4.7 Article

Multi criteria decision making with machine-learning based load forecasting methods for techno-economic and environmentally sustainable distributed hybrid energy solution

Related references

Note: Only part of the references are listed.
Article Green & Sustainable Science & Technology

Technically efficient, economic and environmentally benign hybrid decentralized energy solution for an Indian village: Multi criteria decision making approach

Sayan Das et al.

Summary: Decentralized hybrid energy system is considered as a potential sustainable solution for global energy transition. Optimization for better sustainability is complex, involving technical, economic, and environmental issues. A methodology integrating techno-economic optimization, life cycle assessment, and multi criteria decision making approach is demonstrated for a remote Indian village, aiming to achieve technically efficient, economically feasible, and environmentally benign energy solutions.

JOURNAL OF CLEANER PRODUCTION (2023)

Article Green & Sustainable Science & Technology

Short-term electrical load forecasting using hybrid model of manta ray foraging optimization and support vector regression

Siwei Li et al.

Summary: Demand prediction has a crucial role in electricity management and decision-making. Due to the variability in electrical load and the emergence of new renewable energy technologies, power systems face technical challenges. Therefore, short-term forecasting is vital for dispatching commands, managing the spot market, and detecting anomalies. In this study, a hybrid method that optimizes support vector machine parameters using Manta ray foraging optimization is proposed for short-term load forecasting. The proposed method's accuracy is evaluated and compared with five other optimizers. Results from a case study using actual data show that the hybridized technique can address the limitations of single methods, achieving high accuracy for electrical load forecasting.

JOURNAL OF CLEANER PRODUCTION (2023)

Article Computer Science, Artificial Intelligence

Safety assessment of excavation system via TOPSIS-based MCDM modelling in fuzzy environment

Song-Shun Lin et al.

Summary: Excavation construction is a high-risk activity, and accurately identifying and addressing high-risk factors can significantly reduce the likelihood of accidents. This study used the MCDM modelling and TOPSIS method to identify high-risk factors and developed a decision hierarchy based on geotechnical conditions, surrounding environment, construction measurement, and construction and management factors. The results showed that static load, settlement of pipelines, and dynamic load were the top three high-risk factors.

APPLIED SOFT COMPUTING (2023)

Article Thermodynamics

Multi criteria decision making for the most suitable combination of energy resources for a decentralized hybrid energy solution with green hydrogen as the storage option

Sayan Das et al.

Summary: Decentralized hybrid renewable energy systems are becoming possible solutions for remote locations without grid power. Electrochemical storage systems are currently the most common devices used to bridge the gap between demand and supply. An alternative option could be generating hydrogen with excess renewable power, which can then be converted back to electricity with fuel cells. However, the practical feasibility of these options depends on their economic viability and return on investment risks.

ENERGY CONVERSION AND MANAGEMENT (2023)

Article Operations Research & Management Science

Multiple criteria decision making and robust optimization to design a development plan for small and medium-sized enterprises in the east of Iran

Sahar Moazzeni et al.

Summary: This paper focuses on developing small and medium-sized enterprises in South Khorasan, Iran through a combination of multiple criteria decision making and robust multi-objective optimization. The study prioritizes industrial clusters and optimally assigns governmental funds based on weighted evaluation criteria and robust multi-objective mathematical programming. Results show that international market share attraction is the most important criterion and the age of the cluster is the least important criterion in the development of industrial clusters. The proposed methodology successfully aids decision makers in planning funding for industrial clusters.

OPERATIONAL RESEARCH (2023)

Article Construction & Building Technology

Ultra-short term power load forecasting based on CEEMDAN-SE and LSTM neural network

Ke Li et al.

Summary: This article introduces a CEEMDAN-1SE-LSTM model based on time series decomposition-reconstruction modeling and neural network forecasting, which is used to predict ultra-short-term power load in Changsha, China. The study found that the model has significantly better prediction accuracy compared to other models, providing support for ultra-short-term power dispatching in Changsha and serving as a reference for developing short-term and ultra-short-term power load forecasting models in other cities.

ENERGY AND BUILDINGS (2023)

Article Thermodynamics

MCDM for simultaneous optimum economy, investment risk and environmental impact for distributed renewable power: Demonstration with an Indian village data

Sayan Das et al.

Summary: Increasing the share of renewable energy in power supply is a global priority, especially in remote areas where reliable grid power is not available. However, issues such as limited availability of local renewable resources, high unit electricity cost, and investors' uncertainty in return on investment pose challenges. This study aims to find technically efficient, economically optimal, and environmentally friendly energy combinations for distributed generation, using a comprehensive analysis that integrates techno-economic optimization, uncertainty analysis, and environmental impact assessment. The analysis results suggest that a solar photovoltaic-diesel generator-battery system combination is the possible optimum solution, with a cost of electricity of $0.21/kW.h, a standard deviation of 0.07 for investment risk, and moderate environmental impact.

ENERGY CONVERSION AND MANAGEMENT (2023)

Article Thermodynamics

Optimization and techno-economic analysis of a solar photo-voltaic/biomass/diesel/battery hybrid off-grid power generation system for rural remote electrification in eastern India

Pankaj Kumar et al.

Summary: This study presents a case study on powering energy poor remote rural communities in Eastern India using locally available solar, biomass, and diesel energy resources. The optimized system architecture is identified using the Hybrid Optimization Model for Electric Renewables tool. The study finds that the selected low-cost optimized hybrid configuration significantly reduces the cost of electricity and improves system economics, while also reducing emissions. The use of solar energy resource in the optimal system modeling provides substantial return on investment and internal rate of return.

ENERGY (2022)

Article Computer Science, Artificial Intelligence

Short-term electrical load forecasting through heuristic configuration of regularized deep neural network

Ashraful Haque et al.

Summary: This paper presents a method for short-term commercial building electrical load forecasting using a regularized deep neural network. Through detailed analysis and validation, the method demonstrates superior performance in load forecasting.

APPLIED SOFT COMPUTING (2022)

Article Green & Sustainable Science & Technology

Comparative analysis of storage modules under different dispatch strategies for an optimum decentralized hybrid energy solution: a case study of a remote Indian village

Sayan Das et al.

Summary: India, with a large poor population, faces challenges in supplying centralized grid power to remote villages due to adverse topography and poor economic conditions. A decentralized energy combination using locally available resources proves to be a more sustainable solution. The cost and environmental impact of storage devices and dispatch strategies play a significant role in the economy of such a hybrid system. This study analyzes the techno-economic factors of five storage devices and their dispatch strategies, highlighting the benefits of zinc bromide batteries.

CLEAN TECHNOLOGIES AND ENVIRONMENTAL POLICY (2022)

Article Thermodynamics

Meta-ANN e A dynamic artificial neural network refined by meta- learning for Short-Term Load Forecasting

Xun Xiao et al.

Summary: In this paper, a dynamic Artificial Neural Network (ANN) model called Meta-ANN is developed to forecast the short-term grid load. The model uses a base module trained on historical data to learn the long-term trend and seasonality of the grid load, and integrates an error-correction module to capture the nonstationary pattern of the grid load. The experimental results show that Meta-ANN can make more accurate predictions by effectively capturing the nonstationary pattern in grid loads.

ENERGY (2022)

Article Green & Sustainable Science & Technology

A PV-Biomass off-grid hybrid renewable energy system (HRES) for rural electrification: Design, optimization and techno-economic-environmental analysis

Raman Kumar et al.

Summary: This research examines the techno-economic-environmental viability of using photovoltaic and biomass energy in a rural village in Punjab, India. The study found that under optimal conditions, 35.6% of the necessary electricity can be generated from photovoltaic power, while 64.4% can be generated from biomass power.

JOURNAL OF CLEANER PRODUCTION (2022)

Article Automation & Control Systems

A Novel Reinforced Deep RNN-LSTM Algorithm: Energy Management Forecasting Case Study

Xia Fang et al.

Summary: This article introduces a new hybrid deep learning algorithm for a computer-assisted energy management system. The suggested deep neural network optimizes the model through processing gathered AMI data and achieves better prediction results in real-time data.

IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS (2022)

Article Engineering, Electrical & Electronic

Deep learning based short term load forecasting with hybrid feature selection*

Siva Sankari Subbiah et al.

Summary: This paper proposes a deep learning-based Long Short Term Memory (LSTM) model with hybrid feature selection to improve the accuracy of short term load forecasting. Experimental results show that the proposed model outperforms other models.

ELECTRIC POWER SYSTEMS RESEARCH (2022)

Article Thermodynamics

Techno-economic and feasibility assessment of standalone solar Photovoltaic/Wind hybrid energy system for various storage techniques and different rural locations in India

Faizan A. Khan et al.

Summary: This study investigated an economical hybrid solution to find the best storage technology in remote areas of India to meet residential community load. Lead-Acid Flow based technology was found most suitable, with the optimized hybrid arrangement showing lower costs and higher renewable fraction.

ENERGY CONVERSION AND MANAGEMENT (2022)

Article Green & Sustainable Science & Technology

Remarkable dynamic adsorption of Hg2+ ions on the magnetic MOF nanocomposite (CuNi-BTC@Fe3O4): Experimental and modeling using GA plus CFD plus ANFIS method

Amin Sokhansanj et al.

Summary: A magnetic bimetallic metal-organic framework (MOF) nanocomposite was synthesized for the removal of mercury ions in a fixed bed column. The physico-chemical properties of the synthesized sample were characterized using various analytical techniques. The performance of the adsorption column was evaluated under different operating conditions, and the Langmuir model was used to fit the equilibrium data. Commercial models and a combination model were investigated to determine the adsorption behavior of Hg (II) in the column. The combination model, which combined unsteady computational fluid dynamics, adaptive neuro-fuzzy inference, and genetic algorithm, was developed to simulate the dynamic adsorption process. The validation results showed a good agreement between the experimental data and the output of the combination model.

JOURNAL OF CLEANER PRODUCTION (2022)

Article Energy & Fuels

Modelling and techno-economic analysis of standalone SPV/Wind hybrid renewable energy system with lead-acid battery technology for rural applications

Faizan A. Khan et al.

Summary: This study discusses an enhanced optimal solution for electrifying an individual rural consumer in a northern Indian village. The study considers techno-economic and socio-environmental parameters for optimization and sizing assessment. Real-time market-based design variables are utilized, and renewable resources are assessed using the PDAV tool from NASA linked to the HOMER-Pro software. A stand-alone hybrid renewable energy system is designed to meet the domestic load and peak demand of the consumer. Comparative analysis shows that a stand-alone solar photovoltaic and wind energy hybrid system is suitable. The study also analyzes the employment creation and environmental effects of the renewable energy system.

JOURNAL OF ENERGY STORAGE (2022)

Article Thermodynamics

Optimal techno-economic design of hybrid PV/wind system comprising battery energy storage: Case study for a remote area

D. Emad et al.

Summary: This study proposes a generalized mathematical model to optimize PV/wind/battery systems for remote areas, considering the challenges of energy cost and intermittent renewable energy sources. Utilizing the grey wolf optimizer (GWO), the research achieves optimal solutions with a 17% reduction in energy cost. The GWO shows better convergence trends and statistical measures compared to other meta-heuristic algorithms like PSO.

ENERGY CONVERSION AND MANAGEMENT (2021)

Article Engineering, Multidisciplinary

The Arithmetic Optimization Algorithm

Laith Abualigah et al.

Summary: The Arithmetic Optimization Algorithm (AOA) is a new meta-heuristic method that makes use of the distribution behavior of arithmetic operators, demonstrating promising results in solving challenging optimization problems across various search spaces.

COMPUTER METHODS IN APPLIED MECHANICS AND ENGINEERING (2021)

Article Multidisciplinary Sciences

Electric Load Forecasting based on Wavelet Transform and Random Forest

Li-Ling Peng et al.

Summary: A method based on wavelet transform and random forest is proposed to address the problem of strong randomness and low forecasting accuracy in short-term electric load forecasting. By removing noise and decomposing data into characteristic variables, the method improves forecasting accuracy and reliability significantly.

ADVANCED THEORY AND SIMULATIONS (2021)

Article Thermodynamics

Optimal selection and management of hybrid renewable energy System: Neom city as a case study

Tareq Salameh et al.

Summary: This study analyzed and optimized nine case studies for hybrid energy systems using various decision-making techniques to determine the best HES based on economic, environmental, and social assessments. The results indicated that the case study with solar PV, DG, and battery energy storage was the most economically, environmentally, and socially favorable option.

ENERGY CONVERSION AND MANAGEMENT (2021)

Article Energy & Fuels

Techno-economic analysis of solar photo-voltaic/diesel generator hybrid system using different energy storage technologies for isolated islands of India

Pankaj Kumar et al.

Summary: This paper investigates the techno-economic performance of solar photo-voltaic/diesel generator hybrid systems using different battery energy storage technologies in the isolated islands of Andaman & Nicobar and Lakshadweep in India. The analysis shows that the ZBF technology is the most effective, with the highest return of investment and renewable penetration, along with the lowest simple payback period and pollutant emissions. The SPV/DG/ZBF hybrid system is found to be the most techno-economically viable optimized solution for both locations.

JOURNAL OF ENERGY STORAGE (2021)

Article Computer Science, Information Systems

Multi-Convolution Feature Extraction and Recurrent Neural Network Dependent Model for Short-Term Load Forecasting

Hui Hwang Goh et al.

Summary: A hybrid deep learning model combining 1D-CNN and LSTM is proposed for load forecasting accuracy improvement. The model, referred to as MCNN-LSTM, outperformed the widely used CNN-LSTM hybrid model in both single-step and multi-step load forecasting.

IEEE ACCESS (2021)

Article Computer Science, Information Systems

Household-Level Energy Forecasting in Smart Buildings Using a Novel Hybrid Deep Learning Model

Dabeeruddin Syed et al.

Summary: Forecasting energy consumption in smart buildings is crucial for smart grid energy management. A hybrid deep learning model is proposed in this paper, which outperforms commonly used hybrid models in terms of accuracy. Through data cleaning and model building stages, the proposed model captures temporal dependencies effectively and improves forecasting accuracy.

IEEE ACCESS (2021)

Article Engineering, Electrical & Electronic

A proposed intelligent short-term load forecasting hybrid models of ANN, WNN and KF based on clustering techniques for smart grid

Hamed H. H. Aly

ELECTRIC POWER SYSTEMS RESEARCH (2020)

Article Green & Sustainable Science & Technology

Distributed polygeneration using local resources for an Indian village: multiobjective optimization using metaheuristic algorithm

Avishek Ray et al.

CLEAN TECHNOLOGIES AND ENVIRONMENTAL POLICY (2018)

Article Engineering, Environmental

The ecoinvent database version 3 (part I): overview and methodology

Gregor Wernet et al.

INTERNATIONAL JOURNAL OF LIFE CYCLE ASSESSMENT (2016)

Article Green & Sustainable Science & Technology

Assessment of socioeconomic impacts of access to electricity in Brazilian Amazon: case study in two communities in Mamiraua Reserve

L. Roberto Valer et al.

ENERGY FOR SUSTAINABLE DEVELOPMENT (2014)

Article Green & Sustainable Science & Technology

Comparative life cycle energy, emission, and economic analysis of 100 kW nameplate wind power generation

Md Ruhul Kabir et al.

RENEWABLE ENERGY (2012)