CN110753366A - Prediction processing method and device for industry short message gateway capacity - Google Patents
Prediction processing method and device for industry short message gateway capacity Download PDFInfo
- Publication number
- CN110753366A CN110753366A CN201810820109.8A CN201810820109A CN110753366A CN 110753366 A CN110753366 A CN 110753366A CN 201810820109 A CN201810820109 A CN 201810820109A CN 110753366 A CN110753366 A CN 110753366A
- Authority
- CN
- China
- Prior art keywords
- capacity
- short message
- message gateway
- value
- expansion
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000003672 processing method Methods 0.000 title claims description 3
- 238000000034 method Methods 0.000 claims abstract description 34
- 238000003062 neural network model Methods 0.000 claims abstract description 31
- 238000012545 processing Methods 0.000 claims abstract description 25
- 238000004590 computer program Methods 0.000 claims description 10
- 230000015654 memory Effects 0.000 claims description 9
- 238000004891 communication Methods 0.000 claims description 4
- 238000013528 artificial neural network Methods 0.000 description 15
- 238000012360 testing method Methods 0.000 description 14
- 238000012549 training Methods 0.000 description 11
- 210000002569 neuron Anatomy 0.000 description 7
- 230000006403 short-term memory Effects 0.000 description 5
- 238000010586 diagram Methods 0.000 description 4
- 230000007787 long-term memory Effects 0.000 description 4
- 238000010606 normalization Methods 0.000 description 4
- 230000000694 effects Effects 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 230000000306 recurrent effect Effects 0.000 description 3
- 230000004913 activation Effects 0.000 description 2
- 238000006243 chemical reaction Methods 0.000 description 2
- 238000013135 deep learning Methods 0.000 description 2
- 230000007774 longterm Effects 0.000 description 2
- 238000003491 array Methods 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 239000002360 explosive Substances 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W24/00—Supervisory, monitoring or testing arrangements
- H04W24/06—Testing, supervising or monitoring using simulated traffic
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
- H04W4/12—Messaging; Mailboxes; Announcements
- H04W4/14—Short messaging services, e.g. short message services [SMS] or unstructured supplementary service data [USSD]
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Data Exchanges In Wide-Area Networks (AREA)
Abstract
The embodiment of the invention provides a method and a device for predicting and processing the capacity of an industry short message gateway, wherein the method comprises the following steps: the method comprises the steps of obtaining historical operation parameter characteristics of an industry short message gateway in a first time period, obtaining a capacity prediction sequence in a second time period according to the historical operation parameter characteristics and a preset prediction neural network model, comparing each capacity value in the capacity prediction sequence with a preset load threshold value respectively, sending capacity expansion reminding information when the capacity value is determined to exceed the load threshold value, obtaining the maximum capacity value in the capacity prediction sequence, obtaining the capacity expansion capacity value of the industry short message gateway according to the maximum capacity value and a preset capacity expansion formula, achieving the purpose of predicting the capacity of the industry short message gateway in the future time period, and providing reference for the subsequent capacity expansion.
Description
Technical Field
The invention relates to the technical field of communication, in particular to a method and a device for predicting and processing the capacity of an industrial short message gateway.
Background
With the explosive growth of mobile internet applications, the demand of enterprises in various industries on short messages is not reduced and increased, for example, bank verification code short messages, e-commerce payment short messages, various APP login reminding short messages, enterprise promotion short messages and the like, and the industrial application short messages already occupy most of the short message issuing total amount of operators, so that the stable operation of the industrial short message gateway is guaranteed to have a vital significance for the operators in the era of mobile internet. In the prior art, there is no accurate study and calculation method for when and how much capacity needs to be expanded for an industry short message gateway, often a threshold value is simply set for a load to judge the time of expansion, and the size of the capacity needing to be expanded is judged by artificial expert experience, so that the expansion method is still in a simple and extensive stage, the capacity estimation is difficult to obtain higher accuracy, and it is urgent to accurately estimate the load capacity to support accurate expansion in the face of increasing demands, and timely and accurate expansion is a key point for improving the stability of the industry short message gateway of a core network element of an operator.
Disclosure of Invention
The invention provides a method and a device for predicting and processing the capacity of an industrial short message gateway, which are used for solving the problem that the capacity expansion time cannot be accurately acquired in the prior art.
In a first aspect, an embodiment of the present invention provides a method for predicting and processing an industry short message gateway capacity, including:
acquiring historical operating parameter characteristics of an industry short message gateway in a first time period;
and obtaining a capacity prediction sequence in a second time period according to the historical operating parameter characteristics and a preset prediction neural network model.
Optionally, the method further comprises:
comparing each capacity value in the capacity prediction sequence with a preset load threshold value respectively;
and when the existence capacity value is determined to exceed the load threshold value, sending out capacity expansion reminding information.
Optionally, the method further comprises:
acquiring a maximum capacity value in the capacity prediction sequence;
and obtaining the capacity expansion capacity value of the industry short message gateway according to the maximum capacity value and a preset capacity expansion formula.
Optionally, the capacity expansion formula includes:
and R is Max multiplied by k-Z, wherein R is the capacity expansion capacity value, Max is the maximum capacity value in the capacity prediction sequence, k is a preset coefficient, and Z is the total capacity of the industry short message gateway before capacity expansion.
In a second aspect, an embodiment of the present invention provides a device for predicting and processing an industry short message gateway capacity, including:
the acquisition module is used for acquiring the historical operating parameter characteristics of the industry short message gateway in a first time period;
and the prediction module is used for obtaining a capacity prediction sequence in a second time period according to the historical operating parameter characteristics and a preset prediction neural network model.
Optionally, the system further comprises a reminding module, configured to: and comparing each capacity value in the capacity prediction sequence with a preset load threshold value respectively, and sending capacity expansion reminding information when determining that the capacity value exceeds the load threshold value.
Optionally, the system further includes a capacity expansion module, configured to: and acquiring a maximum capacity value in the capacity prediction sequence, and acquiring an expansion capacity value of the industry short message gateway according to the maximum capacity value and a preset expansion formula.
Optionally, the capacity expansion formula includes:
and R is Max multiplied by k-Z, wherein R is the capacity expansion capacity value, Max is the maximum capacity value in the capacity prediction sequence, k is a preset coefficient, and Z is the total capacity of the industry short message gateway before capacity expansion.
In a third aspect, an embodiment of the present invention provides an electronic device, including: a processor, a memory, a bus, and a computer program stored on the memory and executable on the processor;
the processor and the memory complete mutual communication through the bus;
the processor, when executing the computer program, implements the method as described above.
In a fourth aspect, embodiments of the present invention provide a non-transitory computer-readable storage medium having a computer program stored thereon, which when executed by a processor implements the method as described above.
According to the technical scheme, the method for predicting the capacity of the industry short message gateway provided by the embodiment of the invention has the advantages that the historical operation parameter characteristics of the industry short message gateway in the first time period are obtained, and the capacity prediction sequence in the second time period is obtained according to the historical operation parameter characteristics and the preset prediction neural network model, so that the purpose of predicting the capacity of the industry short message gateway in the future time period is achieved, and the reference is provided for the subsequent capacity expansion capacity.
Drawings
Fig. 1 is a schematic flow chart of a method for predicting and processing capacity of an industry short message gateway according to an embodiment of the present invention;
fig. 2 is a schematic flow chart of a method for predicting and processing the capacity of an industry short message gateway according to an embodiment of the present invention;
fig. 3 is a schematic flow chart of a method for predicting and processing the capacity of an industry short message gateway according to an embodiment of the present invention;
fig. 4 is a schematic structural diagram of a prediction processing device for capacity of an industry short message gateway according to an embodiment of the present invention;
fig. 5 is a schematic structural diagram of a prediction processing device for capacity of an industry short message gateway according to an embodiment of the present invention;
fig. 6 is a schematic structural diagram of a prediction processing device for capacity of an industry short message gateway according to an embodiment of the present invention;
fig. 7 is a schematic structural diagram of an electronic device according to an embodiment of the present invention.
Detailed Description
The following detailed description of embodiments of the present invention is provided in connection with the accompanying drawings and examples. The following examples are intended to illustrate the invention but are not intended to limit the scope of the invention.
Fig. 1 shows a method for predicting and processing the capacity of an industry short message gateway according to an embodiment of the present invention, which includes:
s11, acquiring historical operating parameter characteristics of the industry short message gateway in a first time period;
and S12, obtaining a capacity prediction sequence in a second time period according to the historical operating parameter characteristics and a preset prediction neural network model.
For step S11 and step S12, it should be noted that, in the embodiment of the present invention, the industry short message gateway: the full-name industry application short message gateway is a short message issuing channel applied by an operator facing enterprise industry.
The preset prediction neural network model in this embodiment is a model built by building a long-term and short-term memory neural network by using a deep learning framework.
Deep neural network (DNN, deep neural network): a neural network includes an input layer, a hidden layer, and an output layer. By "depth" is meant that the hidden layer in the middle has many layers. So deep learning is really a neural network with many hidden layers. Neurons (Neuron) are the basic units of neural networks, also called nodes (Node), which receive inputs (Input) from external or other nodes and compute outputs (Output) by means of an Activation Function (Activation Function); each input corresponds to a Weight (Weight), i.e., the relative importance of each input received by the node; a Bias (Bias) may be understood as a special input.
RNN (recurrent neural network) is a recurrent neural network. The output of each hidden layer in the RNN is stored in a buffer, the data stored in the buffer can be considered as a part of the input when the hidden layer has data input next time, the output of the neuron is put into the buffer at each time point, and the value in the buffer is overwritten at the next time point. The same neural network is reused as a so-called recurrent neural network. The RNN can be thought of as multiple copies of the same neural network, each neural network module passing a message to the next.
LSTM (long short-term memory) is a special type of RNN, can learn long-term dependence information, can remember long-term information by controlling the time for storing values in a cache, is suitable for predicting time sequences, and solves the problem of RNN gradient variation. Each neuron has four inputs and one output, and each neuron stores a memorized value.
The process of establishing the prediction neural network model is as follows:
s1, acquiring historical operating parameter characteristics of the industry short message gateway in a third time period;
s2, performing normalization processing on the historical operation parameter characteristics, and dividing the processed historical operation parameter characteristics into a training set and a test set;
s3, inputting the training set into a deep long and short term memory neural network model for model training, and inputting the test set into the deep long and short term memory neural network model for model testing to obtain weights corresponding to each neuron;
and S4, taking the deep long-term and short-term memory neural network model and the weight corresponding to each neuron as a prediction neural network model.
With respect to step S1-step S4, it should be noted that, in the embodiment of the present invention, the historical operation parameter features include both the multidimensional motion parameters obtained from the industry short message gateway and the parameter features formed by external factors. For example, the multidimensional operating parameters of the industry short message gateway per hour from 0 point in 12 months and 12 days in 2017 to 24 points in 20 months and 12 days in 2017, which are acquired from the industry short message gateway of a certain operator, total 100 days and 2400 data. During this period spanning 100 days, external factors such as henry, twenty-two, mid-autumn celebration, etc. are included. Therefore, a new feature "date type" related to external factors needs to be introduced, and dates are classified into four categories: 0 (non-holiday and activity day), 1 (legal holiday), 2 (e-commerce activity day, such as twenty-one, twenty-two and 3 (major activity), and in addition, key operation parameters of the previous quarter and the same time of the previous year are added to improve the prediction accuracy. The final industry short message gateway operating parameters include 14 characteristics as follows:
X1: MT downlink short message sending total amount;
X2: transmitting success rate of MT downlink short message;
X3: the success rate of sending MT downlink short messages (the success rate of submitting messages to a short message center by an industry short message gateway);
X4: MO uplink short message sending total amount;
X5: the uplink message of MO sends the success rate;
X6: the success rate of MO uplink short message sending (the success rate of the short message center submitting the message to the industry short message gateway);
X7: the peak load (bar/second) represents the integral highest load of the industry short message gateway and is a value to be predicted by the scheme;
X8: date type (newly introduced externality features);
X9: peak load at the same time in the last quarter;
X10: the total amount of MT downlink short message transmission in the same time in the previous quarter;
X11: MO uplink short message sending total amount at the same time in the previous quarter;
X12: the peak load at the same time in the last year;
X13: the MT downlink short message sending amount at the same time in the last year;
X14: MO uplink short message sending at same time in last yearThe total amount is sent.
The data set can thus be represented as: s ═ X1,X2,X3,X4,X5,X6,X7,X8, X9,X10,X11,X12,X13,X14]。
After data acquisition, the data is first normalized (normalization): normalization refers to scaling the data to fall within a small specific interval. Since LSTM is sensitive to the size of the input data, the data needs to be mapped uniformly into a range of [0,1], and the data is scaled to between a given minimum and maximum value, typically between 0 and 1, using the function minmaxscale (feature _ range ═ 0,1) in sklern. After normalization, the convergence rate of the model and the precision of the model are improved.
Dividing the data set into a training set and a test set: the length of the whole data set is 100 days in total, the training data takes the data of the first 70 days, and the data of the remaining 30 days are taken as test data. The total length of the data set dataset _ length:2400 (i.e., the time span is 2400 hours), the length of the training data train _ data _ size:1680, and the length of the test data test _ data _ size:720 (i.e., the time span is 720 hours).
And (3) carrying out shape conversion on the data: since the LSTM neural network requires a 3-dimensional array for the shape of the input data, it is necessary to convert the data from a 2-dimensional array of samples, features]Conversion into 3-dimensional arrays [ samples, timestamps, features ]]And predicting the peak load condition in the future m hours according to the 14 characteristic historical operating parameters of the last n hours. Taking the example that "n" is 3 and "m" is 1, the "time" is LSTM and considers that each input data is related to how many previous data are input successively, that is, the operation parameters X of the last three hours are determined according to the operation parameters X of the last three hours1-X14To predict the peak load X of the next hour7The case of predicting the value of the next time point (t +1) using the values of the current time point (t) and the previous two time points (t-1) and (t-2) (input t-2, t-1, t, output t + 1). Therefore, the original data set shape is a two-dimensional array of 2400 x 14, and the transformed data set shape is a three-dimensional array of 2400 x 3 x 14The shape of the training data X is train _ x.shape (1680,3,14), the shape of the training data y is train _ y.shape (1680), the shape of the test data X is test _ x.shape (717,3,14), and the shape of the test data y is test _ y.shape (717'). The model is trained with training data and the performance of the model is verified with test data. And after the off-line training and testing are finished, deriving the calculated neural network weight. When prediction is needed next time, the neural network does not need to be trained again, and the trained weights are directly used, so that precious time is saved, and the prediction is faster and more efficient.
In the embodiment of the invention, the establishment of the neural network model belongs to a mature technology, and after the required parameter characteristics are obtained in the fixed field, the neural network model is trained through the training set and the testing set, so that the neural network model capable of predicting data in real time is obtained.
After the neural network model is established, when the gateway capacity in the future time period is predicted, historical operation parameter characteristics of the industry short message gateway in the first time period are required to be obtained, and a capacity prediction sequence in the second time period is obtained according to the historical operation parameter characteristics and the preset prediction neural network model.
According to the method for predicting the capacity of the industry short message gateway, provided by the embodiment of the invention, the historical operation parameter characteristics of the industry short message gateway in the first time period are obtained, and the capacity prediction sequence in the second time period is obtained according to the historical operation parameter characteristics and the preset prediction neural network model, so that the purpose of predicting the capacity of the industry short message gateway in the future time period is achieved, and reference is provided for subsequent capacity expansion.
Fig. 2 shows a method for predicting and processing the capacity of an industry short message gateway, which is provided by an embodiment of the present invention, and the method includes:
s21, acquiring historical operating parameter characteristics of the industry short message gateway in a first time period;
s22, obtaining a capacity prediction sequence in a second time period according to the historical operation parameter characteristics and a preset prediction neural network model;
and S23, comparing each capacity value in the capacity prediction sequence with a preset load threshold value respectively, and sending capacity expansion reminding information when determining that the capacity value exceeds the load threshold value.
Regarding the above step S21-step S22, it should be noted that these steps are the same as the steps S11-step 12 in the above embodiment in principle, and are not described again here.
With respect to step S23, it should be noted that, in the embodiment of the present invention, each capacity value in the capacity prediction sequence is respectively compared with a preset load threshold, and when it is determined that the capacity value exceeds the load threshold, a capacity expansion reminding message is sent out for the operation and maintenance staff to perform corresponding planning and processing on the capacity value.
According to the method for predicting and processing the capacity of the industry short message gateway, the historical operation parameter characteristics of the industry short message gateway in the first time period are obtained, the capacity prediction sequence in the second time period is obtained according to the historical operation parameter characteristics and the preset prediction neural network model, each capacity value in the capacity prediction sequence is compared with the preset load threshold value, when the capacity value is determined to exceed the load threshold value, capacity expansion reminding information is sent out, the purpose of predicting the capacity of the industry short message gateway in the future time period is achieved, and reference is provided for the subsequent capacity expansion.
Fig. 3 shows a method for predicting and processing the capacity of an industry short message gateway, according to an embodiment of the present invention, where the method includes:
s31, acquiring historical operating parameter characteristics of the industry short message gateway in a first time period;
s32, obtaining a capacity prediction sequence in a second time period according to the historical operation parameter characteristics and a preset prediction neural network model;
s33, comparing each capacity value in the capacity prediction sequence with a preset load threshold value respectively, and sending capacity expansion reminding information when determining that the capacity value exceeds the load threshold value;
and S34, acquiring the maximum capacity value in the capacity prediction sequence, and acquiring the capacity expansion capacity value of the industry short message gateway according to the maximum capacity value and a preset capacity expansion formula.
Regarding the above steps S31-S33, it should be noted that these steps are the same as the steps S21-S23 in the above embodiment in principle, and are not described again here.
For step S34, it should be noted that, in the embodiment of the present invention, the maximum capacity value in the capacity prediction sequence is obtained, and the expanded capacity value of the industry short message gateway is obtained according to the maximum capacity value and a preset expansion formula.
In this embodiment of the present invention, the capacity expansion formula includes:
and R is Max multiplied by k-Z, wherein R is the capacity expansion capacity value, Max is the maximum capacity value in the capacity prediction sequence, k is a preset coefficient, and Z is the total capacity of the industry short message gateway before capacity expansion.
But is not limited to the above formula.
According to the method for predicting and processing the capacity of the industry short message gateway, the historical operation parameter characteristics of the industry short message gateway in the first time period are obtained, the capacity prediction sequence in the second time period is obtained according to the historical operation parameter characteristics and the preset prediction neural network model, each capacity value in the capacity prediction sequence is compared with the preset load threshold value, when the capacity value is determined to exceed the load threshold value, capacity expansion reminding information is sent, the maximum capacity value in the capacity prediction sequence is obtained, the capacity expansion capacity value of the industry short message gateway is obtained according to the maximum capacity value and the preset capacity expansion formula, the purpose of predicting the capacity of the industry short message gateway in the future time period is achieved, and reference is provided for the subsequent capacity expansion.
Fig. 4 shows a prediction processing apparatus for industry short message gateway capacity according to an embodiment of the present invention, which includes an obtaining module 41 and a predicting module 42, where:
the obtaining module 41 is configured to obtain historical operating parameter characteristics of an industry short message gateway within a first time period;
and the prediction module 42 is configured to obtain a capacity prediction sequence in the second time period according to the historical operating parameter characteristics and a preset prediction neural network model.
Since the principle of the apparatus according to the embodiment of the present invention is the same as that of the method according to the above embodiment, further details are not described herein for further explanation.
It should be noted that, in the embodiment of the present invention, the relevant functional module may be implemented by a hardware processor (hardware processor).
According to the prediction processing device for the capacity of the industry short message gateway, provided by the embodiment of the invention, the historical operation parameter characteristics of the industry short message gateway in the first time period are obtained, and the capacity prediction sequence in the second time period is obtained according to the historical operation parameter characteristics and the preset prediction neural network model, so that the purpose of predicting the capacity of the industry short message gateway in the future time period is achieved, and reference is provided for subsequent capacity expansion.
Fig. 5 shows a prediction processing apparatus for industry short message gateway capacity according to an embodiment of the present invention, which includes an obtaining module 51, a prediction module 52, and a reminding module 53, where:
the acquisition module 51 is used for acquiring historical operating parameter characteristics of the industry short message gateway in a first time period;
the prediction module 52 is configured to obtain a capacity prediction sequence in a second time period according to the historical operating parameter characteristics and a preset prediction neural network model;
and the reminding module 53 is configured to compare each capacity value in the capacity prediction sequence with a preset load threshold, and send a capacity expansion reminding message when it is determined that the capacity value exceeds the load threshold.
Since the principle of the apparatus according to the embodiment of the present invention is the same as that of the method according to the above embodiment, further details are not described herein for further explanation.
It should be noted that, in the embodiment of the present invention, the relevant functional module may be implemented by a hardware processor (hardware processor).
According to the prediction processing device for the capacity of the industry short message gateway, the historical operation parameter characteristics of the industry short message gateway in the first time period are obtained, the capacity prediction sequence in the second time period is obtained according to the historical operation parameter characteristics and the preset prediction neural network model, each capacity value in the capacity prediction sequence is compared with the preset load threshold value, when the capacity value is determined to exceed the load threshold value, capacity expansion reminding information is sent out, the purpose of predicting the capacity of the industry short message gateway in the future time period is achieved, and reference is provided for the subsequent capacity expansion.
Fig. 6 shows a prediction processing apparatus for industry short message gateway capacity according to an embodiment of the present invention, including an obtaining module 61, a predicting module 62, a reminding module 63, and a capacity expanding module 64, where:
the acquisition module 61 is used for acquiring historical operating parameter characteristics of the industry short message gateway in a first time period;
the prediction module 62 is configured to obtain a capacity prediction sequence in a second time period according to the historical operating parameter characteristics and a preset prediction neural network model;
a reminding module 63, configured to compare each capacity value in the capacity prediction sequence with a preset load threshold, and send a capacity expansion reminding message when it is determined that the capacity value exceeds the load threshold;
and the capacity expansion module 64 is used for acquiring the maximum capacity value in the capacity prediction sequence and acquiring the capacity expansion capacity value of the industry short message gateway according to the maximum capacity value and a preset capacity expansion formula.
Since the principle of the apparatus according to the embodiment of the present invention is the same as that of the method according to the above embodiment, further details are not described herein for further explanation.
It should be noted that, in the embodiment of the present invention, the relevant functional module may be implemented by a hardware processor (hardware processor).
According to the prediction processing device for the capacity of the industry short message gateway, provided by the embodiment of the invention, the historical operation parameter characteristics of the industry short message gateway in the first time period are obtained, the capacity prediction sequence in the second time period is obtained according to the historical operation parameter characteristics and the preset prediction neural network model, each capacity value in the capacity prediction sequence is compared with the preset load threshold value, when the capacity value is determined to exceed the load threshold value, capacity expansion reminding information is sent, the maximum capacity value in the capacity prediction sequence is obtained, the capacity expansion capacity value of the industry short message gateway is obtained according to the maximum capacity value and the preset capacity expansion formula, the purpose of predicting the capacity of the industry short message gateway in the future time period is achieved, and reference is provided for the subsequent capacity expansion.
Fig. 7 shows that an embodiment of the present invention provides an electronic device, including: a processor 71, a memory 72, a bus 73 and computer programs stored on the memory and executable on the processor;
the processor and the memory complete mutual communication through the bus;
the processor, when executing the computer program, implements a method as described above, for example comprising: obtaining historical operation parameter characteristics of an industry short message gateway in a first time period, and obtaining a capacity prediction sequence in a second time period according to the historical operation parameter characteristics and a preset prediction neural network model.
An embodiment of the present invention provides a non-transitory computer readable storage medium, on which a computer program is stored, and when executed by a processor, the computer program implements the method as described above, for example, including: obtaining historical operation parameter characteristics of an industry short message gateway in a first time period, and obtaining a capacity prediction sequence in a second time period according to the historical operation parameter characteristics and a preset prediction neural network model.
Furthermore, those skilled in the art will appreciate that while some embodiments described herein include some features included in other embodiments, rather than other features, combinations of features of different embodiments are meant to be within the scope of the invention and form different embodiments. For example, in the following claims, any of the claimed embodiments may be used in any combination.
It should be noted that the above-mentioned embodiments illustrate rather than limit the invention, and that those skilled in the art will be able to design alternative embodiments without departing from the scope of the appended claims. In the claims, any reference signs placed between parentheses shall not be construed as limiting the claim. The word "comprising" does not exclude the presence of elements or steps not listed in a claim. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. The invention may be implemented by means of hardware comprising several distinct elements, and by means of a suitably programmed computer. In the unit claims enumerating several means, several of these means may be embodied by one and the same item of hardware. The usage of the words first, second and third, etcetera do not indicate any ordering. These words may be interpreted as names.
Those of ordinary skill in the art will understand that: the above embodiments are only used to illustrate the technical solution of the present invention, and not to limit the same; while the invention has been described in detail and with reference to the foregoing embodiments, it will be understood by those skilled in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some or all of the technical features may be equivalently replaced; such modifications and substitutions do not depart from the spirit of the corresponding technical solutions and scope of the present invention as defined in the appended claims.
Claims (10)
1. A prediction processing method for industry short message gateway capacity is characterized by comprising the following steps:
acquiring historical operating parameter characteristics of an industry short message gateway in a first time period;
and obtaining a capacity prediction sequence in a second time period according to the historical operating parameter characteristics and a preset prediction neural network model.
2. The method of claim 1, further comprising:
comparing each capacity value in the capacity prediction sequence with a preset load threshold value respectively;
and when the existence capacity value is determined to exceed the load threshold value, sending out capacity expansion reminding information.
3. The method of claim 2, further comprising:
acquiring a maximum capacity value in the capacity prediction sequence;
and obtaining the capacity expansion capacity value of the industry short message gateway according to the maximum capacity value and a preset capacity expansion formula.
4. The method of claim 3, wherein the expansion formula comprises:
and R is Max multiplied by k-Z, wherein R is the capacity expansion capacity value, Max is the maximum capacity value in the capacity prediction sequence, k is a preset coefficient, and Z is the total capacity of the industry short message gateway before capacity expansion.
5. The utility model provides a prediction processing apparatus of trade SMS gateway capacity which characterized in that includes:
the acquisition module is used for acquiring the historical operating parameter characteristics of the industry short message gateway in a first time period;
and the prediction module is used for obtaining a capacity prediction sequence in a second time period according to the historical operating parameter characteristics and a preset prediction neural network model.
6. The apparatus of claim 5, further comprising a reminder module to: and comparing each capacity value in the capacity prediction sequence with a preset load threshold value respectively, and sending capacity expansion reminding information when determining that the capacity value exceeds the load threshold value.
7. The apparatus of claim 6, further comprising a capacity expansion module configured to: and acquiring a maximum capacity value in the capacity prediction sequence, and acquiring an expansion capacity value of the industry short message gateway according to the maximum capacity value and a preset expansion formula.
8. The apparatus of claim 7, wherein the expansion formula comprises:
and R is Max multiplied by k-Z, wherein R is the capacity expansion capacity value, Max is the maximum capacity value in the capacity prediction sequence, k is a preset coefficient, and Z is the total capacity of the industry short message gateway before capacity expansion.
9. An electronic device, comprising: a processor, a memory, a bus, and a computer program stored on the memory and executable on the processor;
the processor and the memory complete mutual communication through the bus;
the processor, when executing the computer program, implements the method of any of claims 1-4.
10. A non-transitory computer-readable storage medium, having stored thereon a computer program which, when executed by a processor, implements the method of any one of claims 1-4.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810820109.8A CN110753366A (en) | 2018-07-24 | 2018-07-24 | Prediction processing method and device for industry short message gateway capacity |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810820109.8A CN110753366A (en) | 2018-07-24 | 2018-07-24 | Prediction processing method and device for industry short message gateway capacity |
Publications (1)
Publication Number | Publication Date |
---|---|
CN110753366A true CN110753366A (en) | 2020-02-04 |
Family
ID=69275517
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810820109.8A Pending CN110753366A (en) | 2018-07-24 | 2018-07-24 | Prediction processing method and device for industry short message gateway capacity |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110753366A (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113407297A (en) * | 2020-03-17 | 2021-09-17 | 中国移动通信集团浙江有限公司 | Container management method and device and computing equipment |
CN114615698A (en) * | 2020-12-09 | 2022-06-10 | 中国移动通信集团四川有限公司 | IBCF interworking gateway load adjustment method and device |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103970641A (en) * | 2014-05-15 | 2014-08-06 | 浪潮电子信息产业股份有限公司 | Equipment expansion method based on capacity prediction technology |
CN104978610A (en) * | 2015-07-01 | 2015-10-14 | 国家电网公司 | Power grid demand side dispatchable capacity prediction method and power dispatching method |
CN105580407A (en) * | 2014-12-05 | 2016-05-11 | 华为技术有限公司 | Network resource deployment method and device |
CN105992228A (en) * | 2015-01-29 | 2016-10-05 | 中国移动通信集团浙江有限公司 | Wireless network capacity expansion method and device and electronic device |
CN107231264A (en) * | 2017-07-25 | 2017-10-03 | 北京百度网讯科技有限公司 | For the method and apparatus for the capacity for managing Cloud Server |
-
2018
- 2018-07-24 CN CN201810820109.8A patent/CN110753366A/en active Pending
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103970641A (en) * | 2014-05-15 | 2014-08-06 | 浪潮电子信息产业股份有限公司 | Equipment expansion method based on capacity prediction technology |
CN105580407A (en) * | 2014-12-05 | 2016-05-11 | 华为技术有限公司 | Network resource deployment method and device |
CN105992228A (en) * | 2015-01-29 | 2016-10-05 | 中国移动通信集团浙江有限公司 | Wireless network capacity expansion method and device and electronic device |
CN104978610A (en) * | 2015-07-01 | 2015-10-14 | 国家电网公司 | Power grid demand side dispatchable capacity prediction method and power dispatching method |
CN107231264A (en) * | 2017-07-25 | 2017-10-03 | 北京百度网讯科技有限公司 | For the method and apparatus for the capacity for managing Cloud Server |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113407297A (en) * | 2020-03-17 | 2021-09-17 | 中国移动通信集团浙江有限公司 | Container management method and device and computing equipment |
CN113407297B (en) * | 2020-03-17 | 2023-12-26 | 中国移动通信集团浙江有限公司 | Container management method and device and computing equipment |
CN114615698A (en) * | 2020-12-09 | 2022-06-10 | 中国移动通信集团四川有限公司 | IBCF interworking gateway load adjustment method and device |
CN114615698B (en) * | 2020-12-09 | 2023-07-18 | 中国移动通信集团四川有限公司 | IBCF interworking gateway load adjustment method and device |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
JP6384065B2 (en) | Information processing apparatus, learning method, and program | |
US10951500B2 (en) | Method and apparatus for warning | |
EP3822880A1 (en) | Load prediction method and apparatus based on neural network | |
US9436907B2 (en) | Method and system for calculating value of website visitor | |
Ahmed et al. | Simulation-based optimization using simulated annealing with ranking and selection | |
CN110832509B (en) | Black box optimization using neural networks | |
Pi et al. | A grey prediction approach to forecasting energy demand in China | |
CN104217258B (en) | A kind of electric load sigma-t Forecasting Methodology | |
CN110390425A (en) | Prediction technique and device | |
CN105809264B (en) | Power load prediction method and device | |
CN117096875B (en) | Short-term load prediction method and system based on spatial-Temporal Transformer model | |
CN113408797A (en) | Method for generating flow-traffic prediction multi-time-sequence model, information sending method and device | |
CN112150214A (en) | Data prediction method and device and computer readable storage medium | |
CN110753366A (en) | Prediction processing method and device for industry short message gateway capacity | |
Jain et al. | Towards smart manufacturing with virtual factory and data analytics | |
CN113094284A (en) | Application fault detection method and device | |
CN103617146A (en) | Machine learning method and device based on hardware resource consumption | |
US10295992B2 (en) | Production system having constraint evaluator generating constrained sequences | |
US11100586B1 (en) | Systems and methods for callable options values determination using deep machine learning | |
CN108134687B (en) | Gray model local area network peak flow prediction method based on Markov chain | |
CN110781755A (en) | Intelligent identification and metering method and system for construction steel bars | |
Wang et al. | Analysis of a discrete-time queue with server subject to vacations and breakdowns | |
CN112733452B (en) | Track prediction method, track prediction device, electronic equipment and readable storage medium | |
Betterton et al. | Production rate of synchronous transfer lines using Monte Carlo simulation | |
Song et al. | An ordinal optimization based evolution strategy to schedule complex make-to-order products |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200204 |