Power grid energy scheduling method and system based on multi-source data fusion

Abstract

The invention discloses a power grid energy scheduling method and system based on multi-source data fusion, and relates to the technical field of power grid energy scheduling. The method comprises the following steps: S1, acquiring hydroelectric environment data, photovoltaic environment data and load data of a target power grid region; s2, generating a hydropower output constraint condition and a photovoltaic efficiency correction condition; s3, performing time alignment on the preprocessed hydropower output data and photovoltaic output data through a dynamic time warping algorithm, and generating a fusion feature vector containing environmental constraints; and S4, taking the fusion feature vector as input, constructing a multi-target optimization model in combination with the hydropower output constraint condition and the photovoltaic efficiency correction condition, and solving by adopting a rolling optimization algorithm to obtain a scheduling scheme comprising a hydropower output strategy, a photovoltaic output strategy and a thermal power peak regulation strategy. According to the method, aiming at the problem of power grid dispatching in the winter dry season in the high-altitude mountainous area, the energy dispatching accuracy under the environmental constraint is remarkably improved through multi-source data fusion and a dynamic coupling model.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of power grid energy scheduling, in particular to a power grid energy scheduling method and system based on multi-source data fusion. BACKGROUND

[0002] In the high-altitude mountainous power grid, the winter dry season faces unique energy scheduling challenges: river ice jam causes the water capacity of hydropower stations to decrease significantly, and the light transmittance of photovoltaic components is reduced due to morning fog weather, both of which cause the mismatch between energy supply side fluctuation and load side heating load pulse demand. Such power grid has the characteristics of high proportion of hydropower and distributed photovoltaic access, and the winter heating load is affected by the climate and shows high-frequency fluctuation characteristics.

[0003] The prior art does not establish a real-time coupling mechanism of river ice jam degree and hydropower output, and morning fog parameters and photovoltaic efficiency, resulting in that the scheduling model cannot accurately reflect the actual energy supply capacity under environmental constraints. Specifically, when the hydropower output is suddenly reduced due to ice jam, the model cannot dynamically adjust the available capacity boundary; when the photovoltaic efficiency is reduced due to the influence of morning fog, there is a lack of real-time correction of its actual output capacity. The above defects cause the system to rely on frequent peak regulation of thermal power to balance supply and demand, thereby causing problems such as frequent start-stop of thermal power equipment and over-limit of power grid voltage fluctuation, seriously affecting the economy and reliability of power grid operation. SUMMARY

[0004] The purpose of the present application is to provide a power grid energy scheduling method and system based on multi-source data fusion to solve the problems raised in the background art.

[0005] To achieve the above purpose, the present application provides the following technical solution: a power grid energy scheduling method based on multi-source data fusion, comprising the following steps: S1, obtaining hydropower environmental data, photovoltaic environmental data and load data of a target power grid area, the hydropower environmental data including an ice jam degree parameter for reflecting the degree of river ice jam, the photovoltaic environmental data including morning fog light transmittance and morning fog duration for reflecting the influence of morning fog on photovoltaic components, and the load data including a load pulse signal of electric heating equipment; S2, constructing a hydropower output attenuation model based on the ice jam degree parameter, and constructing a photovoltaic efficiency inhibition model based on the morning fog light transmittance and the morning fog duration, to generate a hydropower output constraint condition and a photovoltaic efficiency correction condition, respectively; S3, preprocessing the hydropower output data and the photovoltaic output data by applying the hydropower output constraint condition and the photovoltaic efficiency correction condition, and time aligning the preprocessed hydropower output data and photovoltaic output data by a dynamic time warping algorithm to generate a fusion feature vector containing environmental constraints; S4, constructing a multi-objective optimization model by combining the hydroelectric power output constraint condition and the photovoltaic efficiency correction condition, and solving the model by using a rolling optimization algorithm to obtain a scheduling scheme including a hydroelectric power output strategy, a photovoltaic power output strategy and a thermal power peak shaving strategy.

[0006] Preferably, the acquisition of the hydroelectric environment data in the step S1 comprises: acquiring the ice jam thickness by an ultrasonic sensor network deployed in the river channel, and determining the ice jam degree parameter based on the ice jam thickness; The acquisition of the photovoltaic environment data comprises: acquiring the morning mist transmittance and duration by a sensor on the surface of the photovoltaic module; The collection of the load data comprises: acquiring the start-stop signal and power fluctuation data of the electric heating equipment by a smart meter in the transformer area.

[0007] Preferably, in the step S2, the hydroelectric power output attenuation model is expressed as:

[0008] wherein, is the ice jam degree parameter, is a function fitted based on the fluid mechanics characteristics of the river channel, used to represent the constraint of the ice jam degree on the upper limit of the hydroelectric available output; The photovoltaic efficiency inhibition model is expressed as:

[0009] wherein, is the morning mist transmittance, is the morning mist duration, and is a function established based on the light scattering theory and the module temperature rise characteristics, used to represent the correction of the morning mist on the photovoltaic power generation efficiency.

[0010] Preferably, in the step S3, the preprocessing of the hydroelectric power output data is specifically:

[0011] wherein, is the original hydroelectric power output data, is the upper limit of the hydroelectric available output output by the hydroelectric power output attenuation model; The preprocessing of the photovoltaic power output data is specifically:

[0012] wherein, is the photovoltaic power output prediction data, is the photovoltaic efficiency correction factor output by the photovoltaic efficiency inhibition model.

[0013] Preferably, the dynamic time warping algorithm in the step S3 specifically comprises: constructing a spatiotemporal cost function:

[0014] wherein, is a time deviation weight, is a power deviation weight, are sampling times of the hydropower output data and the photovoltaic output data respectively, are the hydropower output data and the photovoltaic output data after preprocessing respectively; solving an optimal alignment path of the hydropower output data and the photovoltaic output data based on the spatiotemporal cost function, so that the time error does not exceed a preset threshold, to generate a time-aligned joint output sequence; splicing the joint output sequence and the load data to obtain the fusion feature vector.

[0015] Preferably, the multi-objective optimization model in the step S4 takes the thermal power peak shaving cost and the grid voltage deviation as optimization objectives, and the objective function is expressed as: minimizing the thermal power peak shaving cost and the weighted voltage deviation square sum, i.e.:

[0016] wherein, is the thermal power peak shaving cost, is a voltage quality weight, is a node voltage deviation; the constraint conditions of the multi-objective optimization model include:

[0017] wherein, is a hydropower output, is a photovoltaic output, is a photovoltaic rated output, is a thermal power output, is a real-time load, is a rated load, is a power balance allowable error.

[0018] Preferably, the method further comprises: comparing actual execution data and predicted data of the scheduling scheme, and if the deviation exceeds a preset threshold, adaptively modifying parameters of the hydropower output attenuation model and the photovoltaic efficiency suppression model; the parameters include a river channel characteristic coefficient and an atmospheric attenuation coefficient.

[0019] The application further provides a power grid energy scheduling system based on multi-source data fusion, comprising: An edge computing layer is configured to acquire water and electricity environment data, photovoltaic environment data and load data of a target power grid area, the water and electricity environment data comprises an ice jam degree parameter, the photovoltaic environment data comprises morning mist transmittance and morning mist duration, and the load data comprises a load pulse signal of an electric heating device; The edge computing layer is further configured to generate water and electricity output constraint conditions and photovoltaic efficiency correction conditions based on the ice jam degree parameter and the morning mist parameter, to pre-process and time-align water and electricity output data and photovoltaic output data, and to generate a fusion feature vector; A cloud decision layer is configured to receive the fusion feature vector, to construct a multi-objective optimization model comprising the water and electricity output constraint conditions and the photovoltaic efficiency correction conditions, and to obtain a scheduling scheme by using a rolling optimization algorithm; A communication control layer is configured to realize data interaction between the edge computing layer and the cloud decision layer, and to send the scheduling scheme to a power generation device for execution.

[0020] The application further provides an electronic device, which is a physical device, and the electronic device comprises: A processor and a memory, wherein the memory is communicatively connected to the processor; The memory is configured to store executable instructions executed by the processor, and the processor is configured to execute the executable instructions to implement the power grid energy scheduling method and system based on multi-source data fusion as described above.

[0021] The application further provides a computer readable storage medium, wherein a computer program is stored in the computer readable storage medium, and the computer program is executed by a processor to implement the power grid energy scheduling method and system based on multi-source data fusion as described above.

[0022] Compared with the prior art, the application has the following beneficial effects: By quantifying the physical correlation between the ice jam degree and the water and electricity output and the morning mist parameter and the photovoltaic efficiency, the problem of insufficient response to regional characteristics in the traditional model is solved; by using a cross-time scale data alignment technology, the synchronization deviation between minute-level water and electricity data and second-level photovoltaic data is eliminated, so that the multi-objective optimization model can reflect the actual supply capacity in real time; by using a rolling optimization algorithm embedded with environmental constraints, the frequent start-stop of thermal power due to load fluctuations is effectively reduced, the equipment loss is reduced, and the power quality is improved; a closed-loop feedback mechanism continuously optimizes the model parameters, forms adaptive scheduling capability, and overall enhances the reliability and economy of power grid operation under special scenarios; the application aims at the power grid scheduling problem in high-altitude mountainous areas during the winter dry season, and significantly improves the energy scheduling accuracy under environmental constraints through multi-source data fusion and dynamic coupling models. BRIEF DESCRIPTION OF DRAWINGS

[0023] Figure 1 A main flowchart of a power grid energy scheduling method based on multi-source data fusion is provided for an embodiment of the present application. Figure 2 A structural schematic diagram of a power grid energy scheduling system based on multi-source data fusion is provided for an embodiment of the present application. Figure 3 A structural schematic diagram of an electronic device is provided for an embodiment of the present application. DETAILED DESCRIPTION

[0024] The technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative efforts belong to the scope of protection of the present application.

[0025] The execution subject of the method in the present embodiment is a terminal, which can be a mobile phone, a tablet computer, a palm computer PDA, a notebook computer or a desktop computer, and of course, can also be other devices with similar functions, which are not limited in the present embodiment.

[0026] Referring to Figure 1 The present application provides a power grid energy scheduling method and system based on multi-source data fusion. The method is applied to the system, and the method comprises the following steps. In step S1, water and electricity environment data, photovoltaic environment data and load data of a target power grid region are acquired. The water and electricity environment data comprises an ice jam degree parameter for reflecting the degree of river ice jam. The photovoltaic environment data comprises morning mist light transmittance and morning mist duration for reflecting the influence of morning mist on photovoltaic components. The load data comprises a load pulse signal of an electric heating device.

[0027] Specifically, in step S1, a three-dimensional data system with time-space coupling characteristics is constructed based on a geographic information system (GIS), a meteorological monitoring network and an intelligent electric meter collection system. First, spatial data such as topography, power transmission line direction and distribution of substations are accurately collected by using the GIS system to establish a high-precision geographic space model. The meteorological monitoring network in the coverage area is simultaneously accessed to acquire meteorological parameters such as air temperature, humidity, wind speed and sunshine duration in real time. High-frequency monitoring is performed on extreme weather such as freezing rain and heavy fog that are prone to occur in winter. At the same time, the intelligent electric meter collection system is relied on to collect user-side power consumption data, and information such as start / closure time of electric heating devices and load fluctuation curve is captured. After obtaining the original data, statistical methods and machine learning algorithms are used for data cleaning to remove outliers and duplicate data. Through wavelet transform, principal component analysis (PCA) and other technical means, multi-dimensional data is processed for feature extraction and dimension reduction. Finally, the core indicators such as ice jam degree parameter (based on meteorological and geographical data to evaluate the icing risk of power transmission lines), morning mist transmittance and duration (combined with meteorological monitoring and visibility data to build a prediction model), and electric heating load pulse signal (identified by time series analysis of user electricity consumption data) are output as the basic data source for subsequent physical effect quantification. The specific mechanism of each dimension data is as follows: Hydropower environment dimension: Through the fusion of satellite remote sensing images and river sensor data, an ice jam degree quantification model is constructed. The model uses gray level co-occurrence matrix to analyze the ice distribution characteristics, and combines fluid mechanics equations to calculate the flow capacity decay coefficient of the river. The ice jam degree parameter is directly input into the hydropower output attenuation model as a key driving variable, realizing the dynamic evaluation of the impact of winter river icing on hydropower generation capacity. Photovoltaic environment dimension: Based on the visibility, humidity and solar radiation intensity monitoring data of the weather station, a spatio-temporal prediction model of morning mist generation and dissipation is established. The frequency domain characteristics of the morning mist transmittance are analyzed by Fourier transform, and the efficiency suppression model under low light conditions is constructed by combining the photovoltaic component photoelectric conversion efficiency curve. The morning mist parameter is not only used for photovoltaic power prediction, but also as a feedback variable for model parameter optimization to improve prediction accuracy. Load dimension: Minute-level load data collected by smart meters is used to extract the pulse signal characteristics of electric heating equipment through wavelet transform. A load prediction model based on long short-term memory network (LSTM) is established to analyze the temperature-load response curve and identify the load fluctuation rules in peak and valley periods. These feature data are used as dynamic boundary conditions for power balance constraints to support the optimization model to realize source-load collaborative scheduling.

[0028] Step S2, constructing a hydropower output attenuation model based on the ice jam degree parameter, and constructing a photovoltaic efficiency suppression model based on the morning mist transmittance and morning mist duration to generate hydropower output constraint conditions and photovoltaic efficiency correction conditions, respectively.

[0029] Specifically, in step S2, the hydropower output attenuation model is represented as:

[0030] wherein, is the ice jam degree parameter, is a function fitted based on the fluid mechanics characteristics of the river, used to represent the constraint of ice jam degree on the upper limit of hydropower available output; Optionally, by deploying a high-precision ultrasonic sensor network at key sections of the river, the ice jam degree parameter is collected in real time (unit: mm). The sensor network is distributed, with one monitoring point set every 500 meters on the upstream river of the hydropower station, and each monitoring point is equipped with three groups of ultrasonic probes at different angles. The triangular positioning algorithm is used to eliminate the measurement blind area and ensure the accuracy and timeliness of the ice jam thickness data collection.

[0031] Further, in the modeling of hydraulic characteristics, first, based on the open channel flow theory in fluid mechanics, a nonlinear relationship model of ice jam thickness and water area is established , where is the initial water area of the river without ice jam, which is accurately obtained through historical hydrological data combined with laser radar terrain scanning data; is the river characteristic coefficient, which is determined by curve fitting of historical ice data using the least squares method according to river slope, roughness and other parameters; In the derivation of output constraints, combined with the water turbine efficiency characteristic curve and Bernoulli equation, the change of water area is converted into the water power available output constraint, considering the influence of ice jam on water flow velocity and head loss, a correction coefficient is introduced, and finally the upper limit derivation formula of hydropower output is established:

[0032] In the formula, is the water turbine efficiency, is the water density, is the acceleration of gravity, is the average flow velocity, is a correction factor that changes dynamically with the thickness of the ice jam, which is calibrated by laboratory simulation and field measurement data; Further, through the above calculation process, the ice jam constrained hydropower output upper limit sequence containing the time stamp is generated The sequence not only considers the immediate impact of the current ice jam state, but also predicts the development trend of the ice jam within the next 3 hours through a rolling prediction model, and the output constraint boundary data is updated at 15-minute intervals, providing dynamic constraint conditions for the hydropower data preprocessing in step S3, ensuring the safety and economy of the hydropower dispatching decision.

[0033] Specifically, in step S2, in the morning fog environment, the power generation efficiency of the photovoltaic module will fluctuate significantly due to the attenuation of light intensity and the change of module surface temperature. Therefore, a photovoltaic efficiency suppression model is constructed, which is expressed as:

[0034] In the formula, is the light transmittance of the morning fog, The duration of the morning fog is given by , which is a function established based on light scattering theory and component temperature rise characteristics. Used to characterize the effect of morning fog on photovoltaic power generation efficiency.

[0035] Optionally, high-precision sensors deployed on the surface of photovoltaic modules can be used to collect the light transmittance of morning fog in real time. (Unit: %) and duration (Unit: hours), where transmittance The duration is obtained by measuring the ratio of atmospheric transmitted light intensity to standard light intensity using a multispectral radiometer. An event-triggered mechanism is used, which starts timing when the light transmittance is continuously below 90% and stops when it rises back above the threshold.

[0036] Furthermore, based on Mie scattering theory, a dynamic attenuation model of light intensity caused by morning fog particles is established. ,in, Standard light intensity (1000W / ), As an atmospheric attenuation coefficient, it is calibrated jointly using historical meteorological data and actual power generation data (typical value range: 0.05-0.15). Meanwhile, considering the surface temperature drop effect of the module caused by morning fog condensation, a temperature rise delay compensation formula is introduced: each millimeter of fog droplet thickness will cause a linear decrease in photovoltaic efficiency of 0.5%, a coefficient verified by laboratory fog chamber environment testing. Finally, by combining the light intensity attenuation model and the temperature drop correction formula, the photovoltaic efficiency correction factor is iteratively calculated.

[0037] Furthermore, the output photovoltaic efficiency correction factor with morning fog constraint is calculated. This parameter is embedded as a dynamic constraint in the photovoltaic data preprocessing module of step S3. When calculating the real-time power generation of the photovoltaic module, it is used... To achieve power limiting, where The correction factor, representing the nominal power under fog-free conditions, can effectively reduce the power prediction error caused by morning fog to within 3%.

[0038] In this embodiment, the generated and The core constraints that constitute the feature preprocessing in step S3 transform the raw energy output data into an effective supply capacity sequence that takes into account actual environmental limitations, providing a physical boundary for cross-timescale data coupling.

[0039] Step S3: Apply the hydropower output constraints and photovoltaic efficiency correction conditions to the hydropower output data and photovoltaic output data for preprocessing. Then, use a dynamic time warping algorithm to align the preprocessed hydropower output data and photovoltaic output data in time to generate a fused feature vector containing environmental constraints.

[0040] Specifically, in the step S3, the actual output of the hydropower and photovoltaic is affected by multiple factors such as natural conditions, equipment parameters and power grid operation constraints, so the original data needs to be corrected to improve the accuracy of the scheduling model.

[0041] The minute-level hydropower output original data represents the theoretical generating capacity, but in actual operation, constraints such as the maximum flow rate of the water turbine and the reservoir water level limit need to be considered. By applying constraints, the original data is corrected to the actual feasible output. The mathematical expression is:

[0042] In the formula, is the hydropower output original data, is the upper limit of the hydropower available output output by the hydropower output decay model, which is determined by the technical parameters of the hydropower unit, the basin inflow prediction and the stable operation requirements of the power grid. This operation can effectively avoid the failure of the scheduling scheme caused by overestimating the hydropower supply.

[0043] Further, the photovoltaic output prediction data is calculated based on ideal lighting conditions, and the actual power generation is affected by factors such as cloud cover, component conversion efficiency decay, etc. A correction coefficient is introduced, which includes a temperature reduction coefficient, a dust loss coefficient and a device aging factor. The data calibration is realized through the following formula:

[0044] In the formula, is the photovoltaic output prediction data, is the photovoltaic efficiency correction factor output by the photovoltaic efficiency suppression model, which can convert the theoretical predicted power into more actual schedulable power.

[0045] In this embodiment, by constructing an environmental constraint condition model, the theoretical output data of hydropower and photovoltaic is dynamically corrected to convert it into actual available power that meets the real-time environmental restrictions. This method effectively avoids the overestimation risk of the scheduling model on energy supply capacity, significantly improves the feasibility and safety of the power grid energy scheduling scheme, and provides protection for reliable power supply in complex environments.

[0046] Specifically, in the process of power grid multi-source data fusion, due to the differences in data collection frequency and characteristics of hydropower and photovoltaic, a quantitative index needs to be established to measure the temporal and spatial differences. Therefore, a time-space cost function is constructed:

[0047] In the formula, As the weight for time deviation, The weights are for power deviation; these weight parameters are not fixed values ​​but determined through training on a large amount of historical ice blockage-morning fog scenario data. Special meteorological conditions such as ice blockages and morning fog have a significant impact on hydropower and photovoltaic power generation. Using such scenario data to train the weights allows the cost function to better reflect the data alignment requirements under complex operating conditions. The sampling times for hydropower output data and photovoltaic output data are respectively. These are the preprocessed hydropower output data and photovoltaic output data, respectively. The cost function, through weighted summation, comprehensively considers the differences in the time and power dimensions, providing a quantitative basis for subsequent data alignment. Furthermore, an improved DTW (Dynamic Time Warping) algorithm is adopted: Considering that the data acquisition interval for hydropower is 1 minute while that for photovoltaic data is only 10 seconds, this significant difference in sampling frequency can lead to data asynchrony, severely affecting the subsequent generation and analysis of joint features. To address this issue, an improved DTW algorithm is adopted. This algorithm, based on the traditional DTW, allows for an offset of ±3 time steps to accommodate the difference in the two data acquisition frequencies. By solving for the optimal alignment path between hydropower and photovoltaic data using this algorithm, the time error can be controlled within ≤90 seconds, while reducing the power deviation variance by 40%. This optimization effectively solves the data asynchrony problem caused by the difference in sampling frequencies of different sensors, providing accurate time-aligned foundational data for subsequent joint feature generation, and ensuring reliable data support for joint analysis and scheduling decisions based on hydropower and photovoltaic data.

[0048] Furthermore, based on the spatiotemporal cost function, the optimal alignment path between hydropower output data and photovoltaic output data is solved to ensure that the time error does not exceed a preset threshold, thereby generating a time-aligned joint output sequence; the joint output sequence is then concatenated with the load data to obtain the fused feature vector.

[0049] Optionally, in power grid energy dispatch, the impact of environmental factors on energy supply and demand cannot be ignored. The time-aligned hydropower-photovoltaic adjustment sequence is then deeply integrated with load characteristics (including the frequency and amplitude of pulse signals characterizing electric heating electricity consumption). Specifically, a fused feature vector is constructed using data stitching technology.

[0050] in, This represents the adjustment of hydropower output after environmental constraints have been corrected, and its numerical change reflects the limitations of hydrological environment such as river ice blockage on hydropower supply. The photovoltaic output adjustment sequence, which takes into account the impact of meteorological conditions such as morning fog, reflects the dynamic effect of changes in the solar environment on new energy power generation. By using the frequency and amplitude of the electric heating pulse signal, the fluctuation characteristics of electricity load caused by residential heating on the demand side can be accurately characterized.

[0051] Understandably, the output of this fused feature vector achieves an organic integration of supply-side constraints and demand-side fluctuations, forming a complete input dataset. This dataset can be directly used as the state variables of the optimization model in step S4, providing a comprehensive and accurate data foundation for the formulation of subsequent scheduling strategies.

[0052] Furthermore, in the data preprocessing stage, the environmental constraint information extracted in step S2 is introduced to systematically correct the original hydropower, photovoltaic, and load data. This correction mechanism can effectively filter out abnormal data caused by environmental interference, ensuring that the data entering the coupled algorithm truly reflects the limitations of the actual operating environment. The generated fusion feature vector serves as the core input to the optimization model in step S4, taking into account the dynamic impact of environmental factors such as ice blockage and morning fog from the data source. Compared with the decision-making bias problem caused by insufficient data processing in traditional scheduling models, this method can significantly improve the scientificity and accuracy of scheduling strategies, making grid energy scheduling more in line with actual operating scenarios and enhancing the reliability and stability of scheduling decisions.

[0053] In this embodiment, by aligning hydropower and photovoltaic data by time and correcting power, the problems of data asynchrony and prediction deviation are effectively solved. On this basis, the characteristics of electric heating load are incorporated, which not only fully reflects the environmental constraints on the supply side, but also accurately captures the dynamic changes on the demand side. The construction of this fused feature vector provides complete and reliable input data for the subsequent rolling optimization scheduling model, enabling the scheduling strategy to achieve precise source-load coordination under complex and ever-changing environmental conditions.

[0054] Step S4: Using the fused feature vector as input, construct a multi-objective optimization model by combining the hydropower output constraints and photovoltaic efficiency correction conditions, and use a rolling optimization algorithm to solve for a scheduling scheme that includes hydropower output strategy, photovoltaic output strategy and thermal power peak-shaving strategy.

[0055] Specifically, the multi-objective optimization model in step S4 takes the peak-shaving cost of thermal power and the voltage deviation of the power grid as the optimization objectives. This model uses a rolling optimization mechanism to dynamically adjust the scheduling scheme at fixed time intervals, ensuring the continuous output of the optimal scheduling strategy in a complex and ever-changing power grid operating environment. The specific objective function is expressed as follows: Minimize the peak-shaving cost of thermal power plants and the sum of squares of weighted voltage deviations, i.e.:

[0056] In the formula, To account for the peak shaving cost of thermal power, the penalty for each start-up and shutdown is directly related to the frequency characteristics of the load pulse signal. That is, when frequent load fluctuations lead to an increase in the number of start-ups and shutdowns of thermal power equipment, the penalty coefficient will increase significantly to quantify the equipment loss cost. For example, during periods when the electric heating load surges due to extremely cold weather, if thermal power equipment starts up and shuts down frequently. The weights used to balance the cost of thermal power and voltage deviation can be dynamically adjusted according to the actual needs of grid operation. For node voltage deviation, based on the power data in the fused feature vector from step S3, and combined with grid node parameters (such as line impedance, transformer turns ratio, etc.), the voltage deviation is calculated by minimizing... It can effectively avoid voltage over-limit problems caused by uneven power distribution and ensure the safe and stable operation of the power grid; The constraints of the multi-objective optimization model include:

[0057] In the formula, Power output for hydroelectricity, The hydropower output prediction model is based on step S2, where... Representing hydrological parameters such as inflow and water level, this constraint ensures that hydropower dispatch does not exceed the actual available generating capacity, avoiding damage to power generation equipment or waste of water resources due to excessive dispatch. Contribute to photovoltaic power For rated photovoltaic output, For thermal power output, This refers to the photovoltaic efficiency correction function constructed in step S2 based on the light transmittance and duration of morning fog. The value ranges from [0,1], and the closer the value is to 1, the better the light transmittance. The function represents the total duration of morning fog from its formation to its dissipation, expressed in hours. It is established through correlation analysis of historical meteorological data and photovoltaic power monitoring data, and can dynamically quantify the impact of morning fog on the power generation efficiency of photovoltaic power plants, providing more accurate power prediction constraints for energy dispatch. For real-time load, For rated load, To allow for power balance error, this constraint requires that the total output of hydropower, photovoltaic power, and thermal power must match the load demand, and the fluctuation range must be controlled within a safe threshold to ensure the balance of power supply and demand and the stable operation of the power grid.

[0058] Step S5: Compare the actual execution data of the scheduling scheme with the predicted data. If the deviation exceeds the preset threshold, the parameters of the hydropower output attenuation model and the photovoltaic efficiency suppression model are adaptively corrected. The parameters include the river characteristic coefficient and the atmospheric attenuation coefficient.

[0059] Specifically, a Model Predictive Control (MPC) framework is adopted, with a 10-minute rolling window, and the following operations are performed in each cycle: Input: The feature vector generated by fusing multi-source data in step S3. As the core input, this vector integrates multi-dimensional information such as weather forecasts, load predictions, and equipment status, while simultaneously accessing the latest set of environmental constraint parameters. To ensure the timeliness and completeness of the model input data; Solution: For complex optimization problems with nonlinear constraints, an improved particle swarm optimization (IPSO) algorithm is used. This algorithm introduces dynamic inertia weights and adaptive learning factors to quickly locate the optimal solution in a multidimensional solution space. Specific outputs include: Hydropower output range Based on the reservoir capacity, inflow, and power demand, the hydropower output range is output to provide a flexible adjustment range for real-time dispatch. Photovoltaic power limitation By combining cloud cover forecasts with inverter capacity, the photovoltaic power limit value is determined to avoid the risks of curtailment and equipment overload. Thermal power peak shaving strategy Based on system load fluctuations and environmental constraints, a thermal power peak-shaving strategy is generated to optimize unit start-up and shutdown plans and output curves; Feedback: A dual closed-loop control mechanism of "prediction-execution-feedback" is established. The actual power generation data after execution (from the closed-loop control module in step 5) is compared point by point with the model prediction value. When the deviation exceeds the 8% threshold, the parameter adaptive correction program is triggered. Taking hydropower dispatch as an example, the system automatically corrects the fitting coefficient of ice blockage thickness and water flow area and the river characteristic coefficient in reverse. By mining historical data to build a dynamic parameter correction library, the accuracy of the physical effect model is continuously optimized, ultimately forming a complete closed-loop control system of "data acquisition - constraint generation - intelligent scheduling - feedback correction".

[0060] Understandably, the physical constraints in step S2 provide environmental boundary limits for the multi-objective optimization model, and the fusion features in step S3 provide real-time operating status input for the multi-objective optimization model, so that the optimized scheduling results not only conform to the actual supply capacity under ice jam / morning fog environment, but also match the high-frequency fluctuation characteristics of electric heating load, fundamentally solving the problem of frequent start-up and shutdown of thermal power caused by "data disconnection" in traditional models.

[0061] In this embodiment, by quantifying the physical correlation between ice blockage severity and hydropower output, and between morning fog parameters and photovoltaic efficiency, the problem of insufficient response to regional characteristics in traditional models is solved. Cross-timescale data alignment technology is used to eliminate the synchronization deviation between minute-level hydropower data and second-level photovoltaic data, enabling the multi-objective optimization model to reflect actual supply capacity in real time. By embedding a rolling optimization algorithm with environmental constraints, frequent start-ups and shutdowns of thermal power plants due to load fluctuations are effectively reduced, equipment losses are decreased, and power quality is improved. A closed-loop feedback mechanism continuously optimizes model parameters, forming adaptive scheduling capabilities, thus enhancing the overall reliability and economy of power grid operation under special scenarios. This invention addresses the challenge of power grid scheduling during the dry season in high-altitude mountainous areas by significantly improving the accuracy of energy scheduling under environmental constraints through multi-source data fusion and a dynamic coupling model.

[0062] Based on the above embodiments, such as Figure 2 As shown, the present invention also provides a power grid energy dispatching system based on multi-source data fusion, used to support the power grid energy dispatching method based on multi-source data fusion in the above embodiments. The power grid energy dispatching system based on multi-source data fusion includes: Edge computing layer 100 is used to acquire hydropower environment data, photovoltaic environment data and load data of the target power grid area. The hydropower environment data includes ice blockage degree parameters, the photovoltaic environment data includes morning fog transmittance and morning fog duration, and the load data includes load pulse signals of electric heating equipment. The edge computing layer 100 is also used to generate hydropower output constraints and photovoltaic efficiency correction conditions based on the ice blockage degree parameters and morning fog parameters, preprocess and time-align the hydropower output data and photovoltaic output data, and generate a fused feature vector. The cloud-based decision layer 200 is used to receive the fused feature vector, construct a multi-objective optimization model that includes the hydropower output constraints and photovoltaic efficiency correction conditions, and solve the scheduling scheme using a rolling optimization algorithm. The communication control layer 300 is used to realize the data interaction between the edge computing layer and the cloud decision layer, and to send the scheduling scheme to the power generation equipment for execution.

[0063] In this embodiment, by quantifying the physical correlation between ice blockage severity and hydropower output, and between morning fog parameters and photovoltaic efficiency, the problem of insufficient response to regional characteristics in traditional models is solved. Cross-timescale data alignment technology is used to eliminate the synchronization deviation between minute-level hydropower data and second-level photovoltaic data, enabling the multi-objective optimization model to reflect actual supply capacity in real time. By embedding a rolling optimization algorithm with environmental constraints, frequent start-ups and shutdowns of thermal power plants due to load fluctuations are effectively reduced, equipment losses are decreased, and power quality is improved. A closed-loop feedback mechanism continuously optimizes model parameters, forming adaptive scheduling capabilities, thus enhancing the overall reliability and economy of power grid operation under special scenarios. This invention addresses the challenge of power grid scheduling during the dry season in high-altitude mountainous areas by significantly improving the accuracy of energy scheduling under environmental constraints through multi-source data fusion and a dynamic coupling model.

[0064] Furthermore, the power grid energy dispatching system based on multi-source data fusion can run the above-mentioned power grid energy dispatching method based on multi-source data fusion. For specific implementation, please refer to the method embodiment, which will not be repeated here.

[0065] Based on the above embodiments, such as Figure 3 As shown, the present invention also provides an electronic device, the electronic device comprising: The processor 22 includes at least one processor 22, at least one memory 21, a communication interface 23, and a communication bus 24, wherein the processor 22 is communicatively connected to the memory 21. In this embodiment, the memory 21 can be implemented in any suitable manner, for example, the memory 21 can be a read-only memory, a hard disk drive, a solid-state drive, or a USB flash drive, etc.; the memory 21 is used to store at least one executable instruction executed by the processor; In this embodiment, the processor 22 can be implemented in any suitable manner. For example, the processor 22 can take the form of a microprocessor or processor and a computer-readable medium storing computer-readable program code (e.g., software or firmware) that can be executed by the (micro)processor, logic gates, switches, application-specific integrated circuits (ASICs), programmable logic controllers, and embedded microcontrollers, etc.; the processor is used to execute the executable instructions to implement the power grid energy dispatching method based on multi-source data fusion as described above.

[0066] Based on the above embodiments, the present invention also provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the above-described power grid energy dispatching method based on multi-source data fusion.

[0067] Those skilled in the art will recognize that the modules and method steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of this invention.

[0068] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the devices, equipment, and modules described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0069] In the several embodiments provided in this application, it should be understood that the disclosed devices, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of modules is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple modules or units may be combined or integrated into another device, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be an indirect coupling or communication connection through some interfaces, devices, or equipment, and may be electrical, mechanical, or other forms.

[0070] The modules described as separate components may or may not be physically separate. The components shown as modules may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0071] In addition, the functional modules in the various embodiments of the present invention can be integrated into one processing module, or each module can exist physically separately, or two or more modules can be integrated into one module.

[0072] If the aforementioned functions are implemented as software functional modules and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this invention, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program instructions, such as USB flash drives, portable hard drives, read-only storage servers, random access storage servers, magnetic disks, or optical disks.

[0073] Furthermore, it should be noted that the combination of the various technical features in this case is not limited to the combination methods described in the claims of this case or the combination methods described in the specific embodiments. All technical features described in this case can be freely combined or combined in any way, unless they contradict each other.

[0074] It should be noted that the above examples are merely specific embodiments of the present invention, and the present invention is obviously not limited to the above embodiments, with many similar variations. All modifications that can be directly derived or conceived by those skilled in the art from the content disclosed in this invention should fall within the protection scope of this invention.

[0075] The above are merely preferred embodiments of the present invention and are not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A power grid energy dispatching method based on multi-source data fusion, characterized in that, Includes the following steps: S1. Obtain hydropower environment data, photovoltaic environment data and load data of the target power grid area. The hydropower environment data includes ice blockage degree parameters to reflect the degree of river ice blockage. The photovoltaic environment data includes morning fog transmittance and morning fog duration to reflect the impact of morning fog on photovoltaic modules. The load data includes load pulse signals of electric heating equipment. S2. Construct a hydropower output attenuation model based on the ice blockage degree parameter, and construct a photovoltaic efficiency suppression model based on the morning fog transmittance and morning fog duration, and generate hydropower output constraint conditions and photovoltaic efficiency correction conditions respectively. S3. Apply the hydropower output constraint and photovoltaic efficiency correction conditions to the hydropower output data and photovoltaic output data for preprocessing. Then, use the dynamic time warping algorithm to align the preprocessed hydropower output data and photovoltaic output data in time to generate a fusion feature vector containing environmental constraints. S4. Using the fused feature vector as input, a multi-objective optimization model is constructed by combining the hydropower output constraints and photovoltaic efficiency correction conditions. A rolling optimization algorithm is used to solve the scheduling scheme that includes hydropower output strategy, photovoltaic output strategy and thermal power peak-shaving strategy.

2. The power grid energy dispatching method based on multi-source data fusion according to claim 1, characterized in that, The acquisition of hydropower environmental data in step S1 includes: Ice blockage thickness is obtained by deploying an ultrasonic sensor network in the river channel, and the degree of ice blockage is determined based on the ice blockage thickness. The acquisition of the photovoltaic environmental data includes: The transmittance and duration of morning fog are obtained through sensors on the surface of photovoltaic modules; The collection of the load data includes: The start / stop signals and power fluctuation data of electric heating equipment are obtained through smart meters in the transformer substation.

3. The power grid energy dispatching method based on multi-source data fusion according to claim 2, characterized in that, In step S2, the hydropower output attenuation model is expressed as follows: In the formula, The ice blockage degree parameter, It is a function fitted based on the hydrodynamic characteristics of the river channel, used to characterize the constraint of the degree of ice blockage on the upper limit of the available hydropower output; The photovoltaic efficiency suppression model is expressed as follows: In the formula, The light transmittance of the morning fog, The duration of the morning fog is given by , which is a function established based on light scattering theory and component temperature rise characteristics. Used to characterize the effect of morning fog on photovoltaic power generation efficiency.

4. The power grid energy dispatching method based on multi-source data fusion according to claim 3, characterized in that, The preprocessing of hydropower output data in step S3 specifically involves: In the formula, This is the raw data for hydropower output. This represents the upper limit of available hydropower output output output from the hydropower output attenuation model. The preprocessing of photovoltaic output data is as follows: In the formula, For photovoltaic power output forecast data, This is the photovoltaic efficiency correction factor output by the photovoltaic efficiency suppression model.

5. The power grid energy dispatching method based on multi-source data fusion according to claim 4, characterized in that, The dynamic time warping algorithm in step S3 specifically includes: Constructing the spatiotemporal cost function: In the formula, As the weight for time deviation, As power deviation weight, The sampling times for hydropower output data and photovoltaic output data are respectively. These are the pre-processed hydropower output data and photovoltaic output data, respectively. Based on the aforementioned spatiotemporal cost function, the optimal alignment path between hydropower output data and photovoltaic output data is solved to ensure that the time error does not exceed a preset threshold, thereby generating a time-aligned joint output sequence. The combined output sequence is concatenated with the load data to obtain the fused feature vector.

6. The power grid energy dispatching method based on multi-source data fusion according to claim 1, characterized in that, The multi-objective optimization model in step S4 takes the peak-shaving cost of thermal power and the voltage deviation of the power grid as the optimization objectives, and the objective function is expressed as follows: Minimize the peak-shaving cost of thermal power plants and the sum of squares of weighted voltage deviations, i.e.: In the formula, To reduce the peak-shaving cost of thermal power, For voltage quality weighting, For node voltage deviation; The constraints of the multi-objective optimization model include: In the formula, Power output for hydroelectricity, Contribute to photovoltaic power For rated photovoltaic output, For thermal power output, For real-time load, For rated load, This is the allowable error for power balance.

7. The power grid energy dispatching method based on multi-source data fusion according to claim 1, characterized in that, Also includes: The actual execution data of the scheduling scheme is compared with the predicted data. If the deviation exceeds the preset threshold, the parameters of the hydropower output attenuation model and the photovoltaic efficiency suppression model are adaptively corrected. The parameters include the river characteristic coefficient and the atmospheric attenuation coefficient.

8. A power grid energy dispatching system based on multi-source data fusion, characterized in that, include: The edge computing layer is used to acquire hydropower environment data, photovoltaic environment data and load data of the target power grid area. The hydropower environment data includes ice blockage degree parameters, the photovoltaic environment data includes morning fog transmittance and morning fog duration, and the load data includes load pulse signals of electric heating equipment. The edge computing layer is also used to generate hydropower output constraints and photovoltaic efficiency correction conditions based on the ice blockage degree parameters and morning fog parameters, preprocess and time-align the hydropower output data and photovoltaic output data, and generate a fused feature vector. The cloud-based decision-making layer is used to receive the fused feature vector, construct a multi-objective optimization model that includes the hydropower output constraints and photovoltaic efficiency correction conditions, and solve the scheduling scheme using a rolling optimization algorithm. The communication control layer is used to realize the data interaction between the edge computing layer and the cloud decision layer, and to send the scheduling scheme to the power generation equipment for execution.

Images