THE POTENTIAL IMPACT OF DATA MINING ON THE CLEAN ENERGY SECTOR
Table of Contents TOC \o "1-3" \h \z \u Part one: Research PAGEREF _Toc526018291 \h 3Part three: Regulation and Ethics PAGEREF _Toc526018292 \h 4Part 4: Disruption PAGEREF _Toc526018293 \h 6Part six: Video PAGEREF _Toc526018294 \h 8Reference List PAGEREF _Toc526018295 \h 9
Part one: Research
Data mining technology
Data mining can be interpreted as a process that allows organisations to extract useful information from raw data. However, data mining is a complicated process and requires proper software to evaluate a large set of data. Generally, three factors influence the data mining processes, such as data collection, warehousing and computer processing (Thuraisingham, 2014). However, multiple data mining techniques have been observed in the current literature such are:
1 Machine learning
2 Artificial intelligence (AI)
3 Statistical data mining
Data mining process has a versatile application in different domains. Henceforth, multiple phases of data mining have been found in the existing literature. The Knowledge Discovery in Databases (KDD) is Cross Industry Standard Process for Data Mining (CRISP-DM) are two major processes for data mining. Nevertheless, scholars prefer the CRISP-DM method for data mining due to its detailed process that can be helpful in any domain.
The clean Energy sector in Australia
Australian Government has taken future initiatives to promote the clean energy sector, which has been identified as essential for future energy consumption. From a recent report of clean energy council in Australia. It is found that Australian businesses are facing issues in securing long-term contracts for consuming energy. This drives a better demand for the solar energy in Australia. It is identified that wind and hydro generation energy has been able to develop approximately the same energy as electricity. However, households in Australia has also cooperated with the Government as almost 172,000 households have installed solar PV to save high consumption of energy. Henceforth, almost 28000 battery systems have been installed across Australia in 2017. Therefore, the Government has considered following factors that to be considered in 2018:
* Continuous hike of PV system prices
* Increasing the price of PV systems
* Market robustness
Part two: Brainstorming
From the above-discussed report, three possible ways have been found that can allow this industry to be changed significantly. These are:
1 Data mining technology will allow the Australian Government to track the number of solar PV that will be installed in large in recent future
2 Data mining will also help to improve artificial learning process that might clear the energy sector to increase its efficiency
3 However, the implication of data mining technology might increase employment rate as AI will improve the work efficiency of most people (Cleanenergycouncil.org.au, 2018)
Part three: Regulation and Ethics
Pathetic dot theory of Lawrence Lessig
This theory reflects on four constraints that influence the social community in a significant manner. Focusing on this socio-economic theory of regulation, the following things are constructed:
Market: Market is a big factor that might disallow the proper implication of data mining in the clean energy sector of Australia. A significant and spontaneous growth of the clean energy sector has encouraged many players to invest in this industry. However, the clean energy sector is still in the nurture and a strong competition of suppliers (data mining technology) might seem impossible at this moment. However, it can be said that data mining technology can be implemented after the successful expansion of the Australian clean energy sector.
Law: A legislation was imposed in 2012 that covered essential rules to maintain sustainability and effectiveness of this industry in both national and global level. Furthermore, the implication of Renewable Energy (Electricity) Regulation in 2001 has helped to make effective changes in 2017. As per this legislation, the Government is highly concerned about Emissions-Intensive Trade-Exposed (EITE) activities to maintain the environment healthy and pollution free. However, the effective application of multiple data technology might influence the clean energy sector in a significant manner. Henceforth, more innovation in data mining technology is required to be implemented.
Norms: According to the energy council of Australia, it is observed that the Government has undertaken following norms for better practice of this energy:
1 Solar installer accreditation
2 Code of the conduct of solar PV retailer
3 Approved listings of product
Henceforth, it is mentioned that the Clean Energy Council is highly focused regarding the environment as data mining technology might influence these norms in multiple ways.
Architecture: Clean energy sector of Australia is still developing and more innovations are taking places. Therefore, a basic yet complicated architecture of this industry might reduce the chance of data mining application. In this regard, a more versatile approach is needed for imposing this stated technology.
Part 4: Disruption
In order to identify a proper data mining method in clean energy sector, a case study of a coal-fired power plant has been observed. According to (), a coal field of Thailand has taken a significant data mining technique to reduce carbon emission rate from a coal-fired power plant. It is found that complying with the air pollutant standards was the major reason behind the...