CN117412334A - Heterogeneous wireless network bearing power service resource scheduling method - Google Patents
Heterogeneous wireless network bearing power service resource scheduling method Download PDFInfo
- Publication number
- CN117412334A CN117412334A CN202311413377.5A CN202311413377A CN117412334A CN 117412334 A CN117412334 A CN 117412334A CN 202311413377 A CN202311413377 A CN 202311413377A CN 117412334 A CN117412334 A CN 117412334A
- Authority
- CN
- China
- Prior art keywords
- resource
- real
- data
- demand
- time
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 56
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 151
- 238000009826 distribution Methods 0.000 claims abstract description 58
- 238000005259 measurement Methods 0.000 claims abstract description 15
- 238000010586 diagram Methods 0.000 claims abstract description 14
- 238000003064 k means clustering Methods 0.000 claims abstract description 13
- 230000005540 biological transmission Effects 0.000 claims description 117
- 238000012544 monitoring process Methods 0.000 claims description 108
- 238000013468 resource allocation Methods 0.000 claims description 90
- 238000011156 evaluation Methods 0.000 claims description 73
- 238000005457 optimization Methods 0.000 claims description 49
- 238000004458 analytical method Methods 0.000 claims description 27
- 230000002068 genetic effect Effects 0.000 claims description 24
- 238000007781 pre-processing Methods 0.000 claims description 21
- 238000010801 machine learning Methods 0.000 claims description 19
- 238000007405 data analysis Methods 0.000 claims description 17
- 238000007726 management method Methods 0.000 claims description 14
- 238000012546 transfer Methods 0.000 claims description 11
- 238000004140 cleaning Methods 0.000 claims description 8
- 238000005516 engineering process Methods 0.000 claims description 8
- 238000013210 evaluation model Methods 0.000 claims description 8
- 230000006872 improvement Effects 0.000 claims description 7
- 230000008569 process Effects 0.000 claims description 7
- 238000012549 training Methods 0.000 claims description 7
- 238000013480 data collection Methods 0.000 claims description 6
- 238000002360 preparation method Methods 0.000 claims description 6
- 238000012545 processing Methods 0.000 claims description 6
- 230000002159 abnormal effect Effects 0.000 claims description 4
- QVFWZNCVPCJQOP-UHFFFAOYSA-N chloralodol Chemical compound CC(O)(C)CC(C)OC(O)C(Cl)(Cl)Cl QVFWZNCVPCJQOP-UHFFFAOYSA-N 0.000 claims description 4
- 238000012804 iterative process Methods 0.000 claims description 4
- 238000004364 calculation method Methods 0.000 claims description 3
- 238000006243 chemical reaction Methods 0.000 claims description 3
- 238000010219 correlation analysis Methods 0.000 claims description 3
- 238000000605 extraction Methods 0.000 claims description 3
- 230000007246 mechanism Effects 0.000 claims description 3
- 230000035772 mutation Effects 0.000 claims description 3
- 238000004891 communication Methods 0.000 abstract description 10
- 238000013461 design Methods 0.000 abstract description 5
- 239000002699 waste material Substances 0.000 abstract description 5
- 238000013439 planning Methods 0.000 description 5
- 238000005265 energy consumption Methods 0.000 description 4
- 238000013528 artificial neural network Methods 0.000 description 3
- 238000003066 decision tree Methods 0.000 description 3
- 238000012806 monitoring device Methods 0.000 description 3
- 238000012300 Sequence Analysis Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000009472 formulation Methods 0.000 description 2
- 239000000203 mixture Substances 0.000 description 2
- 238000000611 regression analysis Methods 0.000 description 2
- 230000004044 response Effects 0.000 description 2
- 238000002922 simulated annealing Methods 0.000 description 2
- 230000005856 abnormality Effects 0.000 description 1
- 230000004075 alteration Effects 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000007621 cluster analysis Methods 0.000 description 1
- 238000011217 control strategy Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000013209 evaluation strategy Methods 0.000 description 1
- 239000000835 fiber Substances 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000008303 genetic mechanism Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000005381 potential energy Methods 0.000 description 1
- 230000002787 reinforcement Effects 0.000 description 1
- 230000004043 responsiveness Effects 0.000 description 1
- 238000001228 spectrum Methods 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012706 support-vector machine Methods 0.000 description 1
- 230000001960 triggered effect Effects 0.000 description 1
- 238000012800 visualization Methods 0.000 description 1
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W28/00—Network traffic management; Network resource management
- H04W28/02—Traffic management, e.g. flow control or congestion control
- H04W28/08—Load balancing or load distribution
- H04W28/09—Management thereof
- H04W28/0925—Management thereof using policies
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/12—Computing arrangements based on biological models using genetic models
- G06N3/126—Evolutionary algorithms, e.g. genetic algorithms or genetic programming
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W24/00—Supervisory, monitoring or testing arrangements
- H04W24/10—Scheduling measurement reports ; Arrangements for measurement reports
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W28/00—Network traffic management; Network resource management
- H04W28/02—Traffic management, e.g. flow control or congestion control
- H04W28/08—Load balancing or load distribution
- H04W28/09—Management thereof
- H04W28/0917—Management thereof based on the energy state of entities
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
- H04W4/02—Services making use of location information
- H04W4/029—Location-based management or tracking services
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
- H04W4/18—Information format or content conversion, e.g. adaptation by the network of the transmitted or received information for the purpose of wireless delivery to users or terminals
- H04W4/185—Information format or content conversion, e.g. adaptation by the network of the transmitted or received information for the purpose of wireless delivery to users or terminals by embedding added-value information into content, e.g. geo-tagging
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
- H04W4/30—Services specially adapted for particular environments, situations or purposes
- H04W4/38—Services specially adapted for particular environments, situations or purposes for collecting sensor information
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Biophysics (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Theoretical Computer Science (AREA)
- Artificial Intelligence (AREA)
- Molecular Biology (AREA)
- Biomedical Technology (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Genetics & Genomics (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Physiology (AREA)
- Supply And Distribution Of Alternating Current (AREA)
Abstract
The invention provides a heterogeneous wireless network bearing power service resource scheduling method, and relates to the technical field of power communication. The heterogeneous wireless network bearing power service resource scheduling method comprises the steps of measuring resource utilization rate and power demand of different wireless networks by using a sensor, generating a geographic distribution diagram of the resource utilization rate and the power demand, initializing resource scheduling, clustering the resource demands of different areas by adopting a K-means clustering algorithm based on the geographic distribution diagram of the resource utilization rate and the power demand, and determining a resource demand clustering center for subsequent scheduling. Through resource measurement and demand estimation, the sensor is used for measuring the resource utilization rate and the power demand of different wireless networks, and the geographic distribution map of the resource utilization rate and the power demand is generated, so that the power demand is ensured to be met through the design, meanwhile, the resource waste is minimized, and the utilization rate of the resource is improved.
Description
Technical Field
The invention relates to the technical field of power communication, in particular to a heterogeneous wireless network bearing power service resource scheduling method.
Background
In an electric power system, it has become a key requirement to realize information transmission and remote monitoring between electric power devices. To meet these demands, power communication technology is widely used. Traditionally, power communication has relied primarily on wired communication networks, such as fiber optic communication and power line communication. However, with the continuous development of power systems and the increasing demand for intelligence, the demand for wireless communication is also increasing.
A heterogeneous wireless network is a network that incorporates multiple wireless communication technologies including, but not limited to, LTE, wi-Fi, loRa, NB-IoT, and the like. These different wireless technologies have respective characteristics in terms of coverage, bandwidth, power consumption, communication distance, and the like. Therefore, in order to meet the diversified demands of the power service, the adoption of the heterogeneous wireless network becomes an attractive choice, and the existing heterogeneous wireless network load-bearing power service resource scheduling method has the problems of resource waste and low resource utilization rate, and also has the problems of overlarge energy consumption and transmission loss.
Disclosure of Invention
Aiming at the defects of the prior art, the invention provides a heterogeneous wireless network bearing power service resource scheduling method, which solves the problems of resource waste, low resource utilization rate, overlarge energy consumption and transmission loss.
In order to achieve the above purpose, the invention is realized by the following technical scheme: a heterogeneous wireless network bearing power service resource scheduling method comprises the following steps:
s1: resource measurement and demand estimation, wherein a wireless network monitoring sensor, a power measuring sensor and a data acquisition and analysis system are used for measuring the resource utilization rate and the power demand of different wireless networks, and a geographic distribution map of the resource utilization rate and the power demand is generated;
s2: initializing resource scheduling, clustering the resource demands of different areas by adopting a K-means clustering algorithm based on the geographic distribution map of the generated resource utilization rate and the power demands, and determining a resource demand clustering center for subsequent scheduling;
s3: resource scheduling and distributing, namely, based on the resource demand clustering center, carrying out resource distribution by adopting a cost algorithm to ensure that the power demand is met, and generating a resource distribution scheme comprising the resource distribution amount of each network;
s4: an energy supply plan, based on the resource scheduling and distributing scheme, optimizing the energy supply plan by adopting a genetic algorithm to optimize energy transmission loss and generate the energy supply plan;
s5: energy transmission control, based on the energy supply plan, adopting a dynamic power control algorithm to adjust the energy transmission parameters of each network, and the energy supply plan;
S6: real-time resource monitoring, namely installing real-time monitoring equipment, periodically detecting the resource utilization rate and the power demand of each network, comparing the resource utilization rate and the power demand with a prediction result, and monitoring data in real time;
s7: dynamically adjusting resource scheduling, adjusting resource allocation and energy transmission control parameters by adopting a feedback control algorithm based on the real-time monitoring data, wherein the resource allocation and the energy transmission parameters are dynamically adjusted;
s8: performing performance evaluation and optimization, namely performing performance evaluation by adopting a machine learning algorithm based on historical data and the dynamically adjusted resource allocation and energy transmission parameters, and optimizing a resource scheduling strategy according to an evaluation result, a performance evaluation report and the optimized resource scheduling strategy;
s9: and continuously monitoring and improving, establishing a continuous monitoring system, continuously collecting real-time data, comparing with the performance evaluation report and the optimized resource scheduling strategy, improving according to the changed requirements and network conditions, and continuously improving the resource scheduling strategy and the real-time monitoring data.
Preferably, the resource measurement and demand estimation uses a wireless network monitoring sensor, a power measurement sensor and a data acquisition and analysis system to measure the resource utilization rate and the power demand of different wireless networks, and the specific steps of generating the geographic distribution map of the resource utilization rate and the power demand are as follows:
S101: the method comprises the steps of resource measurement and demand estimation, wherein a sensor network is used for deployment at different geographic positions, the resource utilization rate and the power demand of a wireless network are monitored, a Zigbee or LoRa wireless sensor network protocol is adopted, network resource utilization rate and power demand data are collected in a real-time mode, and a real-time resource utilization rate and power demand data set comprising information of each geographic position is generated;
s102: processing and analyzing data acquired in the resource measurement and demand estimation, removing abnormal values and noise data by using a data cleaning method, identifying the geographic distribution rules of the resource utilization rate and the power demand by using a space-time analysis method, converting the data into a geographic distribution map by using a clustering analysis and spatial interpolation technology, generating the geographic distribution map of the resource utilization rate and the power demand, and displaying the resource utilization rate and the power demand conditions of different geographic positions;
s103: the demand prediction model is established based on geographic distribution diagram data in the data processing and analysis, and can be used for incorporating factors such as geographic positions, time, resource utilization rate, power demand and the like into the model by using a machine learning algorithm so as to predict future resource demand trend, and generate a resource demand prediction model for estimating future resource demands;
S104: a resource optimization strategy, based on the demand prediction model, a resource optimization strategy is formulated, and a resource allocation algorithm is adopted according to the predicted resource demand trend so as to optimize the resource utilization rate and the power consumption of the wireless network, and the resource optimization strategy is generated and used for adjusting the network resource allocation in real time;
s105: and (3) real-time resource adjustment, wherein the resource optimization strategy in the resource optimization strategy is applied to a wireless network, the resource allocation and the power control are adjusted in real time through a network management system, the network performance and the power consumption are monitored, the resource allocation strategy is dynamically adjusted according to actual conditions so as to meet the requirements of different geographic areas, the network performance and the power consumption are monitored, and the resource allocation strategy is dynamically adjusted according to actual conditions so as to meet the requirements of different geographic areas.
Preferably, the resource scheduling is initialized, the resource demands in different areas are clustered by adopting a K-means clustering algorithm based on the geographic distribution map of the generated resource utilization rate and the power demand, and a resource demand clustering center is determined, and the specific steps for subsequent scheduling are as follows:
s201: data preparation and preprocessing, preprocessing the data based on the geographical distribution map data of the resource utilization rate and the power demand generated by the resource measurement and the demand estimation, including removing abnormal values, normalizing the data to ensure that the data have the same scale, and converting geographical coordinate information into numerical characteristics for use in clustering;
S202: k mean value clustering, namely clustering the resource demands of different areas by adopting a K mean value clustering algorithm, distributing data points to the closest clustering centers through an iterative process, and updating the clustering centers until convergence, wherein the clustering result of the resource demands comprises the clustering clusters of each area and the positions of the clustering centers;
s203: initializing resource scheduling, and determining initial states of the resource scheduling based on resource demand clustering results in the K-means clustering, wherein the initial points represent resource demand clustering centers in different areas and are used for subsequent resource scheduling, and the initial states of the resource scheduling comprise positions of the resource demand clustering centers;
s204: and after the subsequent scheduling strategy is initialized, the resource scheduling strategy can be further formulated, the allocation of resources and the management of power are adjusted according to the real-time resource requirements and the network state, and the allocation of resources and the management of power are adjusted according to the real-time resource requirements and the network state.
Preferably, the resource scheduling and allocation is performed by adopting a cost algorithm based on the resource demand clustering center, so as to ensure that the power demand is met, and the specific steps for generating a resource allocation scheme are as follows:
S301: determining a resource demand clustering center, namely, utilizing the K-means clustering algorithm to cluster the resource demands of different areas into a plurality of clusters based on the geographic distribution data of the resource demands, wherein the clustering center represents the central point of each resource demand cluster, namely, represents the representative position of the resource demand condition of each area, and generating the resource demand clustering center, including the clustering center coordinates of each resource demand cluster;
s302: a cost algorithm for performing resource allocation based on the position information of the resource demand cluster center and the topology structure of the power supply network, by creating a graph model in which nodes represent resource supply points, resource demand points and power transmission lines while representing the capacity and cost of resource supply and power transmission, and then determining the resource allocation amount of each network by the cost algorithm to ensure that the power demand is satisfied, generating a resource allocation scheme including the resource allocation amount of each network and the cost calculated by the cost algorithm;
s303: optimizing a resource allocation scheme, further optimizing based on the resource allocation scheme in the cost algorithm, and adjusting the allocation of resources through a linear programming algorithm to meet specific constraint conditions or optimization targets, wherein the optimized resource allocation scheme meets additional constraint conditions or further optimizing results;
S304: and the dynamic resource scheduling strategy is used for carrying out resource reallocation in different time periods according to actual conditions and carrying out resource reallocation in different time periods according to actual conditions.
Preferably, the energy supply plan is optimized by adopting a genetic algorithm based on the resource scheduling and distributing scheme so as to optimize energy transmission loss, and the specific steps of generating the energy supply plan are as follows:
s401: preparing a resource scheduling allocation scheme, wherein the allocation scheme in the resource scheduling allocation is obtained, and the allocation scheme comprises the resource allocation amount of each network, which is used as an initial population of a genetic algorithm, and each individual represents one possible energy supply plan;
s402: generating an optimized energy supply plan by using a genetic algorithm, optimizing the energy supply plan by using the genetic algorithm, and generating new individuals by using the selection, crossing and mutation operations of the genetic algorithm so as to gradually improve the energy supply plan and obtain an optimized energy supply plan;
s403: the energy supply plan is further optimized, using other optimization algorithms to meet specific constraints or to further improve the performance of the plan;
S404: and the dynamic energy supply plan strategy is used for adjusting the energy supply plan in real time to cope with the changing power demand and the network state, and the dynamic adjustment result is carried out according to the changing power demand and the network state.
Preferably, the energy transmission control adjusts the energy transmission parameter of each network by using a dynamic power control algorithm based on the energy supply plan, and the specific steps of the energy supply plan are as follows:
s501: energy supply plan preparation, obtaining the energy supply plan including the energy demand and distribution plan of each network, which will be input to the dynamic power control algorithm for adjusting the energy transfer parameters, initial energy supply plan data including the energy demand and distribution plan;
s502: the dynamic power control algorithm is selected, a proper dynamic power control algorithm is selected, the algorithm can adjust energy transmission parameters in real time according to the system state so as to meet the requirement of an energy supply plan, and the selected dynamic power control algorithm is selected;
s503: dynamic power adjustment, based on a selected dynamic power control algorithm, monitoring the energy transmission parameters of each network in real time, and adjusting the energy transmission parameters according to the requirements in an energy supply plan so as to meet the requirements of the energy supply plan;
S504: performance evaluation and feedback, wherein the performance evaluation is carried out on the energy transmission parameters after adjustment, the performance does not meet the requirement, the performance can be fed back to the dynamic power adjustment, different dynamic power control algorithms are selected, or algorithm parameters, performance evaluation results and possible feedback information are further adjusted, so that the energy transmission control is further optimized;
s505: and finally, the energy transmission control is performed, and based on the performance evaluation and feedback information, the final energy transmission parameters are determined so as to meet the requirements of the energy supply plan, and the final energy transmission parameters are used for implementing the energy transmission control to ensure that the requirements of the energy supply plan are met.
Preferably, the real-time resource monitoring, installing a real-time monitoring device, periodically detecting the resource utilization rate and the power demand of each network, comparing with the predicted result, and real-time monitoring the data comprises the following specific steps:
s601: the method comprises the steps of installing real-time resource monitoring equipment and collecting data, wherein special real-time resource monitoring equipment is installed on each network node, and can monitor the resource utilization rate and the power demand of a network in real time and collect real-time monitoring data;
s602: preprocessing data and comparing the preprocessed data with a predicted result, preprocessing the acquired real-time monitoring data, including data cleaning, denoising, data conversion and the like, so as to ensure the accuracy and reliability of the data, and comparing the preprocessed real-time data with the previous predicted result, wherein the comparison result comprises difference analysis and correlation analysis of the real-time monitoring data and the predicted result;
S603: and the real-time monitoring data is applied and further processed, decision making and control are carried out based on the data preprocessing and the comparison result obtained with the prediction result, the real-time monitoring data is fed back to the prediction model for optimizing and improving the model, a closed-loop control system is formed, and the decision making result and the feedback data which are applied in real time are used for real-time adjustment and optimization of the system.
Preferably, the dynamic adjustment of the resource scheduling, based on the real-time monitoring data, adjusts the control parameters of resource allocation and energy transmission by adopting a feedback control algorithm, and the specific steps of the dynamic adjusted parameters of resource allocation and energy transmission are as follows:
s701: real-time monitoring data analysis and resource demand calculation, wherein a data analysis algorithm is adopted to process and analyze the real-time monitoring data so as to acquire the current state and trend of the network, and the current resource demand, including network load, power demand and the like, is calculated based on the analysis result of the data analysis algorithm to generate data of the real-time resource demand, including numerical value and trend analysis of the current resource demand;
s702: the feedback control algorithm adjusts the resource allocation and energy transmission parameters, and the feedback control algorithm is utilized to adjust the resource allocation and energy transmission control parameters according to the real-time resource demand data and the system model, so as to generate the dynamically adjusted resource allocation and energy transmission parameters, thereby meeting the real-time resource demand and keeping the system stable;
S703: and (3) real-time resource scheduling and performance optimization, adjusting the adjusted parameters obtained from the resource allocation and energy transmission parameters based on a feedback control algorithm, implementing resource scheduling and energy transmission control, continuously monitoring the real-time resource utilization rate and the power demand, feeding back and adjusting at any time, continuously monitoring the real-time resource utilization rate and the power demand, and feeding back and adjusting at any time.
Preferably, the performance evaluation and optimization is performed by adopting a machine learning algorithm based on historical data and the dynamically adjusted resource allocation and energy transmission parameters, and the resource scheduling strategy is optimized according to the evaluation result, and the specific steps of the performance evaluation report and the optimized resource scheduling strategy are as follows:
s801: historical data collection and preprocessing, namely collecting historical performance data by adopting a data collection method, wherein the historical performance data comprises network load, resource allocation parameters and power consumption, and performing data preprocessing, namely data cleaning, denoising and feature extraction so as to ensure the quality and usability of the data and generate preprocessed historical performance data;
s802: training a machine learning model, training a performance evaluation model by adopting a machine learning algorithm based on historical performance data, and predicting system performance according to resource allocation and energy transmission parameters by the model to generate a performance evaluation model for predicting system performance;
S803: performance evaluation, namely performing performance evaluation according to the dynamically adjusted resource allocation and energy transmission parameters by using a performance evaluation model in the training of the step machine learning model, and generating a performance evaluation result comprising a predicted value of a performance index;
s804: optimizing the resource scheduling strategy, comparing the performance evaluation result with a target performance index, adopting an optimization algorithm to adjust parameters of the resource scheduling strategy so as to optimize the system performance, and generating an optimized resource scheduling strategy so as to improve the system performance;
s805: and (3) performing performance evaluation report and policy update, and performing performance evaluation again based on the optimized resource scheduling policy to verify the validity of the policy, so as to generate a performance evaluation report and a final optimized resource scheduling policy for system operation and management reference.
Preferably, the continuous monitoring and improvement establishes a continuous monitoring system, continuously collects real-time data, compares the real-time data with the performance evaluation report and the optimized resource scheduling strategy, improves according to the changed requirements and network conditions, and comprises the following specific steps of:
s901: establishing a real-time monitoring system, wherein the real-time monitoring system is established by adopting a distributed data acquisition and transmission system and is used for continuously collecting real-time data;
S902: real-time data analysis and performance evaluation, wherein real-time data is analyzed and processed by using a real-time data analysis tool to generate a real-time performance evaluation result, wherein the real-time performance evaluation result comprises a current performance index and comparison with an optimization strategy;
s903: dynamically adjusting a resource scheduling strategy, and adjusting resource allocation and energy transmission strategies by adopting a dynamic resource scheduling algorithm based on a real-time performance evaluation result to generate a dynamically adjusted resource scheduling strategy so as to cope with real-time changing requirements and network conditions;
s904: and (3) continuously improving and feeding back the circulation, establishing a feedback circulation mechanism, combining the result of the resource scheduling strategy after dynamic adjustment with the real-time monitoring data, continuously improving the strategy, continuously improving the resource scheduling strategy and the real-time monitoring data, and ensuring the continuous optimization and adaptability of the system performance.
The invention provides a heterogeneous wireless network bearing power service resource scheduling method. The device comprises the following
The beneficial effects are that:
according to the invention, through resource measurement and demand estimation, the sensor is used for measuring the resource utilization rate and the power demand of different wireless networks, the geographical distribution map of the resource utilization rate and the power demand is generated, the power demand is ensured to be met through the design, meanwhile, the resource waste is minimized, the resource utilization rate is improved, the energy supply plan is optimized through the genetic algorithm based on the resource scheduling distribution scheme, the energy transmission loss is optimized, the energy supply plan and the energy transmission control are generated, the energy transmission parameters of each network are adjusted through the dynamic power control algorithm based on the energy supply plan, the energy supply plan is designed to optimize the energy supply plan and the energy transmission control, the energy consumption and the transmission loss are reduced, the energy efficiency of the power transmission is improved, the real-time monitoring equipment is installed, the resource utilization rate and the power demand of each network are detected regularly and compared with the prediction result, the real-time monitoring data is designed, the effect of enabling the system to timely cope with network change and demand fluctuation is improved, the real-time response of the network is improved, the performance and the performance of the power transmission system is improved, the performance is improved and the performance is improved by the performance is improved and the performance is improved.
Drawings
FIG. 1 is a schematic diagram of the main steps of the present invention;
FIG. 2 is a detailed schematic of the S1 of the present invention;
FIG. 3 is a schematic diagram of an S2 refinement of the present invention;
FIG. 4 is a schematic diagram of an S3 refinement of the present invention;
FIG. 5 is a schematic diagram of an S4 refinement of the present invention;
FIG. 6 is a schematic diagram of an S5 refinement of the present invention;
FIG. 7 is a schematic diagram of an S6 refinement of the present invention;
FIG. 8 is a schematic diagram of an S7 refinement of the present invention;
FIG. 9 is a schematic diagram of an S8 refinement of the present invention;
fig. 10 is a schematic diagram of the S9 refinement of the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Examples:
as shown in fig. 1-10, an embodiment of the present invention provides a method for scheduling power service resources carried by a heterogeneous wireless network, including the following steps:
s1: the method comprises the steps of measuring resource utilization rate and power demand of different wireless networks by using a wireless network monitoring sensor, a power measuring sensor and a data acquisition and analysis system, and generating a geographic distribution map of the resource utilization rate and the power demand, wherein the wireless network monitoring sensor comprises a Wi-Fi signal strength sensor, a radio frequency spectrum analyzer, a data packet capturing device and a wireless network load sensor, the power measuring sensor comprises an electric energy meter and a current sensor, a power quality sensor, a smart grid sensor, solar energy and wind energy sensors, and the data acquisition and analysis system comprises a data acquisition node, a cloud computing platform, a geographic information system, a data analysis tool and a visualization tool;
S2: initializing resource scheduling, clustering the resource demands of different areas by adopting a K-means clustering algorithm based on a geographic distribution map of the generated resource utilization rate and the power demands, and determining a resource demand clustering center for subsequent scheduling;
s3: the resource scheduling and distribution is carried out by adopting a cost algorithm based on a resource demand clustering center, so that the power demand is met, and a resource distribution scheme is generated, wherein the resource distribution scheme comprises the resource distribution amount of each network;
s4: an energy supply plan, which is optimized by adopting a genetic algorithm based on a resource scheduling and distributing scheme so as to optimize energy transmission loss and generate the energy supply plan;
s5: energy transmission control, based on an energy supply plan, adjusting energy transmission parameters of each network by adopting a dynamic power control algorithm, wherein the energy supply plan;
s6: real-time resource monitoring, namely installing real-time monitoring equipment, periodically detecting the resource utilization rate and the power demand of each network, comparing the resource utilization rate and the power demand with a prediction result, and monitoring data in real time;
s7: dynamic adjustment of resource scheduling, namely adjusting resource allocation and energy transmission control parameters by adopting a feedback control algorithm based on real-time monitoring data, wherein the resource allocation and the energy transmission parameters after dynamic adjustment;
S8: performance evaluation and optimization, namely performing performance evaluation by adopting a machine learning algorithm based on historical data and dynamically adjusted resource allocation and energy transmission parameters, and optimizing a resource scheduling strategy according to an evaluation result, wherein the performance evaluation report and the optimized resource scheduling strategy;
s9: and continuously monitoring and improving, establishing a continuous monitoring system, continuously collecting real-time data, comparing with a performance evaluation report and an optimized resource scheduling strategy, improving according to the changed requirements and network conditions, and continuously improving the resource scheduling strategy and the real-time monitoring data.
The method comprises the steps of measuring resource utilization rate and power demand of different wireless networks through a resource measurement and demand estimation, generating a geographic distribution map of the resource utilization rate and the power demand, ensuring that the power demand is met through the design, simultaneously minimizing resource waste, improving the utilization rate of the resource, optimizing the energy supply plan through a genetic algorithm based on a resource scheduling distribution scheme through the energy supply plan, optimizing energy transmission loss to optimize energy transmission loss, generating an energy supply plan and energy transmission control, adjusting energy transmission parameters of each network through a dynamic power control algorithm based on the energy supply plan, optimizing the energy supply plan and the energy transmission control through the design of the energy supply plan, reducing energy consumption and transmission loss, contributing to improving the energy efficiency of power transmission, and periodically detecting the resource utilization rate and the power demand of each network through real-time resource monitoring, comparing with a prediction result, and real-time monitoring the design of data, achieving the effect that a system can timely cope with network changes and demand fluctuation, improving the real-time responsiveness of the network, evaluating and optimizing the performance of the network based on the performance evaluation and optimization, optimizing the performance of the machine after the resource allocation algorithm based on the data and dynamic adjustment, optimizing the performance of the resource has improved performance of the network, improving the performance of the system, optimizing the performance according to the resource scheduling algorithm, and the performance evaluation strategy, and the performance of the resource allocation has improved.
The method for measuring the resource and estimating the demand by using the wireless network monitoring sensor, the power measuring sensor and the data acquisition and analysis system comprises the following specific steps of:
s101: resource measurement and demand estimation are deployed at different geographic locations using a sensor network to monitor the resource utilization and power demand of the wireless network. The sensors may include wireless network monitoring sensors, power measurement sensors, and the like. Collecting network resource utilization rate and power demand data in a real-time manner by adopting a wireless sensor network protocol such as Zigbee or LoRa, and generating a real-time resource utilization rate and power demand data set comprising information of each geographic position;
s102: data processing and analysis, the data acquired in S101 are processed and analyzed. First, an outlier and noise data are removed using a data cleansing method. Then, a space-time analysis method, such as time sequence analysis, geographic Information System (GIS) technology, etc., is used to identify the resource utilization rate and the geographic distribution rule of the power demand. The data can be converted into a geographic distribution map by using technologies such as cluster analysis, spatial interpolation and the like, the geographic distribution map of the resource utilization rate and the power demand is generated, and the resource utilization rate and the power demand conditions of different geographic positions are displayed;
S103: the demand prediction model is established based on the geographic distribution map data in S102. Machine learning algorithms, such as regression analysis, neural networks or decision trees, can be used to incorporate factors such as geographic location, time, resource utilization, power demand, etc. into the model to predict future resource demand trends, and generate a prediction model of resource demand for estimating future resource demands;
s104: resource optimization strategies are formulated based on the demand prediction model in S103. According to the predicted resource demand trend, a resource allocation algorithm such as dynamic resource allocation, a power control strategy and the like is adopted to optimize the resource utilization rate and the power consumption of the wireless network, and a resource optimization strategy is generated for adjusting the network resource allocation in real time;
s105: and (3) real-time resource adjustment, namely applying the resource optimization strategy in the step S104 to the wireless network, and adjusting resource allocation and power control in real time through a network management system. And (3) monitoring network performance and power consumption, dynamically adjusting a resource allocation strategy according to actual conditions so as to meet the requirements of different geographic areas, applying the resource optimization strategy in the step (4) to a wireless network, and adjusting resource allocation and power control in real time through a network management system. Network performance and power consumption are monitored, and resource allocation strategies are dynamically adjusted according to actual conditions so as to meet the requirements of different geographic areas.
The data analysis result of S102 is used for demand prediction in step S103, the model result of step S103 is used for resource optimization policy formulation in step S104, and the policy of step S104 is implemented and dynamically adjusted in step S105 to realize efficient utilization of resources and management of power demand.
Initializing resource scheduling, clustering the resource demands of different areas by adopting a K-means clustering algorithm based on the geographic distribution map of the generated resource utilization rate and the power demands, and determining a resource demand clustering center, wherein the specific steps for follow-up scheduling are as follows:
s201: data preparation and preprocessing first, geographic profile data of generated resource utilization and power demand is prepared. Preprocessing the data, including removing outliers, normalizing the data to ensure that they have the same scale, converting the geographic coordinate information to numerical features for use in clustering, resulting in a ready, preprocessed dataset;
s202: k mean value clustering, which is to cluster the resource demands of different areas by adopting a K mean value clustering algorithm. The algorithm divides the data set into K clusters, where K is the number of cluster centers set in advance. Here, the choice of K should be determined according to the background and requirements of the problem. Through an iterative process, K-means clustering distributes data points to the closest clustering center, and then the clustering center is updated until convergence, and a clustering result is required by resources, wherein the clustering result comprises clustering clusters to which each region belongs and the positions of the clustering centers;
S203: and initializing the resource scheduling, and determining the initial state of the resource scheduling based on the clustering result of the resource demands in the step S202. This can be achieved by selecting the cluster center of each cluster as the initial point of resource scheduling. The initial points represent resource demand clustering centers in different areas and are used for subsequent resource scheduling to obtain initial states of the resource scheduling, wherein the initial states comprise positions of the resource demand clustering centers;
s204: and the subsequent scheduling strategy can further formulate the resource scheduling strategy after the initialization of the resource scheduling. This may involve dynamic scheduling algorithms that adjust the allocation of resources and the management of power based on real-time resource requirements and network conditions, and may further be formulated according to specific requirements, resource scheduling policies, including algorithms and rules for real-time resource allocation and power management.
The clustering result of S202 is used for the initialization of the resource scheduling of S203 to determine the initial state of the resource scheduling. The initial state of resource scheduling may provide an important reference and basis for subsequent resource scheduling policies. In addition, S204 is optional, and it may be determined whether further resource scheduling policy formulation is required according to specific requirements. The method is beneficial to effectively distributing and managing the resources according to the resource demand characteristics of different areas in the geographic distribution diagram.
The resource scheduling and distributing, based on the resource demand clustering center, the resource distribution is carried out by adopting a cost algorithm, the power demand is ensured to be met, and a resource distribution scheme is generated, wherein the specific steps of the resource distribution amount of each network are as follows:
s301: the resource demand clustering center determines, based on geographic distribution data of resource demands by using a K-means clustering algorithm, the resource demands of different areas are clustered into a plurality of clusters, the clustering center represents a center point of each resource demand cluster, namely represents a representative position of resource demand conditions of each area, and the resource demand clustering center is generated and comprises a clustering center coordinate of each resource demand cluster;
s302: and the cost algorithm is adopted to allocate the resources based on the position information of the resource demand clustering center and the topological structure of the power supply network. The goal of this algorithm is to maximize the total amount of resource allocation while meeting the cost minimization of power requirements and resource provisioning. By building a graph model in which nodes represent resource supply points, resource demand points, and power transmission lines, edges represent the capabilities and costs of resource supply and power transmission. Then, determining the resource allocation amount of each network through a cost algorithm to ensure that the power requirement is met to generate a resource allocation scheme, including the resource allocation amount of each network and the cost calculated by the cost algorithm;
S303: resource allocation scheme optimization, based on the resource allocation scheme in S302, further optimization may be performed, such as adjusting the allocation of resources by linear programming or other optimization algorithms to meet specific constraints or optimization objectives. The step can be customized according to actual demands, and the optimized resource allocation scheme meets additional constraint conditions or further optimized results;
s304: dynamic resource scheduling policies may be designed if real-time adjustment of resource allocation is required to cope with changing power demands and network conditions. This includes the process of monitoring real-time data, calculating new resource allocation schemes, and implementing. The dynamic resource scheduling strategy can reallocate resources in different time periods according to actual conditions, and can dynamically adjust the real-time resource allocation scheme according to changing power requirements and network states.
Step S301 generates a resource demand cluster center as input to step S302 for resource allocation of the cost algorithm. The resource allocation scheme may be optimized in step S303, while step S304 is optional for implementing dynamic resource scheduling. The overall approach ensures efficient allocation of resources to meet power requirements and allows for minimization of resource supply costs.
The energy supply plan is optimized by adopting a genetic algorithm based on a resource scheduling and distributing scheme so as to optimize energy transmission loss, and the specific steps for generating the energy supply plan are as follows:
s401: the resource scheduling allocation scheme is prepared by first acquiring the aforementioned resource scheduling allocation scheme including the resource allocation amount per network. This would be an initial population of genetic algorithms, each individual representing one possible energy supply plan, resulting in an initial population, each individual representing one potential energy supply plan;
s402: the genetic algorithm generates an optimized energy supply plan, and the genetic algorithm is employed to optimize the energy supply plan. Genetic algorithms are optimization algorithms that search for optimal solutions by modeling natural choices and genetic mechanisms. In this step, a fitness function may be defined, measuring the quality of each individual (i.e., the energy supply plan), typically with the goal of minimizing energy transfer losses. Then, using genetic algorithm selection, crossover, mutation and other operations to generate new individuals to gradually improve the energy supply plan, and obtaining an optimized energy supply plan, wherein the optimized energy supply plan comprises an optimal solution for minimizing energy transmission loss;
S403: the energy supply plan is further optimized, and if desired, other optimization algorithms, such as linear programming or simulated annealing algorithms, may be used to meet specific constraints or to further improve the performance of the plan. The step can be customized according to actual requirements, so that the further optimized energy supply plan meets additional constraint conditions or the further optimized result;
s404: dynamic energy supply planning strategy the dynamic energy supply planning strategy can be designed if the energy supply plan needs to be adjusted in real time to cope with changing power demand and network conditions. This includes the process of monitoring real-time data, calculating a new energy supply plan, and implementing. The dynamic energy supply planning strategy can be used for carrying out planning readjustment in different time periods according to actual conditions, and the real-time energy supply planning can be carried out according to the changed power requirement and the network state.
Step S401 provides an initial population as input to the genetic algorithm of step S402 for generating an optimized energy supply plan. Step S403 and step S404 are optional for further optimizing the plan or implementing dynamic adjustments. The overall method aims at generating an optimal energy supply plan to minimize energy transmission losses and takes into account the basis of a resource scheduling allocation scheme.
And (3) energy transmission control, wherein the energy transmission parameters of each network are adjusted by adopting a dynamic power control algorithm based on an energy supply plan, and the energy supply plan comprises the following specific steps:
s501: energy supply plan preparation, first, the aforementioned energy supply plans are acquired, including the energy demand and distribution plans for each network. This will be used as input to the dynamic power control algorithm for adjusting the energy transfer parameters to obtain initial energy supply plan data, including energy demand and distribution plans;
s502: dynamic power control algorithm selection, selecting an appropriate dynamic power control algorithm, such as a PID algorithm (proportional-integral-derivative algorithm) based on feedback control or a Model Predictive Control (MPC) algorithm. The algorithms can adjust the energy transmission parameters in real time according to the system state so as to meet the requirements of an energy supply plan, and select a proper dynamic power control algorithm;
s503: dynamic power adjustment, based on a selected dynamic power control algorithm, monitors the energy transmission parameters (e.g., transmission power or frequency) of each network in real time and adjusts according to the demands in the energy supply plan. This may be a iterative process to ensure proper adjustment of the energy transfer parameters, the adjusted energy transfer parameters to meet the requirements of the energy supply plan;
S504: performance evaluation and feedback, wherein the performance evaluation is carried out on the energy transmission parameters after adjustment, and the performance evaluation comprises the aspects of energy transmission efficiency, stability, response time and the like. If the performance does not meet the requirement, the method can feed back to the step S502, select different dynamic power control algorithms, or further adjust algorithm parameters, performance evaluation results and possible feedback information for further optimizing energy transmission control;
s505: and final energy transmission control, determining final energy transmission parameters based on the performance evaluation and feedback information so as to meet the requirements of an energy supply plan. These parameters may be implemented in the system, implementing the actual energy transfer control, the final energy transfer parameters, for implementing the energy transfer control, ensuring that the requirements of the energy supply plan are met.
Step S501 provides the energy supply plan as input, step S502 selects the appropriate control algorithm, steps S503 and S504 dynamically adjust the parameters and evaluate the performance, and finally the optimal energy transfer parameters are determined in step S505. Thus, the energy transmission can be adjusted in real time according to the actual demand, so as to meet the requirement of an energy supply plan.
Real-time resource monitoring, installing real-time monitoring equipment, periodically detecting the resource utilization rate and the power demand of each network, comparing with a predicted result, and carrying out the specific steps of real-time monitoring data:
s601: the method comprises the steps of installing a real-time resource monitoring device and collecting data, wherein firstly, a special real-time resource monitoring device is installed on each network node, and the device can monitor the resource utilization rate and the power requirement of a network in real time. Collecting data by using sensor technology (such as a current sensor, a temperature sensor, a network flow monitor and the like), wherein the data comprises information of load, power consumption and the like of network equipment, and the collected real-time monitoring data comprises real-time values of resource utilization rate and power demand;
s602: preprocessing the data, comparing the data with a predicted result, and preprocessing the collected real-time monitoring data, wherein the preprocessing comprises data cleaning, denoising, data conversion and other operations so as to ensure the accuracy and reliability of the data. The preprocessed real-time data is then compared with the previous predictions. The comparison process can adopt a statistical method (such as mean value variance analysis, regression analysis and the like) or a machine learning algorithm (such as a support vector machine, a neural network and the like), and the comparison result comprises difference analysis, correlation analysis and the like of real-time monitoring data and a prediction result;
S603: and (3) monitoring data application and further processing in real time, and making decisions and controlling based on the comparison result obtained in the step S602. If the real-time monitoring data is consistent with the predicted result or within an acceptable range, the system continues to operate according to the current energy plan. If abnormality occurs, corresponding emergency measures such as adjusting network load, switching standby energy sources and the like are triggered so as to ensure stable operation of the network. In addition, the real-time monitoring data is fed back to the prediction model for optimization and improvement of the model, so that a closed-loop control system is formed, and the real-time applied decision result and feedback data are used for real-time adjustment and optimization of the system.
The key of the method is accurate collection of real-time monitoring data, comparison analysis with a predicted result and real-time decision and feedback based on the comparison result. Such a closed loop control system may ensure real-time monitoring and regulation of network energy to cope with changing demands and environments.
The dynamic adjustment of resource scheduling, based on real-time monitoring data, adopts a feedback control algorithm to adjust the resource allocation and energy transmission control parameters, and the specific steps of the resource allocation and energy transmission parameters after dynamic adjustment are as follows:
S701: the real-time monitoring data analysis and resource demand calculation are performed, firstly, a data analysis algorithm, such as a time sequence analysis and a filtering algorithm, is adopted to process and analyze the real-time monitoring data so as to acquire the current state and trend of the network. Then, based on the analysis results, calculating the current resource demands, including network loads, power demands and the like, and generating data of the real-time resource demands, including numerical values and trend analysis of the current resource demands;
s702: the feedback control algorithm adjusts the resource allocation and energy transfer control parameters based on real-time resource demand data and the system model using a feedback control algorithm, such as a proportional-integral-derivative (PID) control algorithm or a Model Predictive Control (MPC) algorithm. The parameters comprise load balancing, power distribution, energy transmission power and the like of the network equipment, and the dynamically adjusted resource distribution and energy transmission parameters are generated so as to meet the real-time resource requirement and keep the system stable;
s703: real-time resource scheduling and performance optimization, and resource scheduling and energy transmission control are implemented based on the adjusted parameters obtained in step S702. This may include assigning tasks to appropriate nodes, dynamically adjusting power allocation, energy transmission power, etc. Meanwhile, the utilization rate of the real-time resources and the power demand are continuously monitored, feedback and adjustment are carried out at any time, dynamic scheduling and performance optimization of the real-time resources are realized, and efficient operation of the network in a continuously-changing environment is ensured.
The key of the method is the analysis of real-time monitoring data and the application of a feedback control algorithm, so as to realize the dynamic adjustment of resource allocation and energy transmission parameters, thereby meeting the real-time requirement of a network and improving the system performance. The correlation between the steps ensures efficient utilization of real-time data and stability of the system.
The performance evaluation and optimization, based on historical data and dynamically adjusted resource allocation and energy transmission parameters, adopts a machine learning algorithm to perform performance evaluation, optimizes a resource scheduling strategy according to an evaluation result, and comprises the following specific steps of:
s801: historical data collection and preprocessing, firstly, a data collection method is adopted to collect historical performance data, including network load, resource allocation parameters, power consumption and the like. Then, data preprocessing, including data cleaning, denoising and feature extraction, is carried out to ensure the quality and usability of the data, and preprocessed historical performance data is generated for use in subsequent steps;
s802: machine learning model training, based on historical performance data, uses machine learning algorithms, such as Deep Neural Network (DNN) or decision tree regression (Decision Tree Regression), to train a performance assessment model. The model predicts the system performance according to the resource allocation and the energy transmission parameters, and generates a performance evaluation model for predicting the system performance;
S803: and (3) performance evaluation, wherein the performance evaluation model in the step S802 is used for performing performance evaluation according to the dynamically adjusted resource allocation and energy transmission parameters. This includes predicting performance metrics of the network, such as latency, throughput, energy efficiency, etc., generating performance assessment results, including predicted values of the performance metrics;
s804: and optimizing the resource scheduling strategy, comparing the performance evaluation result with a target performance index, and adjusting parameters of the resource scheduling strategy by adopting an optimization algorithm, such as a genetic algorithm or a simulated annealing algorithm, so as to optimize the system performance. This may include re-assigning tasks, adjusting power allocation policies, optimizing energy transmission power, etc., generating optimized resource scheduling policies to improve system performance;
s805: and (3) performing performance evaluation report and policy update, and performing performance evaluation again based on the optimized resource scheduling policy so as to verify the validity of the policy. Then, a performance assessment report is generated, including improvements in system performance and suggested optimization strategies, and the performance assessment report and final optimized resource scheduling strategy are generated for system operation and management reference.
The method continuously optimizes the resource scheduling strategy through a machine learning model and a performance evaluation circulation process so as to improve the system performance. The correlation between steps ensures that the performance assessment results are used to optimize the policy and continue to improve system performance.
Continuously monitoring and improving, establishing a continuously monitoring system, continuously collecting real-time data, comparing the real-time data with a performance evaluation report and an optimized resource scheduling strategy, improving according to changing requirements and network conditions, and continuously improving the resource scheduling strategy and the real-time monitoring data, wherein the specific steps are as follows:
s901: a real-time monitoring system is established, and a distributed data acquisition and transmission system, such as Kafka or RabbitMQ, is adopted to establish the real-time monitoring system. The system is used for collecting real-time data such as network performance data, resource scheduling strategy parameters, energy transmission parameters and the like, and establishing a real-time monitoring system for continuously collecting the real-time data;
s902: real-time data analysis and performance assessment real-time data is analyzed and processed using real-time data analysis tools, such as Apache Flink or Spark Streaming. Comparing the real-time data with a historical performance evaluation report and an optimized resource scheduling strategy to evaluate the current performance, and generating a real-time performance evaluation result, wherein the real-time performance evaluation result comprises the comparison between the current performance index and the optimized strategy;
s903: and dynamically adjusting a resource scheduling strategy, and adjusting the resource allocation and the energy transmission strategy by adopting a dynamic resource scheduling algorithm, such as reinforcement learning or genetic algorithm, based on the real-time performance evaluation result. This allows the system to optimize the use of resources in real time according to changing demands and network conditions, generating a dynamically adjusted resource scheduling policy to cope with the real-time changing demands and network conditions;
S904: and establishing a feedback circulation mechanism, combining the result of the resource scheduling strategy after dynamic adjustment with real-time monitoring data, and continuously improving the strategy. Monitoring the performance of the strategy, collecting new real-time data, and repeating the step S902 and the step S903 to continuously improve the resource scheduling strategy, continuously improve the resource scheduling strategy and the real-time monitoring data, thereby ensuring continuous optimization and adaptability of the system performance.
The method realizes continuous monitoring and improvement of the system by establishing a real-time monitoring system, real-time data analysis, dynamic adjustment of resource strategies and continuous feedback loops. The correlation between steps ensures that the real-time monitoring data is used to optimize the resource scheduling policy and continuously improve system performance to accommodate changing demands and network conditions.
Although embodiments of the present invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made therein without departing from the principles and spirit of the invention, the scope of which is defined in the appended claims and their equivalents.
Claims (10)
1. The heterogeneous wireless network bearing power service resource scheduling method is characterized by comprising the following steps:
Resource measurement and demand estimation, wherein a wireless network monitoring sensor, a power measuring sensor and a data acquisition and analysis system are used for measuring the resource utilization rate and the power demand of different wireless networks, and a geographic distribution map of the resource utilization rate and the power demand is generated;
initializing resource scheduling, clustering the resource demands of different areas by adopting a K-means clustering algorithm based on the geographic distribution map of the generated resource utilization rate and the power demands, and determining a resource demand clustering center for subsequent scheduling;
resource scheduling and distributing, namely, based on the resource demand clustering center, carrying out resource distribution by adopting a cost algorithm to ensure that the power demand is met, and generating a resource distribution scheme comprising the resource distribution amount of each network;
an energy supply plan, based on the resource scheduling and distributing scheme, optimizing the energy supply plan by adopting a genetic algorithm to optimize energy transmission loss and generate the energy supply plan;
energy transmission control, based on the energy supply plan, adopting a dynamic power control algorithm to adjust the energy transmission parameters of each network;
real-time resource monitoring, namely installing real-time monitoring equipment, periodically detecting the resource utilization rate and the power demand of each network, comparing the resource utilization rate and the power demand with a prediction result, and monitoring data in real time;
Dynamically adjusting resource scheduling, adjusting resource allocation and energy transmission control parameters by adopting a feedback control algorithm based on the real-time monitoring data, wherein the resource allocation and the energy transmission parameters are dynamically adjusted;
performing performance evaluation and optimization, namely performing performance evaluation by adopting a machine learning algorithm based on historical data and the dynamically adjusted resource allocation and energy transmission parameters, and optimizing a resource scheduling strategy according to an evaluation result, a performance evaluation report and the optimized resource scheduling strategy;
and continuously monitoring and improving, establishing a continuous monitoring system, continuously collecting real-time data, comparing with the performance evaluation report and the optimized resource scheduling strategy, improving according to the changed requirements and network conditions, and continuously improving the resource scheduling strategy and the real-time monitoring data.
2. The method for scheduling power service resources carried by a heterogeneous wireless network according to claim 1, wherein the method comprises the steps of: the specific steps of using the wireless network monitoring sensor, the power measuring sensor and the data acquisition and analysis system to measure the resource utilization rate and the power demand of different wireless networks and generating the geographic distribution map of the resource utilization rate and the power demand are as follows:
Resource measurement and demand estimation, wherein the sensor network is deployed at different geographic positions, the resource utilization rate and the power demand of the wireless network are monitored, the Zigbee or LoRa wireless sensor network protocol is adopted, network resource utilization rate and power demand data are collected in a real-time mode, and a real-time resource utilization rate and power demand data set comprising information of each geographic position is generated;
processing and analyzing data acquired in the resource measurement and demand estimation, removing abnormal values and noise data by using a data cleaning method, identifying the geographic distribution rules of the resource utilization rate and the power demand by using a space-time analysis method, converting the data into a geographic distribution map by using a clustering analysis and spatial interpolation technology, generating the geographic distribution map of the resource utilization rate and the power demand, and displaying the resource utilization rate and the power demand conditions of different geographic positions;
the demand prediction model is established based on geographic distribution diagram data in the data processing and analysis, a machine learning algorithm is used for bringing geographic position, time, resource utilization rate and power demand factors into the model so as to predict future resource demand trend, and a resource demand prediction model is generated and used for estimating future resource demand;
A resource optimization strategy, based on the demand prediction model, a resource optimization strategy is formulated, and a resource allocation algorithm is adopted according to the predicted resource demand trend so as to optimize the resource utilization rate and the power consumption of the wireless network, and the resource optimization strategy is generated and used for adjusting the network resource allocation in real time;
and (3) real-time resource adjustment, wherein the resource optimization strategy in the resource optimization strategy is applied to a wireless network, the resource allocation and the power control are adjusted in real time through a network management system, the network performance and the power consumption are monitored, the resource allocation strategy is dynamically adjusted according to actual conditions so as to meet the requirements of different geographic areas, the network performance and the power consumption are monitored, and the resource allocation strategy is dynamically adjusted according to actual conditions so as to meet the requirements of different geographic areas.
3. The method for scheduling power service resources carried by a heterogeneous wireless network according to claim 1, wherein the method comprises the steps of: the resource scheduling is initialized, the resource demands of different areas are clustered by adopting a K-means clustering algorithm based on the geographic distribution map of the generated resource utilization rate and the power demand, and a resource demand clustering center is determined, wherein the specific steps for follow-up scheduling are as follows:
Data preparation and preprocessing, preprocessing the data based on the geographical distribution map data of the resource utilization rate and the power demand generated by the resource measurement and the demand estimation, including removing abnormal values, normalizing the data to ensure that the data have the same scale, and converting geographical coordinate information into numerical characteristics for use in clustering;
k mean value clustering, namely clustering the resource demands of different areas by adopting a K mean value clustering algorithm, distributing data points to the closest clustering centers through an iterative process, and updating the clustering centers until convergence, wherein the clustering result of the resource demands comprises the clustering clusters of each area and the positions of the clustering centers;
initializing resource scheduling, and determining initial states of the resource scheduling based on resource demand clustering results in the K-means clustering, wherein the initial points represent resource demand clustering centers in different areas and are used for subsequent resource scheduling, and the initial states of the resource scheduling comprise positions of the resource demand clustering centers;
and after the subsequent scheduling strategy is initialized, the resource scheduling strategy can be further formulated, the allocation of resources and the management of power are adjusted according to the real-time resource requirements and the network state, and the allocation of resources and the management of power are adjusted according to the real-time resource requirements and the network state.
4. The method for scheduling power service resources carried by a heterogeneous wireless network according to claim 1, wherein the method comprises the steps of: the resource scheduling and distributing, based on the resource demand clustering center, adopts a cost algorithm to distribute the resources, ensures that the power demand is met, and generates a resource distribution scheme by the following specific steps:
determining a resource demand clustering center, namely, utilizing the K-means clustering algorithm to cluster the resource demands of different areas into a plurality of clusters based on the geographic distribution data of the resource demands, wherein the clustering center represents the central point of each resource demand cluster, namely, represents the representative position of the resource demand condition of each area, and generating the resource demand clustering center, including the clustering center coordinates of each resource demand cluster;
a cost algorithm for performing resource allocation based on the position information of the resource demand cluster center and the topology structure of the power supply network, by creating a graph model in which nodes represent resource supply points, resource demand points and power transmission lines while representing the capacity and cost of resource supply and power transmission, and then determining the resource allocation amount of each network by the cost algorithm to ensure that the power demand is satisfied, generating a resource allocation scheme including the resource allocation amount of each network and the cost calculated by the cost algorithm;
Optimizing a resource allocation scheme, further optimizing based on the resource allocation scheme in the cost algorithm, and adjusting the allocation of resources through a linear programming algorithm to meet specific constraint conditions or optimization targets, wherein the optimized resource allocation scheme meets additional constraint conditions or further optimizing results;
and the dynamic resource scheduling strategy is used for carrying out resource reallocation in different time periods according to actual conditions and carrying out resource reallocation in different time periods according to actual conditions.
5. The method for scheduling power service resources carried by a heterogeneous wireless network according to claim 1, wherein the method comprises the steps of: the energy supply plan is optimized by adopting a genetic algorithm based on the resource scheduling and distributing scheme so as to optimize energy transmission loss, and the specific steps of generating the energy supply plan are as follows:
preparing a resource scheduling allocation scheme, wherein the allocation scheme in the resource scheduling allocation is obtained, and the allocation scheme comprises the resource allocation amount of each network, which is used as an initial population of a genetic algorithm, and each individual represents one possible energy supply plan;
Generating an optimized energy supply plan by using a genetic algorithm, optimizing the energy supply plan by using the genetic algorithm, and generating new individuals by using the selection, crossing and mutation operations of the genetic algorithm so as to gradually improve the energy supply plan and obtain an optimized energy supply plan;
the energy supply plan is further optimized, using other optimization algorithms to meet specific constraints or to further improve the performance of the plan;
and the dynamic energy supply plan strategy is used for adjusting the energy supply plan in real time to cope with the changing power demand and the network state, and the dynamic adjustment result is carried out according to the changing power demand and the network state.
6. The method for scheduling power service resources carried by a heterogeneous wireless network according to claim 1, wherein the method comprises the steps of: the energy transmission control adopts a dynamic power control algorithm to adjust the energy transmission parameters of each network based on the energy supply plan, and the energy supply plan comprises the following specific steps:
energy supply plan preparation, obtaining the energy supply plan including the energy demand and distribution plan of each network, which will be input to the dynamic power control algorithm for adjusting the energy transfer parameters, initial energy supply plan data including the energy demand and distribution plan;
The dynamic power control algorithm is selected, a proper dynamic power control algorithm is selected, the algorithm can adjust energy transmission parameters in real time according to the system state so as to meet the requirement of an energy supply plan, and the selected dynamic power control algorithm is selected;
dynamic power adjustment, based on a selected dynamic power control algorithm, monitoring the energy transmission parameters of each network in real time, and adjusting the energy transmission parameters according to the requirements in an energy supply plan so as to meet the requirements of the energy supply plan;
performance evaluation and feedback, wherein the performance evaluation is carried out on the energy transmission parameters after adjustment, the performance does not meet the requirement, the performance can be fed back to the dynamic power adjustment, different dynamic power control algorithms are selected, or algorithm parameters, performance evaluation results and possible feedback information are further adjusted, so that the energy transmission control is further optimized;
and finally, the energy transmission control is performed, and based on the performance evaluation and feedback information, the final energy transmission parameters are determined so as to meet the requirements of the energy supply plan, and the final energy transmission parameters are used for implementing the energy transmission control to ensure that the requirements of the energy supply plan are met.
7. The method for scheduling power service resources carried by a heterogeneous wireless network according to claim 1, wherein the method comprises the steps of: the real-time resource monitoring, installing real-time monitoring equipment, periodically detecting the resource utilization rate and the power demand of each network, comparing with the predicted result, and carrying out the specific steps of real-time monitoring data:
The method comprises the steps of installing real-time resource monitoring equipment and collecting data, wherein special real-time resource monitoring equipment is installed on each network node, and can monitor the resource utilization rate and the power demand of a network in real time and collect real-time monitoring data;
preprocessing data and comparing the preprocessed data with a predicted result, preprocessing the acquired real-time monitoring data, including data cleaning, denoising, data conversion and the like, so as to ensure the accuracy and reliability of the data, and comparing the preprocessed real-time data with the previous predicted result, wherein the comparison result comprises difference analysis and correlation analysis of the real-time monitoring data and the predicted result;
and the real-time monitoring data is applied and further processed, decision making and control are carried out based on the data preprocessing and the comparison result obtained with the prediction result, the real-time monitoring data is fed back to the prediction model for optimizing and improving the model, a closed-loop control system is formed, and the decision making result and the feedback data which are applied in real time are used for real-time adjustment and optimization of the system.
8. The method for scheduling power service resources carried by a heterogeneous wireless network according to claim 1, wherein the method comprises the steps of: the dynamic adjustment of the resource scheduling, based on the real-time monitoring data, adopts a feedback control algorithm to adjust the control parameters of resource allocation and energy transmission, and the specific steps of the resource allocation and the energy transmission parameters after the dynamic adjustment are as follows:
Real-time monitoring data analysis and resource demand calculation, wherein a data analysis algorithm is adopted to process and analyze the real-time monitoring data so as to acquire the current state and trend of the network, and the current resource demand, including network load, power demand and the like, is calculated based on the analysis result of the data analysis algorithm to generate data of the real-time resource demand, including numerical value and trend analysis of the current resource demand;
the feedback control algorithm adjusts the resource allocation and energy transmission parameters, and the feedback control algorithm is utilized to adjust the resource allocation and energy transmission control parameters according to the real-time resource demand data and the system model, so as to generate the dynamically adjusted resource allocation and energy transmission parameters, thereby meeting the real-time resource demand and keeping the system stable;
and (3) real-time resource scheduling and performance optimization, adjusting the adjusted parameters obtained from the resource allocation and energy transmission parameters based on a feedback control algorithm, implementing resource scheduling and energy transmission control, continuously monitoring the real-time resource utilization rate and the power demand, feeding back and adjusting at any time, continuously monitoring the real-time resource utilization rate and the power demand, and feeding back and adjusting at any time.
9. The method for scheduling power service resources carried by a heterogeneous wireless network according to claim 1, wherein the method comprises the steps of: the performance evaluation and optimization are performed by adopting a machine learning algorithm based on historical data and the dynamically adjusted resource allocation and energy transmission parameters, and the resource scheduling strategy is optimized according to the evaluation result, and the specific steps of the performance evaluation report and the optimized resource scheduling strategy are as follows:
Historical data collection and preprocessing, namely collecting historical performance data by adopting a data collection method, wherein the historical performance data comprises network load, resource allocation parameters and power consumption, and performing data preprocessing, namely data cleaning, denoising and feature extraction so as to ensure the quality and usability of the data and generate preprocessed historical performance data;
training a machine learning model, training a performance evaluation model by adopting a machine learning algorithm based on historical performance data, and predicting system performance according to resource allocation and energy transmission parameters by the model to generate a performance evaluation model for predicting system performance;
performance evaluation, namely performing performance evaluation according to the dynamically adjusted resource allocation and energy transmission parameters by using a performance evaluation model in the training of the step machine learning model, and generating a performance evaluation result comprising a predicted value of a performance index;
optimizing the resource scheduling strategy, comparing the performance evaluation result with a target performance index, adopting an optimization algorithm to adjust parameters of the resource scheduling strategy so as to optimize the system performance, and generating an optimized resource scheduling strategy so as to improve the system performance;
and (3) performing performance evaluation report and policy update, and performing performance evaluation again based on the optimized resource scheduling policy to verify the validity of the policy, so as to generate a performance evaluation report and a final optimized resource scheduling policy for system operation and management reference.
10. The method for scheduling power service resources carried by a heterogeneous wireless network according to claim 1, wherein the method comprises the steps of: the continuous monitoring and improvement, the establishment of a continuous monitoring system, the continuous collection of real-time data, the comparison with the performance evaluation report and the optimized resource scheduling strategy, the improvement according to the changed requirements and the network conditions, the continuous improvement of the resource scheduling strategy and the real-time monitoring data comprise the following specific steps:
establishing a real-time monitoring system, wherein the real-time monitoring system is established by adopting a distributed data acquisition and transmission system and is used for continuously collecting real-time data;
real-time data analysis and performance evaluation, wherein real-time data is analyzed and processed by using a real-time data analysis tool to generate a real-time performance evaluation result, wherein the real-time performance evaluation result comprises a current performance index and comparison with an optimization strategy;
dynamically adjusting a resource scheduling strategy, and adjusting resource allocation and energy transmission strategies by adopting a dynamic resource scheduling algorithm based on a real-time performance evaluation result to generate a dynamically adjusted resource scheduling strategy so as to cope with real-time changing requirements and network conditions;
and (3) continuously improving and feeding back the circulation, establishing a feedback circulation mechanism, combining the result of the resource scheduling strategy after dynamic adjustment with the real-time monitoring data, continuously improving the strategy, continuously improving the resource scheduling strategy and the real-time monitoring data, and ensuring the continuous optimization and adaptability of the system performance.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311413377.5A CN117412334A (en) | 2023-10-27 | 2023-10-27 | Heterogeneous wireless network bearing power service resource scheduling method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311413377.5A CN117412334A (en) | 2023-10-27 | 2023-10-27 | Heterogeneous wireless network bearing power service resource scheduling method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117412334A true CN117412334A (en) | 2024-01-16 |
Family
ID=89486782
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311413377.5A Pending CN117412334A (en) | 2023-10-27 | 2023-10-27 | Heterogeneous wireless network bearing power service resource scheduling method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117412334A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117891606A (en) * | 2024-01-19 | 2024-04-16 | 江西志宏数字技术有限公司 | Cloud computing driven industrial park management system |
| CN117890667A (en) * | 2024-03-14 | 2024-04-16 | 杭州欣美成套电器制造有限公司 | Power energy consumption monitoring method and system of standardized metering box |
-
2023
- 2023-10-27 CN CN202311413377.5A patent/CN117412334A/en active Pending
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117891606A (en) * | 2024-01-19 | 2024-04-16 | 江西志宏数字技术有限公司 | Cloud computing driven industrial park management system |
| CN117891606B (en) * | 2024-01-19 | 2024-10-18 | 江西志宏数字技术有限公司 | Cloud computing driven industrial park management system |
| CN117890667A (en) * | 2024-03-14 | 2024-04-16 | 杭州欣美成套电器制造有限公司 | Power energy consumption monitoring method and system of standardized metering box |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN117412334A (en) | Heterogeneous wireless network bearing power service resource scheduling method | |
| CN117036104B (en) | Intelligent electricity utilization method and system based on electric power Internet of things | |
| Sengupta et al. | Multi-objective node deployment in WSNs: In search of an optimal trade-off among coverage, lifetime, energy consumption, and connectivity | |
| CN105531963B (en) | The system and method that multiple target cell is closed in wireless network | |
| CN103036974B (en) | Cloud computing resource scheduling method based on hidden Markov model and system | |
| CN113836796B (en) | Cloud-edge cooperation-based power distribution Internet of things data monitoring system and scheduling method | |
| CN113614460B (en) | Management method, control method and system of air conditioning system and storage medium | |
| US20130325147A1 (en) | Method and System for Complex Smart Grid Infrastructure Assessment | |
| CN110114766B (en) | Method for constructing an existing electrical network for distributing electrical energy | |
| CN107911242A (en) | A kind of cognitive radio based on industry wireless network and edge calculations method | |
| CN111198808A (en) | Method, device, storage medium and electronic equipment for predicting performance index | |
| KR20220042928A (en) | A method of implementing an self-organizing network for a plurality of access network devices and an electronic device performing the same | |
| Li et al. | Efficient resource scaling based on load fluctuation in edge-cloud computing environment | |
| Ouyang et al. | Cost-aware edge resource probing for infrastructure-free edge computing: From optimal stopping to layered learning | |
| CN117793115A (en) | Self-adaptive load balancing method suitable for data center station service grid | |
| Muhammad et al. | Deep-reinforcement-learning-based sustainable energy distribution for wireless communication | |
| CN117479049B (en) | Data transmission control method for intelligent fuel gas, internet of things system and medium | |
| CN114899885A (en) | Power scheduling method, system and storage medium | |
| CN113225994B (en) | Intelligent air conditioner control method facing data center | |
| Li et al. | Fairness-aware task offloading and load balancing with delay constraints for power internet of things | |
| CN117787659A (en) | Smart city energy management system and method based on 5G | |
| JP2018026033A (en) | Power demand control system, power demand control method, aggregator system, consumer power management system, and program | |
| CN114845308B (en) | Cross-MEC resource management method considering power multi-service dynamic requirements | |
| CN116170881A (en) | Cross-domain resource allocation and unloading method and system based on edge calculation | |
| Fei et al. | A bio-inspired coverage-aware scheduling scheme for wireless sensor networks |
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 |