OmniXRI-Jack
    • Create new note
    • Create a note from template
      • Sharing URL Link copied
      • /edit
      • View mode
        • Edit mode
        • View mode
        • Book mode
        • Slide mode
        Edit mode View mode Book mode Slide mode
      • Customize slides
      • Note Permission
      • Read
        • Only me
        • Signed-in users
        • Everyone
        Only me Signed-in users Everyone
      • Write
        • Only me
        • Signed-in users
        • Everyone
        Only me Signed-in users Everyone
      • Engagement control Commenting, Suggest edit, Emoji Reply
      • Invitee
    • Publish Note

      Share your work with the world Congratulations! 🎉 Your note is out in the world Publish Note

      Your note will be visible on your profile and discoverable by anyone.
      Your note is now live.
      This note is visible on your profile and discoverable online.
      Everyone on the web can find and read all notes of this public team.
      See published notes
      Unpublish note
      Please check the box to agree to the Community Guidelines.
      View profile
    • Commenting
      Permission
      Disabled Forbidden Owners Signed-in users Everyone
    • Enable
    • Permission
      • Forbidden
      • Owners
      • Signed-in users
      • Everyone
    • Suggest edit
      Permission
      Disabled Forbidden Owners Signed-in users Everyone
    • Enable
    • Permission
      • Forbidden
      • Owners
      • Signed-in users
    • Emoji Reply
    • Enable
    • Versions and GitHub Sync
    • Note settings
    • Engagement control
    • Transfer ownership
    • Delete this note
    • Save as template
    • Insert from template
    • Import from
      • Dropbox
      • Google Drive
      • Gist
      • Clipboard
    • Export to
      • Dropbox
      • Google Drive
      • Gist
    • Download
      • Markdown
      • HTML
      • Raw HTML
Menu Note settings Sharing URL Create Help
Create Create new note Create a note from template
Menu
Options
Versions and GitHub Sync Engagement control Transfer ownership Delete this note
Import from
Dropbox Google Drive Gist Clipboard
Export to
Dropbox Google Drive Gist
Download
Markdown HTML Raw HTML
Back
Sharing URL Link copied
/edit
View mode
  • Edit mode
  • View mode
  • Book mode
  • Slide mode
Edit mode View mode Book mode Slide mode
Customize slides
Note Permission
Read
Only me
  • Only me
  • Signed-in users
  • Everyone
Only me Signed-in users Everyone
Write
Only me
  • Only me
  • Signed-in users
  • Everyone
Only me Signed-in users Everyone
Engagement control Commenting, Suggest edit, Emoji Reply
Invitee
Publish Note

Share your work with the world Congratulations! 🎉 Your note is out in the world Publish Note

Your note will be visible on your profile and discoverable by anyone.
Your note is now live.
This note is visible on your profile and discoverable online.
Everyone on the web can find and read all notes of this public team.
See published notes
Unpublish note
Please check the box to agree to the Community Guidelines.
View profile
Engagement control
Commenting
Permission
Disabled Forbidden Owners Signed-in users Everyone
Enable
Permission
  • Forbidden
  • Owners
  • Signed-in users
  • Everyone
Suggest edit
Permission
Disabled Forbidden Owners Signed-in users Everyone
Enable
Permission
  • Forbidden
  • Owners
  • Signed-in users
Emoji Reply
Enable
Import from Dropbox Google Drive Gist Clipboard
   owned this note    owned this note      
Published Linked with GitHub
Subscribed
  • Any changes
    Be notified of any changes
  • Mention me
    Be notified of mention me
  • Unsubscribe
Subscribe
# 【vMaker Edge AI專欄 #11】Edge AI如何協助淨零碳排 ![vMaker_EdgeAI_Fig00](https://hackmd.io/_uploads/HkjsYUyE6.jpg) 作者:Jack OmniXRI, 2023/11/13 近年來世界氣候異常,主要受人類大量排放溫室氣體造成。在滿足人類舒適、便捷生活前題下,要如何更加愛護環境、減少二氧化碳及溫室氣體排放(以下簡稱**碳排**)就變成刻不容緩的議題。 減少碳排就像減肥一樣,首先要進行**碳足跡盤查**,了解生產(直接)、外購(間接)及差旅運輸(其它間接)造成的碳足跡。接下來才能擬定**碳減量**計畫,考慮如何減少用電、增加能源使用效率。當執行一段時間後,再檢討是否達標,若否則修正計畫或加大減量力道。當然推動過程就像減肥時不可能不進食,只需讓消耗的卡路里大於吃入的就能持續減重。相同地當引進**負碳排**技術,讓生產和減少的碳排量達成零增加(**碳中和**),就能達到**淨零碳排**的目標。[1] 為了讓大家更了解追求淨零碳排發展歷史及如何利用**邊緣智慧**(Edge AI)及**微型機器學習**(TinyML)技術來改善生活中能源的不當浪費,本文簡單介紹了五個案例,希望能激起大家更多的創意發想,並實際動手作,讓我們的生活環境能更加美好。 ## 1. 從COP到Net Zero 聯合國近日(2023/11/30-12/12)即將於杜拜召開第28屆氣侯變遷大會(Climate Change Conference)重要協議(Conference of the Parties, COP),簡稱COP28。今年是自2015年(COP21)巴黎協定要求各國自定預期貢獻(Intended Nationally Determined Contributions, INDCs),以滿足本世紀末全球升溫不超過2℃並以1.5℃為目標的第一次全球盤點。目前地球已升溫1.2℃,因此各國紛紛提出以2030年排碳減半,2050年淨零碳排(Net Zero)。為了更有效控管碳排,目前各國亦開始推動碳邊境稅、碳費、碳交易等機制,尤其歐盟更要在2026年全面實施,若未實施相關機制則無法銷售到歐盟,或會被課徵重稅,減弱產品(價格)競爭力,讓大家不得不重視。 前美國總統高爾曾於2006年及2017年分別推動「**不願面對的真相**」記錄片第一集及第二集的拍攝,引起世界對氣候異常變遷的重視。去(2022)年更公開了一個名為「**氣侯追蹤(Climate TRACE)**」的網站[2],讓全世界都能知道最主要的碳排大戶(如發電廠、煉油廠、煉鋼廠、水泥廠、機場港口、養牛場等)及污染程度。 ![vMaker_EdgeAI_Fig01](https://hackmd.io/_uploads/SJ2st8JNT.jpg) Fig. 1 COP發展歷史及重要目標。(OmniXRI整理製作,2023/11/13) 一般來說用電量就是最直接可以了解碳排量的重要參考,大家只要拿出家中的電費單就會明顯標示本期碳排量,如如Fig. 2左圖,只要大家節約用電,台電亦會回饋一些獎勵金。另外由於台電近年來加入很多綠電,如太陽能、風力、地熱發電,所以每一度電的碳排量也在逐漸改善。如Fig. 2右圖,以2022年為例,每一度電的碳排量為0.495kg。 ![vMaker_EdgeAI_Fig02](https://hackmd.io/_uploads/ByhiK8yVa.jpg) Fig. 2 台灣電力公司電費單與排碳量。(OmniXRI整理製作,2023/11/13) ## 2. 邊緣智慧與生成智慧 去(2022)年底OpenAI推出大型語言模型(LLM) ChatGPT及自動生成影像(AIGC) Dall.E2後,全世界為之瘋狂,開始大量使用相關技術。雖然滿足了大家對通用型人工智慧的需求,但它也帶來大量的電能消耗。 根據根據半導體研究機構SemiAnalysis的資料,ChatGPT要依靠3,617台NVIDIA HGX A100伺服器、28,936顆GPU來支撐日常運作。德弗里斯以為基礎,計算出ChatGPT每日用電量為564MWh(56.4萬度)。至於GPT-3模型訓練期間的耗電量則為1,287MWh;換言之,ChatGPT運作(推論)3天所消耗的電量,已超過整個數據訓練階段了。因此,ChatGPT可說是一隻「吃電巨獸」,能夠產生大量碳排放。[3]若以每度電碳排0.495kg推算,則產生279.18噸的二氧化碳,非常驚人。 如果把生成式智慧當成高速、大運量的高鐵的話,那邊緣智慧(Edge AI & TinyML)就像機動性高、低能耗的機車、腳踏車一樣,通常只要數瓦(W)到數微瓦(mW)就能完成小型AI運算。如果依需求選擇適當硬體及推論模型,這樣就能得到最佳的性能價格比及最低排碳量(用電量)。 ![vMaker_EdgeAI_Fig03](https://hackmd.io/_uploads/HyzvnLyVT.jpg) Fig. 3 邊緣智慧與生成智慧的對比。(OmniXRI整理製作,2023/11/13) ## 3. 邊緣智慧節能減碳相關案例 一般邊緣運算用的硬體通常採用低階單晶片(Microcontroller Unit, MCU)或中階微處理器(Microprocessor Unit, MPU),更進一步可採用高階單板微電腦(Single Board Computer, SBC)或小型工業電腦(Industrial PC, IPC),現有技術已有部份晶片會內含神經元處理單元(Neural Processing Unit, NPU,俗稱AI晶片)來加速AI推論計算。 (註:更多TinyML MCU開發板介紹可參考延伸閱讀[A],[B]) MCU/MPU通常擁有豐富的週邊信號處理能力,可接收聲音、運動、溫濕度、氣壓、光照、定位、電壓、電流等感測器信號,亦可控制燈光、馬達、LCD顯示幕等輸出裝置,有時也會加入有線或短距/長距無線通訊能力。中高階MCU/MPU甚至可以接入低解析度攝影機訊號,方便進行影像分類及物件偵測等功能。 (註:更多感測器技術介紹可參考延伸閱讀[C]) 以下就簡單列舉五個案例,分別從硬體(開發板、感測器)、智慧功能及主要節能方式來進行說明。 ### 3.1. 智慧電風扇 本案例為Useful Sensors開發,主要使用一低解析度攝影機加上影像辨識晶片(奇景光電Himax WEI-Plus HX6537-A)來偵測人臉或人員位置,不輸出影像只輸出推論結果,進而傳到另一片控制板,控制風扇底盤轉動到人的方向。另外亦可用於智慧電視或筆電上,當人員離開時,自動關閉螢幕背光或令其進入睡眠狀態,以節省用電。 ![vMaker_EdgeAI_Fig03](https://hackmd.io/_uploads/H1hoFUkVT.jpg) Fig. 4 Useful Sensors 人臉/人員追蹤感測器[4]。(OmniXRI整理製作,2023/11/13) {%youtube O-Sr6Ij3WkY %} 影片來源:[Youtube](https://youtu.be/O-Sr6Ij3WkY) ### 3.2. 智慧蓮蓬頭 在學校宿舍或家中有時會忘了關好水籠頭而造成浪費水,這個案例使用了Nordic Tingy:53來做為主要偵測及推論工具。它具有多種感測器,包括聲音、運動、溫濕度等。其主晶片為Nordic nRF5340,它擁有兩個Arm Cortex-M33微處理器還具備藍牙5.2,很適合製作無線智慧感測器。為了能正確分別不同的聲音,包含水流聲、背景聲、音樂聲,這裡還搭配了知名TinyML開發平台Edge Impulse Studio進行資料收集、模型搭建訓練調整及最後的部署。最後成品使用時,還可將偵測到的異常信號透過BLE送到手機,方便提醒使用者,達到節約能源的目標。 ![vMaker_EdgeAI_Fig04](https://hackmd.io/_uploads/Hy2oYU1N6.jpg) Fig. 5 Nordic Thingy:53 - Smart Shower Timer[5]。(OmniXRI整理製作,2023/11/13) {%youtube c3yoBeorY1c %} 影片來源:[Youtube](https://youtu.be/c3yoBeorY1c) ### 3.3. 馬達異常診斷 一般在工廠很容易可以看到大型感應馬達,負責機構傳動、大型排風扇及各式泵浦。由於工作環境惡劣,高溫高粉塵,所以很容易積累過多灰塵造成運轉不順暢或排熱不易造成馬達長期處於高溫、異常出力導致壽命縮短。通常在馬達發出不正常高溫、異常振動或異音時,就需要人力介入保養,以延長壽命。 這個案例使用了Avnet SmartEdge開發板,它有一塊主板,上方可以依不同感測及通訊需求分別加上不同的組合板。這裡採用溫度、運動(加速度計、陀螺儀等)或聲音來偵測馬達工作狀態,再利用Agile Brainium線上服務來分析這些訊號,以早期發現異常工作。這樣除了可以延長馬達壽命外,亦可減少因運轉時產生過多摩擦而造成額外的能量損失。 ![vMaker_EdgeAI_Fig05](https://hackmd.io/_uploads/Sk3oFLkVa.jpg) Fig. 6 Avnet Smart Edge – Motor Diagnostic[6]。(OmniXRI整理製作,2023/11/13) ### 3.4. 智慧百葉窗 在智慧建築應用中,減少使用冷氣(大量用電),多使用自然空氣流通及自然光線(減少照明用電)是常見的作法,不過有時遇到下雨若不能即時關上窗戶可能就會造成另一些不便。這裡有一個案例,使用了兩組開發板,一為Arduino Nicla Voice,它使用Syntiant NDP120作為主晶片,內建有麥克風及NPU,很適合用於偵測環境聲音,如雨聲。而另一為Arduino Nano 33 BLE Sense,它使用Nordic nRF52840作為主晶片,板上有各式感測器,很方便偵測環境溫濕度、氣壓、光照等。亦有許多輸出腳位,可用於控制舵機(伺服馬達)來開關窗戶。最後為更精準進行聲音辨識,這裡搭配了Edge Impulse Studio來完成資料收集、標註、模型訓練調參及最後部署。 ![vMaker_EdgeAI_Fig06](https://hackmd.io/_uploads/rJ6sKUJNT.jpg) Fig. 7 Arudino Nicla Voice – Smart Building[7]。(OmniXRI整理製作,2023/11/13) {%youtube mqk1IRz76HM %} 影片來源:[Youtube](https://youtu.be/mqk1IRz76HM) ### 3.5. 智慧路燈 傳統路燈是依靠定時器來開關,有時遇到突然下大雨,自然照明消失,就要依靠人力或特定感測器來調控,這樣的作法對於比較空曠或少人經過的地方,照明就顯得多餘,電力也產生浪費。若能在路燈上安裝攝影機來明確偵測環境亮度、是否有人車通過而作精密調控,這樣就能更節省電力消耗。 研揚科技在桃園青埔高鐵站附近就有一個智慧路燈的案例,使用小型的工業電腦加上攝影機進行簡易電腦視覺智慧演算,偵測人車狀態來改變燈光照明,不用讓所有燈同時點亮,如此就能大幅節電,又不用擔心照明不足產生人車意外。近年來隨著5G通訊技術提升,智慧路燈也逐漸提升為「智慧桿」,提供更多的服務,如車流監控、違停偵測、電子看板等。 ![vMaker_EdgeAI_Fig07](https://hackmd.io/_uploads/SJ3itUkET.jpg) Fig. 8 研揚(AAEON) – 桃園青埔智慧路燈[8]。(OmniXRI整理製作,2023/11/13) {%youtube jW3Uhj5ZG9A %} 影片來源:[Youtube](https://youtu.be/jW3Uhj5ZG9A) ## 小結 淨零排碳以往可能是選配項目,沒有強制性,但隨著地球快速升溫,各國已開始推動碳稅及碳費,以強制大家重視及將節能減碳作為日常生活的一部份。透過以上介紹的Edge AI & TinyML技術讓大家可更容易時刻監視、即時反應用電狀態及改善用電。相信經過大家的巧思創意,淨零碳排就不再是令人頭疼的問題了。 ## 參考文獻 [1] 許哲豪,【課程簡報】20231111_中央_AI在淨零碳排與節能上之應用 https://omnixri.blogspot.com/2023/11/20231111ai.html [2] 氣侯追蹤網站(CLIMATE TRACE) https://climatetrace.org/map [3] 東森新聞,ChatGPT變吃電巨獸!生成式AI用電量將等同荷蘭一年用電量?專家研發高效演算法與電源裝置鬥節能! https://www.etnet.com.hk/www/tc/lifestyle/digitalnewage/larryleung/87097 [4] Useful Sensor - Person Sensor https://usefulsensors.com/#products [5] Nordic Thingy:53 - Smart Shower Timer https://www.hackster.io/dxcfl/smart-shower-timer-527c6a [6] Avnet Smart Edge – Motor Diagnostic https://www.hackster.io/PSoC_Rocks/industrial-motor-diagnostic-866e96 [7] Arudino Nicla Voice – Smart Building https://edgeimpulse.com/blog/sometimes-you-just-need-to-vent [8] 研揚(AAEON) – 桃園青埔智慧路燈 https://www.twsmartcity.org.tw/smart_application/39 ## 延伸閱讀 [A] 許哲豪,MCU攜手NPU讓tinyML邁向新里程碑 https://omnixri.blogspot.com/2022/10/mcunputinyml.html [B] 許哲豪,有了TinyML加持MCU也能開始玩電腦視覺了 https://omnixri.blogspot.com/2022/12/tinymlmcu.html [C] 許哲豪,【課程簡報】20221108_南開科大_自動化工程系_智慧製造與工業感測技術 https://omnixri.blogspot.com/2022/11/20221108.html **本文同步發表在[【台灣自造者 vMaker】](https://vmaker.tw/)** --- OmniXRI 整理製作,歡迎點贊、收藏、訂閱、留言、分享, ###### tags: `vMaker` `Edge AI`

Import from clipboard

Paste your markdown or webpage here...

Advanced permission required

Your current role can only read. Ask the system administrator to acquire write and comment permission.

This team is disabled

Sorry, this team is disabled. You can't edit this note.

This note is locked

Sorry, only owner can edit this note.

Reach the limit

Sorry, you've reached the max length this note can be.
Please reduce the content or divide it to more notes, thank you!

Import from Gist

Import from Snippet

or

Export to Snippet

Are you sure?

Do you really want to delete this note?
All users will lose their connection.

Create a note from template

Create a note from template

Oops...
This template has been removed or transferred.
Upgrade
All
  • All
  • Team
No template.

Create a template

Upgrade

Delete template

Do you really want to delete this template?
Turn this template into a regular note and keep its content, versions, and comments.

This page need refresh

You have an incompatible client version.
Refresh to update.
New version available!
See releases notes here
Refresh to enjoy new features.
Your user state has changed.
Refresh to load new user state.

Sign in

Forgot password

or

By clicking below, you agree to our terms of service.

Sign in via Facebook Sign in via Twitter Sign in via GitHub Sign in via Dropbox Sign in with Wallet
Wallet ( )
Connect another wallet

New to HackMD? Sign up

Help

  • English
  • 中文
  • Français
  • Deutsch
  • 日本語
  • Español
  • Català
  • Ελληνικά
  • Português
  • italiano
  • Türkçe
  • Русский
  • Nederlands
  • hrvatski jezik
  • język polski
  • Українська
  • हिन्दी
  • svenska
  • Esperanto
  • dansk

Documents

Help & Tutorial

How to use Book mode

Slide Example

API Docs

Edit in VSCode

Install browser extension

Contacts

Feedback

Discord

Send us email

Resources

Releases

Pricing

Blog

Policy

Terms

Privacy

Cheatsheet

Syntax Example Reference
# Header Header 基本排版
- Unordered List
  • Unordered List
1. Ordered List
  1. Ordered List
- [ ] Todo List
  • Todo List
> Blockquote
Blockquote
**Bold font** Bold font
*Italics font* Italics font
~~Strikethrough~~ Strikethrough
19^th^ 19th
H~2~O H2O
++Inserted text++ Inserted text
==Marked text== Marked text
[link text](https:// "title") Link
![image alt](https:// "title") Image
`Code` Code 在筆記中貼入程式碼
```javascript
var i = 0;
```
var i = 0;
:smile: :smile: Emoji list
{%youtube youtube_id %} Externals
$L^aT_eX$ LaTeX
:::info
This is a alert area.
:::

This is a alert area.

Versions and GitHub Sync
Get Full History Access

  • Edit version name
  • Delete

revision author avatar     named on  

More Less

Note content is identical to the latest version.
Compare
    Choose a version
    No search result
    Version not found
Sign in to link this note to GitHub
Learn more
This note is not linked with GitHub
 

Feedback

Submission failed, please try again

Thanks for your support.

On a scale of 0-10, how likely is it that you would recommend HackMD to your friends, family or business associates?

Please give us some advice and help us improve HackMD.

 

Thanks for your feedback

Remove version name

Do you want to remove this version name and description?

Transfer ownership

Transfer to
    Warning: is a public team. If you transfer note to this team, everyone on the web can find and read this note.

      Link with GitHub

      Please authorize HackMD on GitHub
      • Please sign in to GitHub and install the HackMD app on your GitHub repo.
      • HackMD links with GitHub through a GitHub App. You can choose which repo to install our App.
      Learn more  Sign in to GitHub

      Push the note to GitHub Push to GitHub Pull a file from GitHub

        Authorize again
       

      Choose which file to push to

      Select repo
      Refresh Authorize more repos
      Select branch
      Select file
      Select branch
      Choose version(s) to push
      • Save a new version and push
      • Choose from existing versions
      Include title and tags
      Available push count

      Pull from GitHub

       
      File from GitHub
      File from HackMD

      GitHub Link Settings

      File linked

      Linked by
      File path
      Last synced branch
      Available push count

      Danger Zone

      Unlink
      You will no longer receive notification when GitHub file changes after unlink.

      Syncing

      Push failed

      Push successfully