Sustainable and reliable design of reverse osmosis desalination with hybrid renewable energy systems through supply chain forecasting using recurrent neural networks

People in the Middle East are facing the problem of freshwater shortages. This problem is more intense for a remote region, which has no access to the power grid. The use of seawater desalination technology integrated with the generated energy unit by renewable energy sources could help overcome this problem. In this study, we refer a seawater reverse osmosis desalination (SWROD) plant with a capacity of 1.5 m 3 /h used on Larak Island, Iran. Moreover, for producing fresh water and meet the load demand of the SWROD plant, three different stand-alone hybrid renewable energy systems (SAHRES), namely wind turbine (WT)/photovoltaic (PV)/battery bank storage (BBS), PV/BBS, and WT/BBS are modeled and investigated. The optimization problem was coded in MATLAB software. Furthermore, the optimized results were obtained by the division algorithm (DA). The DA has been developed to solve the sizing problem of three SAHRES configurations by considering the object function's constraints. These results show that this improved algorithm has been simpler, more precise, faster, and more flexible than a genetic algorithm (GA) in solving problems. Moreover, the minimum total life cycle cost (TLCC = 243 763$), with minimum loss of power supply probability (LPSP = 0%) and maximum reliability, was related to the WT/PV/BBS configuration. WT/PV/BBS is also the best configuration to use less battery as a backup unit (69 units). The batteries in this configuration have a longer life cycle (maximum average of annual battery charge level) than two other configurations (93.86%). Moreover, the optimized results have shown that utilizing the configuration of WT/PV/BBS could lead to attaining a cost-effective and green (without environmental pollution) SAHRES, with high reliability for remote areas, with appropriate potential of wind and solar irradiance.

show abstract

“…Moreover, CC and MC indicate capital and maintenance costs, respectively. 44,45 3.1 | LCC of the PV system…”

Section: Tlcc = CC + Mc + Tc Mr + Tc Chmentioning

confidence: 99%

“…In the above equation, TC CH and TC MR are the cost of the SWROD plant's chemicals and the membrane replacement cost, respectively. Moreover, CC and MC indicate capital and maintenance costs, respectively 44,45 …”

Section: Economic Modelingmentioning

confidence: 99%

Modeling, design, and optimization of a cost‐effective and reliable hybrid renewable energy system integrated with desalination using the division algorithm

et al. 2020

View full text Add to dashboard Cite

show abstract

“…The algorithm was used to find a solution to locate hubs, reactors and condensers to minimise the total costs. Li et al [127] stated that renewable energy systems are constantly affected by weather or climatic conditions (i.e., solar irradiation, wind speed, external temperature). In order to handle the effect of external disturbances on RES systems performance, the dynamic forecasting, as well as energy storage, shall be provided.…”

Section: Core Developmentsmentioning

confidence: 99%

Towards Efficient and Clean Process Integration: Utilisation of Renewable Resources and Energy-Saving Technologies

et al. 2019

View full text Add to dashboard Cite

The strong demand for sustainable energy supplies had escalated the discovery, and intensive research into cleaner energy sources, as well as efficient energy management practices. In the context of the circular economy, the efforts target not only the optimisation of resource utilisation at various stages, but the products’ eco-design is also emphasized to extend their life spans. Based on the concept of comprehensive circular integration, this review discusses the roles of Process Integration approaches, renewable energy sources utilisation and design modifications in addressing the process of energy and exergy efficiency improvement. The primary focus is to enhance the economic and environmental performance through process analysis, modelling and optimisation. The paper is categorised into sections to show the contribution of each aspect clearly, namely: (a) Design and numerical study for innovative energy-efficient technologies; (b) Process Integration—heat and power; (c) Process energy efficiency or emissions analysis; (d) Optimisation of renewable energy resources supply chain. Each section is assessed based on the latest contribution of this journal’s Special Issue from the 21st conference on Process Integration, Modelling and Optimisation for Energy Saving and Pollution Reduction (PRES 2018). The key results are highlighted and summarised within the broader context of the state of the art development.

show abstract

“…Since the remote and rural electrification suffers the unreachability of the grid power, it needs to prompt for different alternative sources of energy in that areas. Thus, a "hybridrenewable-energy system" (HRES) [11], an example is shown in Figure 2, is used to improve electrical power production and to provide electricity in rural areas [12] while hydrogen can be produced by RES as well. A hybrid system can address and overcome the limitations of renewable energy resources with efficiency, reliability, and economics [13].…”

Section: Introductionmentioning

confidence: 99%

Prospective Methodologies in Hybrid Renewable Energy Systems for Energy Prediction Using Artificial Neural Networks

et al. 2021

View full text Add to dashboard Cite

This paper presents a comprehensive review of machine learning (ML) based approaches, especially artificial neural networks (ANNs) in time series data prediction problems. According to literature, around 80% of the world’s total energy demand is supplied either through fuel-based sources such as oil, gas, and coal or through nuclear-based sources. Literature also shows that a shortage of fossil fuels is inevitable and the world will face this problem sooner or later. Moreover, the remote and rural areas that suffer from not being able to reach traditional grid power electricity need alternative sources of energy. A “hybrid-renewable-energy system” (HRES) involving different renewable resources can be used to supply sustainable power in these areas. The uncertain nature of renewable energy resources and the intelligent ability of the neural network approach to process complex time series inputs have inspired the use of ANN methods in renewable energy forecasting. Thus, this study aims to study the different data driven models of ANN approaches that can provide accurate predictions of renewable energy, like solar, wind, or hydro-power generation. Various refinement architectures of neural networks, such as “multi-layer perception” (MLP), “recurrent-neural network” (RNN), and “convolutional-neural network” (CNN), as well as “long-short-term memory” (LSTM) models, have been offered in the applications of renewable energy forecasting. These models are able to perform short-term time-series prediction in renewable energy sources and to use prior information that influences its value in future prediction.

show abstract

Sustainable and reliable design of reverse osmosis desalination with hybrid renewable energy systems through supply chain forecasting using recurrent neural networks

Cited by 86 publications

References 62 publications

Modeling, design, and optimization of a cost‐effective and reliable hybrid renewable energy system integrated with desalination using the division algorithm

Modeling, design, and optimization of a cost‐effective and reliable hybrid renewable energy system integrated with desalination using the division algorithm

Towards Efficient and Clean Process Integration: Utilisation of Renewable Resources and Energy-Saving Technologies

Prospective Methodologies in Hybrid Renewable Energy Systems for Energy Prediction Using Artificial Neural Networks

Contact Info

Product

Resources

About