A power operation and maintenance control system based on energy efficiency anomaly

Abstract

The present invention provides a power operation and maintenance control system based on energy efficiency anomalies, which relates to the field of power operation and maintenance technology, and includes: a model building module, which is used to build a prediction model of energy efficiency data of the power system; a data acquisition module, which is used to acquire the actual energy efficiency data of the power system; a prediction interval determination module, which is used to determine the prediction interval of the prediction model of the energy efficiency data of the power system; an energy efficiency monitoring module, which is used to monitor whether the actual energy efficiency data is within the prediction interval of the prediction model of the energy efficiency data, to determine whether the actual energy efficiency data is abnormal; and an intelligent terminal, which is used to issue control instructions to the power system according to the actual energy efficiency data and perform control operations on the power system. By predicting the energy efficiency data of the power use area, intelligent control of the power system is achieved according to the prediction results, which improves the utilization efficiency of power resources and makes power distribution more reasonable.

Description

Technical Field

[0001] The present invention relates to the technical field of power operation and maintenance, and in particular to a power operation and maintenance control system based on energy efficiency anomaly. Background Art

[0002] Power operation and maintenance is an important guarantee for the normal operation of the power system. However, traditional power operation and maintenance work often has problems such as low efficiency and large human resource investment. With the continuous development of information technology, the power intelligent operation and maintenance management system has emerged. The system uses artificial intelligence, big data and other technologies to achieve comprehensive control and refined management of the power system and improve the efficiency of power operation and maintenance.

[0003] In the prior art, such as the intelligent energy storage power station operation and maintenance system based on the industrial park in CN114037099A, there are the following problems:

[0004] The lack of prediction of energy efficiency data for electricity-using areas makes it impossible to implement intelligent regulation based on the prediction results. Summary of the invention

[0005] The present invention provides an electric power operation and maintenance control system based on energy efficiency anomaly, which is used to solve the technical problems raised by the above background technology.

[0006] In order to solve the above technical problems, the present invention discloses a power operation and maintenance control system based on energy efficiency abnormality, comprising:

[0007] A model building module is used to build a prediction model for energy efficiency data of the power system;

[0008] A data acquisition module, used to obtain actual energy efficiency data of the power system;

[0009] A prediction interval determination module, used to determine the prediction interval of the prediction model of energy efficiency data of the power system;

[0010] The energy efficiency monitoring module is used to monitor whether the actual energy efficiency data is within the prediction interval of the energy efficiency data prediction model to determine whether the actual energy efficiency data is abnormal;

[0011] Intelligent terminals are used to issue control instructions to the power system based on actual energy efficiency data and perform control operations on the power system.

[0012] Preferably, the model building module includes:

[0013] A region division unit, used for dividing the power use area into a number of sub-areas;

[0014] Using a recording unit for recording historical power load data for each sub-area;

[0015] A preprocessing unit, used for preprocessing the historical power load data of the sub-region;

[0016] The model building unit is used to build a prediction model for energy efficiency data of each sub-region by using the pre-processed historical power load data of the sub-region.

[0017] Preferably, the model building module includes a basic energy efficiency subunit, a natural growth energy efficiency subunit, a special day impact subunit, a temperature impact subunit, and a power consumption period impact subunit;

[0018] The basic energy efficiency subunit is used to obtain basic energy efficiency parameters by removing special values ​​from the historical power load data of the sub-region;

[0019] The natural growth energy efficiency subunit is used to calculate the natural growth rate of basic energy efficiency parameters;

[0020] The special day impact subunit is used to calculate the special day compensation parameter based on the historical power load data of the sub-area on the special date;

[0021] The temperature impact subunit is used to obtain the daily temperature impact parameters and the time-sharing temperature impact parameters according to the historical power load data combined with the historical temperature data of the sub-region;

[0022] The power consumption period influence subunit is used to obtain the power consumption period influence parameter according to the time-sharing historical power load data of the sub-region and the functional attributes of the sub-region;

[0023] The data fusion model is used to correct the basic energy efficiency parameters through the natural growth rate of basic energy efficiency parameters, special day compensation parameters and all-day temperature influence parameters to obtain the all-day prediction value of energy efficiency data; and to allocate the all-day prediction value of energy efficiency data to different time periods through the time-sharing temperature influence parameters and electricity consumption period influence parameters to obtain the time-sharing prediction value of energy efficiency data.

[0024] Preferably, A1=[A*(1+δ)]*ln(e+γ1α+γ2β);

[0025] A2=A*B*ln(e+γ3σ+γ4∈);

[0026] A1 is the whole-day prediction value, A is the whole-day basic energy efficiency parameter, δ is the natural growth rate of the basic energy efficiency parameter, ln is the natural logarithm, e is the natural constant, α is the special day compensation parameter, β is the whole-day temperature influence parameter; A2 is the time-sharing prediction value, B is the time-sharing allocation ratio, σ is the time-sharing temperature influence parameter, ∈ is the electricity consumption period influence parameter; γ1, γ2, γ3, γ4 are the first influence coefficient, the second influence coefficient, the third influence coefficient, and the fourth influence coefficient respectively (the values ​​are greater than 0 and less than 1).

[0027] Preferably, the prediction interval determination module includes:

[0028] An error acquisition unit is used to calculate the time-sharing prediction value of the energy efficiency data of the sub-region according to the prediction model of the energy efficiency data, and to obtain the time-sharing prediction error value of the sub-region by subtracting the time-sharing prediction value of the energy efficiency data of the sub-region from the time-sharing actual energy efficiency data of the sub-region;

[0029] An interval setting unit uses a certain deviation range of the time-sharing prediction value of the energy efficiency data of the sub-region as an error tolerance range of the prediction model;

[0030] The interval verification unit is used to count the distribution probability that the time-sharing prediction error value of the sub-region is within the error tolerance interval. When the distribution probability is higher than a preset threshold, the time-sharing prediction value of the energy efficiency data of the sub-region is used as the median of the prediction interval, and the width of the error tolerance interval is used as the width of the prediction interval of the prediction model to determine the prediction interval of the prediction model. When the distribution probability is less than the preset threshold, the prediction model of the energy efficiency data is optimized through the optimization module, and the prediction interval of the optimized prediction model of the energy efficiency data is determined again.

[0031] Preferably, the intelligent terminal includes:

[0032] The power output control module is used to control the power output of the power system according to the predicted value of the energy efficiency data of the entire power use area;

[0033] The power distribution module is used to distribute the power output of the power system to each sub-area according to the predicted value of the energy efficiency data of each sub-area.

[0034] Preferably, the power output control module includes:

[0035] An output recording unit, used to record historical power output data of the power system;

[0036] The output prediction unit determines the power output efficiency of the power system when it is operating at full power according to the power output data recorded by the output recording unit;

[0037] a total output determination unit, used for determining the total power demand according to the predicted value of the energy efficiency data of the entire power use area;

[0038] The control unit regulates the power output efficiency of the power system according to the total power demand.

[0039] Preferably, it also includes an abnormality control module, which includes:

[0040] An early warning unit, configured to send an early warning message to the inspection unit when the actual energy efficiency data of the sub-area reaches a first threshold preset in the sub-area;

[0041] The inspection unit is used to issue an inspection command to the corresponding sub-area after receiving the warning information;

[0042] The plan generation unit is used to generate a processing plan for this energy efficiency abnormality event.

[0043] Preferably, the plan generating unit includes:

[0044] A priority ranking unit, used for ranking the priorities of all sub-regions according to the importance of each sub-region;

[0045] An abnormality index determination unit, used to calculate an energy efficiency abnormality index of a sub-region with energy efficiency abnormality;

[0046] An analysis unit, used for confirming a processing mode of energy efficiency abnormality according to an energy efficiency abnormality index;

[0047] The control amount determination unit is used to determine the control amount of the power data.

[0048] Preferably, the abnormal index determination unit calculates the energy efficiency abnormal index of the sub-region according to Formula 1, and Formula 1 is:

[0049]

[0050]

[0051] Among them, K A is the energy efficiency anomaly index of the sub-region A at the current moment, α is the importance weighted value of sub-region A; X A is the actual time-sharing energy efficiency data of sub-area A at the current moment; The average time-sharing energy efficiency data of sub-area A on the previous day; is the allowable deviation percentage of the predicted value, X A0 is the time-sharing prediction value of the energy efficiency data of sub-area A at the current moment; W is the function attribute discrimination parameter of sub-area A. When sub-area A is a working area, W takes 1; when sub-area A is a non-working area, W takes 2; Q is the working time discrimination parameter. When the current moment is working time, Q takes 1; when the current moment is non-working time, Q takes 2; M is the total number of recording time periods from the day to the current moment, G AiT is the average energy efficiency data of the i-th recording period of the day in sub-area A; G Ai(T-1) is the average energy efficiency data of the i-th recording period of the previous day in sub-area A; G AMAX is the highest value of the time-sharing energy efficiency data of sub-area A on the previous day; G AMIN is the lowest value of the time-sharing energy efficiency data of sub-area A on the previous day; p is the estimated total power output of the power system on that day; μ is the loss rate of power transmission per unit length; L Ais the transmission distance from sub-region A to the power system; L0 is the unit length for calculating the power transmission loss rate; N is the total number of sub-regions that output power during the power redistribution process between sub-regions; β j is the importance weighted value of the j-th power output sub-area; X j is the actual time-sharing energy efficiency data of the j-th power output sub-area at the current moment; X j0 is the predicted value of the time-sharing energy efficiency data of the j-th power output sub-area at the current moment; R j is the impact coefficient of the power redistribution process on the jth power output sub-area;

[0052] When K A When it is less than the second threshold, the energy efficiency abnormality processing mode adopts the redistribution of power among sub-regions;

[0053] When K A When it is greater than the second threshold, the energy efficiency abnormality processing mode adopts increasing the power output of the power system.

[0054] The technical solution of the present invention is further described in detail below through the accompanying drawings and embodiments.

[0055] Compared with the prior art, the present invention has the following beneficial effects:

[0056] Based on the historical power load data, a prediction model for the energy efficiency data of the power system is established. The power system is regulated according to the prediction results, which avoids the waste of power resources, effectively improves the utilization efficiency of power, and ensures the fair distribution of power. The total power demand is determined according to the predicted value of the prediction model, and the power output of the power system is adjusted by adjusting the power output efficiency of the power system, avoiding the waste of power resources. By monitoring the real-time performance data of the sub-area, the energy efficiency anomaly of the power system is discovered in time. By calculating the energy efficiency anomaly index of the energy efficiency anomaly sub-area, the event processing mode is determined, thereby ensuring more efficient and safe processing of energy efficiency anomaly events. While ensuring the processing effect of the energy efficiency anomaly sub-area, the normal power consumption of the remaining sub-areas is ensured not to be affected, reducing the operation and maintenance cost and improving the safety and reliability of the power system. BRIEF DESCRIPTION OF THE DRAWINGS

[0057] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0058] Figure 1 It is a structural schematic diagram of the present invention. DETAILED DESCRIPTION

[0059] The preferred embodiments of the present invention are described below in conjunction with the accompanying drawings. It should be understood that the preferred embodiments described herein are only used to illustrate and explain the present invention, and are not used to limit the present invention.

[0060] In addition, in the present invention, the descriptions of "first", "second", etc. are only used for descriptive purposes, and do not specifically refer to the order or sequence, nor are they used to limit the present invention. They are only used to distinguish components or operations described with the same technical terms, and cannot be understood as indicating or implying their relative importance or implicitly indicating the number of technical features indicated. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of the features. In addition, the technical solutions and technical features between the various embodiments can be combined with each other, but they must be based on the ability of ordinary technicians in the field to implement them. When the combination of technical solutions is contradictory or cannot be implemented, it should be considered that such a combination of technical solutions does not exist and is not within the scope of protection required by the present invention.

[0061] The present invention provides the following embodiments

[0062] Example 1

[0063] The embodiment of the present invention provides a power operation and maintenance control system based on energy efficiency abnormality, including:

[0064] A model building module is used to build a prediction model for energy efficiency data of the power system;

[0065] A data acquisition module, used to obtain actual energy efficiency data of the power system;

[0066] A prediction interval determination module, used to determine the prediction interval of the prediction model of energy efficiency data of the power system;

[0067] The energy efficiency monitoring module is used to monitor whether the actual energy efficiency data is within the prediction interval of the energy efficiency data prediction model to determine whether the actual energy efficiency data is abnormal;

[0068] Intelligent terminals are used to issue control instructions to the power system based on actual energy efficiency data and perform control operations on the power system.

[0069] Preferably, the model building module includes:

[0070] A region division unit, used for dividing the power use area into a number of sub-areas;

[0071] Using a recording unit for recording historical power load data for each sub-area;

[0072] A preprocessing unit, used for preprocessing the historical power load data of the sub-region;

[0073] The model building unit is used to build a prediction model for energy efficiency data of each sub-region by using the pre-processed historical power load data of the sub-region.

[0074] Preferably, the model building module includes a basic energy efficiency subunit, a natural growth energy efficiency subunit, a special day impact subunit, a temperature impact subunit, and a power consumption period impact subunit;

[0075] The basic energy efficiency subunit is used to obtain basic energy efficiency parameters by removing special values ​​from the historical power load data of the sub-region;

[0076] The natural growth energy efficiency subunit is used to calculate the natural growth rate of basic energy efficiency parameters;

[0077] The special day impact subunit is used to calculate the special day compensation parameter based on the historical power load data of the sub-area on the special date;

[0078] The temperature impact subunit is used to obtain the daily temperature impact parameters and the time-sharing temperature impact parameters according to the historical power load data combined with the historical temperature data of the sub-region;

[0079] The power consumption period influence subunit is used to obtain the power consumption period influence parameter according to the time-sharing historical power load data of the sub-region and the functional attributes of the sub-region;

[0080] The data fusion model is used to correct the basic energy efficiency parameters through the natural growth rate of basic energy efficiency parameters, special day compensation parameters and all-day temperature influence parameters to obtain the all-day prediction value of energy efficiency data; and to allocate the all-day prediction value of energy efficiency data to different time periods through the time-sharing temperature influence parameters and electricity consumption period influence parameters to obtain the time-sharing prediction value of energy efficiency data.

[0081] Preferably, A1=[A*(1+δ)]*ln(e+γ1α+γ2β);

[0082] A2=A*B*ln(e+γ3σ+γ4∈);

[0083] A1 is the whole-day prediction value, A is the whole-day basic energy efficiency parameter, δ is the natural growth rate of the basic energy efficiency parameter, ln is the natural logarithm, e is the natural constant, α is the special day compensation parameter, β is the whole-day temperature influence parameter; A2 is the time-sharing prediction value, B is the time-sharing allocation ratio, σ is the time-sharing temperature influence parameter, ∈ is the power consumption period influence parameter; γ1, γ2, γ3, γ4 are the first influence coefficient, the second influence coefficient, the third influence coefficient, and the fourth influence coefficient respectively.

[0084] Preferably, the prediction interval determination module includes:

[0085] An error acquisition unit is used to calculate the time-sharing prediction value of the energy efficiency data of the sub-region according to the prediction model of the energy efficiency data, and to obtain the time-sharing prediction error value of the sub-region by subtracting the time-sharing prediction value of the energy efficiency data of the sub-region from the time-sharing actual energy efficiency data of the sub-region;

[0086] An interval setting unit uses a certain deviation range of the time-sharing prediction value of the energy efficiency data of the sub-region as an error tolerance range of the prediction model;

[0087] The interval verification unit is used to count the distribution probability that the time-sharing prediction error value of the sub-region is within the error tolerance interval. When the distribution probability is higher than a preset threshold, the time-sharing prediction value of the energy efficiency data of the sub-region is used as the median of the prediction interval, and the width of the error tolerance interval is used as the width of the prediction interval of the prediction model to determine the prediction interval of the prediction model. When the distribution probability is less than the preset threshold, the prediction model of the energy efficiency data is optimized through the optimization module, and the prediction interval of the optimized prediction model of the energy efficiency data is determined again.

[0088] In this embodiment, the energy efficiency data includes power load, and the power load is the total amount of electric power taken from the power system by the electric energy user's electric equipment at a certain moment.

[0089] In this embodiment, the power usage area is an area that needs power supply and is controlled by the operation and maintenance control system.

[0090] In this embodiment, the historical power load data is a record of power usage, such as the power load at a certain time on a certain day.

[0091] In this embodiment, the preprocessing of historical power data includes detection and elimination of outliers and interpolation of missing values. Outliers are data that exceed a reasonable power load range. For example, power load data that exceeds the historical average power load by 50% is recorded as an outlier.

[0092] In this embodiment, the special values ​​removed by the basic energy efficiency subunit are the power load data on special dates, such as statutory holidays, dates of large-scale events, and other dates that cause significant changes in power load.

[0093] In this embodiment, the natural growth rate of the basic energy efficiency parameter is the rate of increase of the basic energy efficiency parameter as time goes by due to the general increase in the power of electrical appliances, the increase in the popularity of electrical appliances, etc.

[0094] In this embodiment, the special day compensation parameter is the proportion of the power load change caused by the special date. For example, the power load in areas such as shopping malls during holidays will increase by 50%.

[0095] In this embodiment, the historical temperature data is the temperature value at each moment in history.

[0096] In this embodiment, the daily temperature impact parameter reflects the degree of change in the average value of the daily power load caused by temperature changes. For example, the average value of the daily power load in summer is 20% higher than that in spring.

[0097] In this embodiment, the time-based temperature impact parameter reflects the degree of change in the power load in each period of a day due to temperature changes. For example, the power load in the afternoon and evening in summer will be 20% higher than that in the morning.

[0098] In this embodiment, the functional attributes of the sub-areas include residential areas, commercial areas, business areas, and scenic areas.

[0099] In this embodiment, the power consumption period influencing parameter reflects that the power load distribution of the sub-areas is different during the day due to the different functional attributes of the sub-areas. For example, the power load in the residential area is mainly concentrated in the morning and evening, and the power load in the business district is mainly concentrated during working hours.

[0100] In this embodiment, the all-day prediction value of energy efficiency data is the total prediction value for the entire day of the prediction date, and the time-sharing prediction value of energy efficiency data is the prediction value at the prediction moment obtained by proportionally allocating the all-day prediction value of energy efficiency data to each prediction moment.

[0101] In this embodiment, the initial prediction interval is the value range (i.e., error range) of the time-sharing prediction error value within a reasonable range; the prediction interval of the prediction model is the value range of the time-sharing prediction value of the energy efficiency data of the sub-region within a reasonable range; the setting process of the interval setting unit is to take 10% of the time-sharing prediction value of the energy efficiency data of the sub-region as the initial prediction interval, for example, the time-sharing prediction value of the energy efficiency data of the sub-region is 10000KW, then the initial prediction interval is [-1000KW, +1000KW], the distribution probability of the time-sharing prediction error value of the sub-region being within [-1000KW, +1000KW] is 90%, the preset threshold is 88%, then the prediction interval of the prediction model is [9000KW, 11000KW].

[0102] In this embodiment, the optimization module optimizes the prediction model in the following ways: increasing the amount of original data used to establish the model; for example, if the historical power load data of the previous year is used to establish the prediction model for the first time, the historical power load data of the previous two years is used in the optimization process; improving the classification accuracy of the original data and introducing new influencing parameters; for example, introducing the beginning / end of the month influencing parameters when establishing the prediction model to improve the accuracy of the predicted value of the energy efficiency data at the beginning / end of the month, thereby improving the accuracy of the entire prediction model.

[0103] The beneficial effects of the above technical solution are:

[0104] Based on the historical power load data, a prediction model for the energy efficiency data of the power system is established, and the power system is regulated according to the prediction results, which avoids the waste of power resources, effectively improves the efficiency of power utilization, and ensures the fair distribution of power. By setting the prediction interval, the normal fluctuation of energy efficiency data in the power use area is accommodated, ensuring the normal use of electricity, avoiding the triggering of early warnings due to the fluctuation of normal energy efficiency data of the power system, and reducing the false alarm rate of the early warning system. By dividing the power use area into several sub-areas, accurate power supply is provided according to the power consumption habits of each sub-area, avoiding the waste of power resources, effectively improving the efficiency of power utilization, and ensuring the fair distribution of electricity.

[0105] Example 2

[0106] Based on Example 1, the intelligent terminal includes:

[0107] The power output control module is used to control the power output of the power system according to the predicted value of the energy efficiency data of the entire power use area;

[0108] The power distribution module is used to distribute the power output of the power system to each sub-area according to the predicted value of the energy efficiency data of each sub-area.

[0109] Preferably, the power output control module includes:

[0110] An output recording unit, used to record historical power output data of the power system;

[0111] The output prediction unit determines the power output efficiency of the power system when it is operating at full power according to the power output data recorded by the output recording unit;

[0112] a total output determination unit, used for determining the total power demand according to the predicted value of the energy efficiency data of the entire power use area;

[0113] The control unit regulates the power output efficiency of the power system according to the total power demand.

[0114] In this embodiment, the power output of the power system is the sum of the power generated by the power plants for the power system.

[0115] In this embodiment, the meteorological data refers to the meteorological conditions around the power plant, and the meteorological data includes sunlight intensity, outdoor temperature, and precipitation conditions.

[0116] In this embodiment, the power output efficiency is the total amount of electric energy produced by the power plant per unit time. For example, when a thermal power plant operates at full power, it produces 40,000 kWh of electricity per hour, but the total power demand is 30,000 kWh of electricity per hour. The thermal power plant can produce 30,000 kWh of electricity per hour by only activating part of the power generation equipment.

[0117] The beneficial effects of the above technical solution are:

[0118] The total electricity demand is determined according to the predicted value of the prediction model, and the power output of the power system is adjusted by adjusting the power output efficiency of the power system, thereby avoiding the waste of power resources, improving the reliability of power supply, and realizing efficient and safe operation and management of the power system.

[0119] Example 3

[0120] On the basis of embodiments 1 and 2, an abnormality control module is also included, and the abnormality control module includes:

[0121] An early warning unit, configured to send an early warning message to the inspection unit when the actual energy efficiency data of the sub-area reaches a first threshold preset in the sub-area;

[0122] The inspection unit is used to issue an inspection command to the corresponding sub-area after receiving the warning information;

[0123] The plan generation unit is used to generate a processing plan for this energy efficiency abnormality event.

[0124] Preferably, the plan generating unit includes:

[0125] A priority ranking unit, used for ranking the priorities of all sub-regions according to the importance of each sub-region;

[0126] An abnormality index determination unit, used to calculate an energy efficiency abnormality index of a sub-region with energy efficiency abnormality;

[0127] An analysis unit, used for confirming a processing mode of energy efficiency abnormality according to an energy efficiency abnormality index;

[0128] The control amount determination unit is used to determine the control amount of the power data.

[0129] In this embodiment, the processing modes of energy efficiency anomalies include internal regulation within sub-regions, power redistribution between sub-regions, and increasing the power output of the power system; internal regulation within sub-regions is to control the power load of some power usage points with lower importance in the sub-regions; power redistribution between sub-regions is to allocate part of the power load from sub-regions with lower priority or sub-regions with larger power load margin to sub-regions with energy efficiency anomalies; increasing the power output of the power system is to improve the power output efficiency of the power system and thus improve the power output efficiency of the power system.

[0130] In this embodiment, the first threshold is a value beyond which the performance data of the sub-region exceeds which the power resources allocated to the sub-region according to the plan are insufficient to support the power usage of the sub-region under the current circumstances.

[0131] In this embodiment, the inspection command includes investigating the cause of the energy efficiency abnormality.

[0132] In this embodiment, the importance of the sub-region is determined according to the severity of the consequences caused by power failure in the sub-region.

[0133] The beneficial effects of the above technical solution are:

[0134] By monitoring the real-time performance data of the sub-area, when the performance data exceeds the first threshold, the power resources allocated to the sub-area are insufficient, and a processing plan needs to be generated to prevent power accidents in the sub-area. By calculating the energy efficiency anomaly index of the sub-area, the processing mode is determined. While ensuring the processing effect on the sub-area with energy efficiency anomalies, the normal power consumption of other sub-areas is not affected, thereby reducing operation and maintenance costs and improving the safety and reliability of the power system.

[0135] Example 4

[0136] Based on Example 3, the abnormal index determination unit calculates the energy efficiency abnormal index of the sub-region according to Formula 1, and Formula 1 is:

[0137]

[0138]

[0139] Among them, K A is the energy efficiency anomaly index of the sub-region A at the current moment, α is the importance weighted value of sub-region A; X A is the actual time-sharing energy efficiency data of sub-area A at the current moment; The average time-sharing energy efficiency data of sub-area A on the previous day; is the allowable deviation percentage of the predicted value, X A0 is the time-sharing prediction value of the energy efficiency data of sub-area A at the current moment; W is the function attribute discrimination parameter of sub-area A. When sub-area A is a working area, W takes 1; when sub-area A is a non-working area, W takes 2; Q is the working time discrimination parameter. When the current moment is working time, Q takes 1; when the current moment is non-working time, Q takes 2; M is the total number of recording time periods from the day to the current moment, G AiT is the average energy efficiency data of the i-th recording period of the day in sub-area A; G Ai(T-1) is the average energy efficiency data of the i-th recording period of the previous day in sub-area A; G AMAX is the highest value of the time-sharing energy efficiency data of sub-area A on the previous day; G AMIN is the lowest value of the time-sharing energy efficiency data of sub-area A on the previous day; p is the estimated total power output of the power system on that day; μ is the loss rate of power transmission per unit length; L Ais the transmission distance from sub-region A to the power system; L0 is the unit length for calculating the power transmission loss rate; N is the total number of sub-regions that output power during the power redistribution process between sub-regions; β j is the importance weighted value of the j-th power output sub-area; X j is the actual time-sharing energy efficiency data of the j-th power output sub-area at the current moment; X j0 is the predicted value of the time-sharing energy efficiency data of the j-th power output sub-area at the current moment; R j is the impact coefficient of the power redistribution process on the jth power output sub-area;

[0140] When K A When it is less than the second threshold, the energy efficiency abnormality processing mode adopts the redistribution of power among sub-regions;

[0141] When K A When it is greater than the second threshold, the energy efficiency abnormality processing mode adopts increasing the power output of the power system.

[0142] In this embodiment, the working area is a sub-area in which workplaces account for more than 60% of the current area; the non-working area is a sub-area in which workplaces account for less than 60% of the current area; the working hours are from 8:00 to 18:00 every day; and the non-working hours are from 18:00 to 8:00 the next day.

[0143] In this embodiment, the length of each recording period is one hour. If the current time is 8:00, the value of M is 8.

[0144] The beneficial effects of the above technical solution are:

[0145] By calculating the energy gap of the sub-region where the energy efficiency anomaly occurs, and then predicting and correcting the change trend and change rate of the energy efficiency data of the next sub-region through the functional attributes and time parameters of the sub-region, the energy gap is compared with the estimated total output of the power system to obtain the ratio of the energy gap to the total output of the power system, and then considering the importance of sub-region A, it is obtained that when the total power output remains unchanged, the impact of filling the energy gap of sub-region A on the entire power system is obtained. After that, the degree of impact on the power output sub-region after the power output sub-region outputs power to fill the energy gap of sub-region A is comprehensively considered, so as to obtain the total impact of the processing mode of power redistribution between sub-regions on the entire power system, that is, K A , when K A When it is less than the second threshold, the impact on the entire power system is small and will not affect the normal power consumption of other sub-areas. Therefore, the power redistribution between sub-areas is used to solve this incident. When K AWhen it is greater than the second threshold, the redistribution of electricity between sub-regions will have a greater impact on the entire power system and will pose a hidden danger to the normal electricity consumption of other sub-regions. Therefore, it is necessary to increase the power output of the power system to make up for the energy gap in sub-region A and ensure the stable operation of the entire power system.

[0146] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. A power operation and maintenance control system based on energy efficiency anomaly, characterized by: include: A model building module is used to build a prediction model for energy efficiency data of the power system; A data acquisition module, used to obtain actual energy efficiency data of the power system; A prediction interval determination module, used to determine the prediction interval of the prediction model of energy efficiency data of the power system; The energy efficiency monitoring module is used to monitor whether the actual energy efficiency data is within the prediction interval of the energy efficiency data prediction model to determine whether the actual energy efficiency data is abnormal; Intelligent terminals are used to issue control instructions to the power system based on actual energy efficiency data and implement control operations on the power system; Smart terminals include: The power output control module is used to control the power output of the power system according to the predicted value of the energy efficiency data of the entire power use area; A power distribution module, used for distributing the power output of the power system to each sub-region according to the predicted value of the energy efficiency data of each sub-region; The power output control module includes: An output recording unit, used to record historical power output data of the power system; The output prediction unit determines the power output efficiency of the power system when it is operating at full power according to the power output data recorded by the output recording unit; A total output determination unit, used for determining the total power demand according to the predicted value of the energy efficiency data of the entire power use area; A control unit that regulates the power output efficiency of the power system according to the total power demand; It also includes an abnormality control module, which includes: An early warning unit, configured to send an early warning message to the inspection unit when the actual energy efficiency data of the sub-area reaches a first threshold preset in the sub-area; The inspection unit is used to issue an inspection command to the corresponding sub-area after receiving the warning information; A plan generation unit, used to generate a processing plan for this abnormal energy efficiency event; The plan generation unit includes: A priority ranking unit, used for ranking the priorities of all sub-regions according to the importance of each sub-region; An abnormality index determination unit, used to calculate an energy efficiency abnormality index of a sub-region with energy efficiency abnormality; An analysis unit, used for confirming a processing mode of energy efficiency abnormality according to an energy efficiency abnormality index; A control quantity determination unit, used to determine the control quantity of power data; The abnormal index determination unit calculates the energy efficiency abnormal index of the sub-region according to Formula 1, which is: ； ； in, is the energy efficiency anomaly index of the sub-region A at the current moment, is the importance weighted value of sub-region A; is the actual time-sharing energy efficiency data of sub-area A at the current moment; The average time-sharing energy efficiency data of sub-area A on the previous day; is the allowed deviation percentage of the predicted value, is the time-sharing prediction value of the energy efficiency data of sub-area A at the current moment; is the function attribute discrimination parameter of sub-area A. When sub-area A is a working area, W is 1; when sub-area A is a non-working area, W is 2. Q is the working time discrimination parameter. When the current moment is working time, Q is 1; when the current moment is non-working time, Q is 2. M is the total number of recording time periods from the current day to the current moment. is the average energy efficiency data of the i-th recording period of the day in sub-area A; is the average energy efficiency data of the i-th recording period of the previous day in sub-area A; The highest value of the time-sharing energy efficiency data of sub-area A on the previous day; The lowest value of the time-sharing energy efficiency data of sub-area A on the previous day; is the estimated total electricity output of the power system on that day; is the loss rate of power transmission per unit length; is the transmission distance from sub-area A to the power system; is the unit length for calculating the power transmission loss rate; N is the total number of sub-regions that output power during the power redistribution process between sub-regions; is the importance weighted value of the j-th power output sub-area; is the actual time-sharing energy efficiency data of the j-th power output sub-area at the current moment; is the predicted value of the time-sharing energy efficiency data of the sub-area with the j-th power output at the current moment; is the impact coefficient of the power redistribution process on the jth power output sub-area; when When it is less than the second threshold, the energy efficiency abnormality processing mode adopts the redistribution of power among sub-regions; when When it is greater than the second threshold, the energy efficiency abnormality processing mode adopts increasing the power output of the power system.

2. According to claim 1, a power operation and maintenance control system based on energy efficiency abnormality is characterized by: The model building module includes: A region division unit, used for dividing the power use area into a number of sub-areas; Using a recording unit for recording historical power load data for each sub-area; A preprocessing unit, used for preprocessing the historical power load data of the sub-region; The model building unit is used to build a prediction model for energy efficiency data of each sub-region by using the pre-processed historical power load data of the sub-region.

3. The power operation and maintenance control system based on energy efficiency anomaly according to claim 2 is characterized in that: The model building module includes basic energy efficiency subunit, natural growth energy efficiency subunit, special day impact subunit, temperature impact subunit, and electricity consumption period impact subunit; The basic energy efficiency subunit is used to obtain basic energy efficiency parameters by removing special values ​​from the historical power load data of the sub-region; The natural growth energy efficiency subunit is used to calculate the natural growth rate of basic energy efficiency parameters; The special day impact subunit is used to calculate the special day compensation parameter based on the historical power load data of the sub-area on the special date; The temperature impact subunit is used to obtain the daily temperature impact parameters and the time-sharing temperature impact parameters according to the historical power load data combined with the historical temperature data of the sub-region; The power consumption period influence subunit is used to obtain the power consumption period influence parameter according to the time-sharing historical power load data of the sub-region and the functional attributes of the sub-region; The data fusion model is used to correct the basic energy efficiency parameters through the natural growth rate of basic energy efficiency parameters, special day compensation parameters and all-day temperature influence parameters to obtain the all-day prediction value of energy efficiency data; and to allocate the all-day prediction value of energy efficiency data to different time periods through the time-sharing temperature influence parameters and electricity consumption period influence parameters to obtain the time-sharing prediction value of energy efficiency data.

4. The power operation and maintenance control system based on energy efficiency abnormality according to claim 1 is characterized in that: The prediction interval determination module includes: An error acquisition unit is used to calculate the time-sharing prediction value of the energy efficiency data of the sub-region according to the prediction model of the energy efficiency data, and to obtain the time-sharing prediction error value of the sub-region by subtracting the time-sharing prediction value of the energy efficiency data of the sub-region from the time-sharing actual energy efficiency data of the sub-region; An interval setting unit uses a certain deviation range of the time-sharing prediction value of the energy efficiency data of the sub-region as an error tolerance range of the prediction model; The interval verification unit is used to count the distribution probability that the time-sharing prediction error value of the sub-region is within the error tolerance interval. When the distribution probability is higher than a preset threshold, the time-sharing prediction value of the energy efficiency data of the sub-region is used as the median of the prediction interval, and the width of the error tolerance interval is used as the width of the prediction interval of the prediction model to determine the prediction interval of the prediction model. When the distribution probability is less than the preset threshold, the prediction model of the energy efficiency data is optimized through the optimization module, and the prediction interval of the optimized prediction model of the energy efficiency data is determined again.

Images