Real Energy Consumption Research Articles

A dual-optimization building energy prediction framework based on improved dung beetle algorithm, variational mode decomposition and deep learning

Accurately predicting building energy consumption is essential for enhancing energy utilization efficiency in buildings. However, the inherent volatility and noise in building energy data, caused by diverse user behaviors and potential sensor errors, make significant challenges to energy consumption prediction. To address these issues, a dual-optimization framework (IDBO-VMD-IDBO-BiLSTM) for building energy consumption prediction, which incorporates improved dung beetle optimization algorithm (IDBO), variational mode decomposition (VMD), and bidirectional long short-term memory network (BiLSTM), was proposed. In this framework, IDBO firstly optimizes the VMD by adaptively determining its optimal parameters to decompose the original building energy consumption series into multiple intrinsic modal functions (IMFs) with smoother characteristics, thereby the effect of mitigating data noise. Then, each IMF component is predicted using the BiLSTM model, with IDBO selecting the optimal hyperparameters for BiLSTM. Finally, the individual predictions of each IMF are superimposed and reconstructed to yield the final predictions. To verify the framework’s effectiveness, real energy consumption data from an office building in Shanghai was collected and analyzed in a comprehensive comparison with seven other comparative models. Experimental results suggested that the proposed framework outperformed the comparative models in terms of root mean square error (RMSE), mean absolute percentage error (MAPE), mean absolute error (MAE), and coefficient of determination (R2), showing both high predictive accuracy and strong robustness. Therefore, the proposed framework can be an effective tool for predicting building energy consumption

Reversible Hydrogen Acceptor–Donor Enables Relay Mechanism for Nitrate‐to‐Ammonia Electrocatalysis

AbstractElectrocatalytic nitrate reduction is a crucial process for sustainable ammonia production. However, to maximize ammonia yield efficiency, this technology inevitably operates at the potentials more negative than 0 V vs. RHE, leading to high energy consumption and competitive hydrogen evolution. To eradicate this issue, hydrogen tungsten bronze (HxWO3) as reversible hydrogen donor‐acceptor is partnered with copper (Cu) to enable a relay mechanism at potentials positive than 0 V vs. RHE, which involves rapid intercalation of H into HxWO3 lattice, prompt de‐intercalation of the lattice H and transfer onto Cu, and spontaneous H‐mediated nitrate‐to‐ammonia conversion on Cu. The resulting catalysts demonstrated a high ammonia yield rate of 3332.9±34.1 mmol gcat−1 h−1 and a Faraday efficiency of ~100 % at 0.10 V vs. RHE, displaying a record‐low estimated energy consumption of 17.6 kWh kgammonia−1. Using these catalysts, we achieve continuous ammonia production in an enlarged flow cell at a real energy consumption of 17.0 kWh kgammonia−1.

Reversible Hydrogen Acceptor-Donor Enables Relay Mechanism for Nitrate-to-Ammonia Electrocatalysis.

Electrocatalytic nitrate reduction is a crucial process for sustainable ammonia production. However, to maximize ammonia yield efficiency, this technology inevitably operates at the potentials more negative than 0 V vs. RHE, leading to high energy consumption and competitive hydrogen evolution.To eradicate this issue, hydrogen tungsten bronze (HxWO3) as reversible hydrogen donor-acceptor is partnered with copper (Cu) to enable a relay mechanism at potentials positive than 0 V vs. RHE, which involves rapid intercalation of H into HxWO3 lattice, prompt de-intercalation of the lattice H and transfer onto Cu, and spontaneous H-mediated nitrate-to-ammonia conversion on Cu.The resulting catalysts demonstrated a high ammonia yield rate of 3332.9±34.1 mmol gcat-1 h-1 and a Faraday efficiency of ~100 % at 0.10 V vs. RHE, displaying a record-low estimated energy consumption of 17.6 kWh kgammonia-1. Using these catalysts, we achieve continuous ammonia production in an enlarged flow cell at a real energy consumption of 17.0 kWh kgammonia-1.

Forming performance and environmental impact of bamboo fiber reinforced polypropylene composites based on injection molding process for automobiles

AbstractTo explore the potential application of plant fiber reinforced composites for automotive component applications, this study prepared bamboo fiber (BF)/nano‐talc/polypropylene (PP) composites based on the injection molding process, comprehensively evaluated the effect of reinforcement materials on the forming properties of composites, including thermal performance, mechanical properties, water absorption, etc. Furthermore, taking a certain automotive injection molded interior part as the object, a life‐cycle assessment from production to the gate was conducted based on the real energy and material consumption during the composite preparation process. The results indicate that adding BF and talc powder increased the thermal stability, density, hardness, viscosity, and crystallinity of the composites while reducing the water contact angle on the surface. Surface‐modified BF and PP showed good compatibility. Talc powder exhibited good dispersibility in PP, and the synergistic effect of BF and talc powder effectively enhanced the composite performance. The tensile, flexural, and impact strength of the composites were improved by 40.64%, 51.48%, and 66.51%, respectively, compared with pure PP. The modulus of the composite increased nearly 2 times compared with pure PP. Additionally, the composite demonstrated good friction and wear properties. The environmental impact of the BF composite manufacturing process was significantly higher than that of pure PP. The substantial consumption of electricity, chemicals, and water resources in the extraction and modification processes of BF were the main factors. The findings of this study contribute to achieving green, high‐performance BF composite manufacturing and the expansion of its applications.Highlights Composites have a higher environmental impact compared to PP. BF and talc can synergistically enhance the performance of composites. BF shows good compatibility with PP. Composites exhibit good friction and wear characteristics.

Improved Nitrate-to-Ammonia Electrocatalysis through Hydrogen Poisoning Effects.

Electrochemical conversion from nitrate to ammonia is a key step in sustainable ammonia production. However, it suffers from low productive efficiency or high energy consumption due to a lack of desired electrocatalysts. Here we report nickel cobalt phosphide (NiCoP) catalysts for nitrate-to-ammonia electrocatalysis that display a record-high catalytic current density of -702±7 mA cm-2, ammonia production rate of 5415±26 mmol gcat -1 h-1 and Faraday efficiency of 99.7±0.2 % at -0.3 V vs. RHE, affording the estimated energy consumption as low as 22.7 kWh kgammonia -1. Theoretical and experimental results reveal that these catalysts benefit from hydrogen poisoning effects, which leave behind catalytically inert adsorbed hydrogen species (HI*) at Co-hollow sites and thereupon enable ideally reactive HII* at secondary Co-P sites. The dimerization between HI* and HII* for H2 evolution is blocked due to the catalytic inertia of HI* thereby the HII* drives nitrate hydrogenation timely. With these catalysts, the continuous ammonia production is further shown in an electrolyser with a real energy consumption of 18.9 kWh kgammonia -1.

Nonlinear Ensemble Deep Learning Model for Energy Consumption Prediction with Bayesian Optimization

Accurate prediction of electric energy consumption is crucial for efficient load dispatching, energy utilization, and grid operation. Traditional statistical and classical machine learning methods struggle with the nonlinear nature of energy consumption data, often leading to higher prediction errors. Additionally, deep learning models using a single approach face challenges such as convergence to local minima and poor generalization. This paper proposes a nonlinear ensemble deep learning model for residential energy consumption prediction, incorporating Bayesian optimization for hyperparameter tuning. The model combines Long Short-Term Memory (LSTM), Bidirectional LSTM (BiLSTM), and 1D Convolutional Neural Networks (1D-CNN), leveraging their powerful nonlinear feature learning capabilities. A k-means clustering approach is used to preprocess and reduce variability in the data, enhancing the ensemble model's performance. The ensemble model was tested on real energy consumption data from two districts in Addis Ababa, showing significant improvements in prediction accuracy with lower MAE, RMSE, and MAPE values compared to single models and un-clustered data. The integration of clustering and Bayesian optimization further enhanced model generalizability and minimized overfitting, demonstrating the effectiveness of a nonlinear approach in capturing complex energy consumption patterns.

Energy consumption of UAE public schools. Mapping of a diversified sector assessing typology, conditions, and educational systems

The UAE school sector impacts several Sustainable Development Goals of the UAE Vision 2021. The sector is designed according to a standardized system of Model buildings, repeated several times throughout the country, comprising facilities that are often obsolete at both functional and technological level; hence, frequently presenting poor energy performances. The paper presents the first comprehensive review of the energy consumption state-of-the-art of the public-school sector in the Emirate of Sharjah, United Arab Emirates, including the first necessary dataset for future upgrade actions. The study was completed by means of a deep mapping, functional, typological, and pedagogical analysis. The collected data of real energy consumption of 69 schools highlighted an average energy consumption of 174 kWh/m2 year, with very consistent results for each educational cycle, even if a larger variance was expected due to difference in size, typology, and working hour. More significant differences can be observed when comparing the result of school with different typologies, stressing the relevance of further investigating the standardized Model system. To quantify their correlation to the buildings’ energy consumption, linear regression analyses were conducted on a number of notable factors, such as building age, net floor area, roof area, shape coefficient, number of students, number of classrooms and labs, presence of gyms and multipurpose halls, and implementation of digital technologies. Schools’ capacity/occupancy ratio, net floor area and roof area, and the use of energy-demanding devices for novel smart learning techniques were found having the highest impact. The tested multiple regression model, which displays a marginal error of 5–30 % when applied to single buildings and 9 % when used to assess larger clusters, could facilitate the estimation of the energy consumption of schools and support stakeholders’ decision making. The outcomes of the study can assist governmental agencies in elaborating suitable refurbishment policies for the energy and functional upgrade of the educational sector, both at the building and urban scale, and school administrator in tackling appropriate actions toward the schools use and resources optimization.

Analysis of aggregated load consumption forecasting in short, medium and long term horizons using Dynamic Mode Decomposition

In response to the growing need for precise energy demand forecasting in distribution grids, this study examines the effectiveness of the Dynamic Mode Decomposition (DMD) algorithm for short, medium, and long-term demand forecasting in distribution grids, leveraging diverse time series energy consumption data. The DMD algorithm, a data-driven approach renowned for its capacity to discern frequencies and trends, will be compared against established forecasting techniques, including XGBoosting Regressor, Long Short-Term Memory, and PROPHET. The research is conducted through a comprehensive case study comprising three distinct phases: study on pattern capturing of DMD, comparison in Long term horizon with all models studied and robustness study of DMD. It recalls upon real aggregated hourly energy consumption data sourced from a Spanish distribution grid. The practical applications and benefits of DMD in time series forecasting are examined carefully in order to show its comparative advantages over alternative forecasting models. To ensure a rigorous assessment of the findings, the analysis will employ four key statistical metrics: Root Mean Square Error (RMSE), Mean Squared Error (MSE), Mean Absolute Error (MAE), and Mean Absolute Percentage Error (MAPE). The results obtained with the case studies showed a 75% reduction on computational waste compared to other models and the results are closer to classical models, obtaining an improvement in the best case study of 44% comparing RMSE with Prophet. The insights gained can help future applications and research in the field.

Energy Complexity of Convolutional Neural Networks.

The energy efficiency of hardware implementations of convolutional neural networks (CNNs) is critical to their widespread deployment in low-power mobile devices. Recently, a number of methods have been proposed for providing energy-optimal mappings of CNNs onto diverse hardware accelerators. Their estimated energy consumption is related to specific implementation details and hardware parameters, which does not allow for machine-independent exploration of CNN energy measures. In this letter, we introduce a simplified theoretical energy complexity model for CNNs, based on only a two-level memory hierarchy that captures asymptotically all important sources of energy consumption for different CNN hardware implementations. In this model, we derive a simple energy lower bound and calculate the energy complexity of evaluating a CNN layer for two common data flows, providing corresponding upper bounds. According to statistical tests, the theoretical energy upper and lower bounds we present fit asymptotically very well with the real energy consumption of CNN implementations on the Simba and Eyeriss hardware platforms, estimated by the Timeloop/Accelergy program, which validates the proposed energy complexity model for CNNs.

Multi-source domain generalization deep neural network model for predicting energy consumption in multiple office buildings

The effective prediction of building energy consumption can be used to optimize building operating modes and reduce the overall energy consumption and carbon emission of the building. To predict the energy consumption of the same type of building in the same area, it is often necessary to train separate prediction models for different buildings, which is usually costly computationally in order to get better prediction results. Therefore, this study will combine deep neural networks and multi-source domain generalization in an encoder-decoder architecture to train a model that can be directly applied to predict the energy consumption of multiple buildings in same type. In order to validate the predictive effectiveness of the model, it will be tested on real office building energy consumption dataset and different comparative experiments will be designed on the source and target domains. The results show that the constructed multi-source domain generalization model is able to accurately predict the energy consumption trend of different buildings 1 h in advance. It also has some energy consumption prediction ability for the unknow training set of buildings.

Innovative hybrid prediction method integrating wavelet threshold decomposition and entropy-based model selection strategy for building energy consumption prediction

Building energy prediction plays a pivotal role in the building energy management system, and an efficient prediction method is crucial to ensure the effective operation of building systems. Existing research enhances prediction accuracy by combining decomposition algorithms with prediction methods to separate non-stationary information from the original sequence. However, the decomposition process and the subsequent prediction of multiple decomposed subsequences result in significant time overhead, making it unsuitable for scenarios with high temporal requirements, such as short-term energy consumption forecasting. Additionally, a single prediction model struggles to adapt to the diverse features of decomposed subsequences, creating prediction accuracy and efficiency bottlenecks. Addressing these challenges, this study proposes a hybrid prediction method that combines wavelet threshold decomposition (WTD) with an entropy-based model selection strategy. The method initially utilizes the efficient WTD algorithm to decompose the original energy consumption data into three fixed subsequences. Subsequently, the permutation entropy for each subsequence is computed, and based on the comprehensive performance of four prediction models (ANN, LSTM, CNN-LSTM, and TCN) on sequences with different entropy values, the optimal prediction model is selected. Finally, the prediction results of the subsequences are aggregated to obtain the ultimate prediction outcome. Experimental results demonstrate that the proposed method significantly outperforms baseline methods in both prediction speed and accuracy across five real building energy consumption datasets with distinct operational modes.

Assessment of renewable power generation applied in homestay hotels: Energy and cost-benefit considering dynamic occupancy rates and reservation prices

Increasing the revenue from hotel operations and decreasing the stress on utility grids from hotel energy consumption are two priorities for the modern tourism industry. Dynamic occupancy rate and hotel reservation prices influence their operations revenue, while occupancy rate also impacts real hotel energy consumption. Renewable power generation as an effective measure can benefit hotels not only by decreasing electricity purchases but also increasing some extra income from selling electricity generated from renewable sources. This study investigated the effects of renewable power generation on energy and the cost-benefit performance of hotel operation prices under different occupancy rates and reservation prices. A two-stage energy and cost-benefit performance assessment and a novel comprehensive cost-benefit assessment model were developed to examine these research issues. The impact of the renewable power generation system (i.e., a photovoltaic-battery system installed on the building rooftop) was considered on the hotel energy and cost-benefit performance. It was found that the novel cost-benefit assessment model accurately quantified the overall hotel profit by calculating its energy consumption cost with the PV-battery system under different occupancy rates and reservation prices. Three typical homestay hotels located in Sanya were tested and assessed. The results showed that PV-battery systems effectively decreased the amount of electricity purchased by hotels. Besides, the renewable energy penetration was above 57.98% in various cases. The overall hotel profit increased by a maximum of 31.4% since renewable power generation was used under different occupancy rates and hotel reservation prices.

Measurement of Power Quality Effects and Energy Efficiency of Various Light Technologies

The paper deals with the influence on the power quality of various light technologies and measurement of their energy efficiency (lighting efficiency). A virtual power quality analyzer which enables measurement of all the power components, using the newest power models and definitions, is shortly described. Details of the measurement of harmonics generation by different light technologies are presented. A more realistic approach to the energy efficiency estimation, by the real electrical energy consumption, is proposed. This approach to the energy (lighting) efficiency estimation could be generalized to other domestic appliances, sources of harmonics.

IoT Connected Smart Energy Meter

Abstract: Dawn of household electricity has revolutionized the world making life much easier and improving standard of living but still 940 million (13% of the world) do not have access to electricity. It is therefore the responsibility of those with stable power supply to keep their use of electricity in check as the less power we waste the more there will be for the ones who need it. Our goal is to design and implement a system to accurately measure the power consumption of a household in kWh using PZEM-004T module and, using IoT principles, wirelessly transmit the data to the ThingSpeak cloud server where it could be visually displayed This could help individual real time energy consumption data so they can take action accordingly. We also aim to collect data from multiple households and use data analysis techniques to find out valuable information and make accurate predictions regarding the future power consumption and consequential actions to be taken.

A real time condition based sustainable maintenance method for milling process

The manufacturing industry must reduce energy consumption during the machining process to comply with energy demand and usage restrictions. Previous research has employed various methods to take a optimization plan in machining process. However, these studies mostly rely on static machining conditions, without paying much attention for the condition variation, which may lead to a coarse energy efficiency optimization in machining process. Hence, this study introduces a real time condition based sustainable maintenance method for machining process. Firstly, a real-time data acquisition system is employed to collect and send data to the developed tool condition prediction model using deep learning. Then, the physical energy prediction model is employed to reflect the real time energy consumption behaviors based on the real time tool condition. Subsequently, a similarity analysis is employed to decide whether a new optimization is required. And, once it is required, an optimization using NSGA-II and TOPSIS is conducted. Experiments were conducted on a milling machine and compared with traditional methods, and verified using triple bottom line. Results indicated that the proposed method can reduce the energy consumption by 2.51% and 7.01%, and it can maintain a qualified product during the machining process.

Dynamic Effects of Energy Consumption and Economic Growth on CO2 Emission: Testing EKC Hypothesis in Africa

This paper focuses on using time series data on real GDP, energy consumption, and CO2 emission to examine the effect of economic growth and energy consumption on CO2 emission for a panel of 23 African countries within the period 1980–2019. The study used Pedroni (1999) approach of panel cointegration analysis to test for existence of long-run cointegration relationship between the variables. Fixed effect model was used to test for the Environmental Kutznets Hypothesis, and income squared was included as an additional explanatory variable. The estimated empirical results for the panel of 23 African countries from fixed effect model indicates the evidence of EKC hypothesis. At the level of individual countries, there is large divergence. 13 countries show evidence of EKC, implying that CO2 emission has fallen over the long run. As income increases, the levels of environmental damage decreases in those countries. 10 countries show opposite relationship among the variables. Based on the estimated results, it is recommended that countries should pursue economic growth policies that are not highly carbon intensive. Policy makers in these countries should adopt strategies that uses environmentally friendly technologies to decrease CO2 emission. Countries should also implement strong regulatory and market-based policies in highly energy-intensive sectors to reduce their current level of emissions and attain sustainable, environment-friendly economic growth.

Development of Smart Meter to Monitor Real Time Energy Consumption for Sustainability

This study constructed a Smart Energy Meter where energy consumption can be viewed by the consumers based on rreal time using data from smart meters. Its goals are to increase productivity, make readings more precise, and take less time to determine an individual residence's energy consumption. The device is made up of the PZEM-016 AC Energy Meter, RS-485 UART Serial Converter, NodeMCU ESP8266, Blynk IoT Application, Arduino Uno R3, and LCD Arduino Keypad Module Shield Board. The PZEM-016 is used in this smart energy meter to measure voltage, current, power, frequency, power factor, and energy consumption. Because it lacks its own display, an RS-485 was utilized to communicate with the NodeMCU and Arduino Uno. The NodeMCU sends the parameters to Blynk IoT App as long as it is connected to a fixed mobile WiFi. The Blynk will then display a real-time measurement of the parameters. The Arduino Uno is programmed to display the parameters to the LCD Keypad Module. The device was tested in an actual household. The researchers conducted 48-hour observation on the household where the energy displayed in the Blynk IoT App and the LCD display matches at approximately 9 kWh which is the same as the actual energy meter of the house that is 9kWh. The device is also tested on different appliances which resulted in the same energy consumption in both the Blynk IoT App and LCD display with the ratingsof the appliances. The device was found functional.

Optimum fenestration characteristics in mediterranean Tunisian context: An energetic, economic and environmental (EEE) study

This paper aims to investigate the energy performance of several techniques integrated into the fenestration system of an office building. The first step was to compare the simulated and real energy consumption of a case study of an office building located in Tunis City. In a second step, the study explores the impact of a glazing retrofit solutions on annual energy saving. To determine the possible energy savings for the existing office building in various climatic zones, we performed several simulations, using the Design Builder software.For these zones, the optimum window-to-wall-ratio (WWR), ensuring a compromise between daylighting and energy consumption, is found to be 40%. Then, for the chosen WWR, we evaluated a retrofit process involving existing commercial technologies such as double-glazed insulated windows, as well as innovative technologies consisting of intelligent coating, in addition to passive techniques including several shading concepts.It is found that, the double-glazed window with outside reveal depth of 20 cm equipped with both low-emissivity (LoE) and electrochromic (EC) coatings ensures the lowest annual energy consumption. Besides, energy savings depends on the climate zone; it reaches 23% in hot climates (ZT3) and almost 20% in cold (ZT1) and temperate climates (ZT2). The possibility of using electrochromic coating was excluded following the economic study because of its exorbitant cost. In fact, this type of renovation can lead to payback periods of up to 74 years for the cases treated.The optimized window designs consist in using a double-glazing window with a LoE coating, an outside reveal depth of 20 cm, and as a shading system (Overhang). These designs save 8 to 20% of energy and reduce CO2 emissions by 6 to 10 kg CO2/m2 per year, with a payback period of less than 6 years depending on the climatic zone.

Solar Resource and Energy Demand for Autonomous Solar Cooking Photovoltaic Systems in Kenya and Rwanda

The challenges associated with traditional cooking methods in African countries, particularly the use of firewood and charcoal, which have negative impacts on the environment, health and human and economic development and safety, are addressed in this work. Given the high annual solar irradiation on the African continent, photovoltaic-powered electric cooking alternatives, such as electric pressure cookers (EPCs), are identified as a potential efficient, clean and affordable cooking solution. This work focuses on the potential of standalone solar electric cookers for use in rural African locations, namely, if this type of solution can satisfy cooking demand. Surveys and experimental data from several households in two different countries (Rwanda and Kenya) were collected. Specifically, the researchers performed a survey regarding cooking habits and an experimental campaign to determine real energy consumption profiles of EPCs. The main results are analyzed and discussed in this work. An assessment of the solar power capability to directly supply the EPCs’ energy demand, as determined from the experimental data, is performed. The findings indicate that, for the most commonly prepared food types, using EPCs saves considerable time in comparison with traditional cooking methods. In Rwanda, time savings range from 55% to 84%, while in Kenya, the time saved varies from 9% to 64%. Results show that, even for scenarios with high installed solar capacity, storage solutions are required to enable the PV-powered EPC system to supply more than 50% of meal demand.

The Use of Real Energy Consumption Data in Characterising Residential Energy Demand with an Inventory of UK Datasets

The availability of empirical energy data from Advanced Metering Infrastructure (AMI)—which includes household smart meters—has enabled residential energy demand to be characterised in different forms. This paper first presents a literature review of applications of measured electricity, gas, and heat consumption data at a range of temporal resolutions, which have been used to characterise and develop an understanding of residential energy demand. User groups, sectors, and policy areas that can benefit from the research are identified. Multiple residential energy demand datasets have been collected in the UK that enable this characterisation. This paper has identified twenty-three UK datasets that are accessible for use by researchers, either through open access or defined processes, and presents them in an inventory containing details about the energy data type, temporal and spatial resolution, and presence of contextual physical and socio-demographic information. Thirteen applications of data relating to characterising residential energy demand have been outlined in the literature review, and the suitability of each of the twenty-three datasets was mapped to the thirteen applications. It is found that many datasets contain complementary contextual data that broaden their usefulness and that multiple datasets are suitable for several applications beyond their original project objectives, adding value to the original data collection.