Smart Energy Management System for Sustainable Energy Use

/ 10

100%

Document text

Smart Energy Management System: Promoting

Efficient Use of Sustainable Energy and Resources

1 Milestone 1

In Australia, the development of solar sharing systems is closely related to renewable energy and decentralization. Australia promotes solar sharing projects and solar buyback programs (Feed-in Tariff, FiT) to encourage households to install rooftop photovoltaic systems. This includes gross metering and net metering, which apply to selling all or surplus electricity to the grid, respectively, to incentivize the production and investment of solar power (Hong Xian Li et al., 2021).

1.1 Challenges

The application of solar photovoltaic systems in distributed generation systems faces challenges due to the mismatch between energy production and demand (Ferreira et al., 2014). The peak of solar power generation typically occurs at noon (Sharma et al., 2019), while peak household energy demand is in the morning and evening (Vilaca & Saraiva, 2017). This mismatch can lead to excess energy being injected into the grid, causing negative impacts on low-voltage networks, such as reverse current issues and accelerated aging of distribution transformers (Lopes et al., 2018; Sgouras et al., 2017).

1.2 Technological Solution

To address this challenge and align with CSIRO's goals for sustainable energy and resources, I propose the following solution:

Develop a user-oriented smart energy management system. The system utilizes machine learning algorithms(ML), combined with historical energy usage data and energy consumption patterns provided by power suppliers or smart meters (for example, regular daily energy consumption and user electricity habits), to predict daily electricity demand.

Each evening, the system will push notifications to users, reporting the electricity collected by solar panels that day (for example, under sunny conditions, about 5-10 kilowatt-hours can be collected on average per day). Based on the user's average daily electricity usage (such as a household average of about 10-15 kilowatt-hours per day), the system intelligently recommends an electricity usage strategy for the next day. This includes advising a reserved percentage of electricity, with the system proposing the most suitable reserve ratio by analyzing historical data and consumption patterns (such as recommending a 30% reserve). The system allows users to manually adjust the next day’s electricity usage plan according to their specific needs, such as reserving enough power for special events (like parties) or selling excess electricity during trips, with the remainder stored in the home battery system.

To enhance the security and transparency of energy trading, the system incorporates blockchain technology, enabling peer-to-peer electricity transactions. Transactions are automatically executed

through smart contracts, allowing for direct sale or free distribution to other users or energy suppliers when there is excess electricity production. Consumers trade directly with energy producers (solar panel users). The decentralized ledger of the blockchain ensures that transaction records are immutable and transparent.

1.3 Infrastructure limitations

According to Chengyang et al., in areas of Australia, installing distributed renewable energy systems such as solar photovoltaics faces challenges such as low space utilization, building safety requirements, and insufficient sunlight. Due to increased urban density and environmental complexity, a robust energy management system is needed to monitor and optimize energy use.

2 Milestone 2

2.1 Model solution

Smart Energy Management System

User Interface (UI): The system provides an intuitive interface displaying current energy usage, historical energy consumption trends, current battery storage and available power, weather data, recommendations for energy use and storage, and user preference.

Database: The database integrates weather data from meteorological providers (such as AccuWeather), historical energy usage data from smart meters or power suppliers, battery storage capacity and available energy, and records and statuses of energy transactions.

Control Center: a. Machine learning algorithms (Vennila et al., 2022): Process data, predict solar panel power generation efficiency for the coming days; b. optimization engine (such as Particle Swarm Optimization Algorithm) (Shi & Eberhart, 1998): Dynamically adjust energy allocation. For example: Automatically adjust energy storage and power usage strategies based on user habits and real-time electricity prices.

Payment System: Includes payment gateway, account management, and settlement system.

Functionalities

The UI helps users track real-time and historical energy usage, identify consumption patterns and trends, and recommends energy usage and storage strategies.

The system interacts with smart meters, power suppliers, and meteorological providers through an API interface, automatically fetching and storing data in a cloud platform data warehouse, and encrypts the database to prevent unauthorized access.

The control center uses ML to predict electricity demand, and combines this with weather data to predict solar panel generation efficiency. The optimization algorithm dynamically adjusts energy distribution, pushing the adjusted power usage strategy to users.

The payment system facilitates direct energy transactions between users, supporting peer-to-peer energy selling.

Blockchain

Transactions: Include input and output vectors, transaction version number, number of inputs and outputs, and lock time(Aitzhan et al., 2018).

Blockchain: Consists of a series of blocks linked by a proof of work algorithm, each block containing multiple verified transactions.

Transactions allow users to change token ownership through digital signatures and broadcasting mechanisms, ensuring the immutability and continuity of transactions by linking the hash value of the previous transaction in the current transaction (Aitzhan et al., 2018).

The blockchain ensures the order and integrity of blocks through the proof of work algorithm, ensuring that transaction records are tamper-proof and transparent (Karame et al., 2012). This algorithm helps the system securely conduct electricity transactions, preventing the same unit of electricity from being sold or billed multiple times.

2.2 Modelling assessment

According to Rogers’ definition of diffusion, I believe the spread of smart energy management systems is primarily hindered by unfamiliarity with modern technology among certain user groups (such as the elderly), leading to distrust in new technologies, a perceived lack of benefits, and uncertainty about credibility (Gatto & Tak, 2008). Additionally, while blockchain enhances transaction security and transparency, the public nature of transaction records may expose user privacy (Ali et al., 2015).

According to my perspective, based on Rogers’ Technology Adoption Lifecycle Model, the system is at the stage where innovators take risks and access new tech. In this phase, innovators are willing to try new technologies and face risks and uncertainties (Rogers, 2003). Subsequently, the positive evaluations from early adopters will influence user acceptance (Bianchi et al., 2017).

According to the Hype Cycle for Emerging Technologies (Liikkanen, 2019), both Artificial General Intelligence and Blockchain for Data Security are positioned between the Innovation Trigger and the Peak of Inflated Expectations. My system primarily integrates these two technologies, thus it also resides at this stage. This phase is characterized by rapidly growing attention and optimistic expectations for applications. Before reaching the Peak of Inflated Expectations, the actual application of the technologies is not fully matured or widely verified.(van Lente et al., 2013).

Hype Cycle for Emerging Technologies, 2018

Figure 1: Hype Cycle for Emerging Tech, 2018

2.3 Dominant design

The above solution falls under the category of Artificial Intelligence (AI) systems. Currently, AI technology is in the early stages of dominant design formation, known as the fluid phase, and is in the era of ferment within technology cycles. During this phase, a variety of methods, hardware architectures, and service models emerge in the market, undergoing continuous iteration and testing. AI is considered capable of becoming a dominant design in an industry due to its broad application potential and innovativeness. For example, its applications in virtual assistants, autonomous vehicles, and smart home devices demonstrate its cross-disciplinary integration capabilities and broad market acceptance (Ferràs et al., 2023).

In hardware development, we can consider using the coupled process of open innovation. The system needs to integrate with compatible hardware devices such as smart meters, solar panels, and energy storage systems. These devices need to precisely measure and record energy consumption data. By collaborating with hardware manufacturers, we can jointly develop more efficient solar panels, reduce energy consumption, enhance the durability of devices, and provide maintenance services when necessary.

In data processing and core algorithm development, we need to adopt a closed innovation. The system involves user historical energy usage data and energy transaction records, and data handling must comply with data protection regulations, such as obtaining user authorization when sharing with third parties (DataGuidance, 2024). Additionally, the algorithms for energy demand forecasting and optimization are the core competitive strengths of the product, and it is necessary to protect the technology from being disclosed and replicated.

3.2 Business strategies

• Value proposition canvas

(a) Customer Profile:

Customer Jobs: According to a report by the Energy Users Association of Australia, South Australia has the third highest electricity costs in the world. High electricity bills prompt users to seek renewable energy solutions to reduce energy expenses. Additionally, facing challenges of climate change and sustainable development (Ruggerio, 2021; Fawzy et al., 2020), environmentally conscious users aim to reduce their carbon footprint and support sustainable energy solutions (Ferreira et al., 2024).

Gains: With the growth in residential energy demand and rising energy prices, households are highly sensitive to energy prices (Charlier & Kahouli, 2019). Users need solutions that optimize energy use and reduce energy costs.

Pains: The Australian government promotes a shared solar program, particularly for users who install solar panels, aiming to maximize the use of self-generated energy.

(b) Value Map:

Product offering: My proposed digital product combines ML and optimization algorithms to precisely predict daily electricity demand based on user energy usage and consumption patterns, achieving energy savings (for example: using electricity during periods of lower prices). The system supports users with solar panels in selling excess electricity to generate income and uses weather forecasting to enhance understanding of solar collection patterns, optimizing electricity use and storage strategies.

Gain Creators: The differentiation of my product lies in changing the traditional energy trading model, allowing users to shift from energy consumers to energy providers and generate income. Compared to traditional electricity, solar energy offers lower operating costs. Additionally, for environmentally conscious users, using renewable energy can evoke positive emotions.

Pain Relievers: 1. Reduce energy costs. Solar energy offers lower energy costs to users compared to traditional electricity. 2. Optimize energy consumption. The system uses algorithms to predict users' electricity demand, helping them adjust their energy usage habits. For example, it allows users with battery storage systems to store electricity when demand is low and use the stored power during periods of high electricity prices. 3. Increase income. For users with solar panels, it allows the sale of surplus electricity to generate income. 4. Environmental protection: Using renewable energy attracts environmentally conscious users.

Users: Online platform

Business or large enterprises: Contract transactions

Retail Clients: Environmental advocates, users looking to save energy and generate income.

Business Clients: Large businesses with their own energy production facilities.

(b) Value Propositions:

Makes money: For solar panel users, income can be generated through self-produced energy; for users needing to buy electricity, the system facilitates energy transactions at costs lower than traditional electricity prices.

Integrates: The system integrates forecasting of user electricity demand, payment, and settlement system.

Self-transcendence: This project benefits not only environmentally conscious users but also supports humanity's fight against climate change.

Users: Online platform

Business or large enterprises: Contract transactions

(d) Customer Relationships:

Automated Services: The system generates customized energy-saving suggestions based on users’ energy history and consumption patterns. Users wanting to purchase electricity can place orders through the system autonomously.

Technical Support: For issues like data synchronization errors and forecast accuracy, users can contact the technical support team by email or phone.

(e) Revenue Streams:

Transaction or Brokerage Fees

(f) Key Activities

Key activities include analyzing data from smart meters and user energy usage records, predicting energy demand, and optimizing energy distribution. Additionally, the system integrates a payment gateway and smart contracts, allowing users to conduct energy transactions on the platform. The system also provides customer support services to resolve technical issues and user inquiries.

(g) Key Resources:

Technology: ML and optimization algorithms autonomously developed to predict users’ energy usage behavior.

User data: Includes smart meters, historical energy usage, and energy transaction records of users.

(h) Key Partnerships:

Energy suppliers, the Australian government, and hardware device manufacturers. Hardware device manufacturers include but are not limited to producers of smart meters, suppliers of solar panels, and home energy storage systems.

(i) Cost Structure:

Software development costs

Cloud service costs

Maintenance and technical support costs

User training costs

3.3 Capital and fundraising pathways

• Local sources

1. Seek government support: As the Australian government promotes renewable energy programs, We can seek cooperation with the government, such as collaborating with the Australian Department of Environment. We can consider implementing promotions through government websites or social platforms to introduce the advantages of sustainable energy and subsidy plans to users.

2. Bank loans: The Australian government offers specific loan programs for sustainable energy projects, such as the Clean Energy Finance Corporation (CEFC).

• International sources

1. Technology companies: We can seek cooperation with companies like Google that have AI and data analysis teams to optimize our algorithms.

2. Solar panel manufacturers: We can collaborate with solar panel manufacturers like SunPower and Tesla Solar to optimize solar products, including battery storage systems.

4 Conclusions

This report achieves sustainable energy use by developing a user-oriented smart energy management system, aligning with CSIRO's objectives. Currently, the system is still in the proposal stage and has areas needing improvement, such as voltage instability in peer-to-peer transactions via physical power grids. Therefore, most regional power transactions are currently scheduled and distributed through the central grid. How to safely and effectively transfer electricity to other users involves technical fields such as electrical engineering, which requires further exploration.

References

[1] AccuWeather. (n.d.). Local, national, & global daily weather forecast — AccuWeather. https://www.accuweather.com/

[2] Aitzhan, N. Z., & Svetinovic, D. (2018). Security and Privacy in Decentralized Energy Trading Through Multi-Signatures, Blockchain and Anonymous Messaging Streams. IEEE Transactions on Dependable and Secure Computing, 15(5), 840–852. https://doi.org/10.1109/TDSC.2016.2616861

[3] Ali, S. T., McCorry, P., Lee, P. H., & Hao, F. (2015). ZombieCoin: Powering Next-Generation Botnets with Bitcoin. In Lecture notes in computer science (pp. 34–48). https://doi.org/10.1007/978-3-662-48051-9-3

[4] Australia - Data protection overview. (2024, February 6). DataGuidance. https://www.dataguidance.com/notes/australia-data-protection-overview

[5] Beikverdi, A., & Song, J. (2015). Trend of centralization in Bitcoin's distributed network. The Institute of Electrical and Electronics Engineers, Inc. (IEEE) Conference Proceedings, 1-.

[6] Bianchi, M., Di Benedetto, A., Franzò, S., & Frattini, F. (2017). Selecting early adopters to foster the diffusion of innovations in industrial markets: Evidence from a multiple case study. European Journal of Innovation Management, 20(4), 620–644. https://doi.org/10.1108/EJIM-07-2016-0068

[7] Charlier, D., & Kahouli, S. (2019). From Residential Energy Demand to Fuel Poverty: Income-induced Non-linearities in the Reactions of Households to Energy Price Fluctuations. The Energy Journal (Cambridge, Mass.), 40(2), 101–138. https://doi.org/10.5547/01956574.40.2.dcha

[8] Decker, C., & Wattenhofer, R. (2014). Bitcoin Transaction Malleability and MtGox. Computer Security - ESORICS 2014, 8713(2), 313–326. https://doi.org/10.1007/978-3-319-11212-1-8

[9] Department of Finance. (2024, March 15). Clean Energy Finance Corporation. https://www.finance.gov.au/government/specialist-investment-vehicles/clean-energy-finance-corporation

[10] Department of Climate Change, Energy, The Environment and Water. (n.d.). Government rebates and loans for solar. https://www.energy.gov.au/solar/financial-benefits-solar/government-rebates-and-loans-solar

[11] Ferreira, E., Miguel, M. S., & João, P. G. (2024). Sharing Is Caring: Exploring Distributed Solar Photovoltaics and Local Electricity Consumption through a Renewable Energy Community. Sustainability, 16(7), 2777. https://doi.org/10.3390/su16072777

[12] Ferreira, E., Sequeira, M. M., & Gouveia, J. P. (2024). Sharing Is Caring: Exploring Distributed Solar Photovoltaics and Local Electricity Consumption through a Renewable Energy Community. Sustainability (Basel, Switzerland), 16(7), 2777. https://doi.org/10.3390/su16072777

[13] Fawzy, S., Osman, A., Doran, J., & Rooney, D. W. (2020). Strategies for mitigation of climate change: a review. Environmental Chemistry Letters, 18(6), 2069–2094. https://doi.org/10.1007/s10311-020-01059-w

[14] Ferrás-Hernández, X., Nyland, P. A., & Brem, A. (2023). The Emergence of Dominant Designs in Artificial Intelligence. California Management Review, 65(3), 73–91. https://doi.org/10.1177/00081256231164362

[15] Gatto, S. L., & Tak, S. H. (2008). Computer, Internet, and E-mail Use Among Older Adults: Benefits and Barriers. Educational Gerontology, 34(9), 800–811. https://doi.org/10.1080/03601270802243697

[16] Gartner. (n.d.). Gartner hype cycle. Retrieved May 6, 2024. https://www.gartner.com/en/research/methodologies/gartner-hype-cycle

[17] Heat blamed for high SA electricity prices; A government department has defended the high cost of electricity for South Australians, blaming air-conditioning demand. (2012). In ABC Premium News. Australian Broadcasting Corporation.

[18] Karem, G., Androulaki, E., & Capkun, S. (2012). Double-spending fast payments in bitcoin. Proceedings of the 2012 ACM Conference on Computer and Communications Security, 906–917. https://doi.org/10.1145/2382196.2382292

[19] Li, H. X., Zhang, Y., Li, Y., Huang, J., Costin, G., & Zhang, P. (2021). Exploring payback-year based feed-in tariff mechanisms in Australia. Energy Policy, 150, 112133. https://doi.org/10.1016/j.enpol.2021.112133

[20] Lopes, R. A., Magalhães, P., Gouveia, J. P., Aelenei, D., Lima, C., & Martins, J. (2018). A case study on the impact of nearly Zero-Energy Buildings on distribution transformer aging. Energy (Oxford), 157, 669–678. https://doi.org/10.1016/j.energy.2018.05.148

[21] Liu, C., Yang, R., Wang, K., & Zhang, J. (2023). Community-Focused Renewable Energy Transition within Virtual Power Plant in an Australian City—A Case Study. Buildings (Basel), 13(4), 844-. https://doi.org/10.3390/buildings13040844

[22] Liikkanen, L. A. (2019). It Ain’t Nuttin’ New – Interaction Design Practice After the AI Hype. Human-Computer Interaction – INTERACT 2019, 11749, 600–604. https://doi.org/10.1007/978-3-030-29390-145

[23] Mullane, J., & Mullane, J. (2024, February 7). Net metering: What is it and how does it work? Canstar Blue. https://www.canstarblue.com.au/solar/what-is-net-metering/

[24] Qayyum, F., Jamil, H., & Ali, F. (2024). A Review of Smart Energy Management in Residential Buildings for Smart Cities. Energies (Basel), 17(1), 83-. https://doi.org/10.3390/en7010083

[25] Ruggerio, C. A. (2021). Sustainability and sustainable development: A review of principles and definitions. The Science of the Total Environment, 786, 147481–147481. https://doi.org/10.1016/j.scitotenv.2021.147481

[26] Residential solar, energy storage and EV charging — SunPower. (n.d.). https://us.sunpower.com/

[27] Sharma, V., Haque, M. H., & Aziz, S. M. (2019). PV generation and load profile data of net zero energy homes in South Australia. Data in Brief, 25, 104235–104235. https://doi.org/10.1016/j.dib.2019.104235

[28] Sgouras, K. I., Bouhours, A. S., Gkaidatzis, P. A., Doukas, D. I., & Labridis, D. P. (2017). Impact of reverse power flow on the optimal distributed generation placement problem. IET Generation, Transmission & Distribution, 11(18), 4626–4632. https://doi.org/10.1049/iet-gtd.2016.1791

[29] Shi, Y., & Eberhart, R. (1998). A modified particle swarm optimizer. 1998 IEEE International Conference on Evolutionary Computation Proceedings. IEEE World Congress on Computational Intelligence (Cat. No.98TH8360), 69–73. https://doi.org/10.1109/ICEC.1998.699146

[30] Solar panel rebates now open to Canberra businesses. (2019). Energy Monitor Worldwide (Amman, Jordan).

[31] Solar Panels — Tesla. (n.d.). https://www.tesla.com/solarpanels

[32] Vilaca Gomes, P., & Saraiva, J. T. (2017). Transmission system planning considering solar distributed generation penetration. 2017 14th International Conference on the European Energy Market (EEM), 1–6. https://doi.org/10.1109/EEM.2017.7981850

[33] Vilaca Gomes, P., & Saraiva, J. T. (2017). Forecasting Solar Energy Production Using Machine Learning. International Journal of Photoenergy, 2022, 1–6. https://doi.org/10.1155/2022/7797488

[34] van Lente, H., Spitters, C., & Peine, A. (2013). Comparing technological hype cycles: Towards a theory. Technological Forecasting & Social Change, 80(8), 1615–1628. https://doi.org/10.1016/j.techfore.2012.12.004