CN109660418A - Mobile communication station communication support capability assessment method, system and electronic equipment neural network based - Google Patents

Mobile communication station communication support capability assessment method, system and electronic equipment neural network based Download PDF

Info

Publication number
CN109660418A
CN109660418A CN201810797901.6A CN201810797901A CN109660418A CN 109660418 A CN109660418 A CN 109660418A CN 201810797901 A CN201810797901 A CN 201810797901A CN 109660418 A CN109660418 A CN 109660418A
Authority
CN
China
Prior art keywords
data
assessment
attribute
communication station
mobile communication
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
Application number
CN201810797901.6A
Other languages
Chinese (zh)
Inventor
黄龙强
周召亮
王恺
苑红晓
张晓冰
邵欣烨
刘腾飞
魏江波
于吉岳
张泽正
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Chinese People's Liberation Army 32125
Original Assignee
Chinese People's Liberation Army 32125
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Chinese People's Liberation Army 32125 filed Critical Chinese People's Liberation Army 32125
Priority to CN201810797901.6A priority Critical patent/CN109660418A/en
Publication of CN109660418A publication Critical patent/CN109660418A/en
Pending legal-status Critical Current

Links

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L43/00—Arrangements for monitoring or testing data switching networks
    • H04L43/08—Monitoring or testing based on specific metrics, e.g. QoS, energy consumption or environmental parameters
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/24—Classification techniques
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/043—Architecture, e.g. interconnection topology based on fuzzy logic, fuzzy membership or fuzzy inference, e.g. adaptive neuro-fuzzy inference systems [ANFIS]
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
    • H04L41/50—Network service management, e.g. ensuring proper service fulfilment according to agreements
    • H04L41/5003—Managing SLA; Interaction between SLA and QoS
    • H04L41/5009—Determining service level performance parameters or violations of service level contracts, e.g. violations of agreed response time or mean time between failures [MTBF]

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Data Mining & Analysis (AREA)
  • Artificial Intelligence (AREA)
  • Signal Processing (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • General Engineering & Computer Science (AREA)
  • Evolutionary Computation (AREA)
  • Software Systems (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Pure & Applied Mathematics (AREA)
  • Mathematical Analysis (AREA)
  • Biophysics (AREA)
  • Computational Linguistics (AREA)
  • Health & Medical Sciences (AREA)
  • Mathematical Optimization (AREA)
  • General Health & Medical Sciences (AREA)
  • Molecular Biology (AREA)
  • Computing Systems (AREA)
  • Biomedical Technology (AREA)
  • Mathematical Physics (AREA)
  • Fuzzy Systems (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Evolutionary Biology (AREA)
  • Computational Mathematics (AREA)
  • Automation & Control Theory (AREA)
  • Environmental & Geological Engineering (AREA)
  • Telephonic Communication Services (AREA)

Abstract

The present invention relates to communication support capability evaluation technical field more particularly to a kind of mobile communication station communication support capability assessment method, system and electronic equipments neural network based.Include: data prediction: all data of the input mobile communication station carries out classification division to data, generates characteristic attribute；Self study training: the characteristic attribute and recruitment evaluation that acquisition communication station equipment opens up operation are trained based on fuzzy neural network as sample, generate data assessment model；Data assessment: carrying out analysis and assessment to device attribute using data assessment model, then device attribute assessment result and personnel's attribute are weighted to integrated, generation comprehensive evaluation result according to Two-tuple Linguistic Information Processing Integrated Operator.The present invention is it is possible to prevente effectively from information when integrated is lost, while the assessment to the communication support ability science of making, and effectively increases the accuracy of assessment result.

Description

Mobile communication station communication support capability assessment method neural network based, system And electronic equipment
Technical field
The present invention relates to communication support capability evaluation technical field more particularly to a kind of mobile communications neural network based Station communication support capability assessment method, system and electronic equipment.
Background technique
Communication is to ensure the basic means of operational commanding, and communication support ability is the important component of army's fighting capacity. In addition to equipment is inefficient caused by the mutation of artificial misoperation and natural conditions can not predict other than, under normal circumstances, pass through Analysis assessment is carried out to the communication support ability of communication station equipment and personnel, can be calculated when the station opens up with scientific quantification Communication support ability makes the analysis decision of science, guarantees the reliability of communication plan, realizes that utilization rate of equipment and installations maximizes, fills " multiplier " effect of communication is waved in distribution.
The communication support capability assessment method of the existing communication station can not well assess communication support ability. Main there are two technological difficulties: first is that being difficult to carry out quantitative evaluation to the station data of input；Second is that due to the property of station devices Energy attribute and personnel evaluation belong to different information types, and the evaluation between attribute is difficult to carry out comprehensive collection there are conflicting At.Both of these problems constrain the forecast assessment of communication support ability, it is difficult to adapt to the construction of modern communication supportability and hair The needs of exhibition.
Summary of the invention
To solve the above problems, the present invention provides a kind of mobile communication station communication support abilities neural network based Appraisal procedure effectively overcomes because of restriction existing for device attribute information type difference, by Various types of data effective integration, to communication The communication support ability of the station provides the assessment result of science.
The concrete scheme that the present invention uses is as follows:
A kind of mobile communication station communication support capability assessment method neural network based, comprising the following steps:
Step 1, data prediction: all data of the input mobile communication station carries out classification division to data, generates special Levy attribute；The characteristic attribute includes device attribute and personnel's attribute；
Step 2, self study training: the characteristic attribute and recruitment evaluation that acquisition communication station equipment opens up operation are as sample This, is trained based on fuzzy neural network, generates data assessment model；
Step 3, data assessment: analysis and assessment are carried out to device attribute using data assessment model, then by device attribute Assessment result and personnel's attribute are weighted integrated, generation comprehensive evaluation result according to Two-tuple Linguistic Information Processing Integrated Operator.
When device attribute includes by local terminal landform/opposite end landform locating for the assessment mobile communication station, test in step 1 Electromagnetic environment, test frequency, measuring distance, measured power, antenna height, local terminal when weather wind-force and temperature and humidity, test and Opposite end speed per hour；Personnel's attribute refers to the head of a station and the respective professional skill quality of operator, including examination and training achievement.
Integrated detailed process is weighted based on Two-tuple Linguistic Information Processing Integrated Operator are as follows:
Firstly, the assessment result of device attribute and personnel's attribute normalizing are converted, by Real-valued, interval type linear transformation Data are transformed into the section [0-1], and linguistic variable type data are without conversion；The data of different attribute are subjected to unification, generate one group Two-tuple Linguistic Information Processing information, Two-tuple Linguistic Information Processing information is by binary group (si,αi) indicate, wherein siIndicate that language phrase predetermined is concentrated Language description, αiReferred to as symbol branch value, αi∈ [- 0.5,0.5), indicate evaluation result and siDeviation；S is PASCAL evaluation PASCAL Collection, si∈ S=(s1,s2,...,sg), β ∈ [0, g], g=evaluate collection interval number -1, then its Two-tuple Linguistic Information Processing can be turned by following It changes function Δ to obtain, wherein round () is to be rounded operator, siIt is subscript and the immediate linguistic variable of β；Δ:[0,g]→S× [-0.5,0.5),
Same Two-tuple Linguistic Information Processing (si,αi) Δ can be passed through-1It is reduced into numerical value β ∈ [0, g]: Δ-1:S×[-0.5,0.5)→ [0,g],Δ-1(si,αi)=i+ αi=β；
Secondly, Two-tuple Linguistic Information Processing information is weighted it is integrated, if T={ (s1,α1),(s2,α2),...,(sg,αg) it is two First semantic collection, w=(w1,w2,...,wg)TIt is the weight vectors that Two-tuple Linguistic Information Processing concentrates corresponding element, uses weighted arithmetic mean Operator (TWA) is defined as:
Wherein, βi =Δ-1(si,αi), i=1,2 ..., g.
A kind of mobile communication station communication support capability evaluation system neural network based, including data prediction mould Block, all data for the mobile communication station to input carry out classification division, generate characteristic attribute；
Self-learning module, for obtaining characteristic attribute and recruitment evaluation that communication station equipment opens up operation as sample This, is trained based on fuzzy neural network, generates data assessment model；
Data evaluation module, for carrying out analysis and assessment to device attribute using data assessment model, then by equipment category Property assessment result and personnel attribute be weighted according to Two-tuple Linguistic Information Processing Integrated Operator integrated, generate comprehensive evaluation result.
A kind of electronic equipment is stored with the program for assessing mobile communication station communication support ability, the journey Sequence can be executed by processor to complete step described in above-mentioned appraisal procedure.
The data of each communication station are first carried out nerve net according to the attributive classification of data, and according to characteristic attribute by the present invention Network self study generates data assessment model.Data assessment process is weighted integrated, Ke Yiyou using Two-tuple Linguistic Information Processing Integrated Algorithm Information when effect avoids integrated is lost, while the assessment to the communication support ability science of making, and effectively increases assessment result Accuracy.
Detailed description of the invention
Fig. 1 is flow diagram of the invention；
Fig. 2 is that Two-tuple Linguistic Information Processing of the invention indicates example；
Fig. 3 is that Two-tuple Linguistic Information Processing of the invention assembles expression example.
Specific embodiment
The following describes the present invention in detail with reference to examples.
Embodiment 1
A kind of mobile communication station communication support capability assessment method neural network based, comprising the following steps:
Step 1, data prediction: all data of the input mobile communication station carries out classification division to data, generates special Levy attribute.The characteristic attribute is divided into device attribute and personnel's attribute.
Weather wind when device attribute includes by local terminal landform/opposite end landform locating for the assessment mobile communication station, test Electromagnetic environment, test frequency, measuring distance, measured power, antenna height, local terminal and opposite end speed per hour when power and temperature and humidity, test Equal attribute values；Evaluation index is divided into the transmission range and communication efficiency of speech, data and transmission of video.Device attribute passes through base It is assessed in the assessment models that previous sample training generates.
Personnel's attribute refers to the head of a station and the respective professional skill quality of operator, is made of examination or training achievement etc..Example Such as: opening up runing time (0~60 minute), emergency maintenance ability (0~100 point) etc..
Step 2, self study training: the characteristic attribute and recruitment evaluation that acquisition communication station equipment opens up operation are as sample This, is trained based on fuzzy neural network, generates data assessment model.
Step 4, data assessment: firstly, carrying out analysis and assessment to device attribute using data assessment model.Such as assessment knot Fruit are as follows:
The communication efficiency of Tone Via: (excellent, good, pass, poor),
The communication efficiency of data transmission: (excellent, good, pass, poor),
The communication efficiency of transmission of video: (excellent, good, pass, poor).
Then device attribute assessment result and personnel's attribute are weighted integrated, generation according to Two-tuple Linguistic Information Processing Integrated Operator Comprehensive evaluation result.
Such as personnel's attribute setting are as follows:
The head of a station: opening up runing time (0~60 minute), emergency maintenance ability (0~100 point)；
Operator: opening up runing time (0~60 minute), emergency maintenance ability (0~100 point).
Integrated detailed process is weighted based on Two-tuple Linguistic Information Processing Integrated Operator are as follows:
Firstly, the assessment result of device attribute and personnel's attribute normalizing are converted.By Real-valued, interval type linear transformation Data are transformed into the section [0-1], and linguistic variable type data are without conversion.After reunification by the data of different attribute, one group two is generated First semantic information.Two-tuple Linguistic Information Processing information is by binary group (si,αi) indicate, wherein siIndicate what language phrase predetermined was concentrated Language description, αiReferred to as symbol branch value, αi∈ [- 0.5,0.5), indicate evaluation result and siDeviation；S is PASCAL evaluation PASCAL collection, si∈ S, β ∈ [0, g], g=evaluate collection interval number -1.For example, the PASCAL evaluation PASCAL collection S being made of five PASCAL evaluation PASCALs can define Are as follows: S={ s5=VG (fine), s4=G (good), s3=M (general), s2=B (poor), s1=VB (very poor) }, g takes 4, there are five It is subordinate to section, as shown in Figure 2.
If H is real number, interval number and PASCAL evaluation PASCAL etc., S is PASCAL evaluation PASCAL value set, S=(s0,s1,...,sg).So Two-tuple Linguistic Information Processing collection can be converted by H by mapping as follows:
τ:[0,1]→F(S)
τ (H)={ (si,ωi) | i ∈ { 0 ..., g } } (1),
ωi=maxmin { μH(y),μSi(y)}
Wherein, μH(·),μSi() respectively indicates H and siSubordinating degree function.
Enable τ (H)={ (s0,ω0),(s1,ω1),...,(sg,ωg), the Two-tuple Linguistic Information Processing for being indeterminacy section number H is converted Value, then can convert Two-tuple Linguistic Information Processing for Two-tuple Linguistic Information Processing collection τ (H) by mapping χ represents numerical value: χ: F (S) → [0, g]
Thus data can be unified for Two-tuple Linguistic Information Processing type by formula (1), (2), facilitate and calculate in next step.
For convenience of formula is understood, illustration is all types of to be converted to Two-tuple Linguistic Information Processing process, as shown in exemplary diagram 3.
It is assumed that personnel's attribute is actually as follows: opening up runing time average area is 27~36 minutes (0~60 minute), is answered Anxious maintainability is scored at 80 points (0~100 points).First step normalization: obtaining corresponding section is to open up runing time section to be 0.4-0.55 (the shorter the time the better, needs to take benefit), emergency maintenance ability 0.8.Second step is converted to Two-tuple Linguistic Information Processing operator, carries out Assemble.
Real-valued:
Interval type: χ (τ [0.4,0.55])=1.875, Δ (1.875)=(s2,-0.125)
Evaluation type: excellent=(s4,0)
Secondly, it is integrated to Two-tuple Linguistic Information Processing information weighting, generate comprehensive evaluation result.If T={ (s1,α1),(s2, α2),...,(sg,αg) it is Two-tuple Linguistic Information Processing collection, w=(w1,w2,...,wg)TBe Two-tuple Linguistic Information Processing concentrate corresponding element weight to Amount, uses weighted arithmetic mean operator (TWA) is defined as:
All evaluations are thus turned to Two-tuple Linguistic Information Processing (si,αi) indicate data type information.Then according to institute above Showing that formula (3) assemble can be obtained final comprehensive evaluation result.
Embodiment 2
A kind of mobile communication station communication support capability evaluation system neural network based, including data prediction mould Block, self-learning module and data evaluation module.Wherein data preprocessing module is used for the items to the mobile communication station of input Data carry out classification division, generate characteristic attribute；Characteristic attribute is divided into device attribute and personnel's attribute.Self-learning module is used for Characteristic attribute and recruitment evaluation sample that communication station equipment opens up operation are obtained, is trained based on fuzzy neural network, Generate data assessment model.Data evaluation module, for carrying out analysis and assessment to device attribute using data assessment model, then Device attribute assessment result and personnel's attribute are weighted to integrated, generation overall merit knot according to Two-tuple Linguistic Information Processing Integrated Operator Fruit.Operational process inside self study determination module and data evaluation module is with embodiment 1, and details are not described herein.
Embodiment 3
A kind of electronic equipment, is stored with the program for assessing mobile communication station communication support ability, described program by Processor executes, to realize step described in embodiment 1.

Claims (5)

1. a kind of mobile communication station communication support capability assessment method neural network based, it is characterised in that including following step It is rapid:
Step 1, data prediction: all data of the input mobile communication station carries out classification division to data, generates feature category Property；The characteristic attribute includes device attribute and personnel's attribute；
Step 2, self study training: obtaining characteristic attribute and recruitment evaluation that communication station equipment opens up operation as sample, It is trained based on fuzzy neural network, generates data assessment model；
Step 3, data assessment: analysis and assessment are carried out to device attribute using data assessment model, then assess device attribute As a result integrated, generation comprehensive evaluation result is weighted according to Two-tuple Linguistic Information Processing Integrated Operator with personnel's attribute.
2. mobile communication station communication support capability assessment method neural network based according to claim 1, special Sign is: when device attribute includes by local terminal landform/opposite end landform locating for the assessment mobile communication station, test in step 1 Electromagnetic environment, test frequency, measuring distance, measured power, antenna height, local terminal when weather wind-force and temperature and humidity, test and Opposite end speed per hour；Personnel's attribute refers to the head of a station and the respective professional skill quality of operator, including examination and training achievement.
3. mobile communication station communication support capability assessment method neural network based according to claim 1, special Sign is: integrated detailed process is weighted based on Two-tuple Linguistic Information Processing Integrated Operator are as follows:
Firstly, the assessment result of device attribute and personnel's attribute normalizing are converted, by Real-valued, interval type linear transformation data It is transformed into the section [0-1], linguistic variable type data are without conversion；The data of different attribute are subjected to unification, generate one group of binary Semantic information, Two-tuple Linguistic Information Processing information is by binary group (si,αi) indicate, wherein siIndicate the language that language phrase predetermined is concentrated Speech description, αiReferred to as symbol branch value, αi∈ [- 0.5,0.5), indicate evaluation result and siDeviation；S is PASCAL evaluation PASCAL collection, si ∈ S=(s1,s2,...,sg), β ∈ [0, g], g=evaluate collection interval number -1, then its Two-tuple Linguistic Information Processing can pass through following conversion letter Number Δ obtains, wherein round () is to be rounded operator, siIt is subscript and the immediate linguistic variable of β；
Δ:[0,g]→S×[-0.5,0.5),
Same Two-tuple Linguistic Information Processing (si,αi) Δ can be passed through-1It is reduced into numerical value β ∈ [0, g]: Δ-1:S×[-0.5,0.5)→[0,g], Δ-1(si,αi)=i+ αi=β；
Secondly, Two-tuple Linguistic Information Processing information is weighted it is integrated, if T={ (s1,α1),(s2,α2),...,(sg,αg) it is binary language Justice collection, w=(w1,w2,...,wg)TIt is the weight vectors that Two-tuple Linguistic Information Processing concentrates corresponding element, uses weighted arithmetic mean operator (TWA) is defined as:
Wherein, βi= Δ-1(si,αi), i=1,2 ..., g.
4. a kind of mobile communication station communication support capability evaluation system neural network based, it is characterised in that: including
Data preprocessing module, all data for the mobile communication station to input carry out classification division, generate feature category Property；
Self-learning module, for obtaining characteristic attribute and recruitment evaluation that communication station equipment opens up operation as sample, base It is trained in fuzzy neural network, generates data assessment model；
Then data evaluation module is commented device attribute for carrying out analysis and assessment to device attribute using data assessment model Estimate result and personnel's attribute is weighted integrated, generation comprehensive evaluation result according to Two-tuple Linguistic Information Processing Integrated Operator.
5. a kind of electronic equipment, is stored with the program for assessing mobile communication station communication support ability, feature exists In: described program can be executed by processor to complete step described in claim 1.
CN201810797901.6A 2018-07-19 2018-07-19 Mobile communication station communication support capability assessment method, system and electronic equipment neural network based Pending CN109660418A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201810797901.6A CN109660418A (en) 2018-07-19 2018-07-19 Mobile communication station communication support capability assessment method, system and electronic equipment neural network based

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201810797901.6A CN109660418A (en) 2018-07-19 2018-07-19 Mobile communication station communication support capability assessment method, system and electronic equipment neural network based

Publications (1)

Publication Number Publication Date
CN109660418A true CN109660418A (en) 2019-04-19

Family

ID=66110251

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201810797901.6A Pending CN109660418A (en) 2018-07-19 2018-07-19 Mobile communication station communication support capability assessment method, system and electronic equipment neural network based

Country Status (1)

Country Link
CN (1) CN109660418A (en)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112510840A (en) * 2020-12-09 2021-03-16 广西科技师范学院 Wireless base station intelligent power utilization management system
CN112668861A (en) * 2020-12-23 2021-04-16 吉林大学 Numerical control machine tool reliability distribution method based on binary semantics and PFOVA operator

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102789545A (en) * 2012-07-12 2012-11-21 哈尔滨工业大学 Method for predicating remaining life of turbine engine based on degradation model matching
CN103488994A (en) * 2012-06-12 2014-01-01 达索系统公司 Symbiotic helper
CN105893669A (en) * 2016-03-30 2016-08-24 浙江大学 Global simulation performance predication method based on data digging
CN106355030A (en) * 2016-09-20 2017-01-25 浙江大学 Fault detection method based on analytic hierarchy process and weighted vote decision fusion
CN106845696A (en) * 2017-01-03 2017-06-13 河海大学 A kind of intelligent optimization Water Resources Allocation method

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103488994A (en) * 2012-06-12 2014-01-01 达索系统公司 Symbiotic helper
CN102789545A (en) * 2012-07-12 2012-11-21 哈尔滨工业大学 Method for predicating remaining life of turbine engine based on degradation model matching
CN105893669A (en) * 2016-03-30 2016-08-24 浙江大学 Global simulation performance predication method based on data digging
CN106355030A (en) * 2016-09-20 2017-01-25 浙江大学 Fault detection method based on analytic hierarchy process and weighted vote decision fusion
CN106845696A (en) * 2017-01-03 2017-06-13 河海大学 A kind of intelligent optimization Water Resources Allocation method

Non-Patent Citations (3)

* Cited by examiner, † Cited by third party
Title
于战果，张尧，邓威，杨冰峰: "基于BP神经网络的部队后勤机动平台维修能力评估", 《军事交通学院学报》 *
冯园等: "基于柯氏模型和二元语义的应急预案培训效果评估", 《中国安全科学学报》 *
陈永兴等: "二元语义方法在仿真系统可信性评估中的应用", 《电光与控制》 *

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112510840A (en) * 2020-12-09 2021-03-16 广西科技师范学院 Wireless base station intelligent power utilization management system
CN112668861A (en) * 2020-12-23 2021-04-16 吉林大学 Numerical control machine tool reliability distribution method based on binary semantics and PFOVA operator
CN112668861B (en) * 2020-12-23 2022-10-25 吉林大学 Numerical control machine tool reliability distribution method based on binary semantics and PFOVA operator

Similar Documents

Publication Publication Date Title
CN107817404B (en) Portable metering automation terminal fault diagnosis device and diagnosis method thereof
Goh et al. Complex-valued forecasting of wind profile
Hongkang et al. Recurrent neural network model for prediction of microclimate in solar greenhouse
CN107704966A (en) A kind of Energy Load forecasting system and method based on weather big data
Islam et al. Vertical extrapolation of wind speed using artificial neural network hybrid system
Dash et al. Fuzzy neural network and fuzzy expert system for load forecasting
CN111695724B (en) Wind speed prediction method based on hybrid neural network model
CN104966161B (en) A kind of power quality recorder data calculation and analysis methods based on gauss hybrid models
CN111127246A (en) Intelligent prediction method for transmission line engineering cost
Madadi et al. Dynamic line rating forecasting based on integrated factorized Ornstein–Uhlenbeck processes
CN109660418A (en) Mobile communication station communication support capability assessment method, system and electronic equipment neural network based
CN113283547A (en) Optimal power flow calculation method based on multi-task deep learning
CN105488335A (en) Lyapunov exponent based power system load prediction method and apparatus
WO2020228568A1 (en) Method for training power generation amount prediction model of photovoltaic power station, power generation amount prediction method and device of photovoltaic power station, training system, prediction system and storage medium
CN114091647A (en) Solar 10.7 cm radio flow forecasting method based on BP neural network
CN111882128A (en) TCN-based flood season climate trend prediction method
CN115545333A (en) Method for predicting load curve of multi-load daily-type power distribution network
CN112885378B (en) Speech emotion recognition method and device and storage medium
Shayanfar et al. Wind power prediction model based on hybrid strategy
CN114492199A (en) Method and system for analyzing performance of voltage transformer, electronic equipment and medium
Dedović et al. Application of artificial neural network and empirical mode decomposition for predications of hourly values of active power consumption
Saikhu et al. Non-Linear Spatio-Temporal Input Selection for Rainfall Forecasting Using Recurrent Neural Networks
Obeidi et al. Sunspot number-based neural network model for global solar radiation estimation in Ghardaïa
CN112926758A (en) Short-term wind speed prediction method and system
Hsieh et al. The jacobian matrix-based learning machine in student

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

Application publication date: 20190419

RJ01 Rejection of invention patent application after publication