Power grid energy management optimization platform based on big data

Abstract

The invention discloses a power grid energy management optimization platform based on big data, and relates to the technical field of power grid energy management, and the platform comprises the following steps: firstly, deploying real-time power monitoring equipment in an area where high-tech industries are centralized, and obtaining real-time power consumption data of enterprises and key electric equipment in real time through the power monitoring equipment; and a data interface is established, an enterprise is allowed to autonomously upload power utilization data of internal key equipment, and the comprehensiveness and accuracy of the data are improved. According to the scheme, through real-time power monitoring, feature extraction and machine learning model evaluation, accurate monitoring and intelligent scheduling of power consumption are realized. Aiming at normal and surge power demands, stable power supply and efficient utilization of resources are ensured through load prediction and a distributed optimization algorithm, risks of network paralysis, power failure and the like caused by sudden power demands are avoided, and enterprise operation and power grid safety are guaranteed.

Description

Technical Field

[0001] The present invention relates to the technical field of power grid energy management, and in particular to a power grid energy management optimization platform based on big data. Background Art

[0002] The power grid energy management optimization platform based on big data is a solution that uses large-scale data processing technology combined with intelligent algorithms to achieve efficient management and optimization of the power grid system. The platform comprehensively understands the operation status of the power grid by collecting, analyzing and processing various data in the operation of the power grid (such as load, energy consumption, meteorological data, user electricity consumption behavior, etc.) in real time. With the help of big data analysis, the platform can accurately predict electricity demand, optimize the allocation of power resources, ensure the stable operation of the power supply system, and improve energy utilization efficiency and reduce energy waste. In addition, the platform can also identify potential problems and hidden dangers through in-depth mining of historical data, conduct predictive maintenance in advance, and avoid large-scale power outages caused by sudden failures.

[0003] The core of the platform is intelligent optimization algorithms and data-driven decision-making. It can not only flexibly adjust to different power consumption scenarios, but also dynamically optimize the load balance of the power grid to ensure real-time matching of power supply and demand. In the access scenario of renewable energy, the big data platform can also adjust the power generation and grid connection strategies of clean energy according to changes in external factors such as weather, light, and wind speed, improve the utilization rate of new energy, and reduce the use of fossil energy. Through intelligent and automated management of the entire power grid system, the power grid energy management optimization platform based on big data can not only effectively improve the safety and economy of the power grid, but also lay the foundation for the development of low-carbon and environmentally friendly energy.

[0004] The prior art has the following deficiencies:

[0005] The existing power grid mainly relies on forecasts of regional electricity demand for planning and scheduling, because the production and consumption of electricity must be matched in time (large-scale electricity is difficult to store for a long time). Through the load forecasting model, the power system estimates future demand in advance and arranges the production and allocation of resources. However, in areas where high-tech industries are concentrated, when companies encounter large-scale cyber attacks (such as distributed denial of service attacks DDoS or ransomware infections), server clusters need to expand rapidly to divert attack traffic or restore damaged data systems. Such sudden expansion and additional computing needs may cause a surge in regional electricity consumption beyond the forecast range. If the power system fails to dispatch power supply in time, companies will not be able to expand servers to respond to attacks, causing network paralysis and forcing core businesses such as e-commerce, financial services, and cloud computing to be interrupted.

[0006] The above information disclosed in this Background section is only for enhancement of understanding of the background of the present disclosure and therefore it may contain information that does not constitute the prior art that is already known to one of ordinary skill in the art. Summary of the invention

[0007] The purpose of the present invention is to provide a power grid energy management optimization platform based on big data. Through real-time power monitoring, feature extraction and evaluation of machine learning models, the solution realizes accurate monitoring and intelligent scheduling of power consumption. For normal and surge power demand, load forecasting and distributed optimization algorithms are used to ensure stable power supply and efficient resource utilization, avoid risks such as network paralysis and power outages caused by sudden power demand, ensure enterprise operations and power grid security, and solve the problems in the above-mentioned background technology.

[0008] In order to achieve the above object, the present invention provides the following technical solution: a power grid energy management optimization platform based on big data, comprising the following steps:

[0009] First, deploy real-time power monitoring equipment in areas where high-tech industries are concentrated. Use the power monitoring equipment to obtain real-time power consumption data of enterprises and key power-consuming equipment. Establish a data interface to allow enterprises to independently upload power consumption data of internal key equipment, thereby improving the comprehensiveness and accuracy of the data.

[0010] Extract features from the acquired power consumption data, and based on the extracted power consumption data features, use the pre-learned machine learning model to intelligently evaluate the power consumption data in the area under the monitoring window;

[0011] Based on the evaluation results of the machine learning model, the regional power demand is divided into normal power demand and surge power demand;

[0012] In response to normal power demand, we will continue to supply power stably according to the established load forecast plan, ensure the balance between power production and consumption, and maintain the normal operation of the power grid;

[0013] In response to the surge in electricity demand, a distributed optimization algorithm is used to initiate intelligent power dispatching adjustments based on the established load forecast plan, while adjusting the power supply distribution in the remaining areas to optimize the grid load.

[0014] Preferably, feature extraction is performed on the acquired power consumption data, and the extracted features include the degree of deviation of the power factor in a short time and the ratio of the instantaneous peak value to the average value of the power consumption in a short time. After acquisition, the degree of deviation of the power factor in a short time and the ratio of the instantaneous peak value to the average value of the power consumption in a short time are analyzed within the detection window to generate a power factor offset index and an instantaneous load fluctuation index, respectively, and the power factor offset index and the instantaneous load fluctuation index are input into a pre-learned machine learning model, and a power consumption coefficient is generated through the machine learning model, and the changes in regional power consumption are intelligently evaluated through the power consumption coefficient.

[0015] Preferably, within the detection window, the power factor deviation index is generated after analyzing the degree of deviation of the power factor within a short period of time, and the specific steps are as follows:

[0016] In the detection window, the instantaneous power factor is calculated from the instantaneous waveforms of current and voltage. The calculation expression is as follows: PF(t) = cos(E(t)) = cos(φ V (t)-φ I (t)), where PF(t) is the instantaneous power factor, which means the instantaneous power factor of the power system at time t, E(t) is the instantaneous phase angle difference, which means the phase difference between voltage and current at time t, cos(E(t)) is the instantaneous power factor, φ V (t) is the instantaneous phase angle of voltage, φ I (t) is the instantaneous phase angle of the current;

[0017] Next, we define an indicator to quantify the power factor deviation in a short period of time, called the instantaneous deviation rate. The instantaneous deviation rate measures the deviation rate of the power factor in a very short period of time, and expresses the change of the power factor over time in the form of a derivative. The calculation expression is as follows:

[0018] ,

[0019] Where ΔPF(t) is the instantaneous power factor deviation rate, which indicates the deviation speed of the instantaneous power factor PF(t) at time t, that is, the instantaneous power factor deviation rate of the instantaneous power factor. is the derivative of the instantaneous power factor with time, It is the calculation process of instantaneous power factor deviation;

[0020] In order to capture the overall intensity of the power factor deviation, the instantaneous power factor deviation rate ΔPF(t) is weighted and integrated, and the time weight function is introduced. The calculation expression is as follows:

[0021] ,

[0022] Where PF Shift Strength is the power factor shift strength, t0 and t1 are the detection window start time and detection window end time, W(t) is the time weight function,

[0023] Next, a nonlinear offset discrimination function is defined to compare the offset degree of the power factor with its critical value to generate a function that measures the degree of abnormal deviation. The calculation expression is as follows:

[0024] ,

[0025] Where f(PF) is the nonlinear offset discriminant function, E ref is the reference phase angle, that is, the reference phase angle under normal circumstances, β is the weight coefficient, k is the nonlinear amplification coefficient, cos(E ref ) is the reference instantaneous power factor;

[0026] The power factor offset index is generated based on the nonlinear offset discriminant function f(PF), and the calculation expression is as follows: PFΔI=ln(1+θ·f(PF)), where PFΔI is the power factor offset index and θ is the amplification factor used to adjust the sensitivity and range of the index.

[0027] Preferably, within the detection window, the ratio of the instantaneous peak value to the average value of the power consumption within a short period of time is analyzed to generate an instantaneous load fluctuation index, and the specific steps are as follows:

[0028] In the detection window, the current and voltage sampling values ​​are obtained in real time, and the obtained current sampling value is calibrated as I(t), and the voltage sampling value is calibrated as V(t). I(t) refers to the current sampling value at time t, and V(t) refers to the voltage sampling value at time t.

[0029] At each time point t, the difference in instantaneous power change is calculated to reflect the sudden change trend of equipment power. The calculation expression is as follows: ΔP(t) = |I(t)·V(t)-I(t-Δt)·V(t-Δt)|, where ΔP(t) is the instantaneous change in power, indicating the instantaneous change in power at time point t, Δt is the sampling time interval, which is used to calculate the change between two adjacent time points, I(t-Δt) is the current sampling value at the previous time point, and V(t-Δt) is the voltage sampling value at the previous time point;

[0030] In order to capture the cumulative fluctuation of the instantaneous change of power within the entire detection window, the cumulative absolute change function is used to avoid the mutual cancellation of positive and negative power fluctuations. The calculation expression is as follows:

[0031] ,

[0032] In the formula, C P is the cumulative value of power jumps within the detection window, indicating the total change of power fluctuations within the detection window, and M is the total number of sampling points within the detection window, reflecting the number of data points collected within the detection window;

[0033] In order to accurately capture the dynamic change trend of the load, an exponential decay weight function is introduced to respond more sensitively to the latest power fluctuations, thereby generating an instantaneous load fluctuation index. The calculation expression is as follows:

[0034] ,

[0035] Where I-LFX is the instantaneous load fluctuation index, e is the natural base, β is the instantaneous load fluctuation exponential attenuation coefficient, which controls the speed of exponential attenuation, and Mt represents the distance between the sampling point and the current time.

[0036] Preferably, the power consumption coefficient generated after analyzing the power consumption data acquired under the monitoring window is compared and analyzed with a preset power consumption coefficient reference threshold, and the regional power demand is divided, and the division result is as follows:

[0037] If the power consumption coefficient is greater than or equal to a preset power consumption coefficient reference threshold, the regional power demand is classified as a surge power demand;

[0038] If the power consumption coefficient is less than a preset power consumption coefficient reference threshold, the regional power demand is classified as normal power demand.

[0039] Preferably, for surge power demand, a distributed optimization algorithm is used to start intelligent power dispatching adjustment based on the established load forecasting plan, and the power supply distribution in the remaining areas is adjusted at the same time. The steps for optimizing the power grid load are as follows:

[0040] In the high-tech enterprise area, the power factor deviation index PFΔI and the instantaneous load fluctuation index I-LFX are obtained in real time through power monitoring equipment. Once a load surge is detected, it is necessary to determine whether to start scheduling, and the following judgment conditions are used for judgment;

[0041] ,

[0042] Wherein, Trigger Adjustment is the trigger variable, θ1 is the preset reference threshold of the power factor deviation index PFΔI, and θ2 is the preset reference threshold of the instantaneous load fluctuation index I-LFX;

[0043] When the dispatch is triggered, the optimal power distribution between regions is solved to meet the surge demand at the lowest cost. The calculation expression is as follows:

[0044] ,

[0045] In the formula, min is the minimization objective function, C i is the unit electricity supply cost in region i, P i is the actual power supply in region i, represents the total power supply cost of each region, λ is the penalty coefficient, is the forecast load of region i, is the penalty term for load forecast error, the purpose of which is to reduce the actual power supply P i Power supply forecast The deviation between them, N represents the total number of regions participating in the dispatch in the power grid system;

[0046] In the distributed optimization process, it is necessary to ensure the balance between power supply and demand. At the same time, the load in each area must meet the constraints. The power balance constraint and regional load constraint are set. The power balance constraint expression is as follows:

[0047] ,

[0048] In the formula, is the total power supply capacity in the system at the current moment;

[0049] The regional load constraint expression is as follows: In the formula, is the area i with the least load, is the area i is the maximum load;

[0050] Since power dispatching involves multiple regions, the distributed Lagrangian relaxation method is used to decompose the global optimization problem into several sub-problems and solve them in parallel. The calculation expression is as follows:

[0051] ,

[0052] In the formula, L(P i ,μ) is the Lagrangian function, is the cost and forecast error part of the power grid system, which calculates the power supply cost and its forecast load error in all regions, μ is the power balance constraint term, μ is the Lagrange multiplier;

[0053] After the dispatching plan is implemented, feedback is provided based on real-time data, and the power supply strategy is dynamically adjusted to ensure the stable operation of the power grid. The calculation expression is as follows: In the formula, is the adjusted power supply of region i, α is the scheduling coefficient, which is used to control the adjustment strength of the power supply of each region, P t is the actual total load of the system at the current moment, is the forecast total load at the current moment.

[0054] In the above technical solution, the technical effects and advantages provided by the present invention are:

[0055] The present invention realizes accurate monitoring and intelligent analysis of regional power consumption through real-time power monitoring and feature extraction, combined with the evaluation capability of machine learning models. In particular, by analyzing the power factor offset index and the instantaneous load fluctuation index, it is possible to accurately determine whether there is a surge in power demand in the region. This capability enables the power system to quickly identify sudden power demands caused by network attacks or server expansion, and respond in a timely manner to avoid serious consequences such as network paralysis and business interruption caused by insufficient power supply. The intelligent evaluation mechanism of the scheme also ensures the dynamic adjustment of load forecasting, improves the flexibility of power management, enables the power grid to more accurately adapt to the rapid changes in corporate needs, and maintain the stable development of the regional economy and industry.

[0056] The present invention has formulated differentiated dispatching strategies for normal power demand and surge power demand. For normal demand, the load forecasting plan is used to maintain a stable power supply, ensure the balance between power production and consumption, and effectively avoid power waste and systematic power shortage. In the surge demand scenario, the scheme uses a distributed optimization algorithm to achieve intelligent power dispatching and adjustment. By optimizing the power supply distribution within the region and between adjacent regions, the load pressure in a single region is reduced to the maximum extent, avoiding the risk of power outages caused by overloaded power grids. This distributed intelligent dispatching not only improves the utilization efficiency of power resources, but also ensures the emergency power supply needs of enterprises when encountering sudden network attacks, provides stable power support for enterprises, and reduces operational risks and economic losses. BRIEF DESCRIPTION OF THE DRAWINGS

[0057] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present invention. For ordinary technicians in this field, other drawings can also be obtained based on these drawings.

[0058] Figure 1 This is a method flow chart of a power grid energy management optimization platform based on big data in the present invention. DETAILED DESCRIPTION

[0059] Example embodiments will now be described more fully with reference to the accompanying drawings. However, example embodiments can be implemented in a variety of forms and should not be construed as limited to the examples set forth herein; rather, these example embodiments are provided so that the description of the present disclosure will be more comprehensive and complete, and the concept of the example embodiments will be fully conveyed to those skilled in the art.

[0060] The present invention provides Figure 1 A power grid energy management optimization platform based on big data is shown, comprising the following steps:

[0061] First, deploy real-time power monitoring equipment in areas where high-tech industries are concentrated. Use the power monitoring equipment to obtain real-time power consumption data of enterprises and key power-consuming equipment. Establish a data interface to allow enterprises to independently upload power consumption data of internal key equipment, thereby improving the comprehensiveness and accuracy of the data.

[0062] In areas where high-tech industries are concentrated, it is crucial to deploy real-time power monitoring equipment. These devices include smart meters, high-precision current sensors, and data acquisition terminals, which can accurately record real-time power consumption data of enterprises and key power-consuming equipment. These devices are usually installed in the company's main power consumption nodes, data center computer rooms, server clusters, production lines, and refrigeration systems to ensure comprehensive monitoring of all important power consumption points. Through high-bandwidth networks (such as 5G and fiber optic networks), these monitoring data will be transmitted to the regional power management center in real time to provide data support for real-time analysis and scheduling of the system.

[0063] In addition, establishing a data interface to support enterprises to upload power consumption data of key equipment independently can further improve the comprehensiveness and accuracy of the data. For example, the control system of the internal server, cooling system or automated production equipment of the enterprise can directly transmit the internal energy consumption information to the power management platform. This information sharing not only helps the power grid to understand the power consumption of each enterprise in a timely manner, but also improves the accuracy of forecasting and scheduling. When an enterprise has abnormal power consumption (such as server expansion or emergency production tasks), the management platform can immediately perceive and respond quickly to ensure that the power supply meets demand and prevent emergencies from causing systemic risks.

[0064] Extract features from the acquired power consumption data, and based on the extracted power consumption data features, use the pre-learned machine learning model to intelligently evaluate the power consumption data in the area under the monitoring window;

[0065] Extract features from the acquired power consumption data, the extracted features include the degree of deviation of the power factor in a short period of time and the ratio of the instantaneous peak value to the average value of the power consumption in a short period of time. After acquisition, analyze the degree of deviation of the power factor in a short period of time and the ratio of the instantaneous peak value to the average value of the power consumption in a short period of time within the detection window, generate a power factor deviation index and an instantaneous load fluctuation index respectively, input the power factor deviation index and the instantaneous load fluctuation index into a pre-learned machine learning model, generate a power consumption coefficient through the machine learning model, and intelligently evaluate the change of regional power consumption through the power consumption coefficient;

[0066] A sudden deviation of the power factor in a short period of time usually indicates that the power consumption in the area is surging. This is because the power factor reflects the ratio between active power (actual energy consumed) and apparent power (total energy transmitted). When high-power loads (such as server clusters, refrigeration systems, motors, etc.) are connected in large numbers in a short period of time, these devices usually have strong inductive or capacitive characteristics, causing the power factor to drop or rise rapidly and deviate from normal levels. The sudden start-up of such loads will significantly increase the reactive power demand of the power system (energy used to maintain the electromagnetic field), causing the power factor of the power supply system to fluctuate for a short time. At the same time, this load is usually accompanied by large-scale power consumption, so the drastic change of the power factor is often an important signal of a surge in power consumption in the area. The deviation of the power factor may also lead to a decrease in the transmission efficiency of the power grid, so that more current needs to be transmitted through the transmission line to transmit the same power, aggravating the load on the power grid, further confirming the rapid growth of regional power demand.

[0067] In the detection window, the power factor deviation index is generated by analyzing the degree of deviation of the power factor in a short period of time. The specific steps are as follows:

[0068] In the detection window, the instantaneous power factor is calculated from the instantaneous waveforms of current and voltage. The calculation expression is as follows: PF(t) = cos(E(t)) = cos(φ V (t)-φ I (t)), where PF(t) is the instantaneous power factor, which indicates the instantaneous power factor of the power system at time t. The power factor reflects the ratio between the active power (effective power) and the apparent power (total power) in the power system. E(t) is the instantaneous phase angle difference, which indicates the phase difference between the voltage and current at time t. The phase difference reflects the lag or lead relationship between the current and voltage waveforms. cos(E(t)) represents the instantaneous power factor, which is the cosine value of the phase angle difference and indicates the utilization efficiency of electric energy. V (t) is the instantaneous phase angle of the voltage, which represents the instantaneous phase angle of the voltage waveform at time t, φ I (t) is the instantaneous phase angle of the current, which represents the instantaneous phase angle of the current waveform at time t;

[0069] By analyzing the instantaneous waveforms of current and voltage and calculating the phase angle difference between them, the instantaneous power factor PF(t) is obtained. The power factor reflects the operating efficiency of the power system. Monitoring its changes helps to adjust the power supply in time in emergencies (such as load fluctuations or equipment startup) to ensure the stability and efficiency of the system.

[0070] Phase angle refers to the angle corresponding to the time difference between the voltage waveform and the current waveform in an AC circuit, expressed in degrees or radians. Since voltage and current usually change in the form of sine waves in AC systems, their characteristic points such as peaks and troughs may not be synchronized (that is, they are not reached at the same time). This asynchronicity leads to a phase difference between the two, and the phase angle is the specific quantification of this phase difference. The sign of the phase angle is also important: if the current lags behind the voltage, the phase angle is positive, which usually occurs in inductive loads (such as motors); if the current leads the voltage, the phase angle is negative, which is common in capacitive loads (such as capacitors). When the phase angle is 0°, the voltage and current are completely synchronized, indicating that there is no reactive power in the system and all electrical energy is effectively converted into active power. If the phase angle is close to ±90°, it indicates that there is a large amount of reactive power in the system and the energy utilization efficiency is low. Monitoring the phase angle is very important for optimizing energy utilization, reducing losses, and improving system stability.

[0071] Next, we define an indicator to quantify the power factor deviation in a short period of time, called the instantaneous deviation rate. The instantaneous deviation rate measures the deviation rate of the power factor in a very short period of time, and expresses the change of the power factor over time in the form of a derivative. The calculation expression is as follows:

[0072]

[0073] , where ΔPF(t) is the instantaneous power factor deviation rate, which indicates the deviation speed of the instantaneous power factor PF(t) at time t, that is, the instantaneous power factor deviation rate of the instantaneous power factor. It is the derivative of the instantaneous power factor with time. This is the result of taking the time derivative of the instantaneous power factor cos(E(t)), which indicates the rate of deviation of the power factor at a certain instant. It is the calculation process of instantaneous power factor deviation, which is the derivative of instantaneous power factor cos(E(t)), reflecting the sensitivity of power factor to phase angle difference;

[0074] In order to capture the overall intensity of the power factor deviation, the instantaneous power factor deviation rate ΔPF(t) is weighted and integrated, and the time weight function is introduced. The calculation expression is as follows:

[0075]

[0076] , where PF Shift Strength is the power factor shift strength, t0 and t1 are the detection window start time and detection window end time, W(t) is the time weight function, which represents the weight coefficient at time t, and is used to give different importance to changes in different time periods.

[0077] Next, a nonlinear offset discrimination function is defined to compare the offset degree of the power factor with its critical value to generate a function that measures the degree of abnormal deviation. The function that measures the degree of abnormal deviation maps the offset intensity to a nonlinear scale to determine whether the deviation is abnormal. The calculation expression is as follows:

[0078]

[0079] , where f(PF) is the nonlinear offset discriminant function, E ref is the reference phase angle, that is, the reference phase angle under normal circumstances, β is the weight coefficient, which is used to control the sensitivity of the phase angle offset in the discriminant function, k is the nonlinear amplification coefficient, which is used to control the nonlinearity in the discriminant function, cos(E ref ) is the reference instantaneous power factor;

[0080] The power factor offset index is generated based on the nonlinear offset discriminant function f(PF), and the calculation expression is as follows: PFΔI=ln(1+θ·f(PF)), where PFΔI is the power factor offset index, and θ is the amplification factor used to adjust the sensitivity and range of the index;

[0081] It can be seen from the calculation expression of the power factor deviation index that, within the detection window, the larger the performance value of the power factor deviation index generated after analyzing the degree of deviation of the power factor in a short period of time, the greater the sudden access of a large number of inductive or capacitive loads in the area (such as the startup of server clusters, cooling systems or emergency equipment), which will significantly increase the reactive power demand and cause the power factor to deviate rapidly from normal levels. This usually means that the demand for electricity in the region is surging, because these devices will significantly increase the load on the power grid when they are started and running. On the contrary, if the performance value of the power factor deviation index is small or stable within the normal range, it indicates that the regional electricity consumption is relatively stable, the power consumption is within the predicted range, and there is no significant load growth.

[0082] The ratio of the instantaneous peak value to the average value of electricity consumption in a short period of time rises rapidly, usually indicating that electricity consumption in the region is surging. This phenomenon indicates that electricity consumption has changed dramatically in a short period of time, and the instantaneous peak value is much higher than the conventional average value, reflecting that multiple high-power consumption devices may be started or expanded at the same time. When responding to emergencies (such as cyber attacks, urgent data processing or production tasks), enterprises in the region often quickly increase the operating load of servers, refrigeration equipment and other key equipment, resulting in a surge in instantaneous power demand. The concentrated start-up of these loads in a short period of time causes a sharp peak in the electricity consumption curve, while the average value fails to rise synchronously due to the lower initial load in the time window, widening the gap between the peak and the average value. Therefore, the sharp rise in the ratio indicates that the electricity demand in the region is breaking through the forecast range, indicating that the load surge may continue or even expand further. If the power system fails to respond to this change in a timely manner, it may lead to risks such as grid overload or equipment downtime.

[0083] In the detection window, the ratio of the instantaneous peak value to the average value of power consumption in a short period of time is analyzed to generate the instantaneous load fluctuation index. The specific steps are as follows:

[0084] In the detection window, the current and voltage sampling values ​​are obtained in real time, and the obtained current sampling value is calibrated as I(t), and the voltage sampling value is calibrated as V(t). I(t) refers to the current sampling value at time t, and V(t) refers to the voltage sampling value at time t.

[0085] At each time point t, the difference in instantaneous power change is calculated to reflect the sudden change trend of the equipment power. Here, the nonlinear relationship between current and voltage is used to capture the instantaneous jump of power. The calculation expression is as follows: ΔP(t) = |I(t)·V(t)-I(t-Δt)·V(t-Δt)|, where ΔP(t) is the instantaneous change in power, indicating the instantaneous change in power at time point t, Δt is the sampling time interval, which is used to calculate the change between two adjacent time points, I(t-Δt) is the current sampling value at the previous time point, and V(t-Δt) is the voltage sampling value at the previous time point;

[0086] The purpose of calculating the difference in instantaneous power changes at each time point is to capture various sudden changes in equipment power. These changes reflect the switching of equipment between different operating states, which may be the result of events such as equipment startup, shutdown, load transfer, etc. These differences not only reveal the operating status of the equipment itself, but also reflect the volatility of enterprise electricity demand and whether the power grid is facing unstable load challenges. The following details the difference types of instantaneous power changes and their corresponding power mutation trends:

[0087] 1. Power jump difference: equipment startup or expansion trend

[0088] Definition: When a device or server cluster is suddenly started, the product of current and voltage (i.e. power) will experience a significant instantaneous jump.

[0089] Trends reflected:

[0090] Server expansion: When a data center or high-tech enterprise encounters a cyber attack, the server cluster will be rapidly expanded, resulting in an instantaneous surge in power.

[0091] Emergency start-up of equipment: Backup generators, cooling equipment, data recovery systems, etc. are started in an emergency, which can also cause an instantaneous power jump.

[0092] explain:

[0093] This power jump usually means that the equipment is switching from low-power mode to high-load operation, and timely power supply adjustment is required, otherwise it may cause local overload of the power grid.

[0094] 2. Power drop differences: equipment shutdown or load unloading trends

[0095] Definition: When a device is shut down or part of the load is unloaded, there will be a sudden drop in power for a short period of time.

[0096] Trends reflected:

[0097] Planned downtime: When an enterprise is carrying out equipment maintenance or completing high-intensity tasks, some high-power-consuming equipment stops operating.

[0098] Load unloading: In order to cope with grid load pressure or internal enterprise optimization, the system may actively unload part of the load.

[0099] explain:

[0100] A sudden drop in power may cause unnecessary dispatch delays in the power grid. If the dispatch system cannot respond in time, it may cause voltage fluctuations and frequency anomalies.

[0101] 3. Volatility differences: Frequent starts and stops or unstable power trends

[0102] Definition: Frequent start and stop of equipment or rapid switching of operating states causes drastic power fluctuations in a short period of time.

[0103] Trends reflected:

[0104] Server failure recovery: When the system is attacked or fails, the server may restart frequently.

[0105] Frequent adjustment of the temperature control system: The air conditioning or cooling system frequently starts and stops due to changes in ambient temperature, which can also cause frequent power fluctuations.

[0106] explain:

[0107] The emergence of fluctuation differences means that the system's operating state is unstable. Frequent fluctuations may accelerate equipment aging and even affect the frequency and voltage stability of the power grid.

[0108] 4. Short-term peak difference: emergency load trend

[0109] Definition: Power reaches a peak in a short period of time and then quickly drops back to normal levels.

[0110] Trends reflected:

[0111] Emergency system testing: The backup power generation system and cooling system will generate short-term peak power during the test.

[0112] Instantaneous high-power consumption tasks: Data centers may perform high-energy consumption computing tasks in a short period of time, such as large-scale AI model training.

[0113] explain:

[0114] Short-term peak differences indicate that the system requires a large amount of electricity in an instant. If this demand cannot be responded to in time, it may cause system instability or load transfer failure.

[0115] 5. Continuous load change difference: continuous expansion or contraction trend

[0116] Definition: A change in power that occurs over a period of time rather than instantaneously.

[0117] Trends reflected:

[0118] Data center expansion: As servers continue to expand, loads continue to rise and power also gradually increases.

[0119] Production tasks are gradually shrinking: enterprises are gradually ending high-energy-consuming tasks, and equipment is gradually stopping operation, resulting in a slow decline in power.

[0120] explain:

[0121] Continuous load changes usually mean that the system is gradually adjusting its operating mode, requiring the power system to respond flexibly to maintain stable power supply.

[0122] The difference in instantaneous power changes can reflect various mutation trends of equipment, including equipment startup, shutdown, frequent start and stop, short-term peaks, and continuous expansion or contraction. These differences are crucial for real-time monitoring of power systems, helping to identify key nodes in enterprise operations and respond to different types of load changes in a timely manner through intelligent power dispatching systems to avoid the risk of system instability or insufficient power supply.

[0123] In order to capture the cumulative fluctuation of the instantaneous change of power within the entire detection window, the cumulative absolute change function is used to avoid the mutual cancellation of positive and negative power fluctuations. The calculation expression is as follows:

[0124] ,

[0125] In the formula, C P is the cumulative value of power jumps within the detection window, indicating the total change of power fluctuations within the detection window, and M is the total number of sampling points within the detection window, reflecting the number of data points collected within the detection window;

[0126] In order to accurately capture the dynamic change trend of the load, an exponential decay weight function is introduced to respond more sensitively to the latest power fluctuations, thereby generating an instantaneous load fluctuation index. The calculation expression is as follows:

[0127] ,

[0128] In the formula, I-LFX is the instantaneous load fluctuation index, e is the natural base, β is the instantaneous load fluctuation index attenuation coefficient, which controls the speed of exponential attenuation, and Mt represents the distance between the sampling point and the current time. The closer to the current time, the higher the weight of the instantaneous load fluctuation index.

[0129] From the calculation expression of the instantaneous load fluctuation index, it can be seen that within the detection window, the larger the performance value of the instantaneous load fluctuation index generated after analyzing the ratio of the instantaneous peak value to the average value of electricity consumption in a short period of time, the more rapid the increase in electricity consumption in a short period of time, which usually reflects that multiple high-energy-consuming devices are started at the same time in a short period of time or the load increases rapidly, resulting in a surge in electricity demand in the region. On the contrary, if the ratio is maintained at a low level and changes smoothly, the performance value of the instantaneous load fluctuation index is also small, indicating that the regional electricity consumption is in a normal or stable state and there is no abnormal fluctuation. Therefore, the larger the performance value of the instantaneous load fluctuation index, the more it can reflect the sudden changes in electricity demand in the region.

[0130] The machine learning model is not limited here, and any machine learning model that can perform a comprehensive analysis of the power factor offset index PFΔI and the instantaneous load fluctuation index I-LFX to generate the power consumption coefficient η-PCC is acceptable. In order to implement the technical solution of the present invention, the present invention provides a specific implementation method:

[0131] The calculation formula for generating the power consumption coefficient η-PCC is as follows:

[0132]

[0133] , where k1 and k2 are the preset proportional coefficients of the power factor deviation index PFΔI and the instantaneous load fluctuation index I-LFX, respectively, and both k1 and k2 are greater than 0.

[0134] It can be seen from the calculation expression of the power consumption coefficient that, under the detection window, the larger the power factor deviation index performance value generated after analyzing the degree of deviation of the power factor in a short period of time, the larger the instantaneous load fluctuation index performance value generated after analyzing the ratio of the instantaneous peak value to the average value of the power consumption in a short period of time, indicating that the larger the power consumption coefficient performance value generated under the monitoring window, the greater the regional power consumption is in a surge state, and vice versa, indicating that the regional power consumption is in a normal state;

[0135] Based on the evaluation results of the machine learning model, the regional power demand is divided into normal power demand and surge power demand;

[0136] The power consumption coefficient generated by analyzing the power consumption data obtained under the monitoring window is compared and analyzed with the pre-set power consumption coefficient reference threshold, and the regional power demand is divided. The division results are as follows:

[0137] If the power consumption coefficient is greater than or equal to a preset power consumption coefficient reference threshold, the regional power demand is classified as a surge power demand;

[0138] If the power consumption coefficient is less than a preset power consumption coefficient reference threshold, the regional power demand is classified as normal power demand;

[0139] Normal electricity demand refers to the demand within the forecast range and in line with daily electricity consumption patterns; surge electricity demand refers to the demand that exceeds the forecast range and has abnormal growth rate and magnitude.

[0140] In response to normal power demand, we will continue to supply power stably according to the established load forecast plan, ensure the balance between power production and consumption, and maintain the normal operation of the power grid;

[0141] Supply electricity continuously and stably according to the established load forecasting plan. Ensure the balance between electricity production and consumption and maintain the normal operation of the power grid. Regularly update the load forecasting model, adjust the power supply plan according to the actual situation, and improve the accuracy and reliability of power supply. At the same time, maintain communication with enterprises to understand the changes in their production plans and electricity demand, and further optimize power supply services.

[0142] In response to the surge in power demand, a distributed optimization algorithm is used to initiate intelligent power dispatching adjustments based on the established load forecast plan, while adjusting the power supply distribution in the remaining areas to optimize the power grid load;

[0143] In response to the surge in power demand, a distributed optimization algorithm is used to start intelligent power dispatching adjustments based on the established load forecast plan, and the power supply distribution in the remaining areas is adjusted at the same time. The steps to optimize the power grid load are as follows:

[0144] In the high-tech enterprise area, the power factor deviation index PFΔI and the instantaneous load fluctuation index I-LFX are obtained in real time through power monitoring equipment. Once a load surge is detected, it is necessary to determine whether to start scheduling, and the following judgment conditions are used for judgment;

[0145]

[0146] , where Trigger Adjustment is a trigger variable, which is used to determine whether it is necessary to trigger power dispatch adjustment. When the variable is equal to 1, the system will start power dispatch; when it is equal to 0, the system will not make adjustments. θ1 is the preset reference threshold of the power factor offset index PFΔI, and θ2 is the preset reference threshold of the instantaneous load fluctuation index I-LFX;

[0147] When the dispatch is triggered, the optimal power distribution between regions is solved to meet the surge demand at the lowest cost. The optimization goal is to reduce the power supply cost while reducing the load deviation to ensure the smooth operation of the power grid. The calculation expression is as follows:

[0148] ,

[0149] In the formula, min is the minimization objective function, and the optimization algorithm is used to find the variable combination that makes the entire expression achieve the minimum value. i is the unit electricity supply cost in region i, P i is the actual power supply in region i, represents the total power supply cost of each region, λ is the penalty coefficient, which is used to balance the impact of power supply cost and prediction deviation on the optimization target. is the forecast load of region i, λ is the penalty term for load forecast error, the purpose of which is to reduce the actual power supply P i Power supply forecast The deviation between them, N represents the total number of regions participating in the dispatch in the power grid system;

[0150] This objective function balances cost and load fluctuations, ensuring that the dispatch scheme is not only economically reasonable but also reduces the impact of forecast deviations on the power grid.

[0151] In the distributed optimization process, it is necessary to ensure the balance between power supply and demand. At the same time, the load in each area must meet the constraints. The power balance constraint and regional load constraint are set. The power balance constraint expression is as follows:

[0152] ,

[0153] In the formula, is the total power supply capacity in the system at the current moment;

[0154] The regional load constraint expression is as follows: In the formula, is the area i with the least load, is the area i is the maximum load;

[0155] Power balance constraints and regional load constraints ensure that there will be no imbalance in power supply and demand or regional load overload during the scheduling process.

[0156] Since power dispatching involves multiple regions, the distributed Lagrangian relaxation method is used to decompose the global optimization problem into several sub-problems and solve them in parallel. The calculation expression is as follows:

[0157] ,

[0158] In the formula, L(P i ,μ) is the Lagrangian function, which represents the objective function of power dispatch optimization. It is the cost and forecast error part of the power grid system, which calculates the power supply cost and its forecast load error in all regions. is the power balance constraint term, which ensures that the sum of power supply in all regions must be equal to the total power supply capacity of the system. μ is the Lagrange multiplier, which is used to impose constraints to ensure the power supply balance of the system.

[0159] Through distributed solving, each region independently calculates load distribution and coordinates at the system level to achieve optimization of the overall power grid.

[0160] After the dispatching plan is implemented, feedback is provided based on real-time data, and the power supply strategy is dynamically adjusted to ensure the stable operation of the power grid. The calculation expression is as follows: In the formula, is the adjusted power supply of region i, which is the final power supply allocated to the region after dynamic scheduling, ensuring that the power grid optimizes the power supply of each region in a timely manner according to the actual load changes to meet the new load demand. α is the scheduling coefficient, which is used to control the adjustment strength of the power supply of each region. This coefficient determines how each region shares the adjustment task when the total load of the system deviates. t is the actual total load of the system at the current moment, and is the total power demand obtained through real-time monitoring. is the predicted total load at the current moment;

[0161] like (actual load is higher than predicted), then A positive value indicates that the power supply needs to be increased. The power supply in each area will be appropriately increased according to the coefficient α.

[0162] like (actual load is higher than predicted), then A negative value indicates that power supply needs to be reduced. The power supply in each area will be appropriately reduced according to the coefficient α to avoid waste.

[0163] It is used to realize dynamic feedback scheduling of power system and adjust the power supply of each area in real time according to the difference between actual load and predicted load.

[0164] The present invention realizes accurate monitoring and intelligent analysis of regional power consumption through real-time power monitoring and feature extraction, combined with the evaluation capability of machine learning models. In particular, by analyzing the power factor offset index and the instantaneous load fluctuation index, it is possible to accurately determine whether there is a surge in power demand in the region. This capability enables the power system to quickly identify sudden power demands caused by network attacks or server expansion, and respond in a timely manner to avoid serious consequences such as network paralysis and business interruption caused by insufficient power supply. The intelligent evaluation mechanism of the scheme also ensures the dynamic adjustment of load forecasting, improves the flexibility of power management, enables the power grid to more accurately adapt to the rapid changes in corporate needs, and maintain the stable development of the regional economy and industry.

[0165] The present invention has formulated differentiated dispatching strategies for normal power demand and surge power demand. For normal demand, the load forecasting plan is used to maintain a stable power supply, ensure the balance between power production and consumption, and effectively avoid power waste and systematic power shortage. In the surge demand scenario, the scheme uses a distributed optimization algorithm to achieve intelligent power dispatching and adjustment. By optimizing the power supply distribution within the region and between adjacent regions, the load pressure in a single region is reduced to the maximum extent, avoiding the risk of power outages caused by overloaded power grids. This distributed intelligent dispatching not only improves the utilization efficiency of power resources, but also ensures the emergency power supply needs of enterprises when encountering sudden network attacks, provides stable power support for enterprises, and reduces operational risks and economic losses.

[0166] The above description is only by way of illustration of certain exemplary embodiments of the present invention. It is undoubted that those skilled in the art can modify the described embodiments in various ways without departing from the spirit and scope of the present invention. Therefore, the above drawings and descriptions are illustrative in nature and should not be construed as limiting the scope of protection of the claims of the present invention.

Claims

1. A power grid energy management optimization platform based on big data, characterized in that: The following steps are involved: First, deploy real-time power monitoring equipment in areas where high-tech industries are concentrated. Use the power monitoring equipment to obtain real-time power consumption data of enterprises and key power-consuming equipment. Establish a data interface to allow enterprises to independently upload power consumption data of internal key equipment, thereby improving the comprehensiveness and accuracy of the data. Extract features from the acquired power consumption data, and based on the extracted power consumption data features, use the pre-learned machine learning model to intelligently evaluate the power consumption data in the area under the monitoring window; Based on the evaluation results of the machine learning model, the regional power demand is divided into normal power demand and surge power demand; In response to normal power demand, we will continue to supply power stably according to the established load forecast plan, ensure the balance between power production and consumption, and maintain the normal operation of the power grid; In response to the surge in electricity demand, a distributed optimization algorithm is used to initiate intelligent power dispatching adjustments based on the established load forecast plan, while adjusting the power supply distribution in the remaining areas to optimize the grid load.

2. A power grid energy management optimization platform based on big data according to claim 1, characterized in that: The acquired power consumption data is subjected to feature extraction, and the extracted features include the degree of deviation of the power factor in a short period of time and the ratio of the instantaneous peak value to the average value of the power consumption in a short period of time. After acquisition, the degree of deviation of the power factor in a short period of time and the ratio of the instantaneous peak value to the average value of the power consumption in a short period of time are analyzed within the detection window to generate a power factor deviation index and an instantaneous load fluctuation index respectively, and the power factor deviation index and the instantaneous load fluctuation index are input into a pre-learned machine learning model, and a power consumption coefficient is generated through the machine learning model, and the changes in regional power consumption are intelligently evaluated through the power consumption coefficient.

3. The power grid energy management optimization platform based on big data according to claim 2 is characterized in that: In the detection window, the power factor deviation index is generated by analyzing the degree of deviation of the power factor in a short period of time. The specific steps are as follows: In the detection window, the instantaneous power factor is calculated from the instantaneous waveforms of current and voltage. The calculation expression is as follows: PF(t) = cos(E(t)) = cos(φ V (t)-φ I (t)), where PF(t) is the instantaneous power factor, which means the instantaneous power factor of the power system at time t, E(t) is the instantaneous phase angle difference, which means the phase difference between voltage and current at time t, cos(E(t)) is the instantaneous power factor, φ V (t) is the instantaneous phase angle of voltage, φ I (t) is the instantaneous phase angle of the current; Next, we define an indicator to quantify the power factor deviation in a short period of time, called the instantaneous deviation rate. The instantaneous deviation rate measures the deviation rate of the power factor in a very short period of time, and expresses the change of the power factor over time in the form of a derivative. The calculation expression is as follows: ， Where ΔPF(t) is the instantaneous power factor deviation rate, which indicates the deviation speed of the instantaneous power factor PF(t) at time t, that is, the instantaneous power factor deviation rate of the instantaneous power factor. is the derivative of the instantaneous power factor with time, It is the calculation process of instantaneous power factor deviation; In order to capture the overall intensity of the power factor deviation, the instantaneous power factor deviation rate ΔPF(t) is weighted and integrated, and the time weight function is introduced. The calculation expression is as follows: ， Where PF Shift Strength is the power factor shift strength, t0 and t1 are the detection window start time and detection window end time, W(t) is the time weight function, Next, a nonlinear offset discriminant function is defined to compare the offset degree of the power factor with its critical value to generate a function that measures the degree of abnormal deviation. The calculation expression is as follows: ， Where f(PF) is the nonlinear offset discriminant function, E ref is the reference phase angle, that is, the reference phase angle under normal circumstances, β is the weight coefficient, k is the nonlinear amplification coefficient, cos(E ref ) is the reference instantaneous power factor; The power factor offset index is generated based on the nonlinear offset discriminant function f(PF), and the calculation expression is as follows: PFΔI=ln(1+θ·f(PF)), where PFΔI is the power factor offset index and θ is the amplification factor used to adjust the sensitivity and range of the index.

4. The power grid energy management optimization platform based on big data according to claim 2 is characterized in that: In the detection window, the ratio of the instantaneous peak value to the average value of power consumption in a short period of time is analyzed to generate the instantaneous load fluctuation index. The specific steps are as follows: In the detection window, the current and voltage sampling values ​​are obtained in real time, and the obtained current sampling value is calibrated as I(t), and the voltage sampling value is calibrated as V(t). I(t) refers to the current sampling value at time t, and V(t) refers to the voltage sampling value at time t. At each time point t, the difference in instantaneous power change is calculated to reflect the sudden change trend of equipment power. The calculation expression is as follows: ΔP(t) = |I(t)·V(t)-I(t-Δt)·V(t-Δt)|, where ΔP(t) is the instantaneous change in power, indicating the instantaneous change in power at time point t, Δt is the sampling time interval, which is used to calculate the change between two adjacent time points, I(t-Δt) is the current sampling value at the previous time point, and V(t-Δt) is the voltage sampling value at the previous time point; In order to capture the cumulative fluctuation of the instantaneous change of power within the entire detection window, the cumulative absolute change function is used to avoid the mutual cancellation of positive and negative power fluctuations. The calculation expression is as follows: ， In the formula, C P is the cumulative value of power jumps within the detection window, indicating the total change of power fluctuations within the detection window, and M is the total number of sampling points within the detection window, reflecting the number of data points collected within the detection window; In order to accurately capture the dynamic change trend of the load, an exponential decay weight function is introduced to respond more sensitively to the latest power fluctuations, thereby generating an instantaneous load fluctuation index. The calculation expression is as follows: ， Where I-LFX is the instantaneous load fluctuation index, e is the natural base, β is the instantaneous load fluctuation index attenuation coefficient, which controls the speed of exponential attenuation, and Mt represents the distance between the sampling point and the current time.

5. The power grid energy management optimization platform based on big data according to claim 2 is characterized by: The power consumption coefficient generated by analyzing the power consumption data obtained under the monitoring window is compared and analyzed with the pre-set power consumption coefficient reference threshold, and the regional power demand is divided. The division results are as follows: If the power consumption coefficient is greater than or equal to a preset power consumption coefficient reference threshold, the regional power demand is classified as a surge power demand; If the power consumption coefficient is less than a preset power consumption coefficient reference threshold, the regional power demand is classified as normal power demand.

6. A power grid energy management optimization platform based on big data according to claim 5, characterized in that: In response to the surge in power demand, a distributed optimization algorithm is used to start intelligent power dispatching adjustments based on the established load forecast plan, and the power supply distribution in the remaining areas is adjusted at the same time. The steps to optimize the power grid load are as follows: In the high-tech enterprise area, the power factor deviation index PFΔI and the instantaneous load fluctuation index I-LFX are obtained in real time through power monitoring equipment. Once a load surge is detected, it is necessary to determine whether to start scheduling, and the following judgment conditions are used for judgment; ， Wherein, Trigger Adjustment is the trigger variable, θ1 is the preset reference threshold of the power factor deviation index PFΔI, and θ2 is the preset reference threshold of the instantaneous load fluctuation index I-LFX; When the dispatch is triggered, the optimal power distribution between regions is solved to meet the surge demand at the lowest cost. The calculation expression is as follows: ， In the formula, min is the minimization objective function, C i is the unit electricity supply cost in region i, P i is the actual power supply in region i, represents the total power supply cost of each region, λ is the penalty coefficient, is the forecast load of region i, is the penalty term for load forecast error, the purpose of which is to reduce the actual power supply P i Power supply forecast The deviation between them, N represents the total number of regions participating in the dispatch in the power grid system; In the distributed optimization process, it is necessary to ensure the balance between power supply and demand. At the same time, the load in each area must meet the constraints. The power balance constraint and regional load constraint are set. The power balance constraint expression is as follows: ， In the formula, is the total power supply capacity in the system at the current moment; The regional load constraint expression is as follows: In the formula, is the area i with the least load, is the area i is the maximum load; Since power dispatching involves multiple regions, the distributed Lagrangian relaxation method is used to decompose the global optimization problem into several sub-problems and solve them in parallel. The calculation expression is as follows: ， In the formula, L(P i ,μ) is the Lagrangian function, is the cost and forecast error part of the power grid system, which calculates the power supply cost and its forecast load error in all regions, μ is the power balance constraint term, μ is the Lagrange multiplier; After the dispatching plan is implemented, feedback is provided based on real-time data, and the power supply strategy is adjusted dynamically to ensure the stable operation of the power grid. The calculation expression is as follows: In the formula, is the adjusted power supply of region i, α is the scheduling coefficient, which is used to control the adjustment strength of the power supply of each region, P t is the actual total load of the system at the current moment, is the forecast total load at the current moment.

Images