Optimize Energy Use Research Articles

Cathode Position Detection in a Transferred Arc Plasma Using Artificial Neural Network

In a transferred arc plasma system, the position of the cathode is difficult to detect during the smelting process as it remains inside the cylindrical anode. Real-time and accurate cathode position detection leads to efficient smelting operation with optimal use of electrical energy. In this article, a machine learning technique is proposed to accurately detect the position of the cathode in a direct current (DC) transferred arc plasma system. The measured voltage signal sampled at 20 kHz is processed using a tunable Q-factor wavelet transform (TQWT) followed by statistical features extraction and a machine learning algorithm to provide accurate cathode position information. Two different machine learning algorithms are used in this work, namely, single hidden layer neural network (SHLNN) and single-layer extreme learning machine (SELM). The output of these machine learning algorithms provides accurate position information and is also compared to the traditional voltage-related position information. The experimental signal of a 30-kW DC plasma system and cathode position detection results is shown.

A Systematic Study on Reinforcement Learning Based Applications

We have analyzed 127 publications for this review paper, which discuss applications of Reinforcement Learning (RL) in marketing, robotics, gaming, automated cars, natural language processing (NLP), internet of things security, recommendation systems, finance, and energy management. The optimization of energy use is critical in today’s environment. We mainly focus on the RL application for energy management. Traditional rule-based systems have a set of predefined rules. As a result, they may become rigid and unable to adjust to changing situations or unforeseen events. RL can overcome these drawbacks. RL learns by exploring the environment randomly and based on experience, it continues to expand its knowledge. Many researchers are working on RL-based energy management systems (EMS). RL is utilized in energy applications such as optimizing energy use in smart buildings, hybrid automobiles, smart grids, and managing renewable energy resources. RL-based energy management in renewable energy contributes to achieving net zero carbon emissions and a sustainable environment. In the context of energy management technology, RL can be utilized to optimize the regulation of energy systems, such as building heating, ventilation, and air conditioning (HVAC) systems, to reduce energy consumption while maintaining a comfortable atmosphere. EMS can be accomplished by teaching an RL agent to make judgments based on sensor data, such as temperature and occupancy, to modify the HVAC system settings. RL has proven beneficial in lowering energy usage in buildings and is an active research area in smart buildings. RL can be used to optimize energy management in hybrid electric vehicles (HEVs) by learning an optimal control policy to maximize battery life and fuel efficiency. RL has acquired a remarkable position in robotics, automated cars, and gaming applications. The majority of security-related applications operate in a simulated environment. The RL-based recommender systems provide good suggestions accuracy and diversity. This article assists the novice in comprehending the foundations of reinforcement learning and its applications.

A comparison of prediction and forecasting artificial intelligence models to estimate the future energy demand in a district heating system

Forecasting the short-term future energy demand in buildings and districts is a vital component towards the optimization of energy use and consequently the reduction in greenhouse gas emissions. This paper explores artificial intelligence approaches applied to estimate the future heating load in a district heating system. A distinction is made within thisd work between a prediction and forecasting based approach; a comparison is then accomplished by applying each method with prominent Machine Learning and Deep Learning based algorithms to estimate the future heating demand over 6 h and 24 h ahead. This analysis used available data from a Canadian district heating system in Quebec and actual weather forecasts obtained from Canadian meteorological services. All models within this work applied a grid search in order to calibrate their respective hyperparameters. Results of this work indicated that the prediction-based approach (with forecasted inputs) obtained a higher accuracy than the forecasting approach. All the machine learning models obtained good accuracy with errors not exceeding 16% CV(RMSE) and closer to 10% CV(RMSE) for the top performing models. Furthermore, the LSTM and XGBoost were consistently among the top performing algorithms and provided good performance over a variety of hyperparameters. The biggest difference between the two algorithms was the computational times; it was observed that the XGBoost was significantly faster to train.

Investigating the impact of variable energy prices and renewable generation on the annualized cost of hydrogen

Hydrogen can be produced from onsite renewable energy, energy from the power grid, or a combination of both. While the cost of grid energy is driven by the energy prices, onsite renewable investments are driven by the levelized cost of renewable energy. Energy prices can widely vary in time and in different locations, potentially having a large impact on the annualized cost of hydrogen (ACOH). Renewable sources can also vary significantly for different locations and seasons. In this paper, we develop a semi-empirical model to find key ACOH locational drivers and trends. The model finds the optimal capacity of the onsite solar and wind generators and the electrolyzer, together with the optimal use of grid energy. We found that an optimal balance between onsite renewable investments and grid energy use is strongly driven by the type of energy price (fixed or variable) and location.

Development of electric load prediction techniques for rajasthan region and suggestive measures for optimum use of energy using multi-objective optimization

• Electric load forecasting has a major impact on the efficiency of the power network. • Using the MOO model, this research proposed a new electric load prediction technique. • The attributes of historical records were first summarized using an EMI technique. • The GRNN is then employed to forecast the electric load in the forecasting module. • To fine-tune the hyperparameters, a fuzzy based GEO strategy is used. The effectiveness of the power network system's activities and financial gains are significantly impacted by electric load forecasting. This domain offers a wide range of capacity prediction models to improve prediction performance; nonetheless, precise forecasting models are required. Therefore, this research proposed novel Electric Load Prediction Techniques for Rajasthan Region and Suggestive Measures for Optimal Energy using the Multi-Objective Optimization model. Specifically, data preparation, a subset of features component, a training prediction subsystem, and a management system that helps make up our integrative system. An enhanced mutual information technique was first used to summarize historical records qualities. Then, the Generalized Recursive Neural Network (GRNN) is used to predict the electric load values in the training and forecasting module. Furthermore, a Fuzzy based Golden eagle optimization approach is employed to fine-tune the mode's hyper parameters. Moreover, the proposed model's MAPE is lower when compared to the benchmark models. Our UMI-based model has a reduced MAPE error of 0.4920%, which enhances prediction performance by minimizing error. The research findings indicate that the constructed approach can be applied as a technique for electrical grid programming and has considerable advantages over most specific products.

Aplikačné možnosti HCCI technológie

This text describes the current state of the art of HCCI technology, which is based on combining the characteristics of a petrol and diesel engine. HCCI engines offer higher fuel efficiency and lower nitrogen oxide emissions. However, they also have disadvantages such as limited load range, control complexity and cold weather starting problems. The next section of the text discusses hybrid propulsion, which uses a combination of an internal combustion engine and an electric motor. It describes the different types of hybrid powertrains such as soft hybrids, plug-in hybrids and full hybrids. Explains their advantages and possible applications. A solution is then proposed where the HCCI engine would serve as a generator in a series hybrid vehicle with an electric motor. Such an arrangement allows optimization of energy use and reduction of emissions. Finally, the relevance of HCCI technology for improving the efficiency of fuel engines and hybrid vehicle design is evaluated.

Experimental investigation of heat transfer performance of Al2O3 nanofluids in a compact plate heat exchanger

• Heat transfer of Al2O3 nanofluids in compact plate heat exchanger is investigated. • Stability of Al2O3 nanofluids is evaluated. • Thermophysical properties of Al2O3 nanofluids are characterized. • Energy performance and heat transfer enhancement are demonstrated. • Al2O3 nanofluids showed great promises for applications in thermal management systems. This study experimentally investigates the performance of a compact gasketed plate heat exchanger (PHE) employing Al 2 O 3 nanofluids prepared for several low concentrations of Al 2 O 3 (0.01, 0.05, 0.10, 0.15 and 0.20 vol.%) and base fluids of distilled water (DW) and its mixture with ethylene glycol (15% and 30% of EG) for several flow rates (0.03-0.093 l/s). The main thermophysical properties of those nanofluid samples were experimentally measured. The prepared nanofluids samples showed a Newtonian rheological behaviour and an increase in viscosity up to 7.5% for 0.2 vol.%. The enhancements in the thermal conductivity were significant and the values were 7.3 %, 8.4% and 9.1% for Al 2 O 3 nanofluids at 0.2 vol.% compared to the base fluids DW, 15% EG and 30% EG, respectively. A newly developed experimental setup is used to operate the nanofluids through the PHE under particular conditions for heating purposes (mainly high temperature), and their performance is evaluated in comparison with the conventional heat transfer fluids (the base fluids). Nusselt number, pressure drop, and energy efficiency factor were determined for the nanofluids and base fluids. The results indicated a heat transfer enhancement with the increase of the particles’ concentration reached the maximum value of 27% at 0.2 vol.% for DW based Al 2 O 3 nanofluid and was accompanied by an increase in pressure drop of 8%. The heat transfer enhancement became lower with the increase of the EG percentage such as 19.1% at 0.2 vol.% for 30% of EG based Al 2 O 3 nanofluid based. In addition, the energy efficiency factor increased by the addition of Al 2 O 3 nanoparticles to the base fluids and with the increase of flow rates up to the value of 1.3 at the highest particles concentrations. This work provides an important step concerning the performance of particular design of Al 2 O 3 nanofluids and operation conditions in compact PHEs on the road to the development of thermal management systems under the current industry’s trends for optimizing energy use and minimizing equipment.

A generic algorithm-based application for pinch-exergy prediction in process industries: A case study

In the industrial sector, efficient production and optimal use of thermal energy are primary concerns for managers and engineers. Considerable research has been devoted to improving and promoting thermal energy efficiency, especially energy recovery in the context of sustainability. Pinch analysis is one of the most powerful methods in this regard. To maximise the energy recovery (MER), the pinch method is well-established in designing an optimal heat exchange network (HEN). Exergy analysis is combined with the pinch method to minimise the work potential loss (exergy loss) while ensuring maximum heat recovery. This study presents a generic algorithm built using Python language to predict and quantify energy and exergy targets in industrial processes. It provides a framework to guide experts and planners in efficiently using the combined analysis tools. The generic algorithm is based on advanced numerical and graphical tools. It provides exergy problem table algorithm (Ex–PTA) and grand composite curve (EHR and HRP) tools. For Δ T min = 10°C, the generic algorithm is implemented in a building complex case study. The energy targets for heating and cooling requirements are 316.2625 kW and 0 kW, respectively. The obtained exergy targets are less attractive given an improvement from advanced utility integration; this is due to the treated system (medium-temperature system) and not to the reliability and efficiency of the generic algorithm. To evaluate the generic algorithm calculations, they are executed in a low-temperature process in which pinch exergy analysis (PExA) has already been performed. The simulated and generated results are identical, demonstrating the reliability and effectiveness of the developed generic algorithm.

Bim-based energy analysis and optimization using insight 360 (case study)

Building information modeling (BIM) is a modern data information platform and management tool that promotes the development of green buildings. In Pakistan, the building sector consumes more than 50 % of total energy consumption and it is growing at annual rates of 4.7 % and 2.5 % in household and commercial sectors, respectively. The energy problem is the biggest single economic drag on Pakistan, the Pakistan BIM Council (PBC) is attempting to implement BIM adoption in the construction industry. Using Autodesk Insight 360 and Green Building Studio, an energy analysis and optimization case study of A-Block COMSATS Abbottabad, Pakistan is chosen. This study explores the energy performance of an academic building as a case study in order to optimize energy use by rotating the building 360 degrees at 45-degree intervals and utilizing BIM to install energy-efficient construction materials. Existing academic buildings have lower energy use and annual cost savings. The annual energy and financial savings are 585.10 kWh and 550 $, respectively. Applying factors to energy analysis can result in improved conceptual design with good environmental effectiveness, thus assisting in the pursuit of environmental sustainability.

Distributed cyber-physical systems that enhance local-based frugal innovation toward a sustainable built environment

The paper debates the comparison between centralized cyber-physical systems and distributed cyber-physical systems (CPS). Centralized CPS implies a system where a single player standardizes data format and protocol together with core services. Distributed CPS implies a system where varieties of digitalization systems by multiple vendors are interconnected to adapt to specific local contexts. Then the paper identifies that distributed CPS has practical advantages over centralized CPS. However, distributed CPS has potential disadvantages that threaten interconnectivity among digitalization systems by multiple vendors. The paper illustrates how such fragmentation could be avoided; it presents how interoperable linkage among multiple systems is realized. IoT-Hub, a sort of data conversion system, is an enabler of interoperability. The paper illustrates the framework of distributed CPS. That comprises several layers that could be managed autonomously by independent players regardless of activities in other layers. The paper exemplifies local-based frugal innovation by such distributed CPS. One example is IoT-based proactive energy demand control system. The system is composed of sensing systems, component systems and application software. The distributed CSP that deploys IoT-Hub enables adaptable coordination of building elements and digitalized systems respecting local specific contexts. In such a way, distributed CPS provides a comfortable indoor climate with optimized energy use. The other example is IoT-based inventory system for building materials. The system is composed of manufacturing process monitoring systems and logistics monitoring systems. The integrated system could provide reportable and verifiable inventory data of building materials. The system can facilitate responsible use of building materials by providing inventory data that is a piece of essential information for environmental declaration. Exemplified cases suggest how distributed CPS strategy has the potential to encourage a broad range of entrepreneurs to commit to frugal innovation toward a sustainable built environment.

Research on the evaluation of distributed integrated energy system using improved analytic hierarchy process-information entropy method

ABSTRACT Comprehensive performance evaluation is a fundamental part of the design and operation optimization of distributed integrated energy systems (IES), and the evaluation is currently focused on three types of elements: economic, energy efficiency and environmental protection. In this paper, energy use quality elements are proposed from the high energy supply requirements of users for distributed IES and characterized by the supply-demand imbalance rate indicator. Then the Analytic Hierarchy Process (AHP) and the information entropy method are combined to form a combined evaluation method by weighing the subjective and objective methods. The comprehensive performance evaluation of distributed IES with nine indicators considering four elements of economy, energy efficiency, environmental protection and energy use quality is realized. The feasibility and validity of the proposed indicators and the difference between the proposed combination method and the existing combination method are verified by the calculation examples. In the single-objective optimization with optimal energy use quality, the supply-demand imbalance rates for heat and cold are −0.05 and −0.035, respectively, which are the best among the five optimization schemes and fully guarantee the stability and quality of energy supply. However, its CO2 emission of 5738.91 (t/year) shows that this indicator is not suitable for the limitation of single-objective optimization, and it would be more suitable for comprehensive optimization with the above three indicators. The weights of operation cost, heat and cold supply-demand imbalance in the AHP method are 0.2247,0.0539,0.0539. The corresponding weights in the information entropy method are 0.0930,0.1670,0.1864. The corrected values are 0.1999, 0.0861, 0.0961. The results show the corrective effect of the information entropy method on the AHP. In addition, the combination method proposed in this paper corrects the configuration cost term to 0.2032, which is larger than both 0.1588 in the AHP method and 0.1388 in the information entropy method, highlighting the difference from existing combination methods. The above data show that the comprehensive evaluation by the AHP-information entropy method can effectively consider the four elements’ role. It provides a new idea for the research on the impact of distributed IES energy storage on the energy use quality of the system and the construction and operation optimization of the comprehensive performance evaluation indicator of the system.

Energy, exergy and cost analysis of flour production from wheat in Nigeria: Case study of Nigeria Eagle Flour mills, Ibadan

The significant increase in energy costs has generally contributed to an increase in the cost of production, flour production inclusive. In manufacturing industries, efforts are being made towards the reduction of the cost of energy consumed during production. This study was therefore designed to evaluate the energy requirements, operation costs, exergy losses, and propose methods for optimizing energy use in wheat flour production, using Nigeria Eagle Flour Mill, Ibadan as a case study. Analysis was carried out in three phases, pre-analysis, data collection and detailed analysis phases. A walk-through process analysis method was used for data collection and a model containing the mass, energy, and exergy balance equations were built in Microsoft Excel® 2010 to analyse data collected. Electrical energy was found to be the most used energy in both mills and the milling process was the most energy intensive in flour production, accounting for an average energy intensity of 187.49MJ/ton in Mill A and 280.37MJ/ton in Mill B. Lighting was observed to consume approximately 7% of the electrical energy supplied, prompting a lighting analysis to highlight potential energy savings. The energy cost per ton was found to be the lowest (4404naira/ton) when electrical energy from the gas plant accounted for 77 per-cent of energy input. The mill's overall irreversibility and exergetic efficiency were calculated to be 404.942KW and 15.74 percent, respectively. Only 16% of the total exergy input into the flour mill exited through product streams, 1% through waste streams, and 83% was destroyed due to irreversibilities. The B1/B2 rolling bench destroyed the most exergy, accounting for approximately 8.53 percent of the mill's irreversibility. It was established that the components with the highest waste streams had the highest irreversibilities. Minimizing waste streams would reduce the amount of exergy lost and increase the exergetic efficiency of components. To improve system efficiency, several process optimization and machine modifications were recommended.

Feeding habits influence species habitat associations at the landscape scale in a diverse clade of Neotropical fishes

AbstractAimA primary goal of community ecology is to understand the mechanisms that drive species' spatial distribution and habitat associations. Species' geographic distribution can be influenced by the distribution of their prey partly because consumers' behaviour is oriented to optimal energy use during foraging. We analysed how differences in dietary preferences influence the spatial distribution and habitat associations of species at the landscape scale. We hypothesized that differences in feeding guilds will lead to divergent habitat association patterns among species.LocationAmazon River drainage basin.TaxonCharaciform fishes in the family Serrasalmidae (piranhas and pacus).MethodsWe used diet data to classify species into feeding guilds (frugivores, herbivores, piscivores, fin and scale feeders and planktivores). We used three proxies of habitat association derived from satellite products: floodplain extent, landscape heterogeneity and flood duration, in three distance buffers. We implemented phylogenetic generalized least squares models to evaluate the relationship between habitat association and feeding guilds.ResultsFrugivores, piscivores and fin and scale feeders presented similar patterns of habitat associations, with frugivores occupying wider areas of floodplain and greater landscape heterogeneity. Herbivores and planktivores were associated with smaller floodplain extents and lower landscape heterogeneity. All feeding guilds were associated with similar levels of flood duration.Main conclusionsDifferences in resource distribution (assessed through feeding guilds) can influence habitat association. Considering the hydrological variability (i.e. floodplain extent) and landscape heterogeneity that characterize floodplains, the patterns of habitat association vary with the spatial scale considered. This work highlights the importance of understanding species habitat associations by fish as well as food resource dynamics and floodplain dependence. This realization is critical for assessing the impact of anthropogenic activities on freshwater ecosystems.

Comprehensive assessment for optimal wind energy use in cottage construction

Comprehensive assessment for optimal wind energy use in cottage construction

Dataflow Driven Partitioning of Machine Learning Applications for Optimal Energy Use in Batteryless Systems

Sensing systems powered by energy harvesting have traditionally been designed to tolerate long periods without energy. As the Internet of Things (IoT) evolves toward a more transient and opportunistic execution paradigm, reducing energy storage costs will be key for its economic and ecologic viability. However, decreasing energy storage in harvesting systems introduces reliability issues. Transducers only produce intermittent energy at low voltage and current levels, making guaranteed task completion a challenge. Existing ad hoc methods overcome this by buffering enough energy either for single tasks, incurring large data-retention overheads, or for one full application cycle, requiring a large energy buffer. We present Julienning : an automated method for optimizing the total energy cost of batteryless applications. Using a custom specification model, developers can describe transient applications as a set of atomically executed kernels with explicit data dependencies. Our optimization flow can partition data- and energy-intensive applications into multiple execution cycles with bounded energy consumption. By leveraging interkernel data dependencies, these energy-bounded execution cycles minimize the number of system activations and nonvolatile data transfers, and thus the total energy overhead. We validate our methodology with two batteryless cameras running energy-intensive machine learning applications. Using a solar testbed, we replay real-world illuminance traces to experimentally demonstrate optimized batteryless execution with a transducer-to-application energy efficiency of 74.5%. Partitioning results demonstrate that compared to ad hoc solutions, our method can reduce the required energy storage by over 94% while only incurring a 0.12% energy overhead.

Influential Article Review - Maximizing Smart Home Energy Management With Geodesic Acceleration and LevMar

This paper examines using artificial neural networks to optimize energy management in smart homes. We present insights from a highly influential paper. Here are the highlights from this paper: Home energy optimization is increasing in research interest as smart technologies in appliances and other home devices are increasing in popularity, particularly as manufacturers move to produce appliances and devices which work in conjunction with the Internet. Home energy optimization has the potential to reduce energy consumption through “smart energy management” of appliances. Information and communications technologies (ICTs) help achieve energy savings with the goal of reducing greenhouse gas emissions and attaining effective environmental protection in several contexts including electricity generation and distribution. This “smart energy management” is utilized at the residential customer level through “smart homes.” This paper compares two artificial neural networks (ANN) used to support home energy management (HEM) systems based on Bluetooth low energy, called BluHEMS. The purpose of the algorithms is to optimize energy use in a typical residential home. The first ANN uses the Levenberg￾Marquardt algorithm and the second uses the Levenberg-Marquardt algorithm enhanced by a second order correction known as geodesic acceleration. For our overseas readers, we then present the insights from this paper in Spanish, French and German.

Dynamic fuel cell model improvement based on macroscopic energy representation

<p><span lang="EN-GB">In this paper, a new dynamic model is presented of the proton exchange membrane fuel cell (PEMFC), using energetic macroscopic representation (EMR). This model is developed for electric automotive applications, powered by a hybrid energy storage system (HESS). The PEMFC can be used as a primary source, the supercapacitors (SC) and/or batteries are the secondary sources. The model design enables the optimization of energy use and the reduction of equipment costs, by involving the fuel cell (FC) in the transient regimes. This model takes into consideration dynamic phenomena, such as double layer capacitance, charge transfer, energy losses caused by the propagation fuel and oxidant delay. The new developed model has been tested and validated using BAHIA bench of HELION/AREVA.</span></p>

Energy Consumption Prediction for Fused Deposition Modelling 3D Printing Using Machine Learning

Additive manufacturing (AM) technologies are growing more and more in the manufacturing industry; the increase in world energy consumption encourages the quantification and optimization of energy use in additive manufacturing processes. Orientation of the part to be printed is very important for reducing energy consumption. Our work focuses on defining the most appropriate direction for minimizing energy consumption. In this paper, twelve machine learning (ML) algorithms are applied to model energy consumption in the fused deposition modelling (FDM) process using a database of the FDM 3D printing of isovolumetric mechanical components. The adequate predicted model was selected using four performance criteria: mean absolute error (MAE), root mean squared error (RMSE), R-squared (R2), and explained variance score (EVS). It was clearly seen that the Gaussian process regressor (GPR) model estimates the energy consumption in FDM process with high accuracy: R2 > 99%, EVS > 99%, MAE < 3.89, and RMSE < 5.8.

Internet of Things (IoT) adoption challenges in renewable energy: A case study from a developing economy

Digitalization of Renewable Energy (RE) systems will play a decisive role in integrating clean energy sources and optimizing energy use. While energy digitalization is mainly governed by technological progress, the societal acceptance of such emerging technologies is essential for a successful energy transition. This study aims to identify critical challenges to IoT-enabled renewable energy use through the lens of the consumers. It attempts to analyze the challenges to implementing IoT effectively in emerging economies like India. The present study employs Exploratory Factor Analysis (EFA) to classify 16 critical challenges into five main dimensions, using the responses obtained from 95 participants. Subsequently, the fuzzy decision-making trial and evaluation laboratory (DEMATEL) prioritizes the identified challenges and organizes them into cause-and-effect groups based on their interactions. The findings indicate that technological challenges constitute the most critical cause barrier that affects other category barriers. Besides technology, challenges reflecting the social infrastructure have emerged prominently in this study. Thereafter, the analysis suggests that modifications to the structure, procedures, and technology are required to create capabilities and enhance the compatibility of IoT with RE applications. Further, proactive governance and reorienting market design are highlighted to foster emerging technologies and develop a robust regulatory framework. The insights from this study are pertinent for policymakers, regulatory bodies, and practitioners seeking to capitalize on the immense potential of this sector and expedite energy transactivity.

ASSESSING LAND SURFACE TEMPERATURE IN URBAN AREAS USING OPEN-SOURCE GEOSPATIAL TOOLS

Abstract. Land surface temperature (LST) in urban areas can be traditionally observed by thermal remote sensors. The increasing availability of 3D city models provides an alternative approach based on geospatial modeling. Using solar radiation tools and scripting in GRASS GIS, we have developed a physically-based LST model that can be used to estimate LST in urban areas represented by vector 3D city models. It uses standard input parameters such as solar irradiance, albedo or convection heat transfer coefficient for urban surfaces. The solar irradiance is estimated using the v.sun solar radiation add-on module in GRASS GIS. The LST values are calculated using map algebra operations using a Python script. The suggested methodology was applied to the study area in the city of Košice, Slovakia. Results indicate that urban morphology has a strong impact on spatial distribution of LST during the daylight hours. The accurate parameterization of urban surfaces can increase the accuracy of the model that can be used for urban planning, optimization of energy use in buildings or mitigation of urban heat island effects.