## 374

participants

#### Topic provider

ITRI 工業技術研究院成立於1973年，以科技研發，帶動產業發展，創造經濟價值，增進社會福祉為任務；成立四十多年來，累積近3萬件專利，並新創及育成281家公司。

#### Introduction

Net Zero Emissions has been an international consensus and a global goal. Currently 136 countries have participated and some countries have even reached the initial goals. Recently Taiwan has formulated four major strategies and expects to achieve zero carbon emissions by 2050. Increasing the proportion of renewable energy generation such as solar power and wind power is also an important direction for energy transformation.

This topic uses the historical data of solar power generation such as daily solar irradiation, installation capacity, etc., to predict the solar power generation at various places with machine learning and hope participants can find out the key factors affecting the amount of generation and make a positive impact for the details of future solar energy construction.

Reference： 2050 Net-Zero Emissions

#### Prize

Award eligibility: the score is lower than baseline (RMSE < 260) on Private Leaderboard

Award nameAward money
First place1 personNTD $50,000 (Tax included) And TWS 100,000 cloud credits Second place1 personNTD$30,000 (Tax included)
And TWS 80,000 cloud credits
Third place1 personNTD \$20,000 (Tax included)
And TWS 50,000 cloud credits
Honorable mentionmultiple personsTWS 20,000 cloud credits
(Hold first place for longest time)
1 personTWS 30,000 cloud credits
• Commercial software is not allowed, and model validation is performed when necessary.
• No awards will be given to the participants that are employees (as well as interns and part-time workers) of ITRI or workers from the topic provider. If the award has been given, the prize will be revoked, and the participants will need to return the prize money as well as certificate.
• Please note that only the top three participants on the Private Leaderboard who submitted the written report before the deadline are eligible for the award.
• Participants will not be eligible for the award if no report is submitted before the deadline. (The report will not be disclosed or published)
• TWS services can only be awarded to the awardees that hold the nationality of ROC.
• TWS services in the award will be valid for six months.

#### Activity time

The time is based on UTC+8 as follows:

TimeEvent
2022/06/23Private Leaderboard announcement and report submission starts
2022/07/06Awards announcement

#### Evaluation Criteria

After the participants submitted the prediction result, the back-end of the system would process them in batches regularly to calculate the score. Evaluations are conducted by calculating the Root-Mean-Square Error, RMSE, of the actual value. The formula is as follows: $$RMSE = \sqrt{{1 \over n} \sum_{j=1}^{n} (y_i - \hat{y}_i) ^ 2}$$

#### Rules

1. The evaluation will be based on the final uploaded result. If two participants (or more) get the same evaluation scores, the time of uploading will determine the ranking.
2. The maximum number of uploading times is 5 times per day.
3. No awards will be given to the participants that are employees (as well as interns and part-time workers) of ITRI or workers from the topic provider. If the award has been given, the prize will be revoked, and the participants will need to return the prize money as well as certificate.
4. This topic does not offer a team-up option, only one account per person is allowed, and each person can only participate once. If any violations are found, people who are involved would be forced to withdraw the activity.
5. All the data, techniques and source codes that are used belong to the participants. If any third-party claims their intellectual property rights or other rights and interests are being violated, the participant will need to handle the disputes personally. If any participants violate intellectual property rights, they will be disqualified, and shall bear legal responsibilities.
6. When using external data sets, participants should avoid using future data as the basis of the prediction results, and must state source of datasets in the forum for references.
7. All the achievements and their IPRs (intellectual property rights) belong to the participants, and the Copyright License Agreements, patent applications, technology transfer and equity distributions of them, should be in accordance with the relevant Laws and Regulations.
8. The organizers reserve the right to enquire the results or take any related actions.
9. There should be no answer discussions between different accounts, or it will be considered as cheating.
10. If there is cheating or fraud during the activity, the participant that cheats will be disqualified from the activity and the vacancy would be filled up by other participants in the ranking order.
11. After uploading, the answers of test data would be divided into two parts to calculate the score:
• Before the deadline of the activity: The system will examine and calculate the score refer to the Ground Truth of 60％ of the entire test data. The result will be posted on the Public Leaderboard.
• After the deadline of the activity: The system will examine and calculate the score referring to the Ground Truth of the remaining test data (40％). The result will be posted on the Private Leaderboard as reference for the final score and ranking.
• Awards only will be given to the participants whose score on the Private Leaderboard is lower than the baseline，RMSE baseline is 260
12. Any artificial marking is forbidden.
13. Award Provisions and Eligibility
• Commercial software is not allowed, and model validation is performed when necessary.
• Please note that only the top three participants on the Private Leaderboard who submitted the written report before the deadline are eligible for the award.
• Participants will not be eligible for the award if no report is submitted before the deadline. (The report will not be disclosed or published)
14. Should there be disputes, the organizers reserves the right to the final decision.
15. The organizers reserve the right to modify any details regarding the contest when needed.