Power system data acquisition and analysis method and system based on wireless sensor network

Abstract

The present invention discloses a method and system for collecting and analyzing data of an electric power system based on a wireless sensor network, and relates to the field of energy regulation technology, including: evaluating the abnormal risk coefficient of power generation equipment, predicting the basic total power generation and the fluctuating total power generation in each region, and predicting the power demand of power-consuming equipment in each region; judging whether the basic total power generation of power generation equipment in each region meets the power demand of power-consuming equipment, and if so, it is allocated according to the near-end scheduling, and if not, it is judged whether the fluctuating total power generation of power generation equipment in each region meets the power demand of power-consuming equipment; when the fluctuating total power generation of power generation equipment in each region is allocated according to the near-end and cross-domain scheduling, a dynamic peak-shaving decision model is established, and a peak-shaving instruction is generated, which is applied to the active power generation equipment in each region. The advantages of the present invention are: realizing the dynamic peak-shaving decision of the power system and improving the stability of power supply.

Description

Technical Field

[0001] The present invention relates to the technical field of energy regulation and control, and in particular to a method and system for collecting and analyzing power system data based on a wireless sensor network. Background Art

[0002] The power system is a system that integrates distributed energy resources (such as wind power, solar power, energy storage systems, demand response, etc.) through information and communication technologies for centralized management and coordinated scheduling.

[0003] Since the power system cannot obtain key real-time data due to information transmission delays when making scheduling decisions, the accuracy and effectiveness of the peak-shaving strategy are reduced. Secondly, the independent peak-shaving strategy in a single area makes the applicability of the power system poor. Therefore, a dynamic scheduling and peak-shaving scheme is proposed, which can control the active and passive power generation equipment in the overall area on a large scale. Summary of the invention

[0004] In order to solve the above technical problems, a method and system for collecting and analyzing power system data based on wireless sensor networks are provided. This technical solution solves the above-mentioned problem that when the power system makes scheduling decisions, it is unable to obtain key real-time data due to information transmission delay, thereby reducing the accuracy and effectiveness of the peak-shaving strategy. Secondly, the independent peak-shaving strategy in a single area makes the applicability of the power system poor. Therefore, a dynamic scheduling and peak-shaving solution is proposed, which can control the active and passive power generation equipment in the overall area on a large scale.

[0005] In order to achieve the above purpose, the technical solution adopted by the present invention is:

[0006] A method for collecting and analyzing power system data based on a wireless sensor network, comprising:

[0007] Obtain the historical maintenance log of each power generation equipment, analyze the operating status of each power generation equipment based on the historical maintenance log, and evaluate the abnormal risk factor of the power generation equipment;

[0008] Based on the comprehensive factors affecting power generation equipment in each region and the abnormal risk coefficient of power generation equipment, the total basic power generation and fluctuating power generation in each region are predicted;

[0009] Obtain comprehensive data on factors affecting electrical equipment in each region and predict the power demand of electrical equipment in each region;

[0010] Determine whether the total basic power generation of power generation equipment in each region meets the power demand of power consumption equipment. If yes, allocate it according to the near-end dispatch. If no, determine whether the total fluctuating power generation of power generation equipment in each region meets the power demand of power consumption equipment. If yes, allocate it according to the near-end dispatch. If no, perform cross-domain dispatch.

[0011] If local and cross-domain dispatch and allocation are carried out according to the total fluctuating power generation of power generation equipment in each region, a dynamic peak-shaving decision model is established to generate peak-shaving instructions and apply them to the active power generation equipment in each region.

[0012] Preferably, obtaining the historical maintenance log of each power generation equipment, analyzing the operating status of each power generation equipment based on the historical maintenance log, and evaluating the abnormal risk factor of the power generation equipment specifically include:

[0013] Based on the historical maintenance logs of power generation equipment, the associated parameters that cause abnormal events in power generation equipment are screened out, and a set of associated parameters of abnormal events is established;

[0014] By establishing a set of abnormal event association parameters and training Logistic regression, a prediction model for abnormal power generation risk coefficient is obtained;

[0015] Collect the real-time operation data of each power generation equipment, extract the operation characteristic parameters of the power generation equipment in the real-time operation data, substitute them into the power generation abnormal risk coefficient prediction model, and use the abnormal risk coefficient of each power generation equipment as the output;

[0016] Among them, the prediction model expression of power generation abnormal risk coefficient is:

[0017]

[0018] Where P is the abnormal risk factor of the power generation equipment, X u is the uth operating characteristic parameter of the power generation equipment, β0, β1, β u , β U are all regression coefficients, and U is the total number of operating characteristics of power generation equipment.

[0019] Preferably, based on the comprehensive factor data affecting the power generation equipment in each region and the abnormal risk coefficient of the power generation equipment, predicting the total basic power generation and the total fluctuating power generation in each region specifically includes:

[0020] Based on meteorological data, obtain comprehensive factor data affecting power generation equipment; the comprehensive factor data includes: light radiation, wind direction and speed, and ambient temperature;

[0021] Carry out data preprocessing for comprehensive factors affecting power generation equipment;

[0022] Based on different power generation equipment in each region, statistical analysis is performed on the comprehensive factor data to screen out the factor data that affects different power generation equipment as the influencing factor characteristic parameters of the corresponding power generation equipment;

[0023] Based on multiple linear regression, a power forecasting model is constructed;

[0024] The characteristic parameters of the influencing factors of the corresponding power generation equipment are used as the input of the power prediction model, and the predicted power generation of the power generation equipment in each area is used as the output;

[0025] Based on the predicted power generation of power generation equipment in each region and the abnormal risk coefficient of power generation equipment, the total amount of fluctuating power generation in each region is calculated by fitting;

[0026] Filter out the fluctuating power generation in the total fluctuating power generation in each region to obtain the basic total power generation in each region;

[0027] Among them, the power prediction model expression of the power generation equipment is:

[0028] Y i =α0+α1F1+α i F i +…+α n F n

[0029] Where Y i is the predicted power generation of the ith power generation equipment, F i are the characteristic parameters of the influencing factors corresponding to the i-th power generation equipment, α0, α1, α i , α n are linear regression coefficients, n is the total number of power generation equipment;

[0030] The calculation of the total amount of fluctuating power generation in each area is specifically as follows:

[0031]

[0032] Where S is the total amount of fluctuating power generation in each region, P i is the abnormal risk coefficient of the i-th power generation equipment;

[0033] The basic total power generation calculation expression is:

[0034]

[0035] In the formula, S' is the total basic power generation in each region, Y' i is the basic power generation of the ith power generation equipment.

[0036] Preferably, obtaining comprehensive factor data affecting electrical equipment in each area and predicting the power demand of electrical equipment in each area specifically includes:

[0037] Based on the historical electricity demand data in each region, obtain comprehensive factor data that affects the electricity-consuming equipment; the comprehensive factor data includes: seasonal changes, holiday arrangements, and economic growth;

[0038] Carry out data preprocessing for comprehensive factors affecting electrical equipment;

[0039] Based on the electrical equipment in each region, statistical analysis is performed on the comprehensive factor data to screen out the factor data that affects the electrical equipment as the characteristic parameters of the influencing factors of the electrical equipment;

[0040] Based on multiple linear regression, a power consumption prediction model is constructed;

[0041] The characteristic parameters of the influencing factors of the power consumption equipment are used as the input of the power consumption prediction model, and the predicted power demand of the power consumption equipment in each area is used as the output;

[0042] Among them, the electricity consumption forecast model expression is:

[0043] D i =α0+α1H1+α j H j +…+α m H m

[0044] Where D i is the predicted power demand of the ith electrical equipment, H j are the characteristic parameters of the influencing factors corresponding to the jth electrical equipment, α0, α1, α j , α n are all linear regression coefficients, and m is the total number of electrical equipment.

[0045] Preferably, when the local and cross-domain dispatching and allocation are performed according to the total fluctuating power generation of power generation equipment in each region, a dynamic peak-shaving decision model is established to generate peak-shaving instructions, which are applied to active power generation equipment in each region, specifically including:

[0046] Based on the total fluctuating power generation in each region and the power demand of power-consuming equipment, the power supply duration of the basic power generation in the total fluctuating power generation is analyzed, and the consumption critical point of the basic power generation in each region is recorded as the power supply critical point;

[0047] The power supply duration of the total basic power generation is used as the time constraint of peak load regulation, and the power supply critical point is used as the peak load regulation decision constraint;

[0048] Construct a dynamic peak-shaving decision model;

[0049] Based on time constraints and decision constraints, the power demand of power-consuming equipment, the basic power generation of power generation equipment, and the fluctuating power generation are substituted into the dynamic peak-shaving decision model. The peak-shaving objectives are to minimize power shortages, maximize power supply stability, and minimize peak-shaving costs. Dynamic peak-shaving instructions are generated and sent to active power generation equipment in each area.

[0050] Among them, the dynamic peak load decision model expression is:

[0051]

[0052] Where D k (t) is the power demand of the kth region at time point t, S' k (t) is the basic total power generation of the kth region at the tth time point, S k (t) is the total fluctuating power generation of the kth region at the tth time point, V k (t) is the peak-shaving power generation of the kth region at the tth time point, C kl (t) is the total power dispatched from the kth region to the lth region at the tth time point, C lk (t) is the total power dispatched from the lth area to the kth area at the tth time point, T k is the basic power generation duration of the kth region, is the average value of the total basic power generation in the kth region, min(V k ) is the minimum peak-shaving power generation capacity of the kth region, max(V k ) is the maximum peak-shaving power generation of the kth region, and O is the total number of regions.

[0053] Furthermore, a power system data acquisition and analysis system based on a wireless sensor network is proposed, which is used to implement the power system data acquisition and analysis method based on a wireless sensor network as described above, including:

[0054] Risk assessment module: The risk assessment module is used to obtain the historical maintenance log of each power generation equipment, analyze the operating status of each power generation equipment based on the historical maintenance log, and assess the abnormal risk factor of the power generation equipment;

[0055] A power generation prediction module, the power generation prediction module is electrically connected to the risk assessment module, and the power generation prediction module is used to predict the total basic power generation and the total fluctuating power generation in each region based on the comprehensive factor data affecting the power generation equipment in each region and the abnormal risk coefficient of the power generation equipment;

[0056] The power consumption prediction module is used to obtain comprehensive factor data affecting power consumption equipment in each area and predict the power demand of power consumption equipment in each area;

[0057] A judgment module, the judgment module is electrically connected to the power generation prediction module and the power consumption prediction module, and the judgment module is used to judge whether the basic total power generation of the power generation equipment in each area meets the power demand of the power consumption equipment. If so, it is allocated according to the near-end scheduling. If not, it is judged whether the fluctuating total power generation of the power generation equipment in each area meets the power demand of the power consumption equipment. If so, it is allocated according to the near-end scheduling. If not, cross-domain scheduling is performed;

[0058] The dynamic peak-shaving module is electrically connected to the judgment module. The dynamic peak-shaving module is used to establish a dynamic peak-shaving decision model and generate peak-shaving instructions when performing proximal and cross-domain scheduling and allocation according to the total fluctuating power generation of power generation equipment in each area, and to apply them to the active power generation equipment in each area.

[0059] Optionally, the risk assessment module includes:

[0060] The collection unit, based on the historical maintenance log of the power generation equipment, screens out the associated parameters that cause abnormal events in the power generation equipment and establishes an abnormal event associated parameter collection;

[0061] The first model building unit uses the established abnormal event association parameter set to train Logistic regression to obtain a power generation abnormal risk coefficient prediction model;

[0062] The risk prediction unit collects the real-time operation data of each power generation equipment, extracts the operation characteristic parameters of the power generation equipment in the real-time operation data, substitutes them into the power generation abnormal risk coefficient prediction model, and takes the abnormal risk coefficient of each power generation equipment as the output.

[0063] Optionally, the electricity consumption prediction module includes:

[0064] The data acquisition unit obtains comprehensive factor data affecting power generation equipment based on meteorological data;

[0065] A preprocessing unit performs data preprocessing on comprehensive factors affecting power generation equipment;

[0066] The feature marking unit performs statistical analysis on the comprehensive factor data based on different power generation equipment in each region, and selects the factor data affecting different power generation equipment as the influencing factor feature parameters of the corresponding power generation equipment;

[0067] The second model building unit builds a power prediction model based on multiple linear regression;

[0068] The power generation prediction unit uses the characteristic parameters of the influencing factors of the corresponding power generation equipment as the input of the power prediction model and uses the predicted power generation of the power generation equipment in each area as the output;

[0069] The power generation correction unit calculates the total fluctuating power generation in each area based on the predicted power generation of the power generation equipment in each area and the abnormal risk coefficient of the power generation equipment;

[0070] The basic power generation unit selects the fluctuating power generation in the total fluctuating power generation in each area to obtain the basic total power generation in each area.

[0071] Optionally, the dynamic peak-shaving module includes:

[0072] The data analysis unit analyzes the power supply duration of the basic power generation in the total fluctuating power generation based on the total fluctuating power generation and the power demand of the power-consuming equipment in each region, and records the consumption critical point of the basic power generation in each region as the power supply critical point;

[0073] The condition constraint unit uses the available power supply time of the basic total power generation as the time constraint of peak load regulation and the power supply critical point as the peak load regulation decision constraint;

[0074] The third model building unit builds a dynamic peak load regulation decision model;

[0075] The dynamic peak-shaving unit, based on time constraints and decision constraints, substitutes the power demand of power-consuming equipment, the basic total power generation of power generation equipment, and the fluctuating total power generation into the dynamic peak-shaving decision model, takes minimizing power shortages, maximizing power supply stability, and minimizing peak-shaving costs as peak-shaving goals, generates dynamic peak-shaving instructions, and sends them to the active power generation equipment in each area.

[0076] Compared with the prior art, the present invention has the following beneficial effects:

[0077] The present invention proposes a data collection and analysis scheme for an electric power system based on a wireless sensor network. The total power generation is divided into a basic power generation amount and a fluctuating power generation amount based on the operating status of the power generation equipment. When the basic power generation amount satisfies the power-consuming equipment, the basic power generation amount is used for scheduling and allocation without peak load regulation. When the fluctuating power generation amount is used for scheduling and allocation, a peak load regulation instruction is generated based on a dynamic peak load regulation decision model to realize dynamic peak load regulation decision of the electric power system and improve the stability of power supply. BRIEF DESCRIPTION OF THE DRAWINGS

[0078] Figure 1 It is a flow chart of a method for data collection and analysis of power system based on wireless sensor network;

[0079] Figure 2 A flow chart of the method for evaluating the abnormal risk factor of power generation equipment;

[0080] Figure 3 A flow chart of the method for predicting the total basic power generation and the total fluctuating power generation in each region;

[0081] Figure 4 A flow chart of a method for predicting the power demand of electrical equipment in each area;

[0082] Figure 5 To establish a dynamic peak-shaving decision model, a flow chart of the peak-shaving instruction method is generated;

[0083] Figure 6 This is a framework diagram of a power system data acquisition and analysis system based on wireless sensor networks. DETAILED DESCRIPTION

[0084] The following description is used to disclose the present invention so that those skilled in the art can implement the present invention. The preferred embodiments described below are only examples, and those skilled in the art may think of other obvious variations.

[0085] Reference Figure 1 As shown, a method for collecting and analyzing power system data based on a wireless sensor network includes:

[0086] Obtain the historical maintenance log of each power generation equipment, analyze the operating status of each power generation equipment based on the historical maintenance log, and evaluate the abnormal risk factor of the power generation equipment;

[0087] Based on the comprehensive factors affecting power generation equipment in each region and the abnormal risk coefficient of power generation equipment, the total basic power generation and fluctuating power generation in each region are predicted;

[0088] Obtain comprehensive data on factors affecting electrical equipment in each region and predict the power demand of electrical equipment in each region;

[0089] Determine whether the total basic power generation of power generation equipment in each region meets the power demand of power consumption equipment. If yes, allocate it according to the near-end dispatch. If no, determine whether the total fluctuating power generation of power generation equipment in each region meets the power demand of power consumption equipment. If yes, allocate it according to the near-end dispatch. If no, perform cross-domain dispatch.

[0090] If local and cross-domain dispatch and allocation are carried out according to the total fluctuating power generation of power generation equipment in each region, a dynamic peak-shaving decision model is established to generate peak-shaving instructions and apply them to the active power generation equipment in each region.

[0091] This solution divides the total power generation into basic power generation and fluctuating power generation based on the operating status of the power generation equipment. When the basic power generation meets the power-consuming equipment, it is dispatched and allocated according to the basic power generation without peak load regulation. When it is dispatched and allocated according to the fluctuating power generation, peak load regulation instructions are generated based on the dynamic peak load regulation decision model to realize dynamic peak load regulation decisions of the power system and improve the stability of power supply.

[0092] Reference Figure 2As shown, obtaining the historical maintenance log of each power generation equipment, analyzing the operating status of each power generation equipment based on the historical maintenance log, and evaluating the abnormal risk factor of the power generation equipment specifically include:

[0093] Based on the historical maintenance logs of power generation equipment, the associated parameters that cause abnormal events in power generation equipment are screened out, and a set of associated parameters of abnormal events is established;

[0094] By establishing a set of abnormal event association parameters and training Logistic regression, a prediction model for abnormal power generation risk coefficient is obtained;

[0095] Collect the real-time operation data of each power generation equipment, extract the operation characteristic parameters of the power generation equipment in the real-time operation data, substitute them into the power generation abnormal risk coefficient prediction model, and use the abnormal risk coefficient of each power generation equipment as the output;

[0096] Among them, the prediction model expression of power generation abnormal risk coefficient is:

[0097]

[0098] Where P is the abnormal risk factor of the power generation equipment, X u is the uth operating characteristic parameter of the power generation equipment, β0, β1, β u , β U are all regression coefficients, and U is the total number of operating characteristics of power generation equipment.

[0099] It is understandable that for the power generation abnormal risk factor prediction model, the model can be solved by the maximum likelihood function or the minimum loss function to obtain the optimal regression coefficient of each characteristic parameter, which will not be described in detail here.

[0100] Reference Figure 3 As shown in the figure, based on the comprehensive factor data affecting power generation equipment in each region and the abnormal risk coefficient of power generation equipment, the total basic power generation and fluctuating power generation in each region are predicted to include:

[0101] Based on meteorological data, obtain comprehensive factor data affecting power generation equipment; the comprehensive factor data includes: light radiation, wind direction and speed, and ambient temperature;

[0102] Carry out data preprocessing for comprehensive factors affecting power generation equipment;

[0103] Based on different power generation equipment in each region, statistical analysis is performed on the comprehensive factor data to screen out the factor data that affects different power generation equipment as the influencing factor characteristic parameters of the corresponding power generation equipment;

[0104] Based on multiple linear regression, a power forecasting model is constructed;

[0105] The characteristic parameters of the influencing factors of the corresponding power generation equipment are used as the input of the power prediction model, and the predicted power generation of the power generation equipment in each area is used as the output;

[0106] Based on the predicted power generation of power generation equipment in each region and the abnormal risk coefficient of power generation equipment, the total amount of fluctuating power generation in each region is calculated by fitting;

[0107] Filter out the fluctuating power generation in the total fluctuating power generation in each region to obtain the basic total power generation in each region;

[0108] Among them, the power prediction model expression of the power generation equipment is:

[0109] Y i =α0+α1F1+α i F i +…+α n F n

[0110] Where Y i is the predicted power generation of the ith power generation equipment, F i are the characteristic parameters of the influencing factors corresponding to the i-th power generation equipment, α0, α1, α i , α n are linear regression coefficients, n is the total number of power generation equipment;

[0111] The calculation of the total amount of fluctuating power generation in each area is specifically as follows:

[0112]

[0113] Where S is the total amount of fluctuating power generation in each region, P i is the abnormal risk coefficient of the i-th power generation equipment;

[0114] The basic total power generation calculation expression is:

[0115]

[0116] In the formula, S' is the total basic power generation in each region, Y' i is the basic power generation of the ith power generation equipment.

[0117] It is understandable that since the total power generation of power generation equipment is usually fluctuating due to its own abnormal risk interference, the total power generation of each power generation equipment is divided into basic total power generation and fluctuating total power generation. When supplying power, the basic total power generation is given priority to ensure the stability of power supply. The fluctuating total power generation, due to its instability, provides a reference value for subsequent targeted peak regulation, thereby reducing resource waste caused by excessive peak regulation.

[0118] Reference Figure 4As shown, the comprehensive factor data affecting the electrical equipment in each area is obtained, and the power demand of the electrical equipment in each area is predicted, including:

[0119] Based on the historical electricity demand data in each region, obtain comprehensive factor data affecting the electricity-consuming equipment; the comprehensive factor data includes: seasonal changes, holiday arrangements, and economic growth;

[0120] Carry out data preprocessing for comprehensive factors affecting electrical equipment;

[0121] Based on the electrical equipment in each region, the comprehensive factor data is statistically analyzed to screen out the factor data that affects the electrical equipment as the characteristic parameters of the influencing factors of the electrical equipment;

[0122] Based on multiple linear regression, a power consumption prediction model is constructed;

[0123] The characteristic parameters of the influencing factors of the power consumption equipment are used as the input of the power consumption prediction model, and the predicted power demand of the power consumption equipment in each area is used as the output;

[0124] Among them, the electricity consumption forecast model expression is:

[0125] D i =α0+α1H1+α j H j +…+α m H m

[0126] Where D i is the predicted power demand of the i-th electrical equipment, H j are the characteristic parameters of the influencing factors corresponding to the jth electrical equipment, α0, α1, α j , α n are all linear regression coefficients, and m is the total number of electrical equipment.

[0127] Reference Figure 5 As shown in the figure, if the local and cross-domain dispatching and allocation are carried out according to the total fluctuating power generation of power generation equipment in each region, a dynamic peak-shaving decision model is established to generate peak-shaving instructions, which are applied to the active power generation equipment in each region, including:

[0128] Based on the total fluctuating power generation in each region and the power demand of power-consuming equipment, the power supply duration of the basic power generation in the total fluctuating power generation is analyzed, and the consumption critical point of the basic power generation in each region is recorded as the power supply critical point;

[0129] The available power supply duration of the total basic power generation is used as the time constraint for peak load regulation, and the power supply critical point is used as the peak load regulation decision constraint;

[0130] Construct a dynamic peak-shaving decision model;

[0131] Based on time constraints and decision constraints, the power demand of power-consuming equipment, the basic power generation of power generation equipment, and the fluctuating power generation are substituted into the dynamic peak-shaving decision model. The peak-shaving objectives are to minimize power shortages, maximize power supply stability, and minimize peak-shaving costs. Dynamic peak-shaving instructions are generated and sent to active power generation equipment in each area.

[0132] Among them, the dynamic peak load decision model expression is:

[0133]

[0134] Where D k (t) is the power demand of the kth region at time point t, S' k (t) is the basic total power generation of the kth region at the tth time point, S k (t) is the total fluctuating power generation of the kth region at the tth time point, V k (t) is the peak-shaving power generation of the kth region at the tth time point, C kl (t) is the total power dispatched from the kth region to the lth region at the tth time point, C lk (t) is the total power dispatched from the lth area to the kth area at the tth time point, T k is the basic power generation duration of the kth region, is the average value of the total basic power generation in the kth region, min(V k ) is the minimum peak-shaving power generation capacity of the kth region, max(V k ) is the maximum peak-shaving power generation of the kth region, and O is the total number of regions.

[0135] It should be noted that The purpose of the formula is to constrain the balance between supply and demand and ensure that the power demand of each region in each time period is met through local power generation and cross-regional power dispatch. The purpose of the formula is to constrain the peak-shaving time, to ensure that the total power supply (including basic power generation, peak-shaving power generation and cross-regional power dispatch) of each region within a period of time (T time points) does not exceed the average value of the basic power generation in the period multiplied by the basic power generation time, to limit the total amount of peak-shaving power generation, so as to avoid oversupply or undersupply of the power system in a short period of time, |V| kl (t)≤R kl The purpose of the formula is to constrain transmission and ensure that the transmission and generation facilities in the power system operate within their carrying capacity to prevent network overload, min (V k )≤V k (t)≤max(V k) The purpose of the formula is to constrain power generation to ensure that the peak-shaving power generation in each area is between the pre-set minimum and maximum values, so as to maintain the stable operation of power generation facilities and meet scheduling requirements and avoid excessive peak-shaving.

[0136] Reference Figure 6 As shown, based on the same inventive concept of a power system data acquisition and analysis method based on a wireless sensor network, a power system data acquisition and analysis system based on a wireless sensor network is proposed, comprising:

[0137] Risk assessment module: The risk assessment module is used to obtain the historical maintenance log of each power generation equipment, analyze the operating status of each power generation equipment based on the historical maintenance log, and assess the abnormal risk factor of the power generation equipment;

[0138] A power generation prediction module, the power generation prediction module is electrically connected to the risk assessment module, and the power generation prediction module is used to predict the total basic power generation and the total fluctuating power generation in each region based on the comprehensive factor data affecting the power generation equipment in each region and the abnormal risk coefficient of the power generation equipment;

[0139] The power consumption prediction module is used to obtain comprehensive factor data affecting power consumption equipment in each area and predict the power demand of power consumption equipment in each area;

[0140] A judgment module, the judgment module is electrically connected to the power generation prediction module and the power consumption prediction module, and the judgment module is used to judge whether the basic total power generation of the power generation equipment in each area meets the power demand of the power consumption equipment. If so, it is allocated according to the near-end scheduling. If not, it is judged whether the fluctuating total power generation of the power generation equipment in each area meets the power demand of the power consumption equipment. If so, it is allocated according to the near-end scheduling. If not, cross-domain scheduling is performed;

[0141] The dynamic peak-shaving module is electrically connected to the judgment module. The dynamic peak-shaving module is used to establish a dynamic peak-shaving decision model and generate peak-shaving instructions when performing proximal and cross-domain scheduling and allocation according to the total fluctuating power generation of power generation equipment in each area, and to apply them to the active power generation equipment in each area.

[0142] The risk assessment module includes:

[0143] The collection unit, based on the historical maintenance log of the power generation equipment, screens out the associated parameters that cause abnormal events in the power generation equipment and establishes an abnormal event associated parameter collection;

[0144] The first model building unit uses the established abnormal event association parameter set to train Logistic regression to obtain a power generation abnormal risk coefficient prediction model;

[0145] The risk prediction unit collects the real-time operation data of each power generation equipment, extracts the operation characteristic parameters of the power generation equipment in the real-time operation data, substitutes them into the power generation abnormal risk coefficient prediction model, and takes the abnormal risk coefficient of each power generation equipment as the output.

[0146] The electricity consumption prediction module includes:

[0147] The data acquisition unit obtains comprehensive factor data affecting power generation equipment based on meteorological data;

[0148] A preprocessing unit performs data preprocessing on comprehensive factors affecting power generation equipment;

[0149] The feature marking unit performs statistical analysis on the comprehensive factor data based on different power generation equipment in each region, and selects the factor data affecting different power generation equipment as the influencing factor feature parameters of the corresponding power generation equipment;

[0150] The second model building unit builds a power prediction model based on multiple linear regression;

[0151] The power generation prediction unit uses the characteristic parameters of the influencing factors of the corresponding power generation equipment as the input of the power prediction model and uses the predicted power generation of the power generation equipment in each area as the output;

[0152] The power generation correction unit calculates the total fluctuating power generation in each area based on the predicted power generation of the power generation equipment in each area and the abnormal risk coefficient of the power generation equipment;

[0153] The basic power generation unit selects the fluctuating power generation in the total fluctuating power generation in each area to obtain the basic total power generation in each area.

[0154] The dynamic peak-shaving module includes:

[0155] The data analysis unit analyzes the power supply duration of the basic power generation in the total fluctuating power generation based on the total fluctuating power generation and the power demand of the power-consuming equipment in each region, and records the consumption critical point of the basic power generation in each region as the power supply critical point;

[0156] The condition constraint unit uses the available power supply time of the basic total power generation as the time constraint of peak load regulation and the power supply critical point as the peak load regulation decision constraint;

[0157] The third model building unit builds a dynamic peak load regulation decision model;

[0158] The dynamic peak-shaving unit, based on time constraints and decision constraints, substitutes the power demand of power-consuming equipment, the basic total power generation of power generation equipment, and the fluctuating total power generation into the dynamic peak-shaving decision model, takes minimizing power shortages, maximizing power supply stability, and minimizing peak-shaving costs as peak-shaving goals, generates dynamic peak-shaving instructions, and sends them to the active power generation equipment in each area.

[0159] The use process of a power system data acquisition and analysis system based on wireless sensor networks is as follows:

[0160] Step 1: Based on the historical maintenance log of the power generation equipment, the associated parameters that cause abnormal events in the power generation equipment are screened out, and a set of associated parameters of the abnormal events is established;

[0161] Step 2: Use the established abnormal event association parameter set to train Logistic regression and obtain a prediction model for abnormal power generation risk coefficient;

[0162] Step 3: Collect the real-time operation data of each power generation equipment, extract the operation characteristic parameters of the power generation equipment in the real-time operation data, substitute them into the power generation abnormal risk coefficient prediction model, and use the abnormal risk coefficient of each power generation equipment as the output;

[0163] Step 4: Based on meteorological data, obtain comprehensive factor data affecting power generation equipment;

[0164] Step 5: Preprocess the data of comprehensive factors affecting power generation equipment;

[0165] Step 6: Based on different power generation equipment in each region, statistical analysis is performed on the comprehensive factor data to screen out the factor data that affects different power generation equipment as the influencing factor characteristic parameters of the corresponding power generation equipment;

[0166] Step 7: Construct a power forecasting model based on multiple linear regression;

[0167] Step 8: The characteristic parameters of the influencing factors of the corresponding power generation equipment are used as the input of the power prediction model, and the predicted power generation of the power generation equipment in each area is used as the output;

[0168] Step 9: Based on the predicted power generation of power generation equipment in each region and the abnormal risk coefficient of power generation equipment, the total amount of fluctuating power generation in each region is calculated by fitting;

[0169] Step 10: Filter out the fluctuating power generation in the total fluctuating power generation in each region to obtain the basic total power generation in each region;

[0170] Step 11: Obtain comprehensive factor data that affects electrical equipment in each area, and predict the power demand of electrical equipment in each area;

[0171] Step 12: The judgment module is electrically connected to the power generation prediction module and the power consumption prediction module. The judgment module is used to judge whether the basic total power generation of the power generation equipment in each area meets the power demand of the power consumption equipment. If so, it is allocated according to the near-end scheduling. If not, it is judged whether the fluctuating total power generation of the power generation equipment in each area meets the power demand of the power consumption equipment. If so, it is allocated according to the near-end scheduling. If not, cross-domain scheduling is performed;

[0172] Step 13: Based on the total fluctuating power generation in each region and the power demand of power-consuming equipment, analyze the power supply duration of the basic power generation in the total fluctuating power generation, and record the consumption critical point of the basic power generation in each region as the power supply critical point;

[0173] Step 14: Taking the available power supply duration of the basic total power generation as the time constraint condition for peak load regulation, and taking the power supply critical point as the peak load regulation decision constraint condition;

[0174] Step 15: Construct a dynamic peak load regulation decision model;

[0175] Step 16: Based on the time constraints and decision constraints, the power demand of the power-consuming equipment, the basic power generation of the power generation equipment, and the fluctuating power generation are substituted into the dynamic peak-shaving decision model, and the peak-shaving goals are to minimize the power shortage, maximize the power supply stability, and minimize the peak-shaving cost. Dynamic peak-shaving instructions are generated and sent to the active power generation equipment in each area.

[0176] To sum up, the advantages of the present invention are: based on the operating status of the power generation equipment, the total power generation is divided into the basic power generation and the fluctuating power generation. When the basic power generation meets the power-consuming equipment, it is dispatched and allocated according to the basic power generation without peak load regulation. When it is dispatched and allocated according to the fluctuating power generation, a peak load regulation instruction is generated based on the dynamic peak load regulation decision model to realize the dynamic peak load regulation decision of the power system and improve the stability of power supply.

[0177] The above shows and describes the basic principles, main features and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited to the above embodiments. The above embodiments and descriptions only describe the principles of the present invention. The present invention may be subject to various changes and improvements without departing from the spirit and scope of the present invention. These changes and improvements fall within the scope of the present invention. The scope of protection claimed by the present invention is defined by the attached claims and their equivalents.

Claims

1. A method for collecting and analyzing power system data based on wireless sensor networks, characterized in that: include: Obtain the historical maintenance log of each power generation equipment, analyze the operating status of each power generation equipment based on the historical maintenance log, and evaluate the abnormal risk factor of the power generation equipment; Based on the comprehensive factors affecting power generation equipment in each region and the abnormal risk coefficient of power generation equipment, the total basic power generation and fluctuating power generation in each region are predicted; Obtain comprehensive data on factors affecting electrical equipment in each region and predict the power demand of electrical equipment in each region; Determine whether the total basic power generation of power generation equipment in each region meets the power demand of power consumption equipment. If yes, allocate it according to the near-end dispatch. If no, determine whether the total fluctuating power generation of power generation equipment in each region meets the power demand of power consumption equipment. If yes, allocate it according to the near-end dispatch. If no, perform cross-domain dispatch. If the local and cross-domain dispatching allocation is carried out according to the total fluctuating power generation of power generation equipment in each region, a dynamic peak-shaving decision model is established to generate peak-shaving instructions and apply them to the active power generation equipment in each region; The process of obtaining the historical maintenance log of each power generation equipment, analyzing the operating status of each power generation equipment based on the historical maintenance log, and evaluating the abnormal risk factor of the power generation equipment specifically includes: Based on the historical maintenance logs of power generation equipment, the associated parameters that cause abnormal events in power generation equipment are screened out, and a set of associated parameters of abnormal events is established; By establishing a set of abnormal event association parameters and training Logistic regression, a prediction model for abnormal power generation risk coefficient is obtained; Collect the real-time operation data of each power generation equipment, extract the operation characteristic parameters of the power generation equipment in the real-time operation data, substitute them into the power generation abnormal risk coefficient prediction model, and use the abnormal risk coefficient of each power generation equipment as the output; Among them, the prediction model expression of power generation abnormal risk coefficient is: In the formula, is the abnormal risk factor of the power generation equipment, For power generation equipment operating characteristic parameters, , , , are regression coefficients, is the total number of operating characteristics of power generation equipment; Based on the comprehensive factors affecting power generation equipment in each region and the abnormal risk coefficient of power generation equipment, the total basic power generation and fluctuating power generation in each region are predicted to include: Based on meteorological data, obtain comprehensive factor data affecting power generation equipment; the comprehensive factor data includes: light radiation, wind direction and speed, and ambient temperature; Carry out data preprocessing for comprehensive factors affecting power generation equipment; Based on different power generation equipment in each region, statistical analysis is performed on the comprehensive factor data to screen out the factor data that affects different power generation equipment as the influencing factor characteristic parameters of the corresponding power generation equipment; Based on multiple linear regression, a power forecasting model is constructed; The characteristic parameters of the influencing factors of the corresponding power generation equipment are used as the input of the power prediction model, and the predicted power generation of the power generation equipment in each area is used as the output; Based on the predicted power generation of power generation equipment in each region and the abnormal risk coefficient of power generation equipment, the total amount of fluctuating power generation in each region is calculated by fitting; Filter out the fluctuating power generation in the total fluctuating power generation in each region to obtain the basic total power generation in each region; Among them, the power prediction model expression of the power generation equipment is: In the formula, For the The predicted power generation of each power generation equipment, For the corresponding The characteristic parameters of the influencing factors of each power generation equipment, , , , are linear regression coefficients, is the total number of power generation equipment; The calculation of the total amount of fluctuating power generation in each area is specifically as follows: In the formula, is the total amount of fluctuating power generation in each region, is the abnormal risk coefficient of the i-th power generation equipment; The basic total power generation calculation expression is: In the formula, is the total basic power generation in each region, For the Basic power generation capacity of each power generation equipment; Obtain comprehensive data on factors affecting electrical equipment in each region and predict the power demand of electrical equipment in each region, including: Based on the historical electricity demand data in each region, obtain comprehensive factor data affecting the electricity-consuming equipment; the comprehensive factor data includes: seasonal changes, holiday arrangements, and economic growth; Carry out data preprocessing for comprehensive factors affecting electrical equipment; Based on the electrical equipment in each region, the comprehensive factor data is statistically analyzed to screen out the factor data that affects the electrical equipment as the characteristic parameters of the influencing factors of the electrical equipment; Based on multiple linear regression, a power consumption prediction model is constructed; The characteristic parameters of the influencing factors of the power consumption equipment are used as the input of the power consumption prediction model, and the predicted power demand of the power consumption equipment in each area is used as the output; Among them, the electricity consumption forecast model expression is: In the formula, For the The predicted power demand of each power-consuming device, For the corresponding The characteristic parameters of the influencing factors of each electrical equipment, , , , are linear regression coefficients, is the total number of electrical equipment; If the local and cross-domain dispatching and allocation is carried out according to the total fluctuating power generation of power generation equipment in each region, a dynamic peak-shaving decision model is established to generate peak-shaving instructions, which are applied to the active power generation equipment in each region, including: Based on the total fluctuating power generation in each region and the power demand of power-consuming equipment, the power supply duration of the basic power generation in the total fluctuating power generation is analyzed, and the consumption critical point of the basic power generation in each region is recorded as the power supply critical point; The power supply duration of the total basic power generation is used as the time constraint of peak load regulation, and the power supply critical point is used as the peak load regulation decision constraint; Construct a dynamic peak-shaving decision model; Based on time constraints and decision constraints, the power demand of power-consuming equipment, the basic power generation of power generation equipment, and the fluctuating power generation are substituted into the dynamic peak-shaving decision model. The peak-shaving objectives are to minimize power shortages, maximize power supply stability, and minimize peak-shaving costs. Dynamic peak-shaving instructions are generated and sent to active power generation equipment in each area. The dynamic peak load decision model expression is: In the formula, is the power demand of the kth region at the tth time point, is the basic total power generation of the kth region at the tth time point, is the total fluctuating power generation of the kth region at the tth time point, is the peak-shaving power generation of the kth region at the tth time point, is the total power dispatched from the kth region to the lth region at the tth time point, is the total power dispatched from the lth area to the kth area at the tth time point, is the basic power generation duration of the kth region, is the average value of the total basic power generation in the kth region, is the minimum peak-shaving power generation capacity of the kth region, is the maximum peak-shaving power generation of the kth region, and O is the total number of regions.

2. A power system data acquisition and analysis system based on wireless sensor networks, characterized in that: The method for collecting and analyzing power system data based on a wireless sensor network as claimed in claim 1 comprises: Risk assessment module: The risk assessment module is used to obtain the historical maintenance log of each power generation equipment, analyze the operating status of each power generation equipment based on the historical maintenance log, and assess the abnormal risk factor of the power generation equipment; A power generation prediction module, the power generation prediction module is electrically connected to the risk assessment module, and the power generation prediction module is used to predict the total basic power generation and the total fluctuating power generation in each region based on the comprehensive factor data affecting the power generation equipment in each region and the abnormal risk coefficient of the power generation equipment; The power consumption prediction module is used to obtain comprehensive factor data affecting power consumption equipment in each area and predict the power demand of power consumption equipment in each area; A judgment module, the judgment module is electrically connected to the power generation prediction module and the power consumption prediction module, and the judgment module is used to judge whether the basic total power generation of the power generation equipment in each area meets the power demand of the power consumption equipment. If so, it is allocated according to the near-end scheduling. If not, it is judged whether the fluctuating total power generation of the power generation equipment in each area meets the power demand of the power consumption equipment. If so, it is allocated according to the near-end scheduling. If not, cross-domain scheduling is performed; The dynamic peak-shaving module is electrically connected to the judgment module. The dynamic peak-shaving module is used to establish a dynamic peak-shaving decision model and generate peak-shaving instructions when performing proximal and cross-domain scheduling and allocation according to the total fluctuating power generation of power generation equipment in each area, and to apply them to the active power generation equipment in each area.

3. The power system data acquisition and analysis system based on wireless sensor network according to claim 2 is characterized in that: The risk assessment module includes: The collection unit, based on the historical maintenance log of the power generation equipment, screens out the associated parameters that cause abnormal events in the power generation equipment and establishes an abnormal event associated parameter collection; The first model building unit uses the established abnormal event association parameter set to train Logistic regression to obtain a power generation abnormal risk coefficient prediction model; The risk prediction unit collects the real-time operation data of each power generation equipment, extracts the operation characteristic parameters of the power generation equipment in the real-time operation data, substitutes them into the power generation abnormal risk coefficient prediction model, and takes the abnormal risk coefficient of each power generation equipment as the output.

4. The power system data acquisition and analysis system based on wireless sensor network according to claim 3 is characterized in that: The electricity consumption prediction module includes: The data acquisition unit obtains comprehensive factor data affecting power generation equipment based on meteorological data; A preprocessing unit performs data preprocessing on comprehensive factors affecting power generation equipment; The feature marking unit performs statistical analysis on the comprehensive factor data based on different power generation equipment in each region, and selects the factor data affecting different power generation equipment as the influencing factor feature parameters of the corresponding power generation equipment; The second model building unit builds a power prediction model based on multiple linear regression; The power generation prediction unit uses the characteristic parameters of the influencing factors of the corresponding power generation equipment as the input of the power prediction model and uses the predicted power generation of the power generation equipment in each area as the output; The power generation correction unit calculates the total fluctuating power generation in each area based on the predicted power generation of the power generation equipment in each area and the abnormal risk coefficient of the power generation equipment; The basic power generation unit selects the fluctuating power generation in the total fluctuating power generation in each area to obtain the basic total power generation in each area.

5. The power system data acquisition and analysis system based on wireless sensor network according to claim 4 is characterized in that: The dynamic peak-shaving module includes: The data analysis unit analyzes the power supply duration of the basic power generation in the total fluctuating power generation based on the total fluctuating power generation and the power demand of the power-consuming equipment in each region, and records the consumption critical point of the basic power generation in each region as the power supply critical point; The condition constraint unit uses the available power supply time of the basic total power generation as the time constraint of peak load regulation and the power supply critical point as the peak load regulation decision constraint; The third model building unit builds a dynamic peak load regulation decision model; The dynamic peak-shaving unit, based on time constraints and decision constraints, substitutes the power demand of power-consuming equipment, the basic total power generation of power generation equipment, and the fluctuating total power generation into the dynamic peak-shaving decision model, takes minimizing power shortages, maximizing power supply stability, and minimizing peak-shaving costs as peak-shaving goals, generates dynamic peak-shaving instructions, and sends them to the active power generation equipment in each area.

Images