Online probability density prediction method for power load considering the influence of virtual drift and real drift

Abstract

The present invention discloses an online probability density prediction method for power load that considers the influence of virtual drift and real drift. The method comprises the following steps: 1. Using a sliding window to read historical power load and related influencing factor data; 2. Using a variable attention mechanism (VAM) to extract input information; 3. Using a monotone quantile regression long short-term memory (MQRLSTM) neural network to predict power load quantiles and process quantile crossings; 4. Using concept drift detection and an adaptive DDA mechanism to process virtual drift and real drift in the data stream, and using Bayesian optimization to update model parameters; 5. Combining kernel density estimation to convert quantile prediction results into power load probability density predictions. The present invention utilizes a variable attention mechanism to extract effective information, process concept drift, and resolve quantile crossings, achieving both point prediction results and power load probability density predictions, thereby providing scientific guidance for power system operation and scheduling.

Description

Technical Field

[0001] The present invention belongs to the technical field of short-term power load forecasting, and in particular is an online probability density forecasting method for power load taking into account the influence of virtual drift and real drift. Background Art

[0002] In modern power system operations, accurate load forecasting is crucial for power generation planning, grid dispatching, and power market transactions. This requires not only precise forecast values ​​but also an understanding of the degree of forecast uncertainty. For example, in power markets, accurate load forecasts and their uncertainty can help market participants rationally plan power generation and trading strategies, thereby mitigating risk.

[0003] With the development of emerging technologies, novel forecasting methods have emerged in the field of power load, primarily categorized as statistical and artificial intelligence. However, power load is affected by numerous factors, such as seasonal variations, weather conditions, economic activity, and emergencies (such as natural disasters and large-scale events). These factors cause load data to exhibit complex nonlinear and nonstationary characteristics, and the data distribution constantly shifts over time, a phenomenon known as concept drift. Traditional forecasting models can learn from historical data that can become outdated and lack targeted processing of virtual drift in load data, reducing their adaptability to new data patterns. Therefore, addressing concept drift in power load data and taking action to address both virtual and real drift is key to improving model forecasting accuracy.

[0004] Furthermore, traditional forecasting methods typically use offline models, which improve their fitting capabilities by repeatedly training parameters through the input of batch data. However, these parameters, once set, cannot be changed, making offline models unsuitable for forecasting dynamic and constantly changing load data. Therefore, using online models for forecasting and addressing concept drift in load data are issues that urgently need to be improved and addressed in existing models. Summary of the Invention

[0005] In order to address the shortcomings of the above-mentioned existing technologies, the present invention proposes an online probability density prediction method for power load taking into account the influence of virtual drift and real drift, in order to achieve real-time prediction of power load. At the same time, different measures are adopted to process the virtual drift and real drift in the power data to achieve accurate prediction of power load, thereby providing more effective information for more scientific management, operation and scheduling of the power grid system.

[0006] In order to achieve the above-mentioned object, the present invention adopts the following technical solutions:

[0007] The characteristics of the method for predicting the online probability density of power load considering the influence of virtual drift and real drift of the present invention are as follows:

[0008] Step 1. Collect historical power load and related influencing factors and form load characteristic data, then normalize them to obtain the normalized power load characteristic data set. ,in, Represents the normalized The power load characteristic set at the time , Represents the normalized The i-th power load characteristic at time A quantity representing the characteristics of the electric load, Indicates duration;

[0009] Step 2. Calculate using formula (1) The power load characteristic set at the time and The power load characteristic set at the time The divergence between , thus obtaining the divergence set ;

[0010] (1)

[0011] In formula (1), Represents the normalized The i-th power load characteristic at time -1 The probability density function of express The probability density function of

[0012] Step 3. Calculate using equations (2) and (3) Mean value at time and standard deviation :

[0013] (2)

[0014] (3)

[0015] In formula (2) and formula (3), represents the divergence at time n, and ,

[0016] Calculate the judgment threshold of virtual drift using formula (4) :

[0017] (4)

[0018] when When There is a virtual drift, Put it into the storage pool;

[0019] Step 4. Use variable attention mechanism to Weighted to obtain the weighted power load characteristic set ;

[0020] Step 4.1. Calculate using formula (5) Attention score ;

[0021] (5)

[0022] In formula (3), 、 、 and There are 4 parameters to be learned. represents the activation function, express The transpose of

[0023] Step 4.2. Calculate using formula (6) Attention distribution :

[0024] (6)

[0025] In formula (4), represents the activation function;

[0026] Step 4.3. Use formula (7) to calculate the weighted power load characteristic set :

[0027] (7)

[0028] In formula (7), express The i-th power load characteristic after time weighting;

[0029] Step 5. Build the MQRLSTM network, including LSTM hidden layer, monotonic layer and output layer, and Input into the MQRLSTM network for processing to obtain the predicted quantile of power load ;

[0030] Step 6. Calculate the probability density function of the power load forecast distribution at time t using formula (13): The actual value of power load The deviation between :

[0031] (13)

[0032] In formula (13), represents the probability density function of the power load forecast distribution at time t, The load value corresponding to the probability density function of the power load forecast distribution at time t is represented by, express The actual value of the power load at the moment season Otherwise, let ;

[0033] Step 7. Use equations (14) and (15) to calculate Probability density function of power load forecast distribution at time and the true value The mean deviation between and standard deviation :

[0034] (14)

[0035] (15)

[0036] In formula (14) and formula (15), The probability density function representing the power load forecast distribution at time n and the actual value of power load at time n The deviation between ; The load value corresponding to the probability density function of the power load forecast distribution at time n;

[0037] Step 8. Use formula (16) to calculate Warning threshold for moment-to-moment load forecast deviation and drift threshold :

[0038] (16)

[0039] Step 9. When ,Will Put it into the storage pool and execute step 10; otherwise, execute step 10 directly;

[0040] Step 10. When ,express Real drift occurs, and the MQRLSTM network is trained using the data in the storage pool to obtain the updated network weights. Then, follow step 5 to Re-predict and get Quantiles Down There is no power load forecast quantile at the moment when the quantile crosses, and step 11 is executed; otherwise, step 11 is executed;

[0041] Step 11. The predicted value with quantile 0.5 in Power load forecast value at the moment ; Thus, using formula (17) we can get Probability density function of power load forecast distribution at time , Represents the load value corresponding to the power load forecast distribution, and then and After denormalization, we get Denormalized power load forecast value at time and Probability density function of power load forecast distribution at time :

[0042] (17)

[0043] In formula (17), Indicates bandwidth, is a Gaussian function.

[0044] The method for predicting the online probability density of electric load considering the influence of virtual drift and real drift according to the present invention is characterized in that step 5 is performed as follows:

[0045] Step 5.1. Use formula (8) to get Quantiles Down Conditional quantile of power load at the moment :

[0046] (8)

[0047] In formula (8), express The LSTM hidden layer neural network bias at the moment, express The LSTM hidden layer neural network weights at the moment; represents the LSTM hidden layer;

[0048] Step 5.2. Use Equation (9) to construct the objective function of the MQRLSTM network :

[0049] (9)

[0050] In formula (9), express The actual value of the power load at the moment, R represents the total number of quantiles, Indicates the Quantiles The quantile loss under , and has:

[0051] (10)

[0052] In formula (10), represents the independent variable;

[0053] Step 5.3. Use formula (11) to get Quantiles The standardized power load forecast quantile ;

[0054] (11)

[0055] In formula (11), , represents the number of neural units in the LSTM hidden layer, , represents the number of neural units in the monotonic layer, Indicates the Quantiles The jth neural unit of the LSTM hidden layer is transferred to the kth neural unit of the monotonic layer. moment weight;

[0056] Step 5.4. Set the weight range of the K neural units in the monotonic layer to the R neural units in the output layer under R quantiles to , so that in the weight range The weights of the kth neural unit of the monotonic layer under the rth quantile to the rth neural unit of the output layer Perform random initialization;

[0057] Step 5.5. Use formula (12) to get Quantiles Down Quantiles of power load forecast without quantile crossing at any time :

[0058] (12).

[0059] The electronic device of the present invention includes a memory and a processor, and is characterized in that the memory is used to store a program that supports the processor to execute the power load online probability density prediction method, and the processor is configured to execute the program stored in the memory.

[0060] The present invention provides a computer-readable storage medium, wherein a computer program is stored on the computer-readable storage medium, and the computer program executes the steps of the method for predicting the online probability density of electric load when the computer program is executed by a processor.

[0061] Compared with the prior art, the present invention has the following beneficial effects:

[0062] 1. The present invention can update the load forecasting model when virtual concept drift occurs. The historical load data and related influencing factors are read through a sliding window, and the variable attention mechanism is used to extract the effective information in the input, and it is input into the MQRLSTM model to predict the future load power and obtain the monotonic quantile. At the same time, the KL divergence of the window data and the historical data and the model prediction index CRPS are monitored to detect the virtual drift and real drift in the data stream, and the model parameters are tuned using Bayesian optimization. Combined with the kernel density estimation method KDE, it is converted into a load probability density curve, and finally the result is denormalized to achieve a comprehensive and detailed probabilistic description of future wind power, thereby providing a scientific decision-making basis for the operation, management and scheduling of the power system.

[0063] 2. The present invention uses an online model to predict the probability density of power load, combined with a sliding window to process continuous data streams, continuously merging the latest data while discarding outdated information, ensuring that the model remains updated and highly sensitive to data streams. This enables the model to dynamically learn by continuously processing new data, effectively addressing concept drift in power load data, and thus improving the accuracy of load forecasting.

[0064] 3. This invention introduces a variable attention mechanism that, when processing time series data, allocates attention based on the changing importance of each time point in the sequence, focusing on emerging key information rather than being limited to fixed patterns learned in the past. This helps avoid the problem of a sharp decline in model performance due to data changes, allowing the model to maintain relatively stable and accurate prediction performance, thereby providing a more reliable decision-making basis for power system power generation planning, grid scheduling, and power market transactions.

[0065] 4. This invention uses different measures to handle virtual drift and concept drift in data streams, effectively addressing potential changes in data streams. Virtual drift is identified using the KL divergence change between windowed data, and real drift is detected using the CRPS between predicted and actual values ​​of windowed data. By categorizing drift, new features emerging in data streams are better captured, thereby improving forecast accuracy and further optimizing power system resource allocation and operational decisions. BRIEF DESCRIPTION OF THE DRAWINGS

[0066] Figure 1 1 is an overall flow chart of the method of the present invention. DETAILED DESCRIPTION

[0067] In this embodiment, a method for predicting the online probability density of power load considering the influence of virtual drift and real drift is provided. Figure 1 As shown, the steps are as follows:

[0068] Step 1. Collect historical power load and related influencing factors and form load characteristic data. To eliminate the influence of different dimensions on the prediction results, normalize the data to obtain the normalized power load characteristic data set. ,in, Represents the normalized The power load characteristic set at the time , Represents the normalized The i-th power load characteristic at time A quantity representing the characteristics of the power load, Indicates duration.

[0069] Step 2. KL divergence is a measure of the difference between two probability distributions. When the KL divergence of the input data changes significantly, it is determined that virtual drift has occurred in the data stream. Use formula (1) to calculate The power load characteristic set at the time and The power load characteristic set at the time The divergence between , thus obtaining the divergence set ;

[0070] (1)

[0071] In formula (1), Represents the normalized The i-th power load characteristic at time -1 The probability density function of express The probability density function of .

[0072] Step 3. Calculate using equations (2) and (3) The divergence set of moments The mean and standard deviation ,

[0073] (2)

[0074] (3)

[0075] The threshold setting refers to the three standard deviation principle, that is, if the distance between the divergence value and the mean value exceeds the range of three standard deviations, that is, beyond the range of the mean value ± 3 standard deviations, it can usually be regarded as an outlier. The judgment threshold of virtual drift is calculated using formula (4): :

[0076] (4)

[0077] when When There is a virtual drift, Put it into the storage pool.

[0078] Step 4. The core idea of ​​the variable attention mechanism is to assign a weight to each element to indicate its importance when processing sequence data. This weight is calculated based on the input data and context information, which can help the model focus on the important parts and ignore irrelevant information when processing data. Weighted to obtain the weighted power load characteristic set .

[0079] Step 4.1. Calculate using formula (5) Attention score ;

[0080] (5)

[0081] In formula (3), 、 、 and There are 4 parameters to be learned. represents the activation function, express The transpose of

[0082] Step 4.2. Calculate using formula (6) Attention distribution :

[0083] (6)

[0084] In formula (4), Represents the activation function.

[0085] Step 4.3. Use formula (7) to calculate the weighted power load characteristic set :

[0086] (7)

[0087] In formula (7), express The i-th power load characteristic after weighting at each moment.

[0088] Step 5. Construct the MQRLSTM network, which mainly includes: LSTM hidden layer, monotonic layer, and output layer. The monotonic layer is used to eliminate quantile crossing and make the probability distribution of each output obey the monotonically increasing property. Input into the MQRLSTM network for processing to obtain the predicted quantile of power load ;

[0089] Step 5.1. Use formula (8) to get Quantiles Down Conditional quantile of power load at the moment :

[0090] (8)

[0091] In formula (8), express The LSTM hidden layer neural network bias at the moment, express The LSTM hidden layer neural network weights at the moment; Represents the LSTM hidden layer.

[0092] Step 5.2. Use Equation (9) to construct the objective function of the MQRLSTM network :

[0093] (9)

[0094] In formula (9), express The actual value of the power load at the moment, R represents the total number of quantiles, Indicates the Quantiles The quantile loss under , and has:

[0095] (10)

[0096] In formula (10), Represents the independent variable.

[0097] Step 5.3. Use formula (11) to get Quantiles The standardized power load quantile forecast ;

[0098] (11)

[0099] In formula (11), , represents the number of neural units in the hidden layer of LSTM, , represents the number of neural units in the monotonic layer, Indicates the Quantiles The weight from the jth neuron in the lower LSTM hidden layer to the kth neuron in the monotonic layer;

[0100] Step 5.4. Set the weight range of the K neural units in the monotonic layer to the R neural units in the output layer under R quantiles to ; Thus in the weight range The weights of the kth neural unit in the monotonic layer under the rth quantile to the rth neural unit in the output layer Perform random initialization.

[0101] Step 5.5. Use formula (12) to get Quantiles Down Prediction quantile of power load at the moment without quantile crossing :

[0102] (12)

[0103] In formula (12), Represents the normalized quantile forecast of electric load.

[0104] Step 6. Calculate the deviation between the predicted power load value and the actual value at time t using formula (13) .

[0105] (13)

[0106] In formula (13) The predicted quantiles representing the power load without quantile crossing The cumulative distribution of express The actual value of the power load at the moment hour, ,otherwise .

[0107] Step 7. Use equations (14) and (15) to calculate The deviation between the power load forecast value and the actual value at the moment The mean and standard deviation ,

[0108] (14)

[0109] (15)

[0110] Step 8. Also refer to the three standard deviation principle and use formula (16) to calculate the warning threshold of the load forecasting model prediction deviation and drift threshold :

[0111] (16)

[0112] when , which means that when the model prediction deviation exceeds the warning level, Put it into the storage pool. After real drift occurs, the model is retrained with the data in the storage pool to obtain the updated network weights , return to step 5 and continue with the power load forecast for the next moment.

[0113] Step 9. The predicted value with quantile 0.5 in Power load forecast value at the moment ; Thus, using formula (17) we can get Probability density function of load distribution at time , thus and After denormalization, we get Denormalized power load forecast value at time and Probability density distribution function of power load at time :

[0114] (17)

[0115] In formula (17), Indicates bandwidth, is a Gaussian function.

[0116] In this embodiment, an electronic device includes a memory and a processor, wherein the memory is used to store a program that supports the processor to execute the above method, and the processor is configured to execute the program stored in the memory.

[0117] In this embodiment, a computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the above method are executed.

Claims

1. A method for predicting the online probability density of power load considering the influence of virtual drift and real drift, characterized in that: Proceed as follows: Step 1. Collect historical power load and related influencing factors and form load characteristic data, then normalize them to obtain the normalized power load characteristic data set. ,in, Represents the normalized The power load characteristic set at the time , Represents the normalized The i-th power load characteristic at time A quantity representing the characteristics of the electric load, Indicates duration; Step 2. Calculate using formula (1) The power load characteristic set at the time and The power load characteristic set at the time The divergence between , thus obtaining the divergence set ; (1) In formula (1), Represents the normalized The i-th power load characteristic at time -1 The probability density function of express The probability density function of Step 3. Calculate using equations (2) and (3) Mean value at time and standard deviation : (2) (3) In formula (2) and formula (3), represents the divergence at time n, and , Calculate the judgment threshold of virtual drift using formula (4) : (4) when When There is a virtual drift, Put it into the storage pool; Step 4. Use variable attention mechanism to Weighted to obtain the weighted power load characteristic set ; Step 4.

1. Calculate using formula (5) Attention score ; (5) In formula (3), 、 、 and There are 4 parameters to be learned. represents the activation function, express The transpose of Step 4.

2. Calculate using formula (6) Attention distribution : (6) In formula (4), represents the activation function; Step 4.

3. Use formula (7) to calculate the weighted power load characteristic set : (7) In formula (7), express The i-th power load characteristic after time weighting; Step 5. Build the MQRLSTM network, including LSTM hidden layer, monotonic layer and output layer, and Input into the MQRLSTM network for processing to obtain the predicted quantile of power load ; Step 6. Calculate the probability density function of the power load forecast distribution at time t using formula (13): The actual value of power load The deviation between : (13) In formula (13), represents the probability density function of the power load forecast distribution at time t, The load value corresponding to the probability density function of the power load forecast distribution at time t is represented by, express The actual value of the power load at the moment season Otherwise, let ; Step 7. Use equations (14) and (15) to calculate Probability density function of power load forecast distribution at time and the true value The mean deviation between and standard deviation : (14) (15) In formula (14) and formula (15), The probability density function representing the power load forecast distribution at time n and the actual value of power load at time n The deviation between ; The load value corresponding to the probability density function of the power load forecast distribution at time n; Step 8. Use formula (16) to calculate Warning threshold for moment-to-moment load forecast deviation and drift threshold : (16) Step 9. When ,Will Put it into the storage pool and execute step 10; otherwise, execute step 10 directly; Step 10. When ,express Real drift occurs, and the MQRLSTM network is trained using the data in the storage pool to obtain the updated network weights. Then, follow step 5 to Re-predict and get Quantiles Down There is no power load forecast quantile at the moment when the quantile crosses, and step 11 is executed; otherwise, step 11 is executed; Step 11. The predicted value with quantile 0.5 in Power load forecast value at the moment ; Thus, using formula (17) we can get Probability density function of power load forecast distribution at time , Represents the load value corresponding to the power load forecast distribution, and then and After denormalization, we get Denormalized power load forecast value at time and Probability density function of power load forecast distribution at time : (17) In formula (17), Indicates bandwidth, is a Gaussian function.

2. The method for predicting online probability density of power load considering the influence of virtual drift and real drift according to claim 1, characterized in that: Step 5 is performed as follows: Step 5.

1. Use formula (8) to get Quantiles Down Conditional quantile of power load at the moment : (8) In formula (8), express The LSTM hidden layer neural network bias at the moment, express The LSTM hidden layer neural network weights at the moment; represents the LSTM hidden layer; Step 5.

2. Use Equation (9) to construct the objective function of the MQRLSTM network : (9) In formula (9), express The actual value of the power load at the moment, R represents the total number of quantiles, Indicates the Quantiles The quantile loss under , and has: (10) In formula (10), represents the independent variable; Step 5.

3. Use formula (11) to get Quantiles The standardized power load forecast quantile ; (11) In formula (11), , represents the number of neural units in the LSTM hidden layer, , represents the number of neural units in the monotonic layer, Indicates the Quantiles The jth neural unit of the LSTM hidden layer is transferred to the kth neural unit of the monotonic layer. moment weight; Step 5.

4. Set the weight range of the K neural units in the monotonic layer to the R neural units in the output layer under R quantiles to , so that in the weight range The weights of the kth neural unit of the monotonic layer under the rth quantile to the rth neural unit of the output layer Perform random initialization; Step 5.

5. Use formula (12) to get Quantiles Down Quantiles of power load forecast without quantile crossing at any time : (12)。 3. An electronic device comprising a memory and a processor, characterized in that: The memory is used to store a program that supports the processor to execute the power load online probability density prediction method according to claim 1 or 2, and the processor is configured to execute the program stored in the memory.

4. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method for predicting the online probability density of electric load according to claim 1 or 2 are executed.

Images