自從電動車問世以來，此項技術已發展多年，而隨著環保意識抬頭，以及各國政府的法令推動及相關設施建設，最近幾年電動車的數量持續增長，因此電動車已逐漸進入人們的生活。由於電動車不像普通油車可以馬上加油馬上離開，電動車充電時至少需要幾分鐘甚至到幾小時，對於用戶來說這段時間是極為不方便的，因此充電站設置在商業建物旁已成一股趨勢，使電動汽車用戶能夠在等待充電的途中能夠進行其他活動。但相對地，對於商業建物來說，新增充電站系統對他們來說是一筆額外的負擔，若供電動汽車自由充電的話，容易使整個系統的用電不平衡，甚至出現熱門時段用電破錶，從而使最高需量超出該建物向電力公司所簽訂的契約容量的情況，如此就會使整體的用電成本大幅提高，因此在本研究中，我們特別針對與建物合作的充電排程進行最佳化。

因此為了使充電站不僅不會成為建物的額外負擔，甚至可以額外再多增加一筆充電收費的盈收，因此我們的方法的目標為在使總用電不超過契約容量的條件下，能夠最大化充電位利用率。而為了達到這一目標，我們提出一個新的、泛用性高的，把充電資訊離散化的充電排程框架IRSM，透過過去電動汽車的歷史充電資訊，以及建物和太陽能發電的歷史電量資訊，各自在電動汽車使用者登記充電時間長度時，推薦使用者其最佳的行程和對應的Incentive獎勵，期望在固定預算下利用Incentive獎勵去吸引電動汽車在推薦時間充電，從而使熱門時間段總用電不超過契約容量，冷門時間段能夠盡量用掉剩餘契約容量的電量額度，使用電成本最小化，充電收益最大化。

在實驗中，我們將IRSM與其他基本演算法進行比較，並且也比較IRSM中設置不同參數的排程結果，可以得出IRSM的排程結果都優於基本演算法，並且可以透過調控IRSM的參數來達成不同的最佳化效果，使我們的演算法能夠在兼顧電動汽車充電滿意度的情況下，使整體收益能夠最佳化。

Since EVs are not like regular gas vehicles that can be refueled and leave immediately, it takes a period of time to charge an EV, and there is a trend for charging stations to be located next to commercial buildings. It allows EV users to do other activities while waiting for their EVs to charge. However, the addition of a charging station system is an extra burden for commercial buildings. If electric vehicles are allowed to charge freely, the maximum demand may exceed the contract capacity of the building. Therefore, in this paper, we specifically focus on optimizing the charging schedule in cooperation with the building.

To achieve this goal, we propose a new, highly versatile charging scheduling framework, IRSM. The historical electricity information of EVs, the building, and PV, is as input of IRSM to recommend the best schedule and the corresponding incentive for EVs when users register for charging duration. It is expected that incentives will be used to attract EVs to charge at recommended time under a fixed budget, so that the total electricity consumption during popular period does not exceed the contract capacity, and the remaining contract capacity can be used up as much as possible during unpopular period, minimizing the cost of electricity consumption and maximizing charging revenue.

In our experiments, we compare the IRSM with baseline algorithms, and we can conclude that the scheduling results of the IRSM are better than baseline algorithms. It means the we can optimize the overall revenue while taking into account the satisfaction of EV charging.

[1] G. Parkinson, “The osborne effect: Why new car sales will be all electric in six years,” Jul. 2020. [Online]. Available: https://thedriven.io/2020/07/07/the-osborne-effect-why-new-car-sales-will-be-all-electric-in-six-years/
[2] M. Aunedi, M. Woolf, M. Bilton, and G. Strbac, “Impact and opportunitiesfor wide-scale electric vehicle deployment,” Tech. Rep., 09 2014. [Online]. Available: https://www.researchgate.net/publication/283151640 Impact and opportunitiesfor wide-scale electric vehicle deployment
[3] S. Charles and N. Nick, Public EV Charging Business Models for Retail Site Hosts, Atlas Public Policy Logo, Apr. 2020. [Online]. Available: https://atlaspolicy.com/wp-content/uploads/2020/04/Public-EV-Charging-Business-Models-for-Retail-Site-Hosts.pdf
[4] ChargePoint, “Leading retailer partners withchargepoint to attract and retainloyal customers,” 2013. [Online]. Available: https://www.chargepoint.com/files/casestudies/cs-retail.pdf
[5] Z. Jason, N. Nick, S. Stephanie, D. Lauren, and S. Conner, Assessing the Business Case forHosting Electric Vehicle ChargingStations in New York State, Atlas Public Policy, Jun. 2019. [Online]. Available: https://atlaspolicy.com/wp-content/uploads/2019/09/19-31-Business-Case-for-Hosting-Charging-Stations.pdf
[6] F. Andrew, S. Hyeon Shic, and N. Amirreza, Electric Vehicle Ownership Factors and CommutingBehavior in the United States, Morgan State University, Aug. 2018. [Online]. Available: http://www.matsutc.org/wp-content/uploads/2018/11/Environmental-Attributes-of-Electric-Vehicle-Ownership-and-Commuting-Behavior-in-Maryland-Public-pdf
[7] N. Daina, A. Sivakumar, and J. W. Polak, “Modelling electric vehicles use: a survey on the methods,” Renewable and Sustainable Energy Reviews, vol. 68, pp. 447–460, 2017. [Online].Available: https://www.sciencedirect.com/science/article/pii/S1364032116306566
[8] J. Garc’ıa-Villalobos, I. Zamora, J. San Mart’ın, F. Asensio, and V. Aperribay, “Plug-in electric vehicles in electric distribution networks: A review of smart charging approaches,”Renewable and Sustainable Energy Reviews, vol. 38, pp. 717–731, 2014. [Online]. Available: https://www.sciencedirect.com/science/article/pii/S1364032114004924
[9] A. Amin, W. Tareen, M. Usman, H. Ali, I. Bari, B. Horan, S. Mekhilef, M. Asif, S. Ahmed, and A. Mahmood, “A review of optimal charging strategy for electric vehicles under dynamic pricing schemes in the distribution charging network,” Sustainability, vol. 12, 12 2020.
[10] Q. Yan, B. Zhang, and M. Kezunovic, “Optimized operational cost reduction for an ev charging station integrated with battery energy storage and pv generation,” IEEE Transactions on Smart Grid, vol. 10, no. 2, pp. 2096–2106, 2019.
[11] J. An, B. Huang, Q. Kang, and M. Zhou, “Pso-based method to find electric vehicle’s optimal charging schedule under dynamic electricity price,” in 2013 10th IEEE INTERNATIONAL CONFERENCE ON NETWORKING, SENSING AND CONTROL (ICNSC), 2013, pp. 913–918.
[12] J. Chen, X. Huang, S. Tian, Y. Cao, B. Huang, X. Luo, and W. Yu, “Electric vehicle charging schedule considering userapos;s charging selection from economics,” IET Generation, Transmission Distribution, vol. 13, pp. 3388–3396(8), August 2019. [Online]. Available: https://digital-library.theiet.org/content/journals/10.1049/iet-gtd.2019.0154
[13] M. E. Kabir, C. Assi, M. H. K. Tushar, and J. Yan, “Optimal scheduling of ev charging at a solar power-based charging station,” IEEE Systems Journal, vol. 14, no. 3, pp. 4221–4231, 2020.
[14] C.-C. Lin, K.-T. Chuang, W. C.-H. Wu, and M.-S. Chen, “Combining powers of two predictors in optimizing real-time bidding strategy under constrained budget,” in Proceedings of the 25th ACM International on Conference on Information and Knowledge Management, ser. CIKM 16. New York, NY, USA: Association for Computing Machinery, 2016, p. 2143–2148. [Online]. Available: https://doi.org/10.1145/2983323.2983656
[15] L. Chi-Chun, C. Kun-Ta, W. W. Chi-Hsuan, and C. Ming-Syan, Budgetconstrained real-time bidding optimization: Multiple predictors make it better,” ACM Trans. Knowl. Discov. Data, vol. 14, no. 2, Feb. 2020. [Online]. Available: https://doi.org/10.1145/3375393
[16] C.-C. Lin, “Real-time bidding optimization with multiple predictors and multidimensional segmentation,” Ph.D. dissertation, College of Electrical Engineering and Computer Science, National Taiwan University, 2020. [Online]. Available: https://www.airitilibrary.com/Publication/alDetailedMesh1?DocID=U0001-1912201914273000
[17] Y. Zhou, D. Chakrabarty, and R. Lukose, “Budget constrained bidding in keyword auctions and online knapsack problems,” in Internet and Network Economics, C. Papadimitriou and S. Zhang, Eds. Berlin, Heidelberg: Springer Berlin Heidelberg, 2008, pp. 566–576. [Online]. Available: https://www.hpl.hp.com/techreports/2008/HPL-2008-9.pdf
[18] D. Moore and R. Olshavsky, “Brand choice and deep price discounts,” Psychology & Marketing, vol. 6, pp. 181–196, 1989. [Online]. Available: https://www.semanticscholar.org/paper/Brand-choice-and-deep-price-discounts-Moore-Olshavsky/0151e8d056dc5b31e5d572c1fdd0140930bc5143
[19] M. Gunkel, E. Lusk, and B. Wolff, “Country-compatible incentive design,” Schmalenbach Business Review (sbr), vol. 61, pp. 290–309, 07 2009.
[20] H. M. Harcourt, “Utility and preferences,” 2020. [Online]. Available: https://www.cliffsnotes.com/study-guides/economics/theory-of-the-consumer/utility-and-preferences
[21] M.-C. Lee, A. F. Molisch, N. Sastry, and A. Raman, “Individual preference probability modeling and parameterization for video content in wireless caching networks,”IEEE/ACM Transactions on Networking, vol. 27, no. 2, pp. 676–690, 2019.
[22] E. Piedad and C. Kuo, “A 12-month data of hourly energy consumption levels from a commercial-type consumer,” 2018. [Online]. Available: https://www.semanticscholar.org/paper/A-12-month-Data-of-Hourly-Energy-Consumption-Levels-Piedad-Kuo/c9d40586b6b228439dc43eb9ab1cd111d53b928d
[23] Ausgrid, “Solar home electricity data,” Jul. 2012. [Online]. Available: https://www.ausgrid.com.au/Industry/Our-Research/Data-to-share/Solar-home-electricity-data
[24] Z. J. Lee, T. Li, and S. H. Low, “Acn-data: Analysis and applications of an open ev charging dataset,” in Proceedings of the Tenth ACM International Conference on Future Energy Systems, ser. e-Energy ’19. New York, NY, USA: Association for Computing Machinery, 2019, p. 139–149. [Online]. Available: https://doi.org/10.1145/3307772.3328313
[25] 郭華生, 台灣地區集團便利商店自願性節約能源推動, 節約能源中心, Jan. 2007.
[26] 台灣電力公司電價表, 台灣電力公司, Jun. 2018. [Online]. Available: https://www.taipower.com.tw/upload/238/2021062313172068082.pdf