Green electricity transaction prediction method and system based on block chain

Abstract

The invention relates to a block chain-based green electricity transaction prediction method and system. When the green electricity price is predicted, the real-time green electricity transaction data needing to be acquired not only comprises the price data and the transaction volume data, but also comprises the time data, the weather data and the environment data, and the price prediction value of each time point can be predicted more accurately by considering the influence of the time data, the weather data and the environment data on the green electricity price; moreover, when the price prediction values are output through the prediction model, the fluctuation rate of each price prediction value and the probability distribution of each price prediction value in each fluctuation rate interval can be predicted, and the fluctuation size of each prediction value and the fluctuation probability of each prediction value in different fluctuation intervals can be known through the fluctuation rates and the probability distribution. Therefore, effective transaction suggestions can be given.

Description

Technical Field

[0001] The present application relates to the field of green electricity trading technology, and in particular to a green electricity trading prediction method and system based on blockchain. Background Art

[0002] With the development of renewable energy, the green power trading market is expanding. Green power refers to the use of specific power generation equipment, such as wind turbines and solar photovoltaic cells, to convert renewable energy such as wind and solar energy into electrical energy. The existing green power trading system mainly predicts the price of green power through historical price data, and the prediction effect is not good.

[0003] Therefore, how to accurately predict the price of green electricity is a technical problem that technical personnel in this field need to solve. Summary of the invention

[0004] The present application provides a green electricity transaction prediction method and system based on blockchain to accurately predict the price of green electricity.

[0005] In the first aspect, the present application provides a green electricity transaction prediction method based on blockchain, comprising:

[0006] Acquire real-time green electricity transaction data; wherein the real-time green electricity transaction data includes: time data, price data, transaction volume data, price fluctuation range data at different levels, weather data, and environmental data;

[0007] The real-time green electricity transaction data is input into a prediction model, and the transaction prediction data is output through the prediction model; wherein the transaction prediction data includes: a price prediction value at each time point, a volatility of each price prediction value, and a probability distribution of each price prediction value in each volatility range.

[0008] Optionally, the process of generating the price fluctuation range data at different levels includes:

[0009] Get the price mean and price standard deviation of price data within a preset time period;

[0010] Determine the price fluctuation range according to the price mean, the price standard deviation and the dynamic adjustment factor; the dynamic adjustment factor is automatically adjusted according to market volatility;

[0011] The price fluctuation range is divided into price fluctuation range data at different levels.

[0012] Optionally, the prediction model is a multi-layer long short-term memory prediction model; the multi-layer long short-term memory prediction model is generated by training historical green electricity transaction data.

[0013] Optionally, before acquiring the real-time green electricity transaction data, the method further includes:

[0014] Obtain initial green electricity transaction data in real time;

[0015] Preprocessing the initial green electricity transaction data to generate real-time green electricity transaction data;

[0016] The real-time green electricity transaction data is stored in the blockchain.

[0017] Optionally, the acquiring of real-time green electricity transaction data includes:

[0018] The real-time green electricity transaction data is obtained from the blockchain.

[0019] Optionally, the environmental characteristic data includes: temperature data and humidity data.

[0020] Optionally, after outputting the transaction prediction data through the prediction model, the method further includes:

[0021] Generate transaction suggestion information based on the transaction prediction data.

[0022] In the second aspect, the present application provides a green electricity transaction prediction system based on blockchain, including:

[0023] The first acquisition module is used to acquire real-time green electricity transaction data; wherein the real-time green electricity transaction data includes: time data, price data, transaction volume data, price fluctuation range data at different levels, weather data, and environmental data;

[0024] A prediction module is used to input the real-time green electricity transaction data into a prediction model and output transaction prediction data through the prediction model; wherein the transaction prediction data includes: a price prediction value at each time point, a volatility of each price prediction value, and a probability distribution of each price prediction value in each volatility range.

[0025] Optionally, the green electricity transaction prediction system further includes:

[0026] The second acquisition module is used to obtain the price mean and price standard deviation of the price data within a preset time period;

[0027] A first determination module is used to determine a price fluctuation range according to the price mean, the price standard deviation and a dynamic adjustment factor; the dynamic adjustment factor is automatically adjusted according to market volatility;

[0028] The second determining module is used to divide the price fluctuation range into price fluctuation range data at different levels.

[0029] Optionally, the green electricity transaction prediction system further includes:

[0030] The third acquisition module is used to acquire the initial green electricity transaction data in real time;

[0031] A processing module, used for preprocessing the initial green electricity transaction data to generate real-time green electricity transaction data;

[0032] The storage module is used to store the real-time green electricity transaction data in the blockchain.

[0033] The above-mentioned technical scheme provided by the embodiment of the present application has the following advantages compared with the prior art: when predicting the green electricity price, the real-time green electricity transaction data required to be obtained by the present application includes not only price data and transaction volume data, but also time data, weather data, and environmental data. By considering the impact of time data, weather data, and environmental data on the green electricity price, the price forecast value at each time point can be predicted more accurately; and when the present scheme outputs the price forecast value through the prediction model, it can also predict the volatility of each price forecast value and the probability distribution of each price forecast value in each volatility range. Through the volatility and probability distribution, the fluctuation size of each forecast value and the probability of fluctuation in different volatility ranges can be understood, so as to give effective trading suggestions. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the invention and, together with the description, serve to explain the principles of the invention.

[0035] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0036] One or more embodiments are exemplarily described by pictures in the corresponding drawings, and these exemplified descriptions do not constitute limitations on the embodiments. Elements with the same reference numerals in the drawings represent similar elements, and unless otherwise stated, the figures in the drawings do not constitute proportional limitations.

[0037] Figure 1 A flowchart of a green electricity transaction prediction method based on blockchain provided in an embodiment of the present application;

[0038] Figure 2 A schematic diagram of the structure of a green electricity transaction prediction system based on blockchain provided in an embodiment of the present application;

[0039] Figure 3 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0040] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.

[0041] The disclosure below provides many different embodiments or examples to implement different structures of the present invention. In order to simplify the disclosure of the present invention, the parts and settings of specific examples are described below. Of course, they are only examples, and the purpose is not to limit the present invention. In addition, the present invention can repeat reference numbers and / or letters in different examples. This repetition is for the purpose of simplification and clarity, and does not itself indicate the relationship between the various embodiments and / or settings discussed.

[0042] In order to accurately predict the price of green electricity, this application provides a green electricity transaction prediction method and system based on blockchain.

[0043] See also Figure 1 , Figure 1 A flowchart of a green electricity transaction prediction method based on blockchain provided in an embodiment of the present application includes:

[0044] S101, obtaining real-time green electricity transaction data; wherein the real-time green electricity transaction data includes: time data, price data, transaction volume data, price fluctuation range data at different levels, weather data, and environmental data;

[0045] In this embodiment, it is first necessary to obtain real-time green electricity trading data, which includes at least time data, price data, transaction volume data, price fluctuation range data at different levels, weather data, and environmental data; wherein, time data refers to data related to time, such as: current season data, date data, transaction timestamp data, etc., which are not specifically limited here; price data refers to the price value at the current time point; price fluctuation range data at different levels are determined according to the current price mean, price standard deviation and dynamic adjustment factor after the price fluctuation range is determined, and then divided into multiple levels; weather data refers to data related to weather, such as: weather conditions, light conditions, etc.; environmental data refers to data related to the environment of the power generation site, including: temperature data, humidity data, power generation equipment efficiency, etc. at the power generation site.

[0046] It should be noted that when obtaining the above-mentioned multiple green electricity transaction data, relevant data can be collected from multiple data sources, such as: obtaining green electricity transaction price data, transaction volume data, etc. from the power market platform data, obtaining temperature data, humidity data, weather conditions, light conditions and other data from the meteorological station, and obtaining: transaction timestamps and other transaction-related information from the exchange.

[0047] S102. Inputting real-time green electricity transaction data into a prediction model, and outputting transaction prediction data through the prediction model; wherein the transaction prediction data includes: a price prediction value at each time point, a volatility of each price prediction value, and a probability distribution of each price prediction value in each volatility range.

[0048] In this embodiment, price prediction is performed specifically through a prediction model, which needs to be trained in advance with historical green electricity transaction data, and after passing the test, the input real-time green electricity transaction data is predicted. In addition, the transaction prediction data output by the prediction model includes the following three types of data: price prediction value, volatility of price prediction value, and probability distribution of price prediction value in each volatility interval, where volatility refers to the degree of change of the prediction value relative to the mean, which is used to measure the magnitude of the fluctuation of the price prediction value; the probability distribution of price prediction value in each volatility interval refers to the probability distribution of each prediction value in different volatility intervals.

[0049] For example: the price forecast value is: 0.155 yuan / kWh; the probability of being in the volatility range of 0-1% is 30%, the probability of being in the volatility range of 1-2% is 50%, and the probability of being in the volatility range of 2-3% is 20%. That is, although the current price forecast value is 0.155 yuan / kWh, there is a 50% probability that the price forecast value will fluctuate within the volatility range of 2-3%.

[0050] Furthermore, in this embodiment, after the transaction prediction data is output through the prediction model, transaction suggestion information can also be generated according to the transaction prediction data, and the transaction prediction data and transaction suggestion information can be displayed, or sent to the terminal device, email, text message, etc. of the predetermined contact; as shown above, if the price prediction value is: 0.155 yuan / kWh; the probability of being in the volatility range of 0-1% is 30%, the probability of being in the volatility range of 1-2% is 50%, and the probability of being in the volatility range of 2-3% is 20%, then the generated transaction suggestion information can be: Since the predicted volatility is mainly concentrated in the 1-2% range, it is recommended that the transaction parties trade in the range of 0.152-0.158 yuan / kWh to avoid the risks brought by price fluctuations.

[0051] From the above, it can be seen that when predicting the price of green electricity, the real-time green electricity transaction data that needs to be obtained by this application includes not only price data and transaction volume data, but also time data, weather data, and environmental data. By considering the impact of time data, weather data, and environmental data on the price of green electricity, the price forecast value at each time point can be predicted more accurately; and when this scheme outputs the price forecast value through the prediction model, it can also predict the volatility of each price forecast value and the probability distribution of each price forecast value in each volatility range. Through the volatility and probability distribution, the fluctuation size of each forecast value and the probability of fluctuation in different volatility ranges can be understood, which is helpful for demanders and suppliers to evaluate future price trends and thus make better use of green electricity.

[0052] In this embodiment, a specific generation process of price fluctuation range data at different levels is disclosed, and the process includes the following steps:

[0053] Get the price mean and price standard deviation of price data within a preset time period;

[0054] Determine the price fluctuation range according to the price mean, the price standard deviation and the dynamic adjustment factor; the dynamic adjustment factor is automatically adjusted according to market volatility;

[0055] The price fluctuation range is divided into price fluctuation range data at different levels.

[0056] In this embodiment, the price fluctuation range is determined by Upper_Band(t) and Lower_Band(t), where Upper_Band(t) is the upper limit of the fluctuation and Lower_Band(t) is the lower limit of the fluctuation. The specific calculation method of the price fluctuation range is:

[0057] Upper_Band(t)=μ(t)+k×σ(t)

[0058] Lower_Band(t)=μ(t)-k×σ(t)

[0059] Among them, μ(t) is the price mean at time t, σ(t) is the standard deviation at time t, and the price mean and standard deviation at time t are calculated based on the price values ​​within a certain time range; k is a dynamic adjustment factor, which is automatically adjusted according to market volatility. For example, if the market fluctuates violently, the value of k needs to be set relatively large to cover the extreme conditions of the market. If the market fluctuations are relatively mild, a relatively small value can be set, and the value of k is generally an integer.

[0060] After calculating the price fluctuation range, the price fluctuation range can be divided into price fluctuation range data of different levels according to the number of layers n. The price fluctuation range data of the i-th layer is:

[0061]

[0062] Among them, Interval i (t) represents the price fluctuation range data of the i-th layer, i = 1, 2, ..., n.

[0063] It should be noted that the method for generating price fluctuation range data at different levels described in this embodiment is not only used when predicting green electricity prices, but also when training a prediction model. This method is also required to generate price fluctuation range data at different levels in historical green electricity transaction data. By introducing this indicator, the prediction model in this solution can predict the volatility of the price prediction value, so as to give effective trading suggestions and guide the demand side and the supply side to make reasonable expectations for the green electricity price.

[0064] Based on the above embodiment, this embodiment further includes the following steps before obtaining real-time green electricity transaction data:

[0065] Obtain initial green electricity transaction data in real time;

[0066] Preprocessing the initial green electricity transaction data to generate real-time green electricity transaction data;

[0067] The real-time green electricity transaction data is stored in the blockchain.

[0068] In this embodiment, the data type of the initial green electricity transaction data is consistent with the data type of the real-time green electricity transaction data, including: time data, price data, transaction volume data, price fluctuation range data at different levels, weather data, and environmental data; the difference is that the initial green electricity transaction data is unprocessed raw data. For the acquired initial green electricity transaction data, it is necessary to preprocess it first. When preprocessing, it is necessary to process the missing values ​​in the data first. For price data, the forward filling method is used to fill the missing values, such as: directly filling it with the average value of all price data at the current time; for transaction volume data, the missing values ​​are set to 0, and for weather data, the mean filling method is used to process the missing values, etc., which are not specifically limited here; then, various types of data are standardized to eliminate dimensional differences, such as converting price, transaction volume and weather data into standard normal distribution. Finally, the data from different data sources are merged into one data set to ensure that each timestamp has corresponding price, transaction volume and weather data, etc.

[0069] After preprocessing the initial green electricity transaction data, a feature vector can be constructed. The feature vector is recorded as the real-time green electricity transaction data input to the prediction model. In this embodiment, the feature vector is represented by X t , the eigenvector is specifically:

[0070] X t =[P(t),V(t),W(t),Interval 1 (t),Interval 2 (t),…,Interval n (t),T(t),H(t)]

[0071] Among them, P(t) is the price data at time t, V(t) is the transaction volume data, W(t) is the weather data, and Interval i (t) is the price fluctuation range data of the i-th layer, T(t) is the time data, and H(t) is the environmental data.

[0072] It should be noted that in order to ensure the transparency and immutability of the data, this embodiment needs to store the preprocessed data on the blockchain. The specific steps are as follows: create a smart contract for storing and managing data on the blockchain. The smart contract defines the data structure and storage method; upload the data to the blockchain in batches according to timestamps. Each batch of data contains a timestamp and the green electricity transaction data corresponding to the timestamp. Therefore, when obtaining real-time green electricity transaction data, this solution specifically obtains real-time green electricity transaction data from the blockchain to accurately predict prices.

[0073] In summary, this solution introduces blockchain technology in price prediction, so any access and modification to data needs to be done through smart contracts. In this way, the possibility of data tampering is avoided, the security and transparency of the data are ensured, and the accuracy and stability of the prediction of green electricity price fluctuations are improved.

[0074] In this embodiment, the prediction model can specifically adopt a multi-layer long short-term memory prediction model (LSTM, Long Short-Term Memory). The LSTM model can capture the long-term dependencies in time series data, thereby improving the accuracy of the prediction. In addition, the multi-layer long short-term memory prediction model is generated by training historical green electricity trading data, and the historical green electricity trading data is consistent with the type of real-time green electricity trading data described above. After the model is trained with historical green electricity trading data, the trained prediction model can be used to perform price prediction.

[0075] Specifically, the historical green electricity transaction data used for training data also needs to be cleaned by the preprocessing method described in the above embodiment and stored in the blockchain. When training the prediction model, it is also necessary to obtain historical green electricity transaction data from the blockchain. The historical green electricity transaction data obtained needs to be split into a training set and a test set. The training set is used to train the model, and the test set is used to evaluate the model performance. Then, the feature vector and the target variable (such as price) are reshaped to adapt to the input format of the LSTM model; wherein the feature vector needs to include information such as price, transaction volume, temperature, humidity, fluctuation range, time, etc. In this embodiment, the LSTM model consists of multiple LSTM layers and a fully connected layer. The LSTM layer is used to capture dependencies in the time series, and the fully connected layer is used for the final price prediction; this scheme selects an optimizer (such as Adam) and a loss function (such as mean square error) for model compilation. During training, the training set is used to train the LSTM model, and the model parameters are adjusted so that it can accurately predict prices. During the training process, the performance of the LSTM model is monitored and the hyperparameters are adjusted to optimize the model. The hyperparameters include learning rate, batch size, number of iterations, etc.

[0076] Among them, the adaptive learning rate is:

[0077]

[0078] Among them, η 0 is the initial learning rate, λ is the decay rate, and η(t) is the learning rate at time t. Here, the improved prediction model of this scheme is explained:

[0079] f t =σ(W f ·[h t-1 ,x t ]+b f )

[0080] i t =σ(W i ·[h t-1 ,x t ]+b i )

[0081]

[0082] o t =σ(W o ·[h t-1 ,x t ]+b o )

[0083] h t =o t tanh(C t )

[0084] Where: f t is the activation function output of the forget gate, i t is the activation function output of the input gate, o t is the activation function output of the output gate, σ represents the activation function, and the above three activation function outputs are used to control the state update and output of the LSTM network; W f is the first weight matrix, W i is the second weight matrix, W C is the third weight matrix, W o is the fourth weight matrix, which is used to connect the input, the hidden layer state of the previous time step and the activation function of each gate; b f is the first bias vector, b i is the second bias vector, b C is the third bias vector, b o is the fourth bias vector, and the above-mentioned bias vectors are used for the activation function of each gate; t is the hidden layer state of the LSTM network, which is used to capture time series features; C t It is the cell state of the LSTM network, which is used to memorize information over a long time span; It is a special memory unit used to store and transmit long-term dependency information in the LSTM network and is an information transmission channel; t The input vector X t .

[0085] In this embodiment, the output of the prediction model includes not only the price prediction value for a period of time in the future, but also the volatility of each price prediction value and the probability distribution of each price prediction value in each volatility range.

[0086] Specifically, volatility is calculated as follows:

[0087]

[0088] Among them, P t is the predicted value at time t, μ t The historical price average.

[0089] The output obtained by this scheme through the LSTM model is y t , which represents the logarithmic probability of each volatility interval, so this solution needs to convert it into a probability distribution through the Softmax function:

[0090]

[0091] Where: y t,i is the i-th component of the temporal tLSTM model output, y t,jis the jth component of the temporal tLSTM model output, p i is the volatility interval τ at time t t The probability distribution is as follows:

[0092] τ pred (t) = {(p 1 , τ 1 ), (p 2 , τ 2 ),...,(p n , τ n )}

[0093] Among them, τ pred (t) is the predicted volatility distribution at time t, that is, the probability distribution of the predicted price value at time t in each volatility interval, τ i For different volatility interval values, i = 1, 2, ..., n; the volatility interval can be 1-2%, 2-3%, 3%-4%, etc. This scheme can obtain the possibility of price fluctuations in the future by calculating the probability distribution of each volatility interval.

[0094] For example: Suppose the output log probability of the model is y t =[0.1,0.5,1.0], that is, the model predicts that the logarithmic probability of volatility in the following three intervals is:

[0095] Interval 1 (1%-2%): log probability y t1 =0.1

[0096] Interval 2 (2%-3%): log probability y t2 =0.5

[0097] Interval 3 (3%-4%): log probability y t3 =1.0

[0098] Use the Softmax function to calculate the probability of each interval:

[0099]

[0100] Therefore, the probability distribution given by the model is:

[0101] Probability of volatility falling within the 1%-2% range: 20.2%

[0102] Probability of volatility falling within the 2%-3% range: 30.1%

[0103] Probability of volatility falling within the 3%-4% range: 49.7%.

[0104] In summary, the LSTM model generates a probability distribution through the Softmax function, which indicates the probability that the future price volatility may be in various intervals. This distribution provides users with more information about future price fluctuations, rather than just a single volatility prediction value. For example, in the above example, the volatility is most likely to fall in the 3%-4% range (with a probability of 49.7%), followed by the 2%-3% range (30.1%). This probability distribution can help users have a comprehensive assessment of the volatility range of future price trends, and can refer to the probability of this volatility range in green power trading decisions to make more accurate choices.

[0105] Here, a specific embodiment is provided to specifically describe this solution:

[0106] Step 1: Data collection and cleaning:

[0107] 1.1. Obtain data from various data sources: Data obtained from the power market platform include green power transaction prices, transaction volumes, etc.; data obtained from the meteorological station include weather data such as temperature and humidity, etc.; data obtained from the exchange include transaction-related information such as timestamps.

[0108] 1.2. Data processing: The missing value processing operations performed on different types of data include: for price data, missing data is filled according to the mean value near the time; for trading volume data, missing values ​​are filled with known values; for weather data, the mean filling method is used to process missing values.

[0109] Specific data example:

[0110] Timestamp: 2024-08-01 10:00

[0111] Price: 0.15 yuan / kWh

[0112] Transaction volume: 5000kWh

[0113] Temperature: 25℃

[0114] Humidity: 60%

[0115] Price fluctuation range: 0.14-0.16 yuan / kWh

[0116] Trading volume fluctuation range: 4500-5500kWh

[0117] Step 2: Data on-chain

[0118] 2.1. Create a smart contract:

[0119]

[0120] 2.2. Upload the data obtained in step 1 to the blockchain in batches according to timestamps. Each batch of data contains information such as timestamp, price, and transaction volume.

[0121] Step 3: Model training

[0122] 3.1. Split the dataset: Split the dataset into training set (80%) and test set (20%).

[0123] 3.2. Data preparation: Reshape the feature vector and target variable (price) to adapt to the LSTM model input format.

[0124] The eigenvector is: (X_t=[P_t,V_t,W_t,Interval{1t},\ldots,Interval{nt},T_t,H_t])

[0125] (P_t): Price

[0126] (V_t): Trading volume

[0127] (W_t): Weather factors (temperature, humidity)

[0128] (Interval_{it}): The fluctuation interval of the i-th layer

[0129] (T_t): time characteristics

[0130] (H_t): Other environmental characteristics

[0131] Step 4: Model prediction

[0132] 4.1. Use the test set data to perform model prediction and obtain the future price forecast value.

[0133] 4.2. Calculate the volatility distribution of the price forecast value.

[0134] Specific steps:

[0135] Example of prediction results:

[0136] Timestamp: 2024-08-01 11:00

[0137] Forecast price: 0.155 yuan / kWh

[0138] Fluctuation rate: 0.002 yuan / kWh

[0139] Volatility Distribution:

[0140] 0-1%: 30%

[0141] 1-2%: 50%

[0142] 2-3%: 20%

[0143] The generated trading recommendation is: Since the predicted volatility is mainly concentrated in the 1-2% range, it is recommended that the trading party trade in the 0.152-0.158 yuan / kWh range to avoid the risks brought by price fluctuations.

[0144] It can be understood that if the model is successfully tested using the test set data in step four, the trained model can be used to predict real-time green trading data; if the test fails, step three needs to be re-executed to continue training the model until the test succeeds.

[0145] In summary, it can be seen that the present invention, by combining blockchain technology, improved technical indicators and prediction algorithms, not only improves the prediction accuracy of the green electricity trading market, realizes efficient prediction of green electricity cost fluctuations, but also enhances the transparency and credibility of data. The application of improved technical indicators and prediction algorithms in the green electricity trading market can effectively predict power generation cost fluctuations and guide market expectations, and give effective trading suggestions based on the prediction results.

[0146] See also Figure 2 , Figure 2 A schematic diagram of the structure of a green electricity transaction prediction system based on blockchain provided in an embodiment of the present application, the system specifically includes:

[0147] The first acquisition module 11 is used to acquire real-time green electricity transaction data; wherein the real-time green electricity transaction data includes: time data, price data, transaction volume data, price fluctuation range data at different levels, weather data, and environmental data;

[0148] The prediction module 12 is used to input the real-time green electricity transaction data into the prediction model and output transaction prediction data through the prediction model; wherein the transaction prediction data includes: the price prediction value at each time point, the volatility of each price prediction value, and the probability distribution of each price prediction value in each volatility range.

[0149] As an optional embodiment, the green electricity transaction prediction system further includes:

[0150] The second acquisition module is used to obtain the price mean and price standard deviation of the price data within a preset time period;

[0151] A first determination module is used to determine a price fluctuation range according to the price mean, the price standard deviation and a dynamic adjustment factor; the dynamic adjustment factor is automatically adjusted according to market volatility;

[0152] The second determining module is used to divide the price fluctuation range into price fluctuation range data at different levels.

[0153] As an optional embodiment, the prediction model is a multi-layer long short-term memory prediction model; the multi-layer long short-term memory prediction model is generated by training historical green electricity transaction data.

[0154] As an optional embodiment, the green electricity transaction prediction system further includes:

[0155] The third acquisition module is used to acquire the initial green electricity transaction data in real time;

[0156] A processing module, used for preprocessing the initial green electricity transaction data to generate real-time green electricity transaction data;

[0157] The storage module is used to store the real-time green electricity transaction data in the blockchain.

[0158] As an optional embodiment, the first acquisition module is specifically used to: obtain the real-time green electricity transaction data from the blockchain.

[0159] As an optional embodiment, the environmental characteristic data includes: temperature data and humidity data.

[0160] As an optional embodiment, the green electricity transaction prediction system further includes:

[0161] A suggestion generation module is used to generate transaction suggestion information according to the transaction prediction data,

[0162] Regarding the system in the above embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the method, and will not be elaborated here.

[0163] See also Figure 3 , Figure 3 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application, the electronic device specifically includes:

[0164] The processor 21, the memory 22 and a computer program stored in the memory 22 and executable on the processor 21. The processor 21 executes the steps of the green electricity transaction prediction method described in any of the above method embodiments through the computer program.

[0165] Among them, the processor 21 may include one or more processing cores, such as a 4-core processor, an 8-core processor, etc. The processor 21 may be implemented in at least one hardware form of DSP (Digital Signal Processing), FPGA (Field-Programmable Gate Array), and PLA (Programmable Logic Array). The processor 21 may also include a main processor and a coprocessor. The main processor is a processor for processing data in the awake state, also known as a CPU (Central Processing Unit); the coprocessor is a low-power processor for processing data in the standby state. In some embodiments, the processor 21 may be integrated with a GPU (Graphics Processing Unit), which is responsible for rendering and drawing the content to be displayed on the display screen. In some embodiments, the processor 21 may also include an AI (Artificial Intelligence) processor, which is used to process computing operations related to machine learning.

[0166] The memory 22 may include one or more computer-readable storage media, which may be non-transitory. The memory 22 may also include a high-speed random access memory, and a non-volatile memory, such as one or more disk storage devices, flash memory storage devices. In this embodiment, the memory 22 is at least used to store the following computer program 221, wherein, after the computer program is loaded and executed by the processor 21, it can implement the relevant steps in the green electricity transaction prediction method disclosed in any of the aforementioned embodiments. In addition, the resources stored in the memory 22 may also include an operating system 222 and data 223, etc., and the storage method may be temporary storage or permanent storage. Among them, the operating system 222 may include Windows, Unix, Linux, etc.

[0167] In some embodiments, the electronic device may further include a display screen 23 , an input / output interface 24 , a communication interface 25 , a sensor 26 , a power source 27 , and a communication bus 28 .

[0168] certainly, Figure 3 The structure of the electronic device shown does not constitute a limitation on the electronic device in the embodiments of the present application. In actual applications, the electronic device may include Figure 3 More or fewer components than shown, or combinations of certain components.

[0169] In another exemplary embodiment, a computer storage medium is also provided, and when the program instructions are executed by a processor, the steps of the green electricity transaction prediction method described in any of the above method embodiments are implemented. The storage medium may include: a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and other media that can store program codes.

[0170] Optionally, the specific examples in this embodiment may refer to the examples described in the above embodiments, and this embodiment will not be described in detail here.

[0171] It should be understood that the terms used herein are only for the purpose of describing specific example embodiments and are not intended to be limiting. Unless the context clearly indicates otherwise, the singular forms "one", "an" and "said" as used herein may also be meant to include plural forms. The terms "include", "comprise", "contain", and "have" are inclusive, and therefore specify the existence of stated features, steps, operations, elements and / or parts, but do not exclude the existence or addition of one or more other features, steps, operations, elements, parts, and / or combinations thereof. The method steps, processes, and operations described herein are not interpreted as necessarily requiring them to be performed in the specific order described or illustrated, unless the execution order is clearly indicated. It should also be understood that additional or alternative steps may be used.

[0172] The foregoing is merely a specific embodiment of the present invention, which enables those skilled in the art to understand or implement the present invention. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but rather to the widest scope consistent with the principles and novel features claimed herein.

Claims

1. A green electricity transaction prediction method based on blockchain, characterized in that: include: Acquire real-time green electricity transaction data; wherein the real-time green electricity transaction data includes: time data, price data, transaction volume data, price fluctuation range data at different levels, weather data, and environmental data; The real-time green electricity transaction data is input into a prediction model, and the transaction prediction data is output through the prediction model; wherein the transaction prediction data includes: a price prediction value at each time point, a volatility of each price prediction value, and a probability distribution of each price prediction value in each volatility range.

2. The green electricity transaction prediction method according to claim 1, characterized in that: The generation process of the price fluctuation range data at different levels includes: Get the price mean and price standard deviation of price data within a preset time period; Determine the price fluctuation range according to the price mean, the price standard deviation and the dynamic adjustment factor; the dynamic adjustment factor is automatically adjusted according to market volatility; The price fluctuation range is divided into price fluctuation range data at different levels.

3. The green electricity transaction prediction method according to claim 1, characterized in that: The prediction model is a multi-layer long and short-term memory prediction model; the multi-layer long and short-term memory prediction model is generated by training historical green electricity transaction data.

4. The green electricity transaction prediction method according to claim 1, characterized in that: Before obtaining the real-time green electricity transaction data, the method further includes: Obtain initial green electricity transaction data in real time; Preprocessing the initial green electricity transaction data to generate real-time green electricity transaction data; The real-time green electricity transaction data is stored in the blockchain.

5. The green electricity transaction prediction method according to claim 4, characterized in that: The obtaining of real-time green electricity transaction data includes: The real-time green electricity transaction data is obtained from the blockchain.

6. The green electricity transaction prediction method according to claim 1, characterized in that: The environmental characteristic data include: temperature data and humidity data.

7. The green electricity transaction prediction method according to any one of claims 1 to 6, characterized in that: After the transaction prediction data is outputted through the prediction model, the method further includes: Generate transaction suggestion information based on the transaction prediction data.

8. A green electricity transaction prediction system based on blockchain, characterized in that: include: The first acquisition module is used to acquire real-time green electricity transaction data; wherein the real-time green electricity transaction data includes: time data, price data, transaction volume data, price fluctuation range data at different levels, weather data, and environmental data; A prediction module is used to input the real-time green electricity transaction data into a prediction model and output transaction prediction data through the prediction model; wherein the transaction prediction data includes: a price prediction value at each time point, a volatility of each price prediction value, and a probability distribution of each price prediction value in each volatility range.

9. The green electricity transaction prediction system according to claim 8, characterized in that: The green electricity transaction prediction system further includes: The second acquisition module is used to obtain the price mean and price standard deviation of the price data within a preset time period; A first determination module is used to determine a price fluctuation range according to the price mean, the price standard deviation and a dynamic adjustment factor; the dynamic adjustment factor is automatically adjusted according to market volatility; The second determining module is used to divide the price fluctuation range into price fluctuation range data at different levels.

10. The green electricity transaction prediction system according to claim 9, characterized in that: The green electricity transaction prediction system further includes: The third acquisition module is used to acquire the initial green electricity transaction data in real time; A processing module, used for preprocessing the initial green electricity transaction data to generate real-time green electricity transaction data; The storage module is used to store the real-time green electricity transaction data in the blockchain.

Images