Analysis of a New Model of Economic Growth in Renewable Energy for Green Computing

3.1 Energy Generation Strategy

Energy generation from renewable sources positively correlates with economic growth for green computing. The economic growth factor is validated based on energy from renewable sources discussed below.

Figure 1 illustrates the energy generation strategy to incorporate renewable sources of power that are essential due to the worldwide crises caused by carbon emissions. Many nations’ policies for energy security now emphasize the integration of renewable energy sources into the energy sector for economic growth. One of the sustainable goals is to boost renewable energy use for efficient power generation of energy. The article explores how developing green computing technologies might sustainably help the social economy grow. The green technology, including green computing, describes the ecologically conscious use of computing and other technological resources. The challenging characteristic of such renewable energy for green computing is that the cost of fossil fuels, CO₂ emission, and power production are the major limiting forces to slow economic growth. There is a positive relationship between energy usage, inflation, and GDP, even though energy intensity has dropped over time and is often lower in wealthier countries. Energy efficiency is one of several elements that influence the energy intensity of economic growth factors using green computing, as shown in Figure 1.

Figure 1

Effective Prediction and validation of Energy-based economic growth.

3.2 Renewable Energy Production Development (REPD)

Further, the renewable energy limiting and driving factors for green computing are discussed in Figure 2a and b for the economic growth factors has been discussed as follows. The geological and climatic features of many locations are unique. The viability and appropriateness of renewable energy sources, including solar, wind, hydro, and geothermal power, must be considered. The model must be adjusted to maximize a region’s rich and practically viable renewable resources.

Figure 2

(a) Limiting forces for the REPD and (b) driving forces for REPD.

Figure 2a illustrates technological advancements and effective legislative frameworks; renewable energy sources are now inexpensive. Various variables might influence the likelihood that a government will implement a Renewable Energy Sources (RESs) policy that affects several elements such as the cost of fossil fuels, CO₂ emission, and power production. The degree to which these elements play a role is influenced by a nation’s institutional, technological, and economic development. RES deployment is crucial to address energy needs. Green computing for RES is the practical use of environmental science to protect Earth and sustainably exploit its abundant biological diversity and pristine ecosystems. Energy may be produced from renewable sources with green computing technology. The goal of green technology is to lessen environmental pollution by eliminating or mitigating sources of pollution. In Figure 2, the development and penetration of Renewable Energy Production Development (REPD) are hampered by several crucial hurdles, including social, economic, technical, stability and dispatch ability of renewable energy, geographic constraint, and capacity considerations. These limiting forces are due to the cost of fossil fuels, CO₂ emission, and power production. As expected, rising energy costs are proven to be a limiting factor for energy generation from renewable sources for green computing. Data centres are crucial to cloud service providers and information technology (IT). Incorporating renewable energy sources and green computing processes allows these providers to appeal to environmentally conscious customers, boost efficiency, and differentiate in an increasingly competitive industry. Due to the energy required to run data centres and communications networks, the IT sector substantially impacts the environment. Green computing methods and using renewable energy to power data centres may help decrease costs and improve the industry’s environmental footprint. Therefore, factors that mainly influence the driving forces for energy are discussed in Figure 2b. The renewable energy industry is expanding due to rising demand for green energy sources. This includes producing and setting up environmentally friendly technology such as solar panels, wind turbines, etc. Investment patterns, demand for fossil fuels, and employment might all change due to the transition to renewable energy.

Figure 2b denotes renewable energy sources play a significant role in the global economy and society. Long-term economic expansion, in which energy plays an important role in green computing, is an important driving factor for energy consumption. More excellent economic activity often increases energy consumption, necessitating additional capacity and improving the cost of fossil fuel, Co₂ emission, and power production. Even while environmental preservation and economic growth are two of the most important driving forces, the quantity of renewable energy for green computing attached to the utility grid, the cost of renewable energy, the feed of renewable energy, and market demand are all significant pulling forces of the energy. Internal pressures include the effect on ongoing investment project plans, talent and technology, renewable energy accommodation infrastructure, and government policy affecting economic growth. Reduced energy usage is one of the main benefits of green computing methods, including adopting energy-efficient hardware and fine-tuning data centre operations. This leads to decreased power bills and operating expenses for enterprises. Among the many practices that contribute to green computing is efficient resource management. Enhanced productivity, less downtime, and fewer errors are all possible outcomes. Therefore, a graphical survey has been conducted to validate China’s energy consumption during 2021 and 2022 to effectively perceive driving forces based on energy demand, as shown in Figure 3. Economic models often support carbon pricing methods, including cap-and-trade or carbon taxes. Businesses and people are incentivized to decrease their carbon footprint via these measures, which impose a monetary penalty on carbon emissions. As a result, there will be an economic incentive to embrace green practices and products.

Figure 3

Electrical demand during weekends and weekdays in April 2021 and 2022 for China.

3.3 REPD’s Discussion

In China, the demand for electrical energy in the commercial and industrial sectors is expected to decrease by 20% by 2021. The manufacturing sector in China has seen a decline of 13% in electricity consumption. However, home loads have increased due to safety regulations in most countries; for instance, residential energy consumption has increased by about 40% in China. The load profiles were reorganized in many places with the load composition shift. Figure 3 displays the China load profile changes during the first week of April 2021 and 2022. It can be seen in Figure 4 that the peak load has decreased by around 21% during the week and 13% on the weekends. Businesses and industries that switch to green computing and renewable energy sources save money on energy costs and decrease in carbon emissions connected with computing operations and energy use. The model must follow global renewable energy standards to ensure that renewable energy is integrated using accepted procedures. The approach may be adapted whenever possible to fit in with programs that encourage and support data-driven innovation while protecting the environment. Achieving innovation without compromising environmental objectives necessitates balancing data-driven advances and sustainability. An important consideration is how efficiently renewable energy sources like wind turbines and solar panels use resources. With the continued price decline, green computing solutions are becoming more accessible to consumers and enterprises.

Figure 4

(a) ANN architecture, (b) driving forces to ANN Layer, and (c) conceptual framework prediction based on ANN-EGM.

3.4 Architecture of ANN

From the above discussion on predicting and validating limiting and driving forces, the conventional models such as (Gunjan et al., 2020, pp. 21, 22) need to improve several aspects. Therefore, this advent the pathway for ANN-enabled EGM which helps to predict the limiting and driving growth factor as influenced by fossil fuel, Co₂ emission, and power production effectively, as discussed below: Renewable energy sources, including solar, wind, hydro, and geothermal, are fundamental to the proposed new economic growth model. Because of this, less non-renewable energy is used, and instead, computing operations are powered by sustainable and environmentally friendly energy.

Figure 4a illustrates layers in the fundamental structure of an ANN that may be grouped as input, hidden, and output. Depending on the task, ANN may contain one or more of these “hidden layers.” Layers contain one or more synthetic neurons. Directed edges with weights represent the inputs and outputs in a network of neurons. The driving forces of input with the ANN layer are discussed below:

Figure 5

(a) Input vector and (b) renewable energy.

Figure 4b illustrates the estimate of the characteristics of renewable power production and anticipates the spread of carbon emission; the primary predictive model uses two ANN layers, the first of which has 256 neurons and the second of which has 64. State blocks inside the ANN itself take in data at regular intervals. The ANN receives the input vector at each time step and generates an output according to the following formula.

ANN is currently utilized to analyze limiting factors using neuronal networks with dynamic connectivity. Internalized and fleeting, memory is shared among individuals. There is a safety net, and tasks are split up to validate the influenced limiting forces that slow down economic activity. It may be used when there is a lack of knowledge about the rules to follow or when there is incomplete or noisy data. In an ANN, several different signals are sent into each neuron. By applying the functions, the inputs are transformed into neuronal activity. When discussing ANN, each arrow indicates a connection between two neurons, which helps to predict and validate elements such as fossil fuel, Co₂ emission, and power production. All times are weighted and given a whole number based on the element’s influence and weight. There is no need to tweak the weights if the network produces the expected outcomes. In contrast, if the network produces incorrect output, it must be nullified.

The input signals to the neuron are added together after being multiplied by the connection weights. If the combined weights total up to zero, a bias is applied to either make the output positive or increase the system’s responsiveness, which is quantified, and its input is always 1. The final output is obtained by feeding the result of the weighted sum into an activation function, which is often non-linear. The driving forces are validated during the feedback process based on technological growth, economic policies, and finance management. An ANN’s activation function may be seen as the collection of transfer functions applied to effectively deciding based on input and feedback, which effectively decides the limiting and driving forces. The suggested economic growth model depends on different technical advancements to be successful. This model is based on green computing and renewable energy. All three of these goals are at the core of the innovations in the sustainable practices industry. Advanced grid management systems improve the reliability of smart grids by optimizing energy distribution, balancing supply and demand, and using automation in response to real-time data.

3.5 Framework of ANN-based EGM

Figure 4c shows the conceptual framework prediction based on ANN-EGM. The data are taken from the global energy consumption and renewable analytics kaggle dataset [25]. Many articles detail certain elements of using renewable energy for green computing. They point to the industry’s lack of long-term financial stability as a major obstacle to its growth. The role of finance has been crucial to the development of the energy industry. Green computing, which uses renewable energy and energy-efficient technology, may help people and companies save money in the long run. Sustainability in the financial realm is aided by decreased energy use and operational expenses. Due to the shift to renewable power, there will be more openings for those interested in working in renewable energy and allied green technology businesses. Investments in renewable energy infrastructure and technological advancements boost economic development. The evaluation uses measures that reflect the economic maturity in line with international norms, which is the significant driving force for energy. For any treatment to be effective, it must be based on a thorough analysis of the current sustainable development condition and any potential risk factors that may keep the issue from improving. It is found that all nations use two basic decision-making techniques: the first represents the data-driven choice-making process. In contrast, the second illustrates an experience-based decision-making process for effectively predicting limiting and driving forces. The evidence indicates that older data are less likely to choose the approach based on the data. Despite this, the framing effect is only evident among those who use a data-based approach, suggesting that it is more closely linked to selecting a particular course of action. Further, the linear and mathematical have been expressed mathematically, as shown in Figure 5(a). Policies and financial incentives are a part of the proposed economic growth framework to encourage more people and organizations to switch to green energy to power their computing devices. A few instances of such efforts include credits for taxes, government funding, and new rules that mandate the usage of green energy. Green computing and renewable energy-based economic growth models should be intrinsically flexible in light of technological advancements and changes in the renewable energy environment. The proposed model’s longevity and continued relevance depend heavily on its capacity to change and evolve. Improving the dependability of renewable energy sources is highly dependent on the accessibility and effectiveness of energy storage technology. Wind and solar power, for example, are intermittent and dependent on factors like the time of day and weather, in contrast to conventional power production that relies on fossil fuels. Renewable energy production may be unpredictable and unreliable; energy storage technologies can mitigate this problem and provide a more consistent and dependable power source.

From the path diagram, equations (1) and (2) are derived as discussed below:

Figure 5(a) illustrates x t is the input vector, h t − 1 are temporal series of state vectors t and t − 1 , and f w is a non-linear input vector, where w is a variable weight parameter, as shown in equation (1). In this equation, based on the state of vectors, the linear and non-linear data activity has been predicted, which helps to predict the driving forces prominently. The weight factors are calculated based on the data activity in which factors such as technological growth, economic policies, and financial management have been predicted. Further, the renewable energy consumption has been mathematically derived as follows:

In Figure 5(b), y is the actual production inside the country; R , K , and L use renewable energy, real capital, and labour. A shows the country’s planned technological advancements, and e is the error term predicted to behave in a regular, unbiased, and homogeneous fashion. From equation (2), the generation and consumption of renewable energy are discussed in correlation with the economic growth factor for green computing.

ANN-EGM uses the perceptron concept for the effective prediction of limiting and driving factors; perceptron is a network with m of neurons; d is the number of stimuli, and the occurrence y j is the target.

where y j is the input, and w ji is the importance level for each input and result. Activation functions of the threshold type in this design in equation (3). Therefore, the following formula may be used to validate the network’s final results:

where z k is the result, w kj ′ is each processor’s scale, and y j is the message from the shadowy units. The bias is a variance in the input x 0 and y 0 , in which both are equal for the calculation 1 to equation (4). The driving forces are validated based on technological growth, economic policies, and finance management for economic growth in the perceptron layer. An ANN’s activation function may be seen as the collection of transfer functions applied to produce the desired output based on input and feedback, effectively deciding the limiting and driving forces. The new economic growth model for green computing is focused on renewable energy, and its acceptance is influenced by many main forces, including climate change, renewable energy costs, customer preference, and financial support. The increased awareness of the need for sustainable behaviours is reflected in these forces, encompassing economic, environmental, and social disciplines. Renewable energy sources, if implemented, may result in substantial savings over time. Pricing for renewable energy sources like solar and wind have decreased, so they are now competitive with more conventional power plants. Both people and enterprises may achieve lower operating expenses by adopting energy-efficient computing methods. Reduced energy use results in reduced power costs. Renewable energy infrastructure, including solar panels, wind turbines, and similar technologies, might have significant upfront costs that prevent some people and organizations from considering them. Businesses pressed for funds may find it difficult to make the initial investment necessary to purchase energy-efficient equipment and implement sustainable computing practices. Sustainable computing can only progress with the help of public–private partnerships that prioritize renewable energy. This collaboration makes it easier to create, launch, and expand sustainable solutions, which speeds up the shift to greener methods of operation.

4.1 Performance of ANN for 2021 and 2022

Table 1 lists the total amount of energy generation from renewable sources for green computing that has been predicted using ANN for 2021 and 2022 for the industry in Chinese cities. In addition, the cumulative output power is 25.703 kW till 2022, as taken from the global energy consumption and renewable analytics kaggle data set (Saidi & Omri, 2020). The energy production has been shown to cause monthly minimum and maximum values, as given in Table 1

Equation (5) denotes B for the performance ratio of economic growth in l for several ease of use, m for orientation plan formulation of cost, exp σ is the exponential function of time, β is the mathematical function of the human number through the ( m ) ∭ β may lessen the blow of a downturn in the economy ( m exp σ + l ) potential for all renewable sources for people.

4.2 Energy Production Between 2021 and 2022

Figure 6 is a graph depicting the average monthly energy production between 2021 and 2022 based on the energy production premises of China.

Figure 6

Performance of ANN for 2021 and 2022.

The chart includes two different graphics. The y-axis on the left of the bar chart represents the mean speed. However, the middle y-value on the line chart is the average power. In 2021 and 2022, there was a huge increase in energy production. Compared to other existing methods such as DEA-EA, PTRM, FMOLS, DEA-EA, and BPVAR, the proposed EGM-ANN has a higher prediction of the driving forces for energy production, as shown in Figure 6. For green computing projects to be successfully implemented, an energy infrastructure that is durable and secure is essential. The foundational energy infrastructure must be reliable, resilient, and secure if green computing is to succeed in its mission to lessen the environmental effect of information technology (IT).

Equation (6) A to find the mean square error, s for input revision, t for review, tan for the trigonometric function of the development activity, max for maximum value performance outcomes from max 5 s / ∭ t 2 s element strongly connected to economic growth concerns ( tan s ) t 4 increase in energy consumption.

Figure 7 illustrates R-value analysis, which measures how closely one network’s output matches the desired network outcome based on the limiting and driving forces. In this case, the training of the ANN model has been terminated after it passed a maximum validation threshold. Figure 7 illustrates that during the training, validation, and testing phases of ANN design, R equals 1. This is the best result with an R-value of 1 and an MSE of 0, as shown in Figure 7. Further, the graphs show that ANN-EGM equals 1, and existing methods do not equal 1. Hence, the MSE value of the experimental data shows that it must be higher than the MSE value of training data, which is predicted effectively by the ANN-EGM. Encourage governmental and commercial organizations to work together to fund and execute renewable energy initiatives. Private investors may provide Capital and expertise, while the public sector can offer policy support and incentives. Facilitates faster project execution by distributing financial risk and maximizing private sector resources.

Figure 7

Mean square error rate validations.

4.3 Renewable Energy Production Data (2017–2021) and Forecast (2022–2026)

Equation (7) explained ‖ C ‖ for accuracy of renewable energy production in p for the mediator between energy, q for motivation of characteristics, cos for the trigonometric function of instructional strategies, φ is the mathematical function of interaction through the people from p 2 ∑ φ ∫ q capable of meeting the nation’s increasing electrical needs and fostering local economic growth cos t .

Table 1 and Figure 8 illustrate the nation’s population as one of the variables included in this research. Here, the risk-free negative findings and hazardous positive results are reported, even though it has been analyzed using the same historical data to determine the model’s accuracy. It is clear from Table 2 that the green computing framing effect is present in all experimental circumstances. Hence, the proposed ANN-EGM helps to predict energy production and forecast more accurately with the help of ANN. Compared to other existing methods, DEA-EA and BPVAR, the proposed method EGM-ANN is higher in accuracy ratio prediction.

Figure 8

Renewable energy production data (2017–2021) and forecast (2022–2026).

4.4 Prediction Ratio

Equation (8) denotes I for prediction ratio from Q for learning speed in virtual, β is the mathematical function for development and efficiently connecting new production system, log for the logarithmic function in meeting the problems brought on by alternative energy sources, sin for the trigonometric function of computer interaction, δ is the mathematical function of the people from log ∑ Q − ( ∏ Q ) 1 δ 2 control of this new energy system’s energy flows through digital platforms characterized by increasing electricity penetration, in the end, use sin 1 β

Figure 9 measures the prediction ratio of the energy obtained from renewable energy in facilities as a proportion of overall renewable energy for green computing. It facilitates internal trend analysis and external benchmarking by evaluating the ratio. The energy produced from renewables will climb 5% this year and more than 6% in 2022. Despite these high increases, renewables will likely provide roughly half of the projected expansion in global demand in 2021 and 2022. Methods for estimating renewable energy’s future contributions to the world’s energy supply are crucial. The proposed ANN-EGM has a higher prediction ratio than other methods, such as DEA-EA and BPVAR. The computing industry may dramatically lessen its carbon footprint by switching to renewable energy sources like solar, wind, or hydropower to power data centres. These data centres help sustainable development using green computing methods, such as energy-efficient hardware and optimizing cooling systems. The proposed new economic model can potentially encourage novel approaches to software design by facilitating the creation of more energy-efficient algorithms. This significant advance is critical for fostering sustainable application development and decreasing the energy consumption of computing operations. The model must be flexible enough to incorporate cutting-edge technologies like artificial intelligence (AI), blockchain, and edge computing. Computing process optimization, energy efficiency enhancement, and general environmental responsibility are all possible with the help of these technologies.

Figure 9

Prediction ratio.

Therefore, future work discusses creating a brand-new hybrid renewable energy dual-system forecasting with ANN-EGM assistance to validate the performance, accuracy, mean square error rate and prediction results.