Optimizing Energy Usage in Buildings
Energy crisis is one of the significant challenges facing many economies in this era. This is primarily due to scarcity of energy resources and emergent consumption by humans. On the other hand, excess usage of energy by dissimilar societies has threatened the impending life of humans, contaminated the environment and wasted national capitals. There are different methods to protect the atmosphere. The most notable is renewable sources such as solar and effective management of energy resources. These practices are based on creating an energy conservation and sustainability culture aimed at making the right use of energy. This article seeks to discuss different practical approaches employed to optimize energy usage for the purposes of enhancing sustainability and business process with parametric approaches.
Parametric approaches such as regression and triangulation enhances sustainability and business process redesign with Neural Networks and Fuzzy Logic in different forms (Rajasekaran & Pai, 2003). The fuzzy logic is one of the most successful technologies today for developing control systems that are sophisticated. This is because it imitates the ability of humans in making decisions but generate accurate solutions from precise or estimated data. It aids in decision making because it fills the gap in engineering design methods. These gaps result from the inadequacies of purely mathematical and logic-based techniques (Athienitis & O’Brien, 2015).
Regression enables forecasting of energy demand especially in large commercial buildings. Researchers are working on methods of reducing carbon emissions and the total energy consumption levels. Regression is a form of computer model designed to calculate and forecast the amount of energy a building will consume over a give period. The model employs Support Vector Machine Regression (SVMR), a method that creates regression virtuously based on chronological data of the structure, needing no knowledge of the structure’s size, heating, cooling or any other physical properties of the structure.
SVMR puts to use time versus delay coordinates for SVM simulation. The pure dependence on past data makes the model easily applicable to dissimilar structure types and requires very few adjustments on the models. The purpose of the SVM is to predict a week of future usage of the energy of a building basing on past temperature, energy, and dew point temperature information. By calculating this information, it provides Fuzzy logic with the information and then a human-like decision is made (Kartalopoulos, 1996). The Neuro-fuzzy puts the ultimate information deduction and decision-making it the hands of the Neuro-fuzzy. This process helps in coming up with appropriate decisions concerning sustainability and optimization of energy in buildings.
America’s resource inputs
Sources of Revenue
Revenue is the state’s annual income, which helps meet public expenses. The individual income taxes and payroll taxes were a whopping 82% of all income of the federal government in 2010. Estate, gift taxes, excise taxes and miscellaneous receipts accounted for the remainder. The tax revenue structure has altered over the last half-century, but the share of individual income taxes fairly remains approximately the same. By feeding the Neuro-fuzzy information about the historical shifts in the shares of the various taxes, it calculates the outcome and comes with a possible and probable solution on how to tax.
Sources of Raw Materials
The US gets its raw materials from fossil fuels; it gets iron units in taconite or iron ore, carbon units in coal form, coke from coal and steel crap. Mountain Materials, which consists of the non-fuel and non-food, have reduced yet the demand has increased (Liu, 2006). By feeding the information about the trend of the use versus the depletion in the Neuro-fuzzy model, the artificial intelligence model will come up with information and possible solutions on how to tackle the given problem. Other sources of raw materials for the United States industries include stone, gravel, sand, recycled paper, primary paper, and wood products.
Sources of Energy
America is greatly dependent on coal-fired electric power plants (Adali, 1987). The new government is trying to discourage building of any more of these power plants. The current government wants companies to invest in new methods of developing clean coal technology or renewable energy (Larson et. Al, 2013). Another source of energy is crude oil, and according to EIA, there is enough to last the world another 25 years. Renewable energies of all forms are used to generate electricity (Sciubba, Manfrida & Desideri, 2012). The US also uses nuclear power to produce energy. Similar to the Neuro-fuzzy system, the smart grid is a network that employs digital communications technology to sense and respond to local variations in usage. By feeding the Neuro-fuzzy information regarding the usage and depletion of all these energy sources, the network will come up with solutions on how to optimize the energy use and save where possible.
Neuro-fuzzy technology is an advanced technology fused with artificial intelligence by J. S. R. Jang. He proposed it because the ability of the human-like reasoning with learning and connection structure of the neural networks would provide limitless power to solving problems. It aids in sustaining and enhancing optimization of natural gas consumption in buildings with parametric approaches such as regression and is triangulated with Artificial Intelligence approaches such as Fuzzy Logic and Neural Networks.
References
Adali, E., Adalı, E., Tunalı, F., International Federation of Automatic Control., IFAC Committee on Developing Countries., & IFAC Symposium on Microcomputer Application in Process Control. (1987). Microcomputer Application in Process Control: Selected Papers from the IFAC Symposium, Istanbul, Turkey, 22-25 July 1986. Oxford [Oxfordshire: Published for the International Federation of Automatic Control by Pergamon Press.
Athienitis, A., & O’Brien, W. (2015).Modelling, Design, and Optimization of Net-Zero Energy Buildings.Hoboken: Wiley.
In Sciubba, E., In Manfrida, G., & In Desideri, U. (2012). ECOS 2012: The 25th International Conference on Efficiency, Cost, Optimization and Simulation of Energy Conversion Systems and Processes (Perugia, June 26th-June 29th, 2012). Firenze: Firenze University Press.
Kartalopoulos, S. V. (1996). Understanding neural networks and fuzzy logic: Basic concepts and applications.New York: Piscataway, N.J.
Larson, E. W., Gray, C. F., Danlin, U., Honig, B., &Bacarini, D. (2013).Project management: The managerial process. North Ryde, N.S.W: McGraw-Hill education.
Liu, Z. (2006). Taxation in China.Singapore: Cengage Learning Asia.
Rajasekaran, S., &Pai, G. A. V. (2003). Neural networks, fuzzy logic, and genetic algorithms: Synthesis and applications. New Delhi: Prentice-Hall of India.