CN112327965B - Optimization method of temperature regulation self-adaptive distributed device based on genetic algorithm - Google Patents
Optimization method of temperature regulation self-adaptive distributed device based on genetic algorithm Download PDFInfo
- Publication number
- CN112327965B CN112327965B CN202011271780.5A CN202011271780A CN112327965B CN 112327965 B CN112327965 B CN 112327965B CN 202011271780 A CN202011271780 A CN 202011271780A CN 112327965 B CN112327965 B CN 112327965B
- Authority
- CN
- China
- Prior art keywords
- heat dissipation
- radiator
- temperature
- algorithm
- genetic algorithm
- 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.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D23/00—Control of temperature
- G05D23/19—Control of temperature characterised by the use of electric means
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/10—Protocols in which an application is distributed across nodes in the network
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W84/00—Network topologies
- H04W84/18—Self-organising networks, e.g. ad-hoc networks or sensor networks
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D30/00—Reducing energy consumption in communication networks
- Y02D30/70—Reducing energy consumption in communication networks in wireless communication networks
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- Feedback Control In General (AREA)
Abstract
The invention discloses an optimization method of a temperature regulation self-adaptive distributed device based on a genetic algorithm, and belongs to the technical field of control and optimization of a heat dissipation system. The method comprises the steps that an Internet of things chip is embedded into each heat dissipation device by utilizing an Internet of things hardware and software base to form a Mesh communication network; each heat dissipation device is a self-consistent system which is communicated with an accessory neighbor subsystem through a Mesh network; each heat dissipation device is implanted into a control system with a genetic algorithm, so that the heat dissipation device becomes an AI radiator, and all AI radiators form a heat dissipation cluster; the heat dissipation cluster is driven by the environmental pressure to dynamically search the local optimal solution of power saving, and the adaptive adjustment process for responding to the environmental change is completed. In the optimization process, a plurality of radiator devices form a cluster, the change of the decentralized distributed self-adaptive temperature condition and the change of the number of individual clusters are achieved, the electricity is saved, and the cluster has high availability, high flexibility and great robustness.
Description
Technical Field
The invention belongs to the technical field of control and optimization of a heat dissipation system, and particularly relates to an optimization method of a temperature regulation self-adaptive distributed device based on a genetic algorithm.
Background
In a modern computer system, no matter a notebook computer or a cloud server room, a heat dissipation system consumes a large amount of power, a PUE (power utilization efficiency) index of the system is important data for measuring TCO (total cost of ownership), and the heat dissipation system is designed, so that the reduction of the power consumption of the heat dissipation system is an important technology. On the other hand, the designed heat dissipation system is often characterized by a local center type, an overall split, a passive property and an inefficient property. Each heat dissipation part of the heat dissipation system runs with fixed heat dissipation parameters, or passively reports and corresponds to the scheduling of a local central control system, for example, a server mainboard is controlled by a bmc (baseboard Management controller); subsystems of all the heat dissipation systems are administrative and lack unified scheduling in the whole situation. Frosting on snow, a large margin is usually considered by a local central control system, and a large amount of electric power is wasted by adopting a fixed stepped heat dissipation threshold value. If the cloud service data center PUE is close to 1, a large amount of manual fine adjustment is needed. The existing system is poor in robustness, the design of a local center type concentrates risks in the center, once a program has a problem or a fan controlled by the program is damaged, a halt report can be given only to wait for manual intervention, and peripheral subsystems cannot be scheduled to cool down and continue to provide services.
In recent years, the development of the Internet of things is rapid, the Internet of things chip is high in quality and low in cost, and a local Mesh network can be quickly formed by low-power-consumption networking means. The heat dissipation equipment such as fans, air conditioners and the like also has the conditions of global change of heat dissipation parameters such as stepless speed change, frequency conversion and the like, and the hardware foundation has already been provided, so the key problem is how to design a decentralized distributed autonomous condition heat dissipation device with artificial intelligence.
Disclosure of Invention
In view of the problems in the prior art, a technical problem to be solved by the present invention is to provide an optimization method for a distributed temperature regulation adaptive device based on a genetic algorithm, where the distributed device can adapt to changes in temperature conditions and the number of clustered individuals by using the genetic algorithm in artificial intelligence, and achieve high availability, high robustness and great power saving in dynamic balance.
The optimization method of the temperature regulation self-adaptive distributed device based on the genetic algorithm is characterized in that an Internet of things chip is embedded into each heat dissipation device by utilizing an Internet of things hardware and software base to form a Mesh communication network; each heat dissipation device is a self-consistent system which is communicated with an accessory neighbor subsystem through a Mesh network; each heat dissipation device is implanted into a control system with a genetic algorithm, so that the heat dissipation device becomes an AI radiator, and all AI radiators form a heat dissipation cluster; the heat dissipation cluster is driven by the environmental pressure to dynamically search the local optimal solution of power saving, and the adaptive adjustment process for responding to the environmental change is completed.
The optimization method of the temperature regulation self-adaptive distributed device based on the genetic algorithm comprises the following specific processes:
(1) matching a master control for each radiator, forming a Mesh network, and enabling adjacent radiators to interact with each other; then entering a genetic algorithm program;
(2) initialization: setting a basic heat dissipation parameter for each AI heat radiator;
(3) elimination: selecting a elimination proportion for each AI radiator according to the early warning occurrence condition of the temperature area, and entering the step (4) after the elimination algorithm is finished;
(4) neogenesis and evolution: supplementing a new AI radiator after the elimination algorithm is passed, and resetting the heat dissipation efficiency parameters; ending the dynamic adjustment process of the wheel and entering the step (5);
(5) and (5) repeating the steps (3) and (4) once every set time to finish a round of dynamic adjustment process.
The optimization method of the temperature regulation self-adaptive distributed device based on the genetic algorithm comprises the following steps of:
a) setting the temperature interval as three critical values: a temperature early warning threshold value 1, a temperature early warning threshold value 2 and a disaster early warning; if the temperature zone is not alarmed, the AI radiator with the minimum heat dissipation capacity in the temperature zone is eliminated, and the elimination algorithm is finished; otherwise, entering the step b);
b) judging whether the temperature exceeds a threshold value 1 and is less than a threshold value 2, if so, eliminating the AI radiator with the highest temperature in the temperature zone, and ending the elimination algorithm; otherwise, entering the step c);
c) judging whether the temperature exceeds the threshold value 2 and is not greater than a disaster temperature value, if so, eliminating 50% of AI radiators with the highest temperature in the temperature zone, and finishing the elimination algorithm; otherwise, eliminating all AI radiators and simultaneously finishing the algorithm;
the optimization method of the temperature regulation self-adaptive distributed device based on the genetic algorithm comprises the following steps of:
a) judging whether the AI radiator is a newly added AI radiator, if so, entering the step b);
b) judging whether the AI radiator is supplemented after the old AI radiator is eliminated because the temperature exceeds the threshold value, if not, obtaining P according to the average parameter function by the heat radiation efficiency of the AI radiatorxAnd ending the algorithm; otherwise, resetting the heat dissipation efficiency of the AI radiator to the maximum value, and ending the algorithm; pxThe calculation formula of the value is:
Px=f(P1,P2,…Pn)。
according to the optimization method of the temperature regulation self-adaptive distributed device based on the genetic algorithm, the basic heat dissipation parameter is the heat dissipation efficiency E, and the AI heat radiator dissipates heat with the maximum heat dissipation efficiency initially; the calculation formula of the heat dissipation efficiency is as follows:
the smaller E is, the lower the heat dissipation efficiency of the radiator is, and the radiator is easier to be eliminated.
According to the optimization method of the temperature regulation self-adaptive distributed device based on the genetic algorithm, the set time is 1-10 seconds.
Has the advantages that: compared with the prior art, the invention has the advantages that:
in the optimization process, a plurality of radiator devices form a cluster, the decentering and distributed self-adaptation can be achieved, the temperature condition change and the change of the individual number of the cluster can be self-adapted, the electricity is saved, the availability is high, the flexibility is high, and the robustness is extremely high.
Drawings
FIG. 1 is a temperature interval distribution diagram;
FIG. 2 is a flow chart of an elimination algorithm;
fig. 3 is a newborn and evolving flow chart.
Detailed Description
In order to make the aforementioned objects, features and advantages of the present invention comprehensible, embodiments accompanied with examples are described in detail below.
Example 1
The optimization method of the temperature regulation self-adaptive distributed device based on the genetic algorithm is characterized in that an Internet of things chip is embedded into each heat dissipation device by utilizing an Internet of things hardware and software foundation, the Internet of things chip only needs to run a scheduling algorithm described by the method, and a Mesh communication network is formed in a computer system (such as a cloud computer room); each heat dissipation device is a self-consistent system which is communicated with an accessory neighbor subsystem (adjacent AI radiator) through a Mesh network; each heat dissipation device is implanted into a control system with a genetic algorithm, so that the heat dissipation device becomes an AI radiator, and all AI radiators form a heat dissipation cluster; the heat dissipation cluster is driven by preset environmental pressure, is constrained by a genetic algorithm, automatically and dynamically searches for a local optimal solution of power saving, and completes an adaptive adjustment process for responding to environmental changes, wherein the specific process is as follows:
(1) the master control is matched for each radiator, a Mesh network is formed in a computer system by Bluetooth or NB-IoT, and adjacent radiators can interact with each other; then entering a genetic algorithm program;
(2) initialization: setting a basic heat dissipation parameter for each AI radiator, wherein the basic heat dissipation parameter is heat dissipation efficiency E, the AI radiator initially dissipates heat with maximum heat dissipation efficiency, and the calculation formula of the heat dissipation efficiency is as follows:
the smaller E is, the lower the heat dissipation efficiency of the radiator is, and the radiator is easier to be eliminated;
(3) elimination: each AI radiator selects elimination proportion according to the early warning occurrence condition of the temperature zone, and the elimination algorithm flow chart is shown in figure 2 and specifically comprises the following steps:
a) the temperature interval was set to three critical values (as shown in fig. 1): if the temperature zone does not give an alarm, the AI radiator with the minimum heat dissipation efficiency in the temperature zone is eliminated, and the elimination algorithm is finished; otherwise, entering the step b);
b) judging whether the temperature exceeds a threshold value 1 and is less than a threshold value 2, if so, eliminating the AI radiator with the highest temperature in the temperature zone, and ending the elimination algorithm; otherwise, entering the step c);
c) judging whether the temperature exceeds the threshold value 2 and is not greater than a disaster temperature value, if so, eliminating 50% of AI radiators with the highest temperature in the temperature zone, and finishing the elimination algorithm; otherwise, eliminating all AI radiators, simultaneously ending the algorithm, and entering the step (4);
(4) neogenesis and evolution: supplementing a new AI radiator after the elimination algorithm is passed, and resetting the heat dissipation efficiency parameters; the number of newly-generated radiators is equal to the number of eliminated radiators plus the number of newly-added radiators, and a new generation and evolution flow chart is shown in fig. 3 and specifically includes:
a) judging whether the AI radiator is a newly added AI radiator, if so, entering the step b);
b) judging whether the AI radiator is supplemented after the old AI radiator is eliminated because the temperature exceeds the threshold value, if not, obtaining P according to the average parameter function by the heat radiation efficiency of the AI radiatorxAnd ending the algorithm; otherwise, for the newly added AI radiator or the newly added AI radiator which is eliminated due to the advantages or the disadvantages, the newly added radiator is not available, a new radiator is bought and directly put into the system, the self-consistent system can slowly make the system enter a new low-power-consumption steady state, the heat dissipation efficiency of the AI radiator is set to be reset to the maximum value, and the algorithm is ended; pxThe calculation formula of the value is:
Px=f(P1,P2,…Pn)。
ending the dynamic adjustment process of the wheel and entering the step (5);
(5) and (5) repeating the steps (3) and (4) every 5 seconds to finish a round of dynamic adjustment process.
Under the condition that the external environment is not deteriorated (heat sources and computing power are increased), the AI radiator cluster can dynamically adapt to the environment, such as the situation that the heat sources are reduced and the AI radiators are increased, and continuously and dynamically try to find a local optimal solution (with minimum power consumption). When the external environment deteriorates or a catastrophic accident (equipment failure) is sent, the AI radiator cluster can also quickly and autonomously perform adaptive adjustment, and slowly return to a steady state, namely another locally optimal solution (with minimum power consumption) after a period of high energy consumption.
The AI radiator device cluster with decentration, distributed self-adaptation, power saving, high availability, high flexibility and great robustness is achieved.
Claims (5)
1. The optimization method of the temperature regulation self-adaptive distributed device based on the genetic algorithm is characterized in that an Internet of things chip is embedded into each heat dissipation device by utilizing an Internet of things hardware and software base to form a Mesh communication network; each heat dissipation device is a self-consistent system which is communicated with an accessory neighbor subsystem through a Mesh network; each heat dissipation device is implanted into a control system with a genetic algorithm, so that the heat dissipation device becomes an AI radiator, and all AI radiators form a heat dissipation cluster; the heat dissipation cluster is driven by the environmental pressure to dynamically search a local optimal solution for power saving, and an adaptive adjustment process for responding to environmental changes is completed; the specific process is as follows:
(1) matching a master control for each radiator, forming a Mesh network, and enabling adjacent radiators to interact with each other; then entering a genetic algorithm program;
(2) initialization: setting a basic heat dissipation parameter for each AI heat radiator;
(3) elimination: selecting a elimination proportion for each AI radiator according to the early warning occurrence condition of the temperature area, and entering the step (4) after the elimination algorithm is finished;
(4) neogenesis and evolution: supplementing a new AI radiator after the elimination algorithm, and resetting the basic heat dissipation parameters; the specific process is as follows:
a) judging whether the AI radiator is a newly added AI radiator, if so, entering the step b);
b) judging whether the AI radiator is supplemented after the old AI radiator is eliminated because the temperature exceeds the threshold value, if not, obtaining P according to the average parameter function by the heat radiation efficiency of the AI radiatorxAnd ending the algorithm; otherwise, resetting the heat dissipation efficiency of the AI radiator to the maximum value, and ending the algorithm; pxThe calculation formula of the value is:
Px=f(P1,P2,…Pn);
ending the dynamic adjustment process of the wheel and entering the step (5);
(5) and (5) repeating the steps (3) and (4) once every set time to finish a round of dynamic adjustment process.
2. The method for optimizing a distributed adaptive temperature regulation device based on genetic algorithm according to claim 1, wherein the elimination algorithm comprises the following steps:
a) setting the temperature interval as three critical values: a temperature early warning threshold value 1, a temperature early warning threshold value 2 and a disaster early warning; if the temperature zone is not alarmed, the AI radiator with the minimum heat dissipation capacity in the temperature zone is eliminated, and the elimination algorithm is finished; otherwise, entering the step b);
b) judging whether the temperature exceeds a threshold value 1 and is less than a threshold value 2, if so, eliminating the AI radiator with the highest temperature in the temperature zone, and ending the elimination algorithm; otherwise, entering the step c);
c) judging whether the temperature exceeds the threshold value 2 and is not greater than a disaster temperature value, if so, eliminating 50% of AI radiators with the highest temperature in the temperature zone, and finishing the elimination algorithm; otherwise, all AI radiators are eliminated, and the algorithm is ended at the same time.
3. The optimization method for the genetic algorithm-based temperature regulation adaptive distributed device according to claim 1, wherein the basic heat dissipation parameter is heat dissipation efficiency E, and the AI heat sink initially dissipates heat with maximum heat dissipation efficiency; the calculation formula of the heat dissipation efficiency is as follows:
4. the method for optimizing the distributed adaptive temperature regulation device based on genetic algorithm as claimed in claim 1, wherein bluetooth or NB-IoT is used together to form the Mesh network.
5. The optimization method of the temperature regulation adaptive distributed device based on the genetic algorithm is characterized in that the set time is 1-10 seconds.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011271780.5A CN112327965B (en) | 2020-11-13 | 2020-11-13 | Optimization method of temperature regulation self-adaptive distributed device based on genetic algorithm |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011271780.5A CN112327965B (en) | 2020-11-13 | 2020-11-13 | Optimization method of temperature regulation self-adaptive distributed device based on genetic algorithm |
Publications (2)
Publication Number | Publication Date |
---|---|
CN112327965A CN112327965A (en) | 2021-02-05 |
CN112327965B true CN112327965B (en) | 2021-09-10 |
Family
ID=74319198
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202011271780.5A Active CN112327965B (en) | 2020-11-13 | 2020-11-13 | Optimization method of temperature regulation self-adaptive distributed device based on genetic algorithm |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN112327965B (en) |
Citations (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108489013A (en) * | 2018-01-30 | 2018-09-04 | 深圳市新环能科技有限公司 | Central air-conditioner control method based on genetic algorithm and load on-line amending and device |
Family Cites Families (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US10354345B2 (en) * | 2012-01-23 | 2019-07-16 | Whisker Labs, Inc. | Optimizing and controlling the energy consumption of a building |
US9582009B2 (en) * | 2012-04-30 | 2017-02-28 | SmrtEn, LLC | System and method for optimizing and reducing the energy usage of an automatically controlled HVAC system |
CN104613602B (en) * | 2015-02-02 | 2017-09-26 | 河海大学 | A kind of central air-conditioning Precise control method |
CN104933240B (en) * | 2015-06-10 | 2018-02-06 | 中国人民解放军装甲兵工程学院 | A kind of Cooling System of Armored Vehicles layout optimization design method |
CN109902826A (en) * | 2019-03-11 | 2019-06-18 | 珠海格力电器股份有限公司 | Household electrical appliances energy saving model construction method based on genetic algorithm, control method, household electrical appliances |
-
2020
- 2020-11-13 CN CN202011271780.5A patent/CN112327965B/en active Active
Patent Citations (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108489013A (en) * | 2018-01-30 | 2018-09-04 | 深圳市新环能科技有限公司 | Central air-conditioner control method based on genetic algorithm and load on-line amending and device |
Also Published As
Publication number | Publication date |
---|---|
CN112327965A (en) | 2021-02-05 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109800066B (en) | Energy-saving scheduling method and system for data center | |
JP6605609B2 (en) | Power consumption control | |
Fang et al. | Thermal-aware energy management of an HPC data center via two-time-scale control | |
US7979729B2 (en) | Method for equalizing performance of computing components | |
CN111174375B (en) | Data center energy consumption minimization-oriented job scheduling and machine room air conditioner regulation and control method | |
US20140359323A1 (en) | System and method for closed loop physical resource control in large, multiple-processor installations | |
Su et al. | An agent-based distributed real-time optimal control strategy for building HVAC systems for applications in the context of future IoT-based smart sensor networks | |
US20160248251A1 (en) | Variable feed-out energy management | |
Zhang et al. | Two-phase industrial manufacturing service management for energy efficiency of data centers | |
Yao et al. | Adaptive power management through thermal aware workload balancing in internet data centers | |
CN115164361B (en) | Data center control method and device, electronic equipment and storage medium | |
KR20200029553A (en) | Decentralized planning, scheduling and control of multi-agent flow control systems | |
CN112327965B (en) | Optimization method of temperature regulation self-adaptive distributed device based on genetic algorithm | |
CN114662751A (en) | Park multifunctional short-term load prediction and optimization method based on LSTM | |
CN112378047A (en) | Multi-scene-oriented load-adjustable resource aggregation method, system, equipment and storage medium | |
CN116578134A (en) | Universal base station temperature control method and system based on reinforcement learning | |
CN113632132A (en) | Computer-aided energy management method and energy management system | |
CN113094149B (en) | Data center virtual machine placement method, system, medium and equipment | |
CN104298536A (en) | Dynamic frequency modulation and pressure adjustment technology based data center energy-saving dispatching method | |
WO2018005180A1 (en) | Hvac system using model predictive control with distributed low-level airside optimization | |
Tian et al. | Global energy optimization strategy based on delay constraints in edge computing environment | |
Islam et al. | Distributed resource management in data center with temperature constraint | |
Hussin et al. | An Adaptive Energy Allocation for High-Performance Computing Systems Using a Cyber-Physical Approach | |
CN117806834B (en) | Resource adjusting method and device | |
CN110752624A (en) | Economic dispatching method for event-driven power system |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |