室內照明設計是在一定的空間裡，結合
自然光源 與人造光源
以符合 使用者 對照明 需求 進行完整的規劃 ，達到創造情境的效果。
也 由於 LED燈具變成主流 以及 物聯網 的 普及， 讓 照明 設計 市場日益
壯大，相較傳統照明設備，智慧照明可以為使用者帶來更舒適的照
明體驗 ，也能配合連網的功能，讓使用者能透過電腦或行動裝置等
設備的功能進行開啟與關閉，或是能透過使用著的喜好控制燈具，
進行調光 ，讓照明環境更加符合人體工學並 減少 照明系統的電能 消
耗 。
本論文實現一基於機器學習與粒群
演算法最佳化 之室內自動調
光系統，實驗方法以遠端進行， 透過神經網路以及粒群最佳化演算
法，找出最符合當下環境之燈具照明 計算 矩陣，使環境達到使用者
所需之照度。本論文著重於機器學習與演算法的運算及其應用， 透
過 模擬 結果 和 實測結果， 來驗證自動調光系統之正確性與可行性，
最後與傳統 DRDS比較， 以凸顯所提的方法在調光準確率和節能性
能的提升 。

Indoor lighting design is to combine natural light sources and artificial light sources in a specific space and makes complete planning to meet the needs of users for lighting, to achieve the effect of creating a certain scenario. Due to the mainstream of LED lamps and the popularity of the Internet of Things, the lighting design market is growing. Compared with traditional lighting equipment, smart lighting can bring users a more comfortable lighting experience. It can be turned on and off through a computer or mobile device, or the lamps can be controlled and dimmed according to the user's preference, making the lighting environment more ergonomic and reducing the power consumption of the lighting system.
In this thesis, an indoor automatic dimming system based on machine learning and particle swarm optimization (PSO) algorithm is implemented. The experiment is carried out remotely. Through neural network and particle swarm optimization algorithm, the dimming commands of lamps that best fit the current environment are found to meet the illumination requirements of the users. This study focuses on the operation and application of machine learning and PSO algorithm, and verifies the correctness and feasibility of the proposed automatic dimming system by comparing the simulation and measured results with the traditional daylight responsive dimming system (DRDS), and verifies the improvement of dimming accuracy and energy saving performance of the proposed method.

[1] Facing Global Warming-Taiwan’s Response, Available: https://www.tri.org.tw/unfccc/Unfccc/UNFCCC02.htm
[2] UN environment programme, ‘Adaptation Gap Report 2020’ UNEP DTU Partnership (UDP) and the World Adaptation Science Programme (WASP).
[3] In-Tae Kim, Yu-Sin Kim, Hyeonggon Nam, and Taeyon Hwang, Advanced Dimming Control Algorithm for Sustainable Buildings by Daylight Responsive Dimming System, in MDPI sustainability 2018
[4] A.S. Choi , M.K. Sung, Development of a daylight responsive dimming system and preliminary evaluation of system performance, PERGAMON Building and Environment 35 (2000) 663-676
[5] Francis Rubinstein, Photoelectric Control of Equi-illumination Lighting Systems, Energy Efficient Buildings Program, Lawrence Berkeley Laboratory, University of California, Berkeley, CA 94720 (U.S.A.)
[6] Seunghwan Yoo, Jonghun Kim, Cheol-Yong Jang, and Hakgeun Jeong, A sensor-less LED dimming system based on daylight harvesting with BIPV systems, Energy Efficiency Department, Korea Institute of Energy Research, 152 Gajeong-ro, Yuseong-gu, Daejeon, 305- 343, South Korea.
[7] Hoyoung Choi, Seongkwan Hong, Anseop Choi , Minki Sung, Toward the accuracy of prediction for energy savings potential and system performance using the daylight responsive dimming system, ELSEVIER Energy and buildings Volume 133, 1 December 2016, Pages 271-280.
[8] In-Tae Kim, Yu-Sin Kim, Meeryoung Cho, Hyeonggon Nam, Anseop Choi and Taeyon Hwang, High-Performance Accuracy of Daylight-Responsive Dimming Systems with Illuminance by Distant Luminaires for Energy-Saving Buildings, MDPI energies
[9] CP Kurian, RS Aithal, J Bhat and VI George, Robust control and optimisation of energy consumption in daylight–artificial light integrated schemes, Lighting Res. Technol. 2008; 40: 7–24
[10] Nik Sahidah Nik Ahmad, Nur Hanis Mohammad Radzi, Mohd Noor Abdullah, Khairul Rijal Wagiman, Suriana Salimin, Muhammad Nafis Ismail, Assessment on the Optimal Dimming Level in Lighting System between Firefly Algorithm and Particle Swarm Optimization Algorithm, IEEE Student Conference on Research and Development (SCOReD) 27-28 September 2020.
[11] L. Doulos, A. Tsangrassoulis, F. Topalis, Quantifying energy savings in daylight responsive systems: The role of dimming electronic ballasts, ELSEVIER ScienceDirect Energy and Buildings 40 (2008) 36–50
[12] 顏貝珊，「以Andriod應用程式為控制輸入之新型植物工廠系統開發」，國立台灣科技大學電機工程系碩士學位論文，民國105年7月。
[13] pytorch, “Pytorch.” Available: https://pytorch.org/.
[14] United Nations Framework Convention on Climate Change, (UNFCCC), Kyoto Protocol, 1997.
[15] ROHM, Digital 16bit Serial Output Type Ambient Light Sensor IC BH1750FVI, No.11046EDT01, 2011.
[16] MicroPython, ‘MicroPython tutorial for ESP8266’, Available: https://docs.micropython.org/en/latest/esp8266/tutorial/index.html.
[17] AI-thinker, ‘ESP-01 WiFi Modul Version’, 2015
[18] WAGO,照明控制標準-DALI,網址: https://www.wago.com/tw/dali 2020年9月2日。
[19] 中華民國國家標準, 「CNS台灣國家照度標準」,民國76年9月17日。
[20] 深智數位股份有限公司, 「Python王者歸來」,2021年9月
[21] Axway Blog, ’API Builder and MQTT for IoT – Part 1’, Available : https://blog.axway.com/apis/api-builder-and-mqtt-for-iot-part-1
[22] EDUCBA, ‘What is xampp’, Available: https://www.educba.com/what-is-xampp/