CN114004339A - Width learning-based urban lighting system adjusting method and device and storage medium - Google Patents
Width learning-based urban lighting system adjusting method and device and storage medium Download PDFInfo
- Publication number
- CN114004339A CN114004339A CN202111341765.8A CN202111341765A CN114004339A CN 114004339 A CN114004339 A CN 114004339A CN 202111341765 A CN202111341765 A CN 202111341765A CN 114004339 A CN114004339 A CN 114004339A
- Authority
- CN
- China
- Prior art keywords
- neural network
- fuzzy
- layer
- learning
- input
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 47
- 238000013528 artificial neural network Methods 0.000 claims abstract description 118
- 238000000605 extraction Methods 0.000 claims abstract description 48
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 28
- 238000012549 training Methods 0.000 claims abstract description 27
- 239000002245 particle Substances 0.000 claims abstract description 15
- 238000005457 optimization Methods 0.000 claims abstract description 8
- 230000006870 function Effects 0.000 claims description 68
- 238000004364 calculation method Methods 0.000 claims description 28
- 238000004590 computer program Methods 0.000 claims description 16
- 238000012937 correction Methods 0.000 claims description 13
- 238000005286 illumination Methods 0.000 claims description 11
- 230000001537 neural effect Effects 0.000 claims description 3
- 230000008569 process Effects 0.000 description 7
- 238000011217 control strategy Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 3
- 239000000284 extract Substances 0.000 description 3
- 239000000523 sample Substances 0.000 description 3
- 230000005540 biological transmission Effects 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 230000037213 diet Effects 0.000 description 2
- 235000005911 diet Nutrition 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000013507 mapping Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 238000009825 accumulation Methods 0.000 description 1
- 230000032683 aging Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000013523 data management Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000009795 derivation Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 239000000428 dust Substances 0.000 description 1
- 238000005265 energy consumption Methods 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 230000014509 gene expression Effects 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000008447 perception Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 239000004576 sand Substances 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- 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]
-
- 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
- G06N3/08—Learning methods
-
- 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
- G06N3/08—Learning methods
- G06N3/086—Learning methods using evolutionary algorithms, e.g. genetic algorithms or genetic programming
-
- H—ELECTRICITY
- H05—ELECTRIC TECHNIQUES NOT OTHERWISE PROVIDED FOR
- H05B—ELECTRIC HEATING; ELECTRIC LIGHT SOURCES NOT OTHERWISE PROVIDED FOR; CIRCUIT ARRANGEMENTS FOR ELECTRIC LIGHT SOURCES, IN GENERAL
- H05B47/00—Circuit arrangements for operating light sources in general, i.e. where the type of light source is not relevant
- H05B47/10—Controlling the light source
- H05B47/105—Controlling the light source in response to determined parameters
-
- H—ELECTRICITY
- H05—ELECTRIC TECHNIQUES NOT OTHERWISE PROVIDED FOR
- H05B—ELECTRIC HEATING; ELECTRIC LIGHT SOURCES NOT OTHERWISE PROVIDED FOR; CIRCUIT ARRANGEMENTS FOR ELECTRIC LIGHT SOURCES, IN GENERAL
- H05B47/00—Circuit arrangements for operating light sources in general, i.e. where the type of light source is not relevant
- H05B47/10—Controlling the light source
- H05B47/105—Controlling the light source in response to determined parameters
- H05B47/11—Controlling the light source in response to determined parameters by determining the brightness or colour temperature of ambient light
-
- H—ELECTRICITY
- H05—ELECTRIC TECHNIQUES NOT OTHERWISE PROVIDED FOR
- H05B—ELECTRIC HEATING; ELECTRIC LIGHT SOURCES NOT OTHERWISE PROVIDED FOR; CIRCUIT ARRANGEMENTS FOR ELECTRIC LIGHT SOURCES, IN GENERAL
- H05B47/00—Circuit arrangements for operating light sources in general, i.e. where the type of light source is not relevant
- H05B47/10—Controlling the light source
- H05B47/105—Controlling the light source in response to determined parameters
- H05B47/115—Controlling the light source in response to determined parameters by determining the presence or movement of objects or living beings
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02B—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO BUILDINGS, e.g. HOUSING, HOUSE APPLIANCES OR RELATED END-USER APPLICATIONS
- Y02B20/00—Energy efficient lighting technologies, e.g. halogen lamps or gas discharge lamps
- Y02B20/40—Control techniques providing energy savings, e.g. smart controller or presence detection
Abstract
The invention discloses a method, a device and a storage medium for adjusting an urban lighting system based on width learning, wherein the method comprises the steps of acquiring the traffic flow, the speed value and the ambient brightness of a road surface below an intelligent street lamp as initial data through various sensors arranged on the street lamp; after the initial data is subjected to feature extraction and node enhancement in BLS width learning, combining the initial data to serve as a training expansion value of the fuzzy neural network; and constructing a FNN fuzzy neural network, optimizing the learning algorithm part of the fuzzy neural network by applying a Particle Swarm Optimization (PSO) in the offline learning stage of the FNN, acquiring the optimal initial solution of the network and obtaining an optimized improved neural network, and inputting a training extension value to train the improved neural network. The intelligent control of the street lamp brightness in the urban lighting system is realized by the urban lighting system adjusting method.
Description
Technical Field
The invention relates to the technical field of computers, in particular to a method and a device for adjusting an urban lighting system based on width learning and a storage medium.
Background
In recent years, the smart street lamps are rapidly developed along with infrastructure, but the control algorithm of the existing smart street lamps cannot fully convert the functional concept in the concept of the smart city, namely, the intelligent street lamps are not really grounded. Particularly, in the aspect of a software control system, the automatic and energy-saving requirements of street lamp control are still mainly realized by adopting two modes in the conventional urban road lighting control system, and firstly, different street lamp switch control strategies are adopted; and secondly, selecting different street lamp remote control communication modes.
The switch control strategies of the street lamp mainly include three types at present: manual control, timing control and illumination control. The manual control is that the on-duty personnel in the center of the lighting system is responsible for switching on and off the street lamps or adjusting the brightness of the street lamps according to the road conditions. The method is suitable for scenes with insufficient information matching infrastructure capacity, and construction cost of an information control system can be saved to replace local low labor cost. However, in the last decade, major cities have been phased out, and manual control methods are mainly shown as manual intervention at present. The timing control method comprises the steps that reasonable timing control rules are set according to different urban dates and road states, the time control switch corresponding to the street lamp is adjusted according to the rules, the time control rules comprise clock calibration and the on and off time including the dates, the setting of the timing control switch can be realized through field manual or intelligent power supplies, gateways and other methods, and compared with manual control, the method is higher in accuracy and higher in automation degree, and unified informatization management is facilitated. However, since the simple automatic control has no sensing ability at the edge, when dealing with sudden conditions such as rainstorm, sand storm, total daily diet and partial daily diet, the sensing function still needs to be completed by people to meet the urban road lighting requirement under special conditions. The illumination control is to connect or directly integrate the power module of the street lamp with the light controller and lead out the photosensitive probe to sense the external luminosity change. The controller is typically set with a fixed illumination threshold, with the illumination turned on when the natural illumination is below the threshold illumination and turned off when the natural illumination is above the threshold. However, the sensing depending on single-point luminosity has great limitation, for example, in cloudy weather such as thundercloud, the illumination intensity of the outside may fluctuate unstably, and the threshold judgment type control method may cause frequent emission of the controller to cause the street lamp to flicker, thereby affecting the service life of the system and causing poor social experience; in addition, sensor aging, dust accumulation, or stray shielding near the street lamps can also lead to inaccurate control. In addition, the three main flow switch control strategies cannot meet the requirement of smart cities for fine control of urban lighting systems, for example, the lighting system roads cannot be controlled to flexibly adjust the changes of road conditions such as traffic flow, speed and the like in the area.
Disclosure of Invention
Aiming at the defects in the prior art, the invention provides a width learning-based urban lighting system adjusting method, which comprises the following steps:
s1, acquiring the traffic flow, the speed value and the ambient brightness of the road surface below the street lamp through each sensor arranged on the intelligent street lamp as initial data;
s2, combining the initial data collected by the sensor as the training extension value of the fuzzy neural network after feature extraction and node enhancement in BLS width learning;
s3, constructing a FNN fuzzy neural network, wherein the output value of the FNN fuzzy neural network is the brightness of the street lamp, optimizing the learning algorithm part of the FNN fuzzy neural network by applying a particle swarm optimization PSO in the off-line learning stage of the FNN fuzzy neural network, obtaining the optimal initial solution of the network and obtaining the optimized improved neural network, and inputting a training extension value to train the improved neural network.
Preferably, the FNN fuzzy neural network comprises an inputAn input layer, a fuzzy rule calculation layer and an output layer, wherein the input layer and an input parameter xjConnecting, wherein the number of nodes is the same as the dimension of the input vector;
the fuzzy layer fuzzifies the input value by adopting a membership function to obtain a fuzzy membership value, wherein the membership function is
Respectively the center and the width of the membership function, n is the number of fuzzy subsets, and k is the number of input parameters;
the fuzzy rule calculation layer carries out fuzzy calculation on each fuzzy membership degree, and adopts a fuzzy operator as a continuous multiplication operator:
k is the number of input parameters;
the output layer calculates and obtains the output value y of the fuzzy neural networkiWherein
Is x in the ith subset0…xkThe weight coefficients of the corresponding subscripts in the fuzzy neural network.
Preferably, in step S3, the optimizing the learning algorithm part of the network by using the particle swarm optimization PSO specifically includes:
and (3) carrying out error calculation:
wherein y isdFor the desired output of the network, ycE is the error between the expected output and the actual output;
and (3) performing coefficient correction:
wherein
Is the neural network coefficient, alpha is the network learning rate, xjFor inputting parameters, omega, to the networkiIs the product of the membership degree of the input parameters;
and (3) parameter correction:
beta is another network learning rate and is,
respectively the center and width of the membership function.
Preferably, the step S2 specifically includes:
constructing a BLS neural network, wherein the BLS neural network comprises an input layer, a middle layer and an output layer, and the detected traffic flow and the detected vehicle speed are used as input values (x) of the input layer1,x2)；
Calculating characteristic nodes and enhanced nodes of the intermediate layer of the BLS neural network, wherein the characteristic nodes complete characteristic extraction through a characteristic extraction function, and the characteristic extraction function is Z ═ phi (x W)1+B1)，W1For randomly generated weights for connecting the input layer and the feature nodes, B1Generating an enhanced node from the feature node through an enhanced node function for a threshold of the feature extraction function; the enhanced node function is H ═ phi (Z W)2+B2)，W2For randomly generated weights for connecting the enhanced node and the feature node, B2A threshold value that is a function of the enhanced node;
initial data collected by the sensors are combined to be used as a training extension value of the fuzzy neural network after feature extraction and node enhancement of the BLS neural network, and the initial data are used for obtaining traffic flow and speed values of a road surface below the intelligent street lamp for each sensor arranged on the intelligent street lamp.
The invention also discloses a device for adjusting the urban lighting system based on width learning, which comprises: the sensing module is used for acquiring the traffic flow, the speed value and the ambient brightness of the road surface below the street lamp; the control module is used for combining the real-time parameters acquired by the sensor as training extension values of the fuzzy neural network after feature extraction and node enhancement in BLS width learning; constructing a FNN fuzzy neural network, wherein the output value of the FNN fuzzy neural network is the street lamp brightness, optimizing the learning algorithm part of the FNN fuzzy neural network by applying a particle swarm algorithm PSO in the offline learning stage of the FNN fuzzy neural network, acquiring the optimal initial solution of the network and obtaining an optimized improved neural network, and inputting a training extension value to train the improved neural network; and the illumination module is used for adjusting the brightness of the street lamp according to the output value of the real-time parameter obtained by the sensing module from the control module after entering the trained neural network.
Preferably, the FNN fuzzy neural network constructed by the control module comprises an input layer, a fuzzy rule calculation layer and an output layer, wherein the input layer and an input parameter xjConnecting, wherein the number of nodes is the same as the dimension of the input vector; the fuzzy layer fuzzifies the input value by adopting a membership function to obtain a fuzzy membership value, wherein the membership function is
Respectively the center and the width of the membership function, n is the number of fuzzy subsets, and k is the number of input parameters; the fuzzy rule calculation layer carries out fuzzy calculation on each fuzzy membership degree, and adopts a fuzzy operator as a continuous multiplication operator:
k is the number of input parameters; the output layer calculates and obtains the output value y of the fuzzy neural networkiWherein
Is x in the ith subset0…xkThe weight coefficients of the corresponding subscripts in the fuzzy neural network.
Preferably, the control module optimizes a learning algorithm part of the network by using a particle swarm algorithm PSO, and specifically includes: and (3) carrying out error calculation:
wherein y isdFor the desired output of the network, ycE is the error between the expected output and the actual output; and (3) performing coefficient correction:
wherein
Is the neural network coefficient, alpha is the network learning rate, xjFor inputting parameters, omega, to the networkiIs the product of the membership degree of the input parameters; and (3) parameter correction:
beta is another network learning rate and is,
respectively the center and width of the membership function.
It is preferable thatThe control module extracts the real-time parameters acquired by the sensor through features in BLS width learning and enhances nodes, and specifically comprises the following steps: constructing a BLS neural network, wherein the BLS neural network comprises an input layer, a middle layer and an output layer, and the detected traffic flow and the detected vehicle speed are used as input values (x) of the input layer1,x2) (ii) a Calculating characteristic nodes and enhanced nodes of the intermediate layer of the BLS neural network, wherein the characteristic nodes complete characteristic extraction through a characteristic extraction function, and the characteristic extraction function is Z ═ phi (x W)1+B1)，W1For randomly generated weights for connecting the input layer and the feature nodes, B1Generating an enhanced node from the feature node through an enhanced node function for a threshold of the feature extraction function; the enhanced node function is H ═ phi (Z W)2+B2)，W2For randomly generated weights for connecting the enhanced node and the feature node, B2A threshold value that is a function of the enhanced node; initial data collected by the sensors are combined to be used as a training extension value of the fuzzy neural network after feature extraction and node enhancement of the BLS neural network, and the initial data are used for obtaining traffic flow and speed values of a road surface below the intelligent street lamp for each sensor arranged on the intelligent street lamp.
The invention also discloses a city lighting system adjusting device based on width learning, which comprises a memory, a processor and a computer program stored in the memory and capable of running on the processor, wherein the processor realizes the steps of any one of the methods when executing the computer program.
The invention also discloses a computer-readable storage medium, in which a computer program is stored which, when being executed by a processor, carries out the steps of the method according to any one of the preceding claims.
The invention discloses a city lighting system adjusting method and device based on width learning, aiming at the characteristics that the data acquired by the existing intelligent street lamp sensor is unstructured or semi-structured and has ambiguity and flexibility in feature extraction, a fuzzy neural network FNN is adopted for control, and aiming at the problem that the optimal solution is difficult to obtain in the actual dimming process of the fuzzy neural network, a particle swarm algorithm PSO is adopted for optimizing the hyper-parameters in the FNN, so that the problem of fitting unconvergence is avoided, and meanwhile, the width learning BLS is adopted for feature extraction, so that the problems of insufficient dimming sample data or data abnormity frequently encountered in the actual process are overcome to a certain extent. The method for combining BLS and PSO-FNN is equivalent to replacing artificial features or simple feature layers of the FNN with enhanced node output of BLS, so that the effects of high model training efficiency and less network parameters are achieved, and the problem of inaccurate feature extraction in the method for predicting the multi-intelligent street lamp, especially based on edge calculation, can be better solved.
Additional aspects and advantages of the invention will be set forth in part in the description which follows and, in part, will be obvious from the description, or may be learned by practice of the invention.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this application, illustrate embodiment(s) of the invention and together with the description serve to explain the invention without limiting the invention. In the drawings:
fig. 1 is a schematic flow chart illustrating steps of a method for adjusting an urban lighting system based on width learning according to an embodiment of the present invention.
Fig. 2 is a schematic diagram of a width learning structure according to an embodiment of the present invention.
Fig. 3 is a schematic structural diagram of a FNN fuzzy neural network based on a T-S model according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the drawings of the embodiments of the present invention. It is to be understood that the embodiments described are only a few embodiments of the present invention, and not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the described embodiments of the invention without any inventive step, are within the scope of protection of the invention.
In the present invention, unless otherwise expressly specified or limited, the terms "mounted," "connected," "secured," and the like are to be construed broadly and can, for example, be fixedly connected, detachably connected, or integrally connected; can be mechanically or electrically connected; they may be connected directly or indirectly through intervening media, or they may be interconnected between two elements. The specific meanings of the above terms in the present invention can be understood by those skilled in the art according to specific situations.
In the present invention, unless otherwise expressly stated or limited, "above" or "below" a first feature means that the first and second features are in direct contact, or that the first and second features are not in direct contact but are in contact with each other via another feature therebetween. Also, the first feature being "on," "above" and "over" the second feature includes the first feature being directly on and obliquely above the second feature, or merely indicating that the first feature is at a higher level than the second feature. A first feature being "under," "below," and "beneath" a second feature includes the first feature being directly under and obliquely below the second feature, or simply meaning that the first feature is at a lesser elevation than the second feature.
Unless defined otherwise, technical or scientific terms used herein shall have the ordinary meaning as understood by one of ordinary skill in the art to which this invention belongs. The use of "first," "second," and similar terms in the description and claims of the present application do not denote any order, quantity, or importance, but rather the terms are used to distinguish one element from another. Also, the use of the terms "a" or "an" and the like do not denote a limitation of quantity, but rather denote the presence of at least one.
At present, intelligent street lamp control in an urban lighting system needs to solve the problem that a fine dimming strategy tracks the perception change of the edge environment, and in a traditional street lamp control strategy, measures often taken by the government are based on a single factor, such as uniformly and regularly turning on and off street lamps. The street lamp control measures are not intelligent and humanized enough, for example, street lamps at different placing positions have different lighting requirements, such as street lamps close to crossroads, street lamps close to cameras, street lamps close to busy road sections, street lamps close to bends and junctions and the like, and special treatment is needed. Therefore, the intelligent street lamp control system is a multivariable control system, and factors influencing street lamp control are various as follows: temperature, humidity, light, PM2.5, noise, rainfall, traffic flow, holidays, etc. The control problem of multivariable systems has been a research focus and a difficult point in the control field. If according to the traditional industrial control method, the problem of the switch strategy of the street lamp is difficult to be solved after various conditions are considered at the same time.
The FNN network structure after the width learning fusion has smaller error and can better complete energy-saving optimization control. Meanwhile, according to the energy-saving ratio formula, compared with the traditional mode, the energy consumption of the intelligent street lamp control system is greatly reduced. As shown in fig. 1, the method for adjusting an urban lighting system based on width learning disclosed in this embodiment specifically includes the following steps:
and step S1, acquiring the traffic flow, the vehicle speed value and the ambient brightness of the road surface below the intelligent street lamp as initial data through each sensor arranged on the intelligent street lamp.
And step S2, combining the initial data collected by the sensor as a training extension value of the fuzzy neural network after feature extraction and node enhancement in BLS width learning.
Specifically, the Broad Learning System (BLS) is a simple novel fast incremental Learning neural network, and is based on a single hidden layer forward network rvfl (random Vector Functional Link network), the original input is first subjected to sparse mapping feature Learning through feature nodes, then enhancement features are obtained through enhancement node nonlinear expansion, two feature expressions in parallel connection are sent to an output layer as the final total input for classification and identification, so that important features can be learned from training data, and high fitting can be achieved on the training data. The problems of inaccurate precision and the like caused by insufficient data and abnormal data can be well solved through the method. Considering that the fuzzy neural network model can already specify its fuzzy rules, which makes it have good generalization capability, and the BLS has the characteristic of learning important features from training data and achieving high fitting to the training data, in this embodiment, the data is input into the BLS layer by fusing width learning to further extract important feature adding nodes to expand the network structure.
As shown in fig. 2, the width learning is a planar neural network developed from a function chain neural network, and includes an input layer, an intermediate layer and an output layer. The middle layer comprises two different nodes, namely a characteristic node and an enhanced node. The feature nodes finish feature extraction through a phi () feature extraction function, then enhancement nodes are generated from the feature nodes through an epsilon () function, and finally the two nodes jointly form a middle layer. In this embodiment, the step S2 may specifically include the following contents.
Step S21, constructing a BLS neural network, wherein the BLS neural network comprises an input layer, a middle layer and an output layer, and the detected traffic flow and the detected vehicle speed are used as input values (x) of the input layer1,x2)。
Step S22, calculating the feature nodes and the enhanced nodes of the intermediate layer of the BLS neural network, wherein the feature nodes finish feature extraction through a feature extraction function, and the feature extraction function is Z phi (x W)1+B1)，W1For randomly generated weights for connecting the input layer and the feature nodes, B1Generating an enhanced node from the feature node through an enhanced node function for a threshold of the feature extraction function; the enhanced node function is H ═ epsilon (Z W)2+B2)，W2For randomly generated weights for connecting the enhanced node and the feature node, B2To enhance the threshold of the node function.
And step S23, combining initial data acquired by the sensors as training extension values of the fuzzy neural network after characteristic extraction and node enhancement of the BLS neural network, wherein the initial data are used for acquiring traffic flow and speed values of the road surface below the intelligent street lamp for each sensor arranged on the intelligent street lamp. The data collected by the sensors are subjected to feature extraction in width learning, reinforced nodes are generated and then combined to serve as the input of the fuzzy neural network, and then the model is trained.
The present embodiment achieves better accuracy of optimizing the output by expanding the width of the input node. The model has strong nonlinear fitting capability, and does not need too much data to describe the input and output mapping relation of the system and fit the function. The system combines the fuzzy neural network with the width learning system, has simple structure, high model training efficiency and less network parameters, and can better solve the problem of inaccurate feature extraction in the method for predicting the multi-intelligent street lamps.
And step S3, constructing a FNN fuzzy neural network, wherein the output value of the FNN fuzzy neural network is the brightness of the street lamp, optimizing the learning algorithm part of the FNN fuzzy neural network by applying a particle swarm optimization PSO in the offline learning stage of the FNN fuzzy neural network, acquiring the optimal initial solution of the network, obtaining the optimized improved neural network, and inputting a training extension value to train the improved neural network.
In the embodiment, the FNN fuzzy neural network based on the T-S model is divided into an input layer, a fuzzy rule calculation layer and an output layer, wherein the input layer and an input parameter xjAnd connecting, wherein the number of nodes is the same as the dimension of the input vector.
By combining with the urban road lighting design standard, the fuzzy neural network controller is adopted in the intelligent dimming system, and the accuracy of dimming value output and the automation degree of the system are improved by utilizing the learning capability of the neural network and the fuzzy reasoning capability of fuzzy control. As shown in FIG. 3, the T-S model system has strong self-adaptive performance, and not only can be automatically updated, but also can continuously correct the membership function of the fuzzy subset.
Is provided with
Is a fuzzy set of a fuzzy system and,
is a fuzzy system parameter; y isjThe input part is fuzzy and the output part is deterministic for the output derived from the fuzzy rule, which means that the output is a linear combination of the inputs.
Firstly, calculating the membership degree of each input variable xj according to a fuzzy rule: namely, the fuzzy layer fuzzifies the input value by adopting a membership function to obtain a fuzzy membership value, wherein the membership function is
Respectively, the center and the width of the membership function, n is the fuzzy subset number, and k is the input parameter number.
The fuzzy rule calculation layer carries out fuzzy calculation on each fuzzy membership degree, and adopts a fuzzy operator as a continuous multiplication operator:
k is the number of input parameters.
The output layer calculates and obtains the output value y of the fuzzy neural network according to the results of the stepsiWherein
Is x in the ith subset0…xkThe weight coefficients of the corresponding subscripts in the fuzzy neural network.
In step S3, the learning algorithm portion of the network is optimized by using the particle swarm algorithm PSO. Specifically, although the fuzzy system and the neural network have many advantages, the fuzzy neural network adopts a forward error transmission mode, errors are calculated by a gradient method in the forward error transmission mode, multiple optimization process solutions are possibly involved, high-order derivation is used, the fuzzy neural network is difficult to realize optimal solution calculation, and convergence of the whole network may be deteriorated when the parameter selection of the fuzzy neural network is improper. Specifically, in this embodiment, a PSO algorithm is used to optimize a learning algorithm portion of the network, where the learning algorithm of the fuzzy neural network algorithm is divided into three steps, specifically:
and (3) carrying out error calculation:
wherein y isdFor the desired output of the network, ycFor the actual output of the network, e is the error of the desired output and the actual output.
And (3) performing coefficient correction:
wherein
Is the neural network coefficient, alpha is the network learning rate, and is the network input parameter, omegaiIs the product of the membership of the input parameters. The process of model learning requires a per x basisjThe coefficients of (a) are optimized,
meaning equivalent to the input quantity x in the subset for the ithjCoefficient of (2)
T is a count of the number of updates, and takes values of 1,2,3,4 … ….
And (3) parameter correction:
beta is another network learning rate and is,
respectively the center and width of the membership function.
And
i.e. indicating their tth suboptimal update of corrections. The parameter β is a network learning rate having a different value, as is α.
The urban lighting system adjusting method based on width learning disclosed by the embodiment aims at the characteristics that the existing intelligent street lamp sensor acquires data and is unstructured or semi-structured, ambiguity and flexibility exist in feature extraction, the fuzzy neural network FNN is adopted for control, the problem that the optimal solution is difficult to obtain in the actual dimming process of the fuzzy neural network is solved, the particle swarm algorithm PSO is adopted for optimizing the hyper-parameters in the FNN, the problem of fitting unconvergence is avoided, meanwhile, the width learning BLS is adopted for feature extraction, and therefore the problem of insufficient dimming sample data or data abnormity frequently encountered in the actual process is overcome to a certain degree. The method combining BLS and PSO-FNN is equivalent to replacing artificial features or simple feature layers of FNN with enhanced node output of BLS, achieves the effects of high model training efficiency and less network parameters, and can better solve the problem of inaccurate feature extraction in a multi-intelligent street lamp prediction method, particularly based on edge calculation, so that accurate brightness control of street lamps at different placement positions is achieved according to parameters such as traffic flow, speed value and ambient brightness of the street lamp located area, and the intelligent and humanized regulation control of an urban lighting system is achieved.
The invention also discloses a device for adjusting the urban lighting system based on width learning, which comprises: the sensing module is used for acquiring the traffic flow, the speed value and the ambient brightness of the road surface below the street lamp; the control module is used for combining the real-time parameters acquired by the sensor as training extension values of the fuzzy neural network after feature extraction and node enhancement in BLS width learning; constructing a FNN fuzzy neural network, wherein the output value of the FNN fuzzy neural network is the street lamp brightness, optimizing the learning algorithm part of the FNN fuzzy neural network by applying a particle swarm algorithm PSO in the offline learning stage of the FNN fuzzy neural network, acquiring the optimal initial solution of the network and obtaining an optimized improved neural network, and inputting a training extension value to train the improved neural network; and the illumination module is used for adjusting the brightness of the street lamp according to the output value of the real-time parameter obtained by the sensing module from the control module after entering the trained neural network.
Preferably, the FNN fuzzy neural network constructed by the control module comprises an input layer, a fuzzy rule calculation layer and an output layer, wherein the input layer and an input parameter xjConnecting, wherein the number of nodes is the same as the dimension of the input vector; the fuzzy layer fuzzifies the input value by adopting a membership function to obtain a fuzzy membership value, wherein the membership function is
Respectively the center and the width of the membership function, n is the number of fuzzy subsets, and k is the number of input parameters; the fuzzy rule calculation layer carries out fuzzy calculation on each fuzzy membership degree, and adopts a fuzzy operator as a continuous multiplication operator:
k is the number of input parameters; the output layer calculates and obtains the output value y of the fuzzy neural networkiWherein
Is x in the ith subset0…xkWeights for corresponding subscripts in a fuzzy neural networkAnd (4) weight coefficient.
Preferably, the control module optimizes a learning algorithm part of the network by using a particle swarm algorithm PSO, and specifically includes: and (3) carrying out error calculation:
wherein y isdFor the desired output of the network, ycE is the error between the expected output and the actual output; and (3) performing coefficient correction:
wherein
Is the neural network coefficient, alpha is the network learning rate, xjFor inputting parameters, omega, to the networkiIs the product of the membership degree of the input parameters; and (3) parameter correction:
beta is another network learning rate and is,
respectively the center and width of the membership function.
Preferably, the control module extracts and enhances the real-time parameters acquired by the sensor through features and nodes in BLS width learning, and specifically includes: constructing a BLS neural network, wherein the BLS neural network comprises an input layer, a middle layer and an output layer, and the detected traffic flow and the detected vehicle speed are used as input values (x) of the input layer1,x2) (ii) a Computing feature nodes and enhanced nodes in intermediate layers of BLS neural networkWherein the feature node completes feature extraction through a feature extraction function, and the feature extraction function is Z ═ phi (x W)1+B1)，W1For randomly generated weights for connecting the input layer and the feature nodes, B1Generating an enhanced node from the feature node through an enhanced node function for a threshold of the feature extraction function; the enhanced node function is H ═ phi (Z W)2+B2)，W2For randomly generated weights for connecting the enhanced node and the feature node, B2A threshold value that is a function of the enhanced node; initial data collected by the sensors are combined to be used as a training extension value of the fuzzy neural network after feature extraction and node enhancement of the BLS neural network, and the initial data are used for obtaining traffic flow and speed values of a road surface below the intelligent street lamp for each sensor arranged on the intelligent street lamp.
It should be noted that, in the present specification, the foregoing embodiments are described in a progressive manner, each embodiment focuses on differences from other embodiments, and like parts between the embodiments may be referred to each other. The urban lighting system adjusting device based on width learning disclosed by the embodiment corresponds to the urban lighting system adjusting method based on width learning disclosed by the previous embodiment, so that the description is relatively simple, and relevant points can be obtained by referring to the description of the method part.
The invention also provides another city lighting system adjusting device based on width learning, which comprises a memory, a processor and a computer program stored in the memory and capable of running on the processor, wherein the processor executes the computer program to realize the steps of the city lighting system adjusting method based on width learning as described in the embodiments.
The city lighting system adjusting device based on width learning can comprise but is not limited to a processor and a memory. It will be understood by those skilled in the art that the schematic diagram is merely an example of the width learning based urban lighting system adjusting apparatus and does not constitute a limitation of the width learning based urban lighting system adjusting apparatus, and may include more or less components than those shown, or combine some components, or different components, for example, the width learning based urban lighting system adjusting apparatus may further include input-output devices, network access devices, buses, etc.
The Processor may be a Central Processing Unit (CPU), other general purpose Processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), an off-the-shelf Programmable Gate Array (FPGA) or other Programmable logic device, discrete Gate or transistor logic, discrete hardware components, etc. The general purpose processor may be a microprocessor or the processor may be any conventional processor or the like, said processor being the control center of said width learning based urban lighting system adjusting device, various interfaces and lines connecting the various parts of the entire width learning based urban lighting system adjusting device.
The memory may be used for storing the computer programs and/or modules, and the processor may be used for implementing various functions of the city lighting system adjusting device equipment based on width learning by running or executing the computer programs and/or modules stored in the memory and calling the data stored in the memory. The memory may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application program required for at least one function, and the like, and the memory may include a high speed random access memory, and may further include a non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), at least one magnetic disk storage device, a Flash memory device, or other volatile solid state storage device.
The data management method of the urban lighting system adjusting device based on the width learning can be stored in a computer readable storage medium if the method is realized in the form of a software functional unit and sold or used as an independent product. Based on such understanding, all or part of the processes in the method according to the above embodiments may be implemented by a computer program, which may be stored in a computer readable storage medium, and when the computer program is executed by a processor, the steps of the above embodiments of the method for adjusting an urban lighting system based on width learning may be implemented. Wherein the computer program comprises computer program code, which may be in the form of source code, object code, an executable file or some intermediate form, etc. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, usb disk, removable hard disk, magnetic disk, optical disk, computer Memory, Read-Only Memory (ROM), Random Access Memory (RAM), electrical carrier wave signals, telecommunications signals, software distribution medium, and the like. It should be noted that the computer readable medium may contain content that is subject to appropriate increase or decrease as required by legislation and patent practice in jurisdictions, for example, in some jurisdictions, computer readable media does not include electrical carrier signals and telecommunications signals as is required by legislation and patent practice.
Finally, it should be noted that: the above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and the modifications or the substitutions do not make the essence of the corresponding technical solutions depart from the scope of the technical solutions of the embodiments of the present invention.
In summary, the above-mentioned embodiments are only preferred embodiments of the present invention, and all equivalent changes and modifications made in the claims of the present invention should be covered by the claims of the present invention.
Claims (10)
1. A city lighting system adjusting method based on width learning is characterized by comprising the following steps:
s1, acquiring the traffic flow, the speed value and the ambient brightness of the road surface below the street lamp through each sensor arranged on the intelligent street lamp as initial data;
s2, combining the initial data collected by the sensor as the training extension value of the fuzzy neural network after feature extraction and node enhancement in BLS width learning;
s3, constructing a FNN fuzzy neural network, wherein the output value of the FNN fuzzy neural network is the brightness of the street lamp, optimizing the learning algorithm part of the FNN fuzzy neural network by applying a particle swarm optimization PSO in the off-line learning stage of the FNN fuzzy neural network, obtaining the optimal initial solution of the network and obtaining the optimized improved neural network, and inputting a training extension value to train the improved neural network.
2. The method of claim 1, wherein the FNN fuzzy neural network comprises an input layer, a fuzzy rule calculation layer and an output layer, wherein the input layer is associated with an input parameter xjConnecting, wherein the number of nodes is the same as the dimension of the input vector;
the fuzzy layer fuzzifies the input value by adopting a membership function to obtain a fuzzy membership value, wherein the membership function is
j＝1,2,……k；i＝1,2,…,n，
Respectively the center and the width of the membership function, n is the number of fuzzy subsets, and k is the number of input parameters;
the fuzzy rule calculation layer carries out fuzzy calculation on each fuzzy membership degree, and adopts a fuzzy operator as a continuous multiplication operator:
j is 1,2, …, k, k is the number of input parameters;
output layer calculation acquisition fuzzy neural networkOutput value y of the complexiWherein
Is x in the ith subset0…xkThe weight coefficients of the corresponding subscripts in the fuzzy neural network.
3. The method for adjusting an urban lighting system based on width learning according to claim 2, wherein in step S3, the optimization of the learning algorithm part of the network by using the particle swarm algorithm PSO specifically comprises:
and (3) carrying out error calculation:
wherein y isdFor the desired output of the network, ycE is the error between the expected output and the actual output;
and (3) performing coefficient correction:
wherein
Is the neural network coefficient, alpha is the network learning rate, xjFor inputting parameters, omega, to the networkiIs the product of the membership degree of the input parameters;
and (3) parameter correction:
beta is another network learning rate and is,
respectively the center and width of the membership function.
4. The method for adjusting an urban lighting system based on width learning according to claim 3, wherein the step S2 specifically comprises:
constructing a BLS neural network, wherein the BLS neural network comprises an input layer, a middle layer and an output layer, and the detected traffic flow and the detected vehicle speed are used as input values (x) of the input layer1,x2)；
Calculating characteristic nodes and enhanced nodes of the intermediate layer of the BLS neural network, wherein the characteristic nodes complete characteristic extraction through a characteristic extraction function, and the characteristic extraction function is Z ═ phi (x W)1+B1)，W1For randomly generated weights for connecting the input layer and the feature nodes, B1Generating an enhanced node from the feature node through an enhanced node function for a threshold of the feature extraction function; the enhanced node function is H ═ phi (Z W)2+B2)，W2For randomly generated weights for connecting the enhanced node and the feature node, B2A threshold value that is a function of the enhanced node;
initial data collected by the sensors are combined to be used as a training extension value of the fuzzy neural network after feature extraction and node enhancement of the BLS neural network, and the initial data are used for obtaining traffic flow and speed values of a road surface below the intelligent street lamp for each sensor arranged on the intelligent street lamp.
5. An urban lighting system adjusting device based on width learning, characterized by comprising:
the sensing module is used for acquiring the traffic flow, the speed value and the ambient brightness of the road surface below the street lamp;
the control module is used for combining the real-time parameters acquired by the sensor as training extension values of the fuzzy neural network after feature extraction and node enhancement in BLS width learning; constructing a FNN fuzzy neural network, wherein the output value of the FNN fuzzy neural network is the street lamp brightness, optimizing the learning algorithm part of the FNN fuzzy neural network by applying a particle swarm algorithm PSO in the offline learning stage of the FNN fuzzy neural network, acquiring the optimal initial solution of the network and obtaining an optimized improved neural network, and inputting a training extension value to train the improved neural network;
and the illumination module is used for adjusting the brightness of the street lamp according to the output value of the real-time parameter obtained by the sensing module from the control module after entering the trained neural network.
6. The width learning based urban lighting system adjusting device according to claim 5, wherein: the FNN fuzzy neural network constructed by the control module comprises an input layer, a fuzzy rule calculation layer and an output layer, wherein the input layer and an input parameter xjConnecting, wherein the number of nodes is the same as the dimension of the input vector;
the fuzzy layer fuzzifies the input value by adopting a membership function to obtain a fuzzy membership value, wherein the membership function is
j＝1,2,……k；i＝1,2,…,n，
Respectively the center and the width of the membership function, n is the number of fuzzy subsets, and k is the number of input parameters;
the fuzzy rule calculation layer carries out fuzzy calculation on each fuzzy membership degree, and adopts a fuzzy operator as a continuous multiplication operator:
j is 1,2, …, k, k is the number of input parameters;
the output layer calculates and obtains the output value y of the fuzzy neural networkiWherein
Is as followsi subsets x0…xkThe weight coefficients of the corresponding subscripts in the fuzzy neural network.
7. The urban lighting system adjusting device based on width learning of claim 6, wherein the control module optimizes the learning algorithm part of the network by using a particle swarm algorithm (PSO), specifically comprising:
and (3) carrying out error calculation:
wherein y isdFor the desired output of the network, ycE is the error between the expected output and the actual output;
and (3) performing coefficient correction:
wherein
Is the neural network coefficient, alpha is the network learning rate, xjFor inputting parameters, omega, to the networkiIs the product of the membership degree of the input parameters;
and (3) parameter correction:
beta is another network learning rate and is,
respectively the center and width of the membership function.
8. The width learning-based urban lighting system adjusting device according to claim 7, wherein the control module performs feature extraction and node enhancement in BLS width learning on the real-time parameters collected by the sensor, and specifically comprises:
constructing a BLS neural network, wherein the BLS neural network comprises an input layer, a middle layer and an output layer, and the detected traffic flow and the detected vehicle speed are used as input values (x) of the input layer1,x2) (ii) a Calculating characteristic nodes and enhanced nodes of the intermediate layer of the BLS neural network, wherein the characteristic nodes complete characteristic extraction through a characteristic extraction function, and the characteristic extraction function is Z ═ phi (x W)1+B1)，W1For randomly generated weights for connecting the input layer and the feature nodes, B1Generating an enhanced node from the feature node through an enhanced node function for a threshold of the feature extraction function; the enhanced node function is H ═ phi (Z W)2+B2)，W2For randomly generated weights for connecting the enhanced node and the feature node, B2A threshold value that is a function of the enhanced node; initial data collected by the sensors are combined to be used as a training extension value of the fuzzy neural network after feature extraction and node enhancement of the BLS neural network, and the initial data are used for obtaining traffic flow and speed values of a road surface below the intelligent street lamp for each sensor arranged on the intelligent street lamp.
9. An urban lighting system adjusting device based on width learning, comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that: the processor, when executing the computer program, realizes the steps of the method according to any of claims 1-4.
10. A computer-readable storage medium storing a computer program, characterized in that: the computer program when being executed by a processor realizes the steps of the method as claimed in any one of the claims 6-9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111341765.8A CN114004339B (en) | 2021-11-12 | 2021-11-12 | Urban lighting system adjusting method and device based on width learning and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111341765.8A CN114004339B (en) | 2021-11-12 | 2021-11-12 | Urban lighting system adjusting method and device based on width learning and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114004339A true CN114004339A (en) | 2022-02-01 |
| CN114004339B CN114004339B (en) | 2024-05-03 |
Family
ID=79928770
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111341765.8A Active CN114004339B (en) | 2021-11-12 | 2021-11-12 | Urban lighting system adjusting method and device based on width learning and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114004339B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115294674A (en) * | 2022-10-09 | 2022-11-04 | 南京信息工程大学 | Unmanned ship navigation state monitoring and evaluating method |
| CN117596755A (en) * | 2023-12-15 | 2024-02-23 | 广东瑞峰光电科技有限公司 | Intelligent control method and system for street lamp of Internet of things |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112529685A (en) * | 2020-11-27 | 2021-03-19 | 百维金科(上海)信息科技有限公司 | Loan user credit rating method and system based on BAS-FNN |
| CN112863179A (en) * | 2021-01-11 | 2021-05-28 | 上海交通大学 | Intersection signal lamp control method based on neural network model predictive control |
| CN113625560A (en) * | 2021-07-29 | 2021-11-09 | 中国农业机械化科学研究院 | Loss rate control method and device for corn harvester, storage medium and equipment |
-
2021
- 2021-11-12 CN CN202111341765.8A patent/CN114004339B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112529685A (en) * | 2020-11-27 | 2021-03-19 | 百维金科(上海)信息科技有限公司 | Loan user credit rating method and system based on BAS-FNN |
| CN112863179A (en) * | 2021-01-11 | 2021-05-28 | 上海交通大学 | Intersection signal lamp control method based on neural network model predictive control |
| CN113625560A (en) * | 2021-07-29 | 2021-11-09 | 中国农业机械化科学研究院 | Loss rate control method and device for corn harvester, storage medium and equipment |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115294674A (en) * | 2022-10-09 | 2022-11-04 | 南京信息工程大学 | Unmanned ship navigation state monitoring and evaluating method |
| CN115294674B (en) * | 2022-10-09 | 2022-12-20 | 南京信息工程大学 | Unmanned ship navigation state monitoring and evaluating method |
| CN117596755A (en) * | 2023-12-15 | 2024-02-23 | 广东瑞峰光电科技有限公司 | Intelligent control method and system for street lamp of Internet of things |
| CN117596755B (en) * | 2023-12-15 | 2024-04-16 | 广东瑞峰光电科技有限公司 | Intelligent control method and system for street lamp of Internet of things |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114004339B (en) | 2024-05-03 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN114004339A (en) | Width learning-based urban lighting system adjusting method and device and storage medium | |
| CN106171047B (en) | intelligent lighting system with predictive maintenance scheduling and method of operation thereof | |
| CN113316808B (en) | Traffic signal control by space-time expansion search of traffic states | |
| Pizzuti et al. | Smart street lighting management | |
| CN110991713A (en) | Irregular area flow prediction method based on multi-graph convolution sum GRU | |
| CN108694673A (en) | A kind of processing method, device and the processing equipment of insurance business risk profile | |
| Rahimipour et al. | Traffic prediction using a self-adjusted evolutionary neural network | |
| CN111008726B (en) | Class picture conversion method in power load prediction | |
| Liang et al. | A deep spatio-temporal fuzzy neural network for passenger demand prediction | |
| CN113469427A (en) | Convolution LSTM-based photovoltaic power station day-ahead power generation amount prediction method and system | |
| CN113762578A (en) | Training method and device of flow prediction model and electronic equipment | |
| Chen et al. | MultiCycleNet: multiple cycles self-boosted neural network for short-term electric household load forecasting | |
| Vakitbilir et al. | Hybrid deep learning models for multivariate forecasting of global horizontal irradiation | |
| CN111556631A (en) | Tunnel traffic lighting system intelligent control method based on PSO and RBFNN | |
| CN113298569A (en) | Power demand side management method and system based on artificial intelligence | |
| CN114694382B (en) | Dynamic one-way traffic control system based on Internet of vehicles environment | |
| CN115968088A (en) | Intelligent tunnel dimming method and system and computer storage medium | |
| CN113256472B (en) | Intelligent traffic control method and system and brain-like computer readable storage medium | |
| Zhang et al. | Application of machine learning methods in photovoltaic output power prediction: A review | |
| CN111157909B (en) | Electric quantity curve updating method and device, cloud server and battery | |
| Agramelal et al. | Smart Street Light Control: A Review on Methods, Innovations, and Extended Applications | |
| CN113947007A (en) | Energy load prediction method, device and equipment | |
| Mansouri et al. | Neural networks in electric load forecasting: a comprehensive survey | |
| Petelin et al. | Models for forecasting the traffic flow within the city of Ljubljana | |
| CN113723670A (en) | Photovoltaic power generation power short-term prediction method with variable time window |
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 | ||
| GR01 | Patent grant |