Energy Efficiency Classification Research Articles

Energy Efficient Streaming Time Series Classification with Attentive Power Iteration

Efficiently processing time series data streams in real-time on resource-constrained devices offers significant advantages in terms of enhanced computational energy efficiency and reduced time-related risks. We introduce an innovative streaming time series classification network that utilizes attentive power iteration, enabling real-time processing on resource-constrained devices. Our model continuously updates a compact representation of the entire time series, enhancing classification accuracy while conserving energy and processing time. Notably, it excels in streaming scenarios without requiring complete time series access, enabling swift decisions. Experimental results show that our approach excels in classification accuracy and energy efficiency, with over 70% less consumption and threefold faster task completion than benchmarks. This work advances real-time responsiveness, energy conservation, and operational effectiveness for constrained devices, contributing to optimizing various applications.

Energy efficient fault detection and classification using hyperparameter-tuned machine learning classifiers with sensors

This paper presents a novel approach in which hyperparameter-tuned Machine Learning (ML) classifiers with Optuna is used for fault detection and classification over a power transmission line. In this paper, popular ML models Random Forest (RF), Decision Tree (DT), XGBoost (XGB), and Light Gradient Boosting Machine (LGBM) are used for fault detection and classification. This study uses a two-layer approach for fault detection and classification. An electrical utility and data simulation provided the PMU measurement and recorded data from a simulated grid. The faults had varied impedances and included various fault classes at distinct line locations. The optimal feature from 3-phase current and voltage signals is extracted using Pearson correlation, recursive feature elimination, and univariate feature (t-test) methods. The synthetic minority class oversampling technique (SMOTE) was used to address the issue of imbalanced data. Hyperparameters of the evaluated LGBM classifier is trained with the Optuna. The performance of the proposed classifier is measured in terms of the accuracy, precision, Recall and F1-score metrics. The proposed method outperformed the conventional ML methods.

A Bio-inspired Energy Efficient Dynamic Task Scheduling (BEDTS) scheme and classification for virtualization CDC

Cloud Data Centers (CDCs) have evolved into an essential computing infrastructure for businesses. These applications generate a variety of data traffic with varying needs that must be examined and processed on CDCs. Every CDC is made up of multiple servers, virtual infrastructures, and physical connections that manage the internet's informative traffic. CDCs make use of a number of critical technologies, such as virtualization and Service Level Agreements (SLA). Virtualization makes it easier to share cloud computing resources (for example, by separating a powerful Physical Machine (PM) into a series of Virtual Machines (VM)) whose power is comparatively less. Even though virtualization increases the use of PMs by establishing a set of VMs for offering customised services to satisfy the needs of end-users, it also introduces another difficulty to cloud computing: map the VMs to the appropriate PMs. This is referred to as the VM deployment problem, and it is a Nondeterministic Polynomial time problem (NP-problem). CDC task scheduling is appropriate to augment the energy efficiency and resource usage in cloud computing. In the case of real-time tasks in virtualized CDC, the Bio-Inspired Energy Efficient Dynamic Task Scheduling (BEDTS) method is proposed. The Adaptive Elephant Herding Optimization (AEHO) technique is introduced in the BEDTS algorithm for optimal selection of VMs with resource restrictions and jobs. Initially, heterogeneous jobs and VMs are identified using a previous scheduling record. The Bayes classifier and Historical Scheduling Record (HSR), which allow for the identification of both the task type and VM type, serve as the foundation for task categorization. Then, related tasks are combined and then scheduled to make the best use of the host's operational status. When compared to previous approaches, experimental results reveal that BEDTS considerably enhances the scheduling performance on the whole, attains improved CDC resource utilisation, boosts task guarantee ratio, lowers average response time, and decreases the energy usage.

Exploring edge TPU for network intrusion detection in IoT

This paper explores Google's Edge TPU for implementing a practical network intrusion detection system (NIDS) at the edge of IoT, based on a deep learning approach. While a significant number of related works explore machine learning-based NIDS for the IoT edge, they generally lack considering the issue of the required computational and energy resources. The focus of this paper is the exploration of deep learning-based NIDS at the edge of IoT, and in particular, the computational and energy efficiency. In particular, the paper studies Google's Edge TPU as a hardware platform and considers the following three key metrics: computation (inference) time, energy efficiency and traffic classification performance. Various scaled model sizes of two major deep neural network architectures are used to investigate these three metrics. The performance of the Edge TPU-based implementation is compared with that of an energy-efficient embedded CPU (quad-core ARM Cortex-A53).

Analysis of the Effect of Climate on Mortality over Time

Malignant neoplasms, cardiac disease, and cerebrovascular disease are Japan's most common causes of death, with cardiac disease and cerebrovascular disease increasing during the winter season. The indoor environment of Japanese houses is poor in winter. To reduce medical costs for the further aging of the population, it is essential to study the relationship between mortality and the indoor environment. This paper analysed mortality rates by location, age group, year of death, and energy efficiency classification to clarify the relationship between climate and mortality rates in each region. Data were constructed by merging mortality data with climate data. Mortality sensitivity measures the mortality rate increases when the outside temperature falls by 1 ˚C. We also found that mortality among those who died in residential settings was more strongly affected by the cooler outside temperature environment than in nonpresidential settings. It suggests that the mortality rate was more strongly affected by residential areas, which tend to have cooler indoor temperatures during the winter, than non-residential buildings such as hospitals and elderly care facilities. The analysis by age group showed that the sensitivity was higher for older age groups and warmer energy efficiency classification categories in Kyushu and Okinawa.

A high-performance energy efficient packet classification design on FPGA

One of the most crucial thing to safeguard the network against malicious activities is security and the network devices must be able to classify packets. The firewall applications benefit greatly from the architecture of the packet classification engine that is given in this research work. A tree-based approach is used to systematically analyze each field in a packet header, leading to a more secure system. The Packet Classification Engine (PCE) is configured to evaluate Ethernet packets based on the source IP address, destination IP address, source port, destination port, and protocol aspects in the packet header. The PCE shows that the typical clock frequency from input to output is 13 clocks per second. The architecture is extremely rapid, reliable, and adaptable and can make good use of the tree based algorithm's advantages. The proposed architecture has achieved high throughput of 538 MPPS with less energy of 10.6 nJ at low latency of 62 ns. The PCE must have a rapid and reliable FIFO buffer to work effectively. A FPGA (Field Programmable Gate Array) device is being utilized to filter Ethernet packets using the proposed PCE.

ОЦІНЮВАННЯ ТЕПЛОІЗОЛЯЦІЙНИХ ПОКАЗНИКІВ ОГОРОДЖУВАЛЬНИХ КОНСТРУКЦІЙ БУДІВЕЛЬ ЛІНГВІСТИЧНИМИ ЗМІННИМИ

The classification of the factors influencing decision-making at an estimation of thermal conductivity of a heat-insulating cover of the building is offered. The relationship between the parameters of the thermal state of the thermal insulation of buildings and its energy efficiency is presented in the form of a logical conclusion tree. The logical inference tree at the system level characterizes the ratio of parameters that affect thermal conductivity. To create a mathematical model for expert assessment of the technical condition of the thermal insulation of the building, it is advisable to use the apparatus of fuzzy logic and fuzzy set theory. The formalization of quantitative and qualitative factors influencing the thermal efficiency of the building insulation shell has been carried out. When assessing the technical condition of the thermal insulation of the building (energy efficiency), quantitative and qualitative factors of influence are expressed through linguistic variables. Estimation of levels of linguistic variables is represented by term sets. Thermal conductivity as a factor in the thermal insulation of a building is related to the normative classification of energy efficiency of buildings in force in Ukraine.

Ceiling and Wall Illumination, Utilance, and Power in Interior Lighting

The common use of electric lighting in interiors has led to the need to search for user- and environmentally-friendly solutions. In this research, the impact of the luminaires and room parameters on the selected parameters of general lighting in interiors was assessed. To achieve the objective of this work, a computer simulation and statistical analysis of results were conducted. The illuminance uniformity on work plane, ceiling and wall relative illuminances, utilance, and normalized power density of lighting installations for 432 situations were analyzed in detail. The scenarios were varied in terms of room size, reflectance, lighting class, luminaire downward luminous intensity distribution, and layout. The lighting class was a factor having the highest impact on ceiling and wall illumination, utilance, and power. It was also shown that the impact of lighting class on ceiling illumination, utilance and power, was different in interiors of various sizes. The impact of reflectances and luminaire layouts on the analyzed parameters was significantly lower. The results also demonstrated that the use of different lighting classes gave the possibility of reducing the power of general lighting in interiors at a level of 30% on average. Based on the results, a classification of energy efficiency in general lighting in interiors was also proposed. Understanding the correlations between the lighting system used and the effects achieved is helpful in obtaining comfortable and efficient lighting solutions in interiors.

Energy efficient ECG classification with spiking neural network

Heart disease is one of the top ten threats to global health in 2019 according to the WHO. Continuous monitoring of ECG on wearable devices can detect abnormality in the user’s heartbeat early, thereby significantly increasing the chance of early intervention which is known to be the key to saving lives. In this paper, we present a set of inter-patient ECG classification methods that use convolutional (CNNs) and spiking neural networks (SNNs). We focused on inter-patient heartbeat classification, in which the model is trained over several patients and then used to infer that for patients not used in training. Raw heartbeat data is used in this paper because most wearable devices cannot deal with complex data preprocessing. A two-steps convolutional neural network testing method is proposed for saving power. For even greater energy-saving, a spiking neural network is also proposed. The latter is obtained from converting the trained CNN model with a less than one percent accuracy drop. The average power of a two-classes SNN is 0.077 W, or 0.0074× that of previously proposed neural network-based solutions.

Buildings Energy Efficiency Analysis and Classification Using Various Machine Learning Technique Classifiers

Energy efficiency is a major concern to achieve sustainability in modern society. Smart cities sustainability depends on the availability of energy-efficient infrastructures and services. Buildings compose most of the city, and they are responsible for most of the energy consumption and emissions to the atmosphere (40%). Smart cities need smart buildings to achieve sustainability goals. Building’s thermal modeling is essential to face the energy efficiency race. In this paper, we show how ICT and data science technologies and techniques can be applied to evaluate the energy efficiency of buildings. In concrete, we apply machine learning techniques to classify buildings based on their energy efficiency. Particularly, our focus is on single-family buildings in residential areas. Along this paper, we demonstrate the capabilities of machine learning techniques to classify buildings depending on their energy efficiency. Moreover, we analyze and compare the performance of different classifiers. Furthermore, we introduce new parameters which have some impact on the buildings thermal modeling, especially those concerning the environment where the building is located. We also make an insight on ICT and remark the growing relevance in data acquisition and monitoring of relevant parameters by using wireless sensor networks. It is worthy to remark the need for an appropriate and reliable dataset to achieve the best results. Moreover, we demonstrate that reliable classification is feasible with a few featured parameters.

IEC61800-9 System Standards as a Tool to Boost the Efficiency of Electric Motor Driven Systems Worldwide

Recognition of the energy savings potential in motor driven systems has led to the development of energy efficiency testing and classification standards for motors and end-use equipment (e.g., pumps and fans) and the implementation of minimum energy performance regulations targeting them worldwide. However, these standards and regulations have been limited to components, disregarding the interaction between them. The energy savings achievable by addressing and improving the entire system are potentially much higher in relation to those achievable when considering individual components. Recently, an effort to develop standards in this regard was carried out by standardization bodies (IEC and ISO) leading to the publication of the IEC61800-9 Power Drive System standard series. The paper, in its first part, describes recent evolutions in electric motor energy-efficiency standards and in the implementation of related regulations worldwide. In the second part of the paper, using the latest energy efficiency test and classification standards, a comparative analysis of different energy-efficient motor technologies is presented. Using results from laboratory tests combined with data provided by manufacturers, different power drive systems are compared considering different operating points in two typical pumping systems. Estimated economic savings from a total cost of ownership perspective are presented.

A review of air filter test standards for particulate matter of general ventilation

Air filters play an important role in a heating, ventilation and air-conditioning (HVAC) system to maintain good indoor air quality of a building. The air filter test standards act as a guideline to evaluate the air filter performance. The current global test standard, ISO 16890:2016 adopts particulate matter classification which can be easily understood. The European standard, EN 779:2012 is obsolete and replaced by ISO 16890:2016 in June 2018. ASHRAE 52.2:2017 which adopts the minimum efficiency reporting value (MERV) classification is still widely used in the United States. Some countries in Southeast Asia such as Malaysia, Brunei and Singapore are applying different standards: EN779, ASHRAE 52.2 and ISO 16890. A standardization of the air filter testing and classification is undoubtedly important in the global air filtration market. This paper can act as a reference and assist these developing countries in adopting the suitable air filter testing standard to develop their national standard. As all three standards have no specifications on energy efficiency classification, the energy rating system can be obtained using Eurovent 4/21-2018. The HVAC-system-supplied air quality can be further improved with the consideration of WHO annual mean pollutant limits and EN 16798-3 air classification to determine the supply air cleanliness. Practical application: Although EN 779 is replaced by ISO 16890, some developing countries are still in the transition period. Manufacturers and consumers apply different standards which are EN 779, ASHRAE 52.2 and ISO 16890; therefore, a global filter testing standardization is important. This paper can act as a reference and assist the countries in other regions especially in Southeast Asia to develop respective national standard. Besides, some recommendations are given to improve the air filtration and ventilation system by referring to the WHO guidelines for the air pollutant limits, EN 16798-3 for the supply air quality and Eurovent 4/21 for the air filter energy rating.

Comparing domain wall synapse with other non volatile memory devices for on-chip learning in analog hardware neural network

Resistive Random Access Memory (RRAM) and Phase Change Memory (PCM) devices have been popularly used as synapses in crossbar array based analog Neural Network (NN) circuit to achieve more energy and time efficient data classification compared to conventional computers. Here we demonstrate the advantages of recently proposed spin orbit torque driven Domain Wall (DW) device as synapse compared to the RRAM and PCM devices with respect to on-chip learning (training in hardware) in such NN. Synaptic characteristic of DW synapse, obtained by us from micromagnetic modeling, turns out to be much more linear and symmetric (between positive and negative update) than that of RRAM and PCM synapse. This makes design of peripheral analog circuits for on-chip learning much easier in DW synapse based NN compared to that for RRAM and PCM synapses. We next incorporate the DW synapse as a Verilog-A model in the crossbar array based NN circuit we design on SPICE circuit simulator. Successful on-chip learning is demonstrated through SPICE simulations on the popular Fisher’s Iris dataset. Time and energy required for learning turn out to be orders of magnitude lower for DW synapse based NN circuit compared to that for RRAM and PCM synapse based NN circuits.

Voltage-Source Converter Energy Efficiency Classification in Accordance With IEC 61800-9-2

New global energy efficiency classification standard IEC 61800-9-2 for frequency converters and motor systems has been recently launched. It classifies the energy efficiency of the converters and motor-drive systems and introduces three different methods to determine voltage-source converter (VSC) losses for the classification. In here, experimental tests are carried out using the input–output method and the calorimetric method to determine the losses and efficiency of a 160-kW commercial VSC. The measurement results with these two independent methods are compared and the uncertainty of the methods is analyzed. The converter electric input and output power distributions are analyzed in the frequency domain and are used further to estimate the electric power measurement uncertainty. The measurement uncertainty related to losses obtained with the input–output method is compared with the loss difference between the two methods. This is the first research work to accurately evaluate the experimental methods for the determination of the power losses and examine the validity of the energy efficiency classes of the frequency converters according to new IEC61800-9-2. An urgent need to update the loss boundaries of the IE-classes has been found and the measurement uncertainty effect on the IE-classification is discussed.

Multimodal GAN for Energy Efficiency and Cloud Classification in Internet of Things

Efficient processing of large-scale multimodal sensor data is a key issue for applying the Internet of Things (IoT). Accurate cloud classification is critical for weather and climate monitoring, which are parts of IoT applications. In this paper, we propose a novel generative deep model named multimodal generative adversarial network (Multimodal GAN) to improve both the energy efficiency and the cloud classification accuracy in IoT. The proposed Multimodal GAN is composed of a discriminator and a generator, each of which is devised to a two-stream network. The branches of two-stream structure correspond to the cloud visual information and the cloud scalar information, respectively. Therefore, the Multimodal GAN is capable of generating the cloud visual information and cloud scalar information simultaneously. Afterward, the training set is extended by the generated multimodal cloud samples, and the deep multimodal cloud classification model is trained by the extended training set. As a result, the classification model possesses high generalization ability and is less prone to be over-fitting. Moreover, the feature representations extracted from the classification model reflect the salient information of raw multimodal cloud data, and therefore they can be stored and transmitted in IoT. The effectiveness of the proposed method in energy efficiency and cloud classification is validated on the multimodal cloud dataset.

Environmental Sustainability and Energy-Efficient Supply Chain Management: A Review of Research Trends and Proposed Guidelines

This paper conducts a structured review on the topic of energy efficiency and environmental sustainability in the supply chain management context to define research trends on the topic and identify research gaps. The review is carried out using the largest databases of peer-reviewed literature (Scopus and Web of Science). A sample of 122 papers focusing on the topic of energy-efficient and sustainable supply chain management was selected and analyzed through descriptive and content analysis. The review highlights that despite there is a growing research trend on the topic, different research gaps remain to be covered. These gaps concern the factors influencing energy efficiency and environmental sustainability initiatives, the classification of energy efficiency and environmental sustainability initiatives, the impact of energy efficiency and environmental sustainability on supply chain performance, the customer perspective in sustainable and energy-efficient supply chain, and the different technologies supporting the energy efficiency and environmental sustainability initiatives. The research gaps and the research questions identified offer the opportunity to identify areas of investigation to design future research directions and propose guidelines in the field of supply chain management.

Radon safety in terms of energy efficiency classification of buildings

According to the results of survey in Ekaterinburg, Russia, indoor radon concentrations above city average level have been found in each of the studied buildings with high energy efficiency class. Measures to increase energy efficiency were confirmed to decrease the air exchange rate and accumulation of high radon concentrations indoors. Despite of recommendations to use mechanical ventilation with heat recovery as the main scenario for reducing elevated radon concentrations in energy-efficient buildings, the use of such systems did not show an obvious advantage. In real situation, mechanical ventilation system is not used properly both in the automatic and manual mode, which does not give an obvious advantage over natural ventilation in the climate of the Middle Urals in Ekaterinburg. Significant number of buildings with a high class of energy efficiency and built using modern space-planning decisions contributes to an increase in the average radon concentration. Such situation contradicts to “as low as reasonable achievable” principle of the radiation protection.

Urban energy efficiency evaluation system design in China

There exist some problems in energy saving target responsibility, such as low fairness and efficiency, unreasonable goal setting, high execution cost and other issues. Urban energy efficiency evaluation should adapt forms of persuasion disclosure as well as appropriate incentive .This paper puts forward the urban classification and benchmark system of energy efficiency ,the central government plan to classify the cities and use the benchmark to evaluate the level of energy efficiency ,directly determine the urban energy saving target, city government do statistics on the energy consumption data, make report of energy efficiency, learn the management experiences and promote the energy-saving technology, thus all the assessment results will be open to public.

A study for improving the energy efficiency of lifts with adjustable counterweighting

This article presents a study of the potential energy efficiency improvement by means of adjusting the lift counterweight. The lift energy consumption in different counterweight set-ups is studied by employing measured lift traffic and energy consumption data from an office building in Finland. Overall, dimensioning the counterweight based on traffic analysis is one of the fastest and most cost-effective means of improving the energy efficiency of lifts. The results from the building imply, however, that with a relatively constant loading throughout the day, the continuous adjusting of the counterweight provides limited energy savings compared to systems where the counterweight is sized according to the average load. Nevertheless, active adjustment of the counterweight size may provide considerable savings in lift systems if there is a wide variation in the car loading between the hours of the day. Furthermore, reducing the counterweight potentially improves the ISO 25745-2 energy efficiency classification of the lift, thus increasing the product attractiveness in the market. Practical application: This article presents practical approaches to analysing the energy consumption of counterbalanced lifts. The modelled results can be used to optimise the mass of the counterweight in order to achieve considerable energy savings in the actual or expected traffic profile.

Economic Analysis of Agricultural Tractors in South Korea: Classified Based on Energy Efficiency Grades

Abstract. This study involved performing an economic analysis on agricultural tractors classified based on energy efficiency grades using the energy efficiency index. Specifically, 131 models of agricultural tractors commonly used between 2006 and 2010 in South Korea were classified into five categories. The relationship between energy efficiency and economic value was evaluated by a numerical method, and a method of predicting cost and fuel savings based on energy efficiency was developed. Grades of energy efficiency labeled from 1–5 were assumed in order to calculate annual fuel and cost savings. The results indicated that the use of the proposed method resulted in fuel and cost savings given an upgrade from the 5th level of energy efficiency to the 1st level and indicated subsequent improvements with each grade level. This method was applied to data from the year 2008, and total fuel and cost savings were obtained. This indicated that fuel and cost savings in an arbitrary year could be predicted using the proposed method and assuming data from an arbitrary year. Keywords: Agricultural tractors, Economic analysis, Energy efficiency classification grade, Energy efficiency index.