Real-time Energy Usage Research Articles

The Development of a Real-Time Electricity Calculator System Using Machine Learning to Enhance Energy Efficiency

The development of the electric meter system described in this article is titled as Development of a Real-Time Electricity Calculator System Using Machine Learning to Enhance Energy Efficiency. The primary objective is to improve household energy management through prediction and alerts regarding energy usage. The system is designed to collect electricity usage data and various environmental parameters from households, and it employs five machine learning models to identify the best model for this purpose. The chosen model, Support Vector Regression (SVR), is used to predict energy consumption. In the research methodology, the system records real-time energy usage data into a CSV file. The predictive features include temperature, number of occupants, house size, and appliance usage. This data is standardized before being used to train the SVR model. After training, the model’s predictions are evaluated using the Root Mean Square Error (RMSE). The experimental results show that the SVR model effectively predicts electricity consumption, with a normalized RMSE of 57.56 and a cross-validation RMSE of 58.38, indicating the model’s accuracy. The visualizations provide a clear understanding of the overall relationship between actual and predicted values. Household electricity usage prediction enables users to plan energy consumption more efficiently, potentially reducing costs and improving energy efficiency. The development of this system can be applied in various fields, including industry and agriculture, to promote energy conservation and reduce environmental impact.

Sustainability or instant gratification? A study on Chinese perspectives of ‘pay-as-you-use’ smart energy meters in budget hotels

In response to the growing demand for sustainable practices in the hospitality industry, many hotels have concentrated on operational measures to reduce energy consumption. However, the potential for promoting voluntary customer-initiated energy-saving behaviors has been largely overlooked. This study fills that gap by investigating how environmental values (egoistic, altruistic, and biospheric) among Chinese consumers shape their attitudes, personal norms, and behavioral intentions to book budget hotels equipped with ‘pay-as-you-use’ smart energy meters (SMEMs). Unlike previous research, which primarily focuses on consumers’ willingness to pay a premium for green hotels, this study emphasizes cost-saving, pro-environmental behaviors—particularly relevant for cost-conscious travelers. The central challenge lies in understanding how financial incentives and real-time energy usage feedback can effectively drive sustainable behavior in transient hotel settings. The study also examines the moderating role of instant gratification in these relationships. This study employed Partial Least Squares Structural Equation Modeling (PLS-SEM) using SmartPLS and multiple-group analysis (MGA) on data collected from 929 Chinese participants. The findings reveal that environmental values significantly influence attitudes, personal norms, and intentions to book hotels with SMEMs. Moreover, the relationship between environmental values and behavioral intentions is moderated by the level of instant gratification, underscoring the importance of immediate rewards in promoting sustainable consumer behavior. This study contributes to the literature by extending the Values-Attitude-Behavior theory and also provides practical insights for hotel managers seeking to align sustainability goals with consumers’ preferences for cost savings and instant gratification.

Sustainability-driven electrical engineering optimizing energy efficiency through ai and developing eco-friendly electronics

This paper explores the transformative potential of AI-driven solutions in optimizing energy efficiency and the development of eco-friendly materials for electronics. As global energy consumption and electronic waste continue to rise, innovative technologies are essential to mitigate their environmental impact. AI models have shown significant promise in enhancing the performance of smart grids and residential and industrial energy systems by predicting and adjusting energy usage in real time. Additionally, the research and development of sustainable materials for semiconductors and electronic components offer an important pathway to reducing the environmental footprint of electronics manufacturing. By aligning these advancements with national sustainability and climate goals, this paper highlights the critical role of AI and sustainable materials in creating a more energy-efficient and environmentally responsible future. The paper concludes by suggesting areas for future research, emphasizing the long-term impact of these technologies on the electrical engineering field and their contribution to sustainability.

An optimal management architecture based on digital twin for smart solar-based islands incorporating deep learning and modified particle swarm optimization

Smart island (SI) energy management is a type of energy management system used to ensure that energy is used efficiently on islands. It is designed to reduce energy consumption and costs while also improving the sustainability of the island. Smart island energy management systems use a combination of technologies such as solar, wind, and other renewable energy sources, energy storage systems, smart meters, and advanced analytics to monitor and manage energy usage. The system can be used to provide islanders with real-time energy usage data, allowing them to make informed decisions about their energy use. Using the effects on the environment and economics of the SI as a basis for fully modeling the optimum performance of the SI in grid-connected operations, the feasibility and balance of the SI power grid are ensured. In addition, taking into account the impact of interruptible loads (IL) on SI operation costs, a power shift for IL can be performed using storage batteries in a digital twin environment. A new ecology-driven optimization algorithm has been developed that continuously adjusts migration rates with habitat suitability indexes of normalized individuals and adds a differential perturbation to the migration operator of the migration process. The enhanced particle swarm optimization algorithm has been implemented as the SI optimization dispatching algorithm. In order to have a precise prediction of the renewable energy sources, their output power is predicted using the recurrent neural network (RNN) deep learning model. Based on the simulation outcomes, it is evident that the suggested power dispatching model could greatly decrease the overall price of the system by implementing the advanced and effective algorithm and model presented in the study.

Comprehensive Energy Modeling Framework for Multi-Powertrain Bus Transit Systems

With the increasing emphasis on sustainable transportation solutions, there is an urgent need for a system that can accurately assess vehicle-specific energy consumption in real-time. However, the current modeling frameworks have a significant gap in that they are not demand- and congestion-responsive, nor are they capable of modeling the system-wide energy consumption of bus fleets at the vehicle-level, encompassing all three types of powertrains—conventional, hybrid, and electric. To address this gap, we present a comprehensive modeling framework that takes into account passenger loading, considers the dynamics of the system including acceleration, and is capable of predicting the real-time energy usage of each bus in a transit network. Using the Pioneer Valley Transit Authority system as a case study, we calibrated existing powertrain-specific models for conventional diesel, hybrid, and battery electric buses. Our demand- and congestion-responsive energy consumption modeling framework fills this critical gap and offers significant potential for future sustainable transportation planning. Relying on detailed trajectories computed from one month of bus location data, along with passenger counts and road grade, our framework is a novel contribution in that it provides spatiotemporal energy predictions for an entire bus system. As it is readily calibrated with potential improvements in accuracy given more data, this framework can be applied by transit agencies for the purposes of real-time energy consumption monitoring, fleet electrification planning, equity analyses, and carbon emission reduction strategies.

Differentially Private Demand Side Management for Incentivized Dynamic Pricing in Smart Grid

In order to efficiently provide demand side management (DSM) in smart grid, carrying out pricing on the basis of real-time energy usage is considered to be the most vital tool because it is directly linked with the finances associated with smart meters. Hence, every smart meter user wants to pay minimum possible amount along with getting maximum benefits. In here, usage based dynamic DSM pricing strategies plays their role and provide users with specific incentives. However, these reported real-time values can leak privacy of smart meter users, which can cause serious consequences such as spying. Moreover, most of dynamic pricing algorithms charge all users equally irrespective of their contribution in causing peak factor. Therefore, this paper proposes a modified usage based dynamic pricing mechanism that only charges the users responsible for causing peak factor. We further integrate differential privacy to protect the privacy of real-time smart metering data, and to calculate accurate billing we propose a noise adjustment method. Finally, we propose Demand Response enhancing Differential Pricing (DRDP) strategy that effectively enhances demand response along with providing dynamic pricing to smart meter users. The performance evaluation shows that DRDP outperforms previous mechanisms in terms of dynamic pricing and privacy preservation.

How to motivate employees towards organizational energy conservation: Insights based on employees perceptions and an IoT-enabled gamified IS intervention

Employees can help organizations attain Corporate Environmental Performance (CEP) goals and save on energy bills, by conserving electricity. However, they lack the motivation. Information Systems (IS)-enabled energy-related feedback interventions featuring gamification (utilizing game-design elements), have been suggested to increase organizational energy conservation. To identify the behavioral factors that should be considered when designing such interventions towards optimizing their results, this paper focuses on unravelling the intricacies of employee energy consumption behavior and providing answers to the research question: “What drives employees to save energy at work?”. Our research is conducted in three workplaces across Europe. First, we analyze employees' energy-saving motivation and behavior at an individual level of analysis to identify defining behavioral factors behind it. Then, considering these drivers of employees' energy consumption behavior, we focus on answering the question: “How a gamified IS that provides real-time energy usage feedback affects employees' motivation to conserve energy at work, and in turn the actual energy savings in organizations”. Our findings suggest that employees' level of self-determination to conserve energy, energy-saving personal norms, and personal and organizational profile, significantly explain both their energy-saving behavior and the energy behavior change attained through a gamified IS intervention. Moreover, the provision of feedback to employees, via an Internet-Of-Things (IoT)-enabled gamified IS, is proven an effective strategy for accomplishing actual energy conservation at work. The acquired insight on what drives employees' energy usage behavior supports the design of gamified IS interventions that have higher motivational capacity and, thus, can change employees' energy behavior. When designing behavioral interventions aimed at energy conservation at work, we should primarily focus on monitoring (to decide whether a behavioral intervention would be worth organizing) and ultimately positively affecting employees' energy-saving habits and intention. Our findings can be transformed to specific practical suggestions for firms to encourage employees’ energy saving behavior when aspiring to attain CEP goals. They include satisfying their basic psychological needs for autonomy, competence, and relatedness, activating their personal norms in the context of energy-saving at work, and educating and encouraging them towards specific energy-saving behaviors by utilizing gamified IoT-enabled IS that keep their energy-saving “in shape”.

Predictive model for real-time energy disaggregation using long short-term memory

To provide affordable energy-saving solutions for the small and medium-sized manufacturers (SMMs), we propose a unified framework for generating predictive models that support real-time disaggregation of power consumption from combined inputs, enabling automatic machine state identification simultaneously for joint analysis of energy usage patterns. The proposed framework transforms raw power consumption into a time series with look-back and bootstrap capabilities for historical pattern detection, while a learning architecture utilizes the stacked long short-term memory (LSTM) layers as encoders for embedding generation with sequential awareness. Experimental results demonstrate 93.65% minimum accuracy in ideal case of real-time energy usage and machine state prediction.

A contextual sensor system for non-intrusive machine status and energy monitoring

Event-driven contexts in manufacturing occur pervasively as a result of interactions among involved entities such as machines, workers, materials, and environment. One of the primary tasks in smart manufacturing is to derive a context-aware system conveniently incorporating worker knowledge for generating timely actionable intelligence for workers on factory floor and supervisors to respond. In this paper, we propose to design a human-and-machine interaction recognition framework by using a causality concept to collect contextual data for classifications of normal and abnormal machine operations. The causes and effects are between workers and machines for this initial research. To apply the causality to recognize worker interactions, initially a reliable way to identify the states of machines is necessary. The proposed contextual sensor system, consisting of a power meter for measuring machine operation conditions, a visual camera for capturing worker and machine interactions via a finite state machine model, and an algorithm for determining power signatures of individual components via energy disaggregation is implemented on semiconductor fabrication machines (manual or PLC controlled) each with multiple components. The experiment results demonstrate its context extraction capability such as components states and their corresponding energy usage in real time as well as its ability to identify anomalous operation conditions.

Blockchain and homomorphic encryption-based privacy-preserving data aggregation model in smart grid

In recent years, rapid advancements in smart grid technology and smart metering systems have raised serious privacy concerns about the collection of customers’ real-time energy usage behaviors. Due to cybersecurity attacks and threats, data aggregation operations in a smart grid are challenging. The majority of existing techniques have high computation and communication costs and are still vulnerable to various security and privacy concerns. This paper proposes a deep learning and homomorphic encryption-based privacy-preserving data aggregation model to mitigate the negative impact of a flash workload on the accuracy of prediction models. The model also ensures a secure data aggregation process with low computational overhead. The proposed model is 80% more effective than the traditional approach in detecting smart meter manipulation, and the computation cost is 20% to 80% less than existing techniques. Thus, the proposed blockchain and homomorphic encryption-based data aggregation (BHDA) scheme shows a significant improvement in performance and privacy preservation with minimal computation overhead for data aggregation in smart grids.

Quantum-Resistant Lightweight Authentication and Key Agreement Protocol for Fog-Based Microgrids

A microgrid is a flexible and localized grid that can disconnect from the main grid and operate independently on the traditional and/or renewable resource. It also can work with the main grid, and even provide power to the main grid when it has excess power to help relieve the pressure of energy. The flow of power between main grid and microgrid is monitored by smart meter, which kept the end user’s privacy information and his/her energy usage in real time. Hence, ensuring the privacy and security of these information is a considerable challenge. In this paper, we investigate the relationship between microgrids and the main grid, and design a quantum-resistant lightweight authentication and key agreement (AKA) protocol based on fog computing. The proposed protocol provides the mutual authentication and generates a session key between a smart meter and a fog node. More importantly, it can resist against quantum computing attacks, as the security of our scheme relies on the hardness of the learning parity with noise (LPN) problem, an NP-complete problem. Finally, we evaluate the performance of our proposed protocol and prove that our protocol is more lightweight and efficient.

Time-Pattern Profiling from Smart Meter Data to Detect Outliers in Energy Consumption

Smart meters have become a core part of the Internet of Things, and its sensory network is increasing globally. For example, in the UK there are over 15 million smart meters operating across homes and businesses. One of the main advantages of the smart meter installation is the link to a reduction in carbon emissions. Research shows that, when provided with accurate and real-time energy usage readings, consumers are more likely to turn off unneeded appliances and change other behavioural patterns around the home (e.g., lighting, thermostat adjustments). In addition, the smart meter rollout results in a lessening in the number of vehicle callouts for the collection of consumption readings from analogue meters and a general promotion of renewable sources of energy supply. Capturing and mining the data from this fully maintained (and highly accurate) sensing network, provides a wealth of information for utility companies and data scientists to promote applications that can further support a reduction in energy usage. This research focuses on modelling trends in domestic energy consumption using density-based classifiers. The technique estimates the volume of outliers (e.g., high periods of anomalous energy consumption) within a social class grouping. To achieve this, Density-Based Spatial Clustering of Applications with Noise (DBSCAN), Ordering Points to Identify the Clustering Structure (OPTICS) and Local Outlier Factor (LOF) demonstrate the detection of unusual energy consumption within naturally occurring groups with similar characteristics. Using DBSCAN and OPTICS, 53 and 208 outliers were detected respectively; with 218 using LOF, on a dataset comprised of 1,058,534 readings from 1026 homes.

Data-driven power - [Internet of Everything

GOVERNMENTS ARE setting ambitious renewable energy goals in response to climate change. The problem is, the availability of renewable sources doesn't align with the times when our energy demands are the highest. We need more electricity for lights when the sun has set and solar is no longer available, for example. But if utilities could receive information about energy usage in real time, as Internet service providers already do with data usage, it would change the relationship we have with the production and consumption of our energy.

Real-time remote energy consumption location for power management application

ABSTRACT Electricity generation continue to increase to meet the ever-growing demand of the built environment. Building’s miscellaneous plug loads are targeted for energy savings potentials. However, to achieve these savings, monitoring their energy consumption and providing comprehensive real-time energy usage information to the end-user is paramount. Real-time energy monitoring devices are significant tools for this purpose. However, deploying these devices for each load and for entire building, is cost-prohibitive. An alternative approach is to deploy tools to remotely identify the location of active-loads in real-time. This research proposes the development of the Energy Node Locating Method (ENLM) platform that remotely locates and measures power consuming loads at every electrical node, in the building, in real-time based on Sequence Time Domain Reflectometry (STDR). The proposed ENLM utilizes the measured time-delay between an injected and reflected signal at a branch circuit from any connected load to calculate the length of the physical wire to identify the location of energy usage. This information with real-time power consumption data are correlated with occupant’s entry data to identify where and how much energy is used. Various tests are conducted to validate the proposed platform, and the results confirm the validity of the platform.

A Development of Real-time Energy Usage Data Collection and Analysis System based on the IoT

A Development of Real-time Energy Usage Data Collection and Analysis System based on the IoT

Energy Use Intensity Estimation Method Based on Façade Features

In the U.S., over 72% of the total generated power is consumed by commercial and residential buildings. Among a building's envelope, system, and control, which significantly influence the building's energy performance, façade is a major parametric element that accounts for 70% of its energy performance. Compared with the internal mechanical system and operation schedule, façade features information is relatively easy to obtain from the visual aspects of a building. By adopting several key façade attributes, a customized energy use intensity baseline model can be generated by considering building design features. Therefore, instead of using traditional and complicated simulation methods, a mathematical model can be established to estimate EUI baselines based on sufficient existing building practices data. In a national building performance survey, data such as CBECS and building energy usage are collected for a large database to provide performance guidance for new or renovation building projects. Unfortunately, averaged performance data are too aggregated and generic to identify specific conditions for each building category in a specific climate condition. In this research, a vision-based performance prediction model was developed to estimate building energy consumption based on simplified façade attribute information and weather conditions. Data about building façade features, including orientation, façade area, window-to-wall ratio, volume, surface-to-volume ratio, etc., were collected along with energy use public disclosure. A prediction model, based on this dataset, was established to estimate building energy use intensity as a function of façade features. This prediction approach will provide a more realistic EUI estimation tool for calculating an energy use baseline and will enable real-time energy usage monitoring and management of each target building.

Blackout Avoidance and Energy Saving Services with Alert Aggregation

Peak electricity demands from huge number of households in a mega-city would cause contention, leading to potential blackout. This paper proposes bi-directional collaboration via a Smart Energy Monitor System (SEMS) between consumers and energy suppliers, exchanging real-time energy usage data with smart meters over the Internet and mobile devices for well-informed decisions and even predictions. The authors further propose the use of an Alert Management System (AMS) to monitor and aggregate critical energy consumption events for this purpose.

스마트 그리드의 소비자 보호를 위한 안전한 분산 데이터 관리 구조

스마트 그리드 기술은 소비자의 에너지 사용을 실시간으로 감시하고 비사용 기간 동안 차단 요구에 응답할 가정용 기기와 통신함으로써, 에너지 효율을 가정으로까지 확대해 준다. 그러나, 스마트 그리드에서 수집된 정보는 개인 정보의 라이브러리 형태가 될 것이므로 이것을 잘못 다루게 되면 소비자의 개인정보를 크게 해칠 수 있다. 소비자 중심의 투명성과 통제의 원칙이 처음부터 끝까지 필수 설계 원칙으로 취급되지 않는다면 중대한 우려가 있을 것이다. 본 논문에서는 All-Or-Nothing Transform(AONT) 암호화 모드의 특성을 이용하여 스마트 그리드 환경에서의 안전한 소비자 정보보호를 제공하기 위한 효율적인 데이터 분산 보안 관리방안을 제안한다. 본 논문에서 제안된 알고리즘은 처리속도 측면에서 데이터의 고속 분산 및 복원이 가능하며, 각 비밀조각 사이즈의 총합이 평문과 동일하여 스마트 그리드 시스템의 개인 데이터 처리에 적합하다. Smart grid technology can expand energy efficiency into the home by monitoring consumer energy usage in real time and communicating with household devices that respond to demands to shut off during periods of non-use, allowing individual consumers to control their electricity usage more effectively. But, the information collected on a smart grid will form a library of personal information, the mishandling of which could be highly invasive of consumer privacy. There will be major concerns if consumer-focused principles of transparency and control are not treated as essential design principles from beginning to end. In this paper, using. All-Or-Nothing Transform encryption mode for providing smart grid security, we propose efficient distributed data Management based on XOR operation. The contribution of this paper is to provide a secure algorithm that manages efficiently distributed data in the field of private data in smart grid environment.

Clemson University's Energy Systems Laboratory: A Hands–on Learning Experience for Students and Faculty

ABSTRACT The mission of the Clemson University Energy Systems Laboratory (ESL) is to provide real-time energy usage and equipment performance data for simulation, modeling, and analysis by students and faculty in engineering courses and research projects. The ESL is adjacent to the Clemson University Central Energy Plant, forming an effective partnership. This article describes experiences with and strategies for using energy system operating data to bring real-life problem solving into undergraduate engineering courses.

Striving for Cost–effective Energy Information Solutions: Emerging Web–based Technologies Provide Hope!

The internet is providing a cost-effective method of providing energy users with valuable information that enables them to better control their energy usage. The days of relying solely on systems that are on-site to provide this information have passed. The ability of off-site energy managers to collect, process, and disseminate this information using internet based e-mail and web pages accessible by the end user's standard internet browser has become a much more attractive option. While centrally monitored energy management is not new, it has been used primarily by high-end users with dedicated staff to perform the gathering and analysis functions. With low-cost internet communications available, this service can now be provided to a much broader market. This market, consisting of K-12 school corporations, municipalities, medium-sized commercial office buildings, and modest-sized retail chains has been under-served by the energy management community, except in regions with high-cost energy rates. While energy retrofit activities have provided a significant amount of energy savings to much of this market, there are more savings to be had in the operational and system maintenance areas. The only information that many of these under-served markets have is monthly energy bills. They are generally used for billing only, though some energy cost savings can be achieved by analyzing them for mistakes or for rate change recommendations. When one tries to detect the cause of excess energy usage using monthly bills, inadequate results often happen because these bills are time-late and lack energy usage profile information needed to identify the cause of excess energy usage. This article provides information regarding the information systems necessary to manage a facility's energy usage. It demonstrates the need for better, near real-time energy usage information for energy engineers and facility managers. In providing useful, timely energy usage information, the energy engineer and facility manager are better able to manage the energy usage in the facilities.