CN-122022532-A - Water and electricity information intelligent management system and method based on data service bus

CN122022532ACN 122022532 ACN122022532 ACN 122022532ACN-122022532-A

Abstract

The invention discloses a data service bus-based intelligent management system and method for hydropower information, and relates to the technical field of data management, wherein the method comprises the following steps of acquiring real-time and historical hydropower information, setting a safety flow range, comparing real-time warehouse-in flow with the range, and accordingly triggering a low-flow early warning mechanism, flood control emergency response or optimizing a scheduling flow respectively; the method comprises the steps of building a neural network architecture, building a quantitative relation model between target power generation efficiency corresponding to expected load and a current water head, calculating deviation between actual power generation efficiency and target power generation efficiency, calculating performance weight of the generator set under the current working condition based on the current actual efficiency and the historical optimal efficiency of the generator set, healthy operation duration and total operation duration and failure times in unit time, and dynamically optimizing load distribution by combining the performance weight of the generator set and power grid requirements.

Inventors

LI LIN
LI YUANJUN
ZHU JIANG
HU JINGWEI
ZENG TIJIAN
LUO YU
XIAO JIAN
DU ZEXIN
SU QIAN

Assignees

贵州乌江水电开发有限责任公司

Dates

Publication Date: 20260512
Application Date: 20260414

Claims (10)

1. A hydropower information intelligent management method based on a data service bus is characterized by comprising the following steps: acquiring real-time and historical hydropower information, setting a safety flow range, comparing the real-time warehouse-in flow with the safety flow range, and accordingly triggering a low-flow early warning mechanism, flood control emergency response or optimizing a dispatching flow respectively; establishing a quantitative relation model between the target power generation efficiency corresponding to the expected load and the current water head by constructing a neural network model; calculating the deviation between the actual power generation efficiency and the target power generation efficiency; And calculating the performance weight of the generator set under the current working condition based on the current actual efficiency, the historical optimal efficiency, the healthy operation time length and the total operation time length of the generator set and the number of faults in unit time, and dynamically optimizing load distribution by combining the performance weight of the generator set and the power grid demand to determine the target power generation efficiency corresponding to the expected load of each generator set.
2. The intelligent management method of hydropower information based on the data service bus according to claim 1, wherein the method is characterized by obtaining real-time and historical hydropower information, setting a safety flow range, comparing the real-time warehouse-in flow with the safety flow range, and accordingly triggering a low-flow early warning mechanism, a flood control emergency response or an optimized scheduling flow respectively, and specifically comprises the following steps: through a deployed data service bus, the real-time and historical hydropower information which comes from various systems in a designated range and is based on various protocols is accessed, cleaned and integrated uniformly, wherein the real-time and historical hydropower information comprises hydrological resource data, electric power operation environment data, hydraulic equipment facility data, scheduling operation rule data and external demand information; Defining a safety flow range [ Q min ,Q max ], wherein Q min represents the lower limit of the set safety flow range, which is defined as alpha times of preset downstream ecological or water supply guarantee flow, alpha represents a safety lower limit regulating coefficient, Q max represents the upper limit of the set safety flow range, which is defined as beta times of safety flood discharge capacity of a reservoir under the current water level, and beta represents a safety upper limit regulating coefficient; The method comprises the steps of obtaining actual warehousing flow in real time through a data service bus, comparing the actual warehousing flow with a defined safe flow range, judging that incoming water is insufficient when the actual warehousing flow is smaller than the lower limit of the set safe flow range, triggering a low flow early warning mechanism, judging that flood risks exist when the actual warehousing flow is larger than the upper limit of the set safe flow range, triggering a flood control emergency response flow, judging that the warehousing flow is in a safe operation range if the actual warehousing flow is in the safe flow range, and executing an optimized scheduling flow.
3. The intelligent management method of hydroelectric information based on the data service bus according to claim 2, wherein the method is characterized by comprising the following specific steps of: extracting characteristics of the acquired hydropower information, including water head data, load data and power generation efficiency data; processing by adopting a normalization pretreatment coding mode, and eliminating dimension influence; Inputting the encoded data into an established neural network model fused with a full-connection layer and a convolution layer, wherein the full-connection layer is used for learning a global nonlinear relation among water head data, load data and power generation efficiency data, and the convolution layer is used for extracting local depth characteristics of a data sequence under different operation conditions; through learning and mapping of complex association modes among input data features, the established neural network model fused with the full-connection layer and the convolution layer outputs a target power generation efficiency quantification relation model corresponding to the expected load under the current water head.
4. The method for intelligently managing hydropower information based on the data service bus as set forth in claim 3, wherein the calculating of the deviation between the actual power generation efficiency and the target power generation efficiency comprises the following specific steps: Acquiring power generation efficiency, power generation flow and current water head through a data service bus, calculating current actual power generation efficiency, inputting the current water head and actual load into a constructed quantitative relation model, and acquiring target efficiency under current working conditions; calculating efficiency deviation, wherein the definition is shown as delta eta=eta 1-eta 0; Where Δη represents a deviation between the actual power generation efficiency and the target power generation efficiency, η1 represents the current actual power generation efficiency, and η0 represents the target power generation efficiency.
5. The intelligent management method of hydroelectric information based on a data service bus according to claim 4, wherein the method is characterized by calculating the performance weight of the generator set under the current working condition based on the current actual efficiency and the historical optimal efficiency, the healthy operation time length and the total operation time length of the generator set and the number of faults in unit time, dynamically optimizing load distribution by combining the performance weight of the generator set and the power grid demand, and determining the target power generation efficiency corresponding to the expected load of each generator set, and specifically comprises the following steps: Based on the real-time running state and the historical performance data of each generator set, calculating the performance weight of the target generator set under the current working condition, wherein the definition is shown as w i =（η（i）/η（0））*（T 1 /T 0 (1/f), w i represents the performance weight of the ith generator set, eta (i) represents the current actual efficiency of the ith generator set, eta (0) represents the historical standard efficiency of the ith generator set, T 1 represents the healthy running time of the ith generator set, T 0 represents the total running time of the ith generator set, and f represents the fault times in unit time of the ith generator set; The historical standard efficiency of the ith genset is defined as follows: Screening out the efficiency data of the first percent a with the highest efficiency value from the historical efficiency data of the ith generating set, and recording the efficiency data as a first efficiency data set, wherein a represents a proportion threshold value; Extracting the equipment characteristics of the generator set corresponding to the efficiency data contained in the first efficiency data set, and recording the equipment characteristics as { e1, e2, & gt, eM, and/or eM }, wherein eM represents the equipment characteristics of the generator set corresponding to the M-th efficiency data in the extracted first efficiency data set, and M represents the quantity of the efficiency data contained in the first efficiency data set; for the equipment characteristics of the generator set corresponding to the m-th efficiency data in the extracted first efficiency data set, finding out abnormal characteristics, and defining the abnormal characteristics as follows: The device characteristics of the generator set corresponding to the m-th efficiency data in the extracted first efficiency data set are recorded as { m1, m 2.. The number of mZ, & mZ }, mZ represents the Z-th characteristic in the device characteristics of the generator set corresponding to the m-th efficiency data in the extracted first efficiency data set, and Z represents the number of the device characteristics of the generator set corresponding to the m-th efficiency data in the extracted first efficiency data set, and the method specifically comprises the following steps: The first coefficient of mz is calculated, and the definition is shown as U1_z (mz) = (U1-U2)/U1, wherein U1 represents the maximum value of the z-th characteristic in the equipment characteristics of the generator set corresponding to the efficiency data contained in the M groups of first efficiency data sets, and U2 represents the minimum value of the z-th characteristic in the equipment characteristics of the generator set corresponding to the efficiency data contained in the M groups of first efficiency data sets; calculating a second coefficient of mz, defined as u2_z (mz) =1-u1_z (mz); Traversing the equipment characteristics of the generator set corresponding to the m-th efficiency data in the extracted first efficiency data set, and respectively calculating second coefficients of the equipment characteristics of the generator set corresponding to the m-th efficiency data in the Z extracted first efficiency data sets, wherein the second coefficients are denoted as { U2_1 (mz), U2_2 (mz),. Calculating a weighting coefficient of mz, wherein wz=U2_z (mz)/ΣU2_k (mz) is defined, and the value of k is 1 to Z; acquiring reference characteristics of the equipment characteristics of the generator set corresponding to the efficiency data contained in the extracted first efficiency data set; Respectively calculating the deviation between the characteristic of the equipment characteristic of the generator set corresponding to the m-th efficiency data in the extracted first efficiency data set and the reference characteristic of the equipment characteristic of the generator set corresponding to the efficiency data contained in the extracted first efficiency data set, and recording as { v1, v2, & gt, vZ }, wherein vZ represents the deviation between the z-th characteristic of the equipment characteristic of the generator set corresponding to the m-th efficiency data in the extracted first efficiency data set and the z-th characteristic in the reference characteristic of the equipment characteristic of the generator set corresponding to the efficiency data contained in the extracted first efficiency data set; calculating the deviation degree between the equipment characteristic of the generator set corresponding to the m-th efficiency data in the extracted first efficiency data set and the equipment characteristic of the generator set corresponding to the efficiency data contained in the extracted first efficiency data set, wherein Y=w1+w2+v2+ + wZ vZ; Acquiring a deviation threshold according to the historical data; Deleting the m-th efficiency data in the extracted first efficiency data set from the first efficiency data set when the deviation degree between the equipment characteristics of the generator set corresponding to the m-th efficiency data in the extracted first efficiency data set and the equipment characteristics of the generator set corresponding to the efficiency data contained in the extracted first efficiency data set is larger than a deviation degree threshold value; Taking average values of all efficiency values in the second efficiency data set as historical standard efficiency of the ith generating set; According to the performance weight of the generator set and the power grid demand, the load distribution is dynamically optimized, and the definition is as follows: P ᵢ,o =P t ×(W i /ΣW i )+ΔP i , wherein P ᵢ,o represents the expected load assigned to the ith genset, P t represents the total power generation demand of the hydropower station, and ΔP i represents the adjustment increment of the ith genset.
6. A data service bus-based water and electricity information intelligent management system is applied to the data service bus-based water and electricity information intelligent management method, which is characterized by comprising a data service bus module, a water and electricity information acquisition module, a power generation efficiency quantification model construction module and a load optimization module, wherein the data service bus module is used for integrating real-time and historical water and electricity information based on various protocols from various systems in a designated range, the water and electricity information acquisition module is used for acquiring the real-time and historical water and electricity information, setting a safe flow range, comparing the real-time warehousing flow with the range, triggering a low-flow early warning mechanism, flood control emergency response or optimizing a scheduling flow respectively according to the real-time and historical water and electricity information, the power generation efficiency quantification model construction module is used for establishing a quantification relation model between target power generation efficiency corresponding to an expected load and a current water head through building a neural network architecture, the load optimization module is used for calculating deviation between actual power generation efficiency and the target power generation efficiency, calculating performance weight under the current working condition of a generator set based on the current actual efficiency and the historical optimal efficiency, healthy running time and total running time and failure times in unit time, and determining the expected load performance weight of the generator set and the power generation unit corresponding to the expected load dynamic load distribution of the generator set.
7. The intelligent management system for hydropower information based on the data service bus according to claim 6, wherein the data service bus module comprises a multi-source data access unit and a standardization unit, the multi-source data access unit is used for uniformly accessing various systems from a specified range and is based on various protocols, and the standardization unit is used for eliminating noise in data and converting data from different sources into a standardized format through unified normalization and format processing.
8. The intelligent management system for hydropower information based on the data service bus, which is disclosed in claim 7, is characterized in that the hydropower information acquisition module comprises a hydropower information acquisition unit, a safe flow range definition unit and a flow matching unit, wherein the hydropower information acquisition unit is used for uniformly accessing, cleaning and integrating real-time and historical hydropower information based on various protocols from various systems in a designated range, the real-time and historical hydropower information comprises hydrological resource data, electric power operation environment data, hydraulic equipment facility data, dispatching operation rule data and external demand information, the safe flow range definition unit is used for defining a safe flow range, and the flow matching unit is used for comparing actual warehouse-in flow acquired in real time through the data service bus with the defined safe flow range, and accordingly triggering a low-flow early warning mechanism, a flood prevention emergency response or optimizing a dispatching flow respectively.
9. The intelligent management system for the hydroelectric information based on the data service bus is characterized in that the power generation efficiency quantification model construction module comprises a hydroelectric characteristic extraction unit, a preprocessing unit and a neural network construction unit, wherein the hydroelectric characteristic extraction unit is used for extracting characteristics of acquired hydroelectric information, including water head data, load data and power generation efficiency data, the preprocessing unit is used for processing in a normalization preprocessing coding mode to eliminate dimensional influence, and the neural network construction unit is used for inputting the coded data into an established neural network model integrating a full-connection layer and a convolution layer.
10. The intelligent management system for hydropower information based on the data service bus according to claim 9, wherein the load optimization module comprises an efficiency deviation calculation unit, a historical standard efficiency calculation unit, a unit performance weight calculation unit and a load distribution optimization unit, wherein the efficiency deviation calculation unit is used for calculating deviation between actual power generation efficiency and target power generation efficiency, the historical standard efficiency calculation unit is used for calculating historical standard efficiency of a target generator unit, the unit performance weight calculation unit is used for calculating performance weight of the target generator unit under current working conditions based on real-time running states and historical performance data of each generator unit, and the load distribution optimization unit is used for dynamically optimizing load distribution according to the performance weight of the generator unit and power grid requirements.

Description

Water and electricity information intelligent management system and method based on data service bus Technical Field The invention relates to the technical field of data management, in particular to a hydropower information intelligent management system and method based on a data service bus. Background Hydropower is used as clean low-carbon, safe and efficient renewable energy, is one of the core supports for energy structure transformation in China, and along with the large-scale development and intelligent demand improvement of hydropower engineering, the operation management of hydropower stations relates to multidimensional information such as hydrologic water resources, electric power operation, hydraulic equipment, scheduling rules and the like, the data sources are dispersed, the protocols are various, and the data cooperation and business linkage are needed to be realized through efficient information management means; However, when the traditional hydropower station management method is used for coping with complex operation scenes and multi-objective demands, obvious short plates exist, intelligent management requirements are difficult to meet, the problems that firstly, the integration capability of multi-source data is weak, data island problems exist, the hydrologic monitoring, electric power operation, equipment management, scheduling decision and other systems of the traditional hydropower station tend to independently operate, data formats are not uniform, protocols are not compatible, unified access and integration channels are not available, so that real-time and historical hydropower information data fragmentation is serious, secondly, the quantized matching precision of power generation efficiency and working conditions is insufficient, the power generation efficiency of the hydropower station is influenced by working condition parameters such as water head and load, but the traditional management method is difficult to capture complex relations among water head, load and power generation efficiency due to the fact that an empirical formula or a simple linear model is established, furthermore, the unit performance evaluation and load distribution lack scientificity, the traditional load distribution method is mostly adopted, and the actual performance difference of different generating units is not fully considered. Disclosure of Invention The invention aims to provide a hydropower information intelligent management system and method based on a data service bus, which are used for solving the problems in the prior art. In order to achieve the purpose, the invention provides the following technical scheme that the intelligent management method for the hydropower information based on the data service bus comprises the following steps: Acquiring real-time and historical hydropower information, setting a safety flow range, comparing the real-time warehouse-in flow with the interval, and accordingly triggering a low-flow early warning mechanism, flood control emergency response or optimizing a scheduling flow respectively; Establishing a quantitative relation model between the target power generation efficiency corresponding to the expected load and the current water head by constructing a neural network architecture; calculating the deviation between the actual power generation efficiency and the target power generation efficiency; And calculating the performance weight of the generator set under the current working condition based on the current actual efficiency, the historical optimal efficiency, the healthy operation time length and the total operation time length of the generator set and the number of faults in unit time, and dynamically optimizing load distribution by combining the performance weight of the generator set and the power grid demand to determine the target power generation efficiency corresponding to the expected load of each generator set. Acquiring real-time and historical hydropower information, setting a safety flow range, comparing the real-time warehouse-in flow with the interval, and accordingly triggering a low-flow early warning mechanism, flood control emergency response or optimizing a scheduling flow respectively, wherein the method comprises the following specific steps of: through a deployed data service bus, the real-time and historical hydropower information which comes from various systems in a designated range and is based on various protocols is accessed, cleaned and integrated uniformly, wherein the real-time and historical hydropower information comprises hydrological resource data, electric power operation environment data, hydraulic equipment facility data, scheduling operation rule data and external demand information; Defining a safety flow range [ Q min,Qmax ], wherein Q min represents the lower limit of the set safety flow range, which is defined as alpha times of preset downstream ecological or water supply guarantee flow, alpha represents a s