program product, which includes computer program instructions, which, when executed by a processor, enable the processor to execute the steps of a smart energy optimization control method for a port provided in any embodiment of the present application.

[0129] The computer program product may be written in any combination of one or more programming languages ​​to write program codes for performing the operations of the embodiments of the present application, including object-oriented programming languages, such as Java, C++, etc., and conventional procedural programming languages, such as "C" language or similar programming languages. The program code may be executed entirely on the user computing device, partially on the user device, as an independent software package, partially on the user computing device and partially on a remote computing device, or entirely on a remote computing device or server.

[0130] In addition, an embodiment of the present application may also be a computer-readable storage medium on which computer program instructions are stored. When the computer program instructions are executed by a processor, the processor executes the steps of a smart energy optimization control method for a port provided in any embodiment of the present application.

[0131] The computer readable storage medium can adopt any combination of one or more readable media. The readable medium can be a readable signal medium or a readable storage medium. The readable storage medium can include, for example, but is not limited to, a system, device or device of electricity, magnetism, light, electromagnetic, infrared, or semiconductor, or any combination of the above. More specific examples (non-exhaustive list) of readable storage media include: an electrical connection with one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above.

[0132] It should be noted that the terms used in the present invention are only for describing specific embodiments, rather than limiting the scope of the present application. As shown in the present specification, unless the context clearly indicates an exception, the words "one", "a", "a kind of" and / or "the" do not specifically refer to the singular, but may also include the plural. The terms "include", "comprise" or any other variant thereof are intended to cover non-exclusive inclusion, so that the process, method or device including a series of elements includes not only those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such process, method or device. In the absence of more restrictions, the elements defined by the sentence "include one..." do not exclude the presence of other identical elements in the process, method or device including the elements.

[0133] It should also be noted that the terms "center", "up", "down", "left", "right", "vertical", "horizontal", "inside", "outside", etc., indicating the orientation or positional relationship, are based on the orientation or positional relationship shown in the drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as a limitation on the present invention. Unless otherwise clearly specified and limited, the terms "installed", "connected", "connected", etc. should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be an indirect connection through an intermediate medium, or it can be a connection between the two elements. For those of ordinary skill in the art, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0134] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the technical solutions of the embodiments of the present invention.

Claims

1. A smart energy optimization control method for a port, characterized in that: include: Step 1: Collect energy from the target port area and obtain a historical energy consumption dataset; The historical energy consumption data set includes at least: a historical time period and historical energy consumption values ​​generated during the historical time period; Step 2: Based on the historical energy consumption data set, a nonlinear regression model is constructed to predict the future energy consumption value of energy; Step 3, construct confidence intervals based on the historical energy consumption dataset; Step 31, calculating the average of the historical energy consumption values ​​according to the historical energy consumption values ​​generated in the historical time period; Step 32, calculating the standard deviation of the historical energy consumption values ​​according to the mean value and the historical energy consumption values; Step 33, obtaining the number of data points of historical energy consumption values ​​generated in the historical time period, and calculating the standard error of the mean based on the number of data points and the standard deviation; Step 34, obtaining the influence weight of external factors on historical energy consumption; Step 341, obtaining external factors according to historical energy consumption values; Step 342, obtaining external factor data of the historical energy consumption values ​​of the current data point and the previous data point; Step 343, obtaining the change range of the external factor according to the external factor data of the historical energy consumption value of the current data point and the external factor data of the historical energy consumption value of the previous data point; Step 344, obtaining an adjustment factor according to the change range; Among them, the energy consumption change of the data point with the largest change amplitude is used as the adjustment factor; Step 345, obtaining the influence weight according to the adjustment factor and the change range; Step 35, obtaining the upper limit value of the confidence interval and the lower limit value of the confidence interval according to the mean, standard deviation, standard error, and influence weight; Step 4, compare the future energy consumption value with the confidence interval. When the future energy consumption value is greater than or equal to the lower limit of the confidence interval and less than or equal to the upper limit of the confidence interval, the future energy consumption value is determined to be a normal energy consumption value; when the future energy consumption value is less than the lower limit of the confidence interval, or greater than the upper limit of the confidence interval, the future energy consumption value is determined to be an abnormal energy consumption value; Step 5, calculating the optimization coefficient for each data point of the abnormal energy consumption value, and determining the abnormal point corresponding to the abnormal energy consumption value and the abnormal degree of the abnormal point according to the optimization coefficient; Step 6: Optimize the control of the abnormal point according to its abnormality degree.

2. The intelligent energy optimization control method for a port according to claim 1 is characterized in that: The nonlinear regression model is: In the formula, y represents the future energy consumption value, , , , , c, d represent model parameters, represents the error term, Represents the historical energy consumption value in the tth time period.

3. The intelligent energy optimization control method for a port according to claim 1 is characterized in that: The standard error is calculated as follows: ； In the formula, represents the standard error, represents the standard deviation, n represents the number of data points of historical energy consumption values ​​generated in the historical time period, and W is the adjustment coefficient.

4. The intelligent energy optimization control method for a port according to claim 1 is characterized in that: The calculation of the optimization coefficient includes: Step 51, determining the energy consumption value of each data point in the abnormal energy consumption value according to the future energy consumption value; Step 52, calculating the optimization coefficient of each data point in the abnormal energy consumption value according to the energy consumption value and the upper limit value of the confidence interval and the lower limit value of the confidence interval.

5. The intelligent energy optimization control method for a port according to claim 4 is characterized in that: The calculation formula of the optimization coefficient is: ； In the formula, Represents the optimization coefficient of the i-th data point in the abnormal energy consumption value, Represents the energy consumption value of the i-th data point in the abnormal energy consumption value, represents the upper limit of the confidence interval, Represents the lower limit of the confidence interval.

6. The intelligent energy optimization control method for a port according to claim 1 is characterized in that: The abnormal point corresponding to the abnormal energy consumption value and the abnormal degree of the abnormal point are determined according to the optimization coefficient, including: Step 53, divide the confidence interval into several sub-intervals on average; define the first x sub-intervals close to the lower limit of the confidence interval as warning sub-intervals, define the first y sub-intervals close to the upper limit of the confidence interval as warning sub-intervals, and define the sub-intervals of the confidence interval other than the warning sub-interval and the warning sub-interval as normal sub-intervals; Step 54, comparing the optimization coefficient of each data point with each sub-interval, determining whether the optimization coefficient of each data point belongs to any one of the warning sub-interval, the normal sub-interval, and the warning sub-interval, and obtaining an abnormal point; Step 55, obtaining the number of optimization coefficients in the warning sub-interval, the normal sub-interval, and the warning sub-interval, and determining the continuity of the energy consumption value of the data point in each of the warning sub-interval, the normal sub-interval, and the warning sub-interval; Step 56, obtaining the severity of the abnormal point according to the continuity of the energy consumption value of the data point.

7. A smart energy optimization control system for a port, used to execute a smart energy optimization control method for a port as described in any one of claims 1 to 6, characterized in that: Includes the following modules: Historical energy consumption data set acquisition module: used to collect energy in the target port area and obtain the historical energy consumption data set; Nonlinear regression model: connected with the historical energy consumption data set acquisition module to predict the future energy consumption value of energy; Confidence interval construction module: connected with the historical energy consumption data set acquisition module, used to construct a confidence interval based on the historical energy consumption data set; Abnormal energy consumption value judgment module: connected to the confidence interval construction module, used to compare the future energy consumption value with the confidence interval. When the future energy consumption value is greater than or equal to the lower limit of the confidence interval and less than or equal to the upper limit of the confidence interval, the future energy consumption value is determined to be a normal energy consumption value; when the future energy consumption value is less than the lower limit of the confidence interval, or greater than the upper limit of the confidence interval, the future energy consumption value is determined to be an abnormal energy consumption value; Optimization coefficient calculation module: connected to the abnormal energy consumption value judgment module, used to calculate the optimization coefficient for each data point of the abnormal energy consumption value, and determine the abnormal point corresponding to the abnormal energy consumption value and the abnormal degree of the abnormal point according to the optimization coefficient; Optimization control module: connected with the optimization coefficient calculation module, used to perform optimization control on the abnormal points according to the abnormality degree of the abnormal points.

Images