Electricity Usage Research Articles

Green AI‐Driven Concept for the Development of Cost‐Effective and Energy‐Efficient Deep Learning Method: Application in the Detection of Eimeria Parasites as a Case Study

Although large‐scale pretrained convolutinal neural networks (CNN) models have shown impressive transfer learning capabilities, they come with drawbacks such as high energy consumption and computational cost due to their potential redundant parameters. This study presents an innovative weight‐level pruning technique that mitigates the challenges of overparameterization, and subsequently minimizes the electricity usage of such large deep learning models. The method focuses on removing redundant parameters while upholding model accuracy. This methodology is applied to classify Eimeria species parasites from fowls and rabbits. By leveraging a set of 27 pretrained CNN models with a number of parameters between 3.0M and 118.5M, the framework has identified a 4.8M‐parameter model with the highest accuracy for both animals. The model is then subjected to a systematic pruning process, resulting in an 8% reduction in parameters and a 421M reduction in floating point operations while maintaining the same classification accuracy for both fowls and rabbits. Furthermore, unlike the existing literature where two separate models are created for rabbits and fowls, this article presents a combined model with 17 classes. This approach has resulted in a CNN model with nearly 50% reduced parameter size while retaining the same accuracy of over 90%.

Efficient energy management of domestic loads with electric vehicles by optimal scheduling of solar-powered battery energy storage system

The increasing adoption of electric vehicles (EVs) and variable energy usage patterns substantially strain the electrical grid; indeed, optimal energy management, monitoring, and utilization are required for the reliable operation of the grid. This paper introduces a novel model design of a solar-powered battery energy storage system (SPBESS) as a viable substitute for conventional demand-side management (DSM) and time of use (ToU) pricing schemes, intending to optimize energy management and utilization with IoT monitoring. In addition, the IoT-based prototype has been developed to monitor and control the proposed system. To validate the proposed SPBESS model, the study examines two distinct cases: one encompassing domestic loads and the other integrating EV loads alongside household demand. Using ToU pricing, it determines the optimal charging and discharging strategies for the SPBESS, evaluates their implications for the system configuration and grid ToU pricing, and quantifies the annual reductions in power purchases, electricity bills, energy costs, and carbon emissions. Moreover, the study comprehensively analyzes the optimal power exchanges between the photovoltaic system, battery energy storage system, and the grid, precisely considering the specific load requirements and grid ToU pricing. The conducted research findings manifest considerable decreases in energy costs, with the domestic load condition witnessing a reduction from $0.312 per kilowatt-hour to $0.245 per kilowatt-hour and the scenario involving EV and residential loads experiencing a decline from $0.27 per kilowatt-hour to $0.197 per kilowatt-hour. Furthermore, the annualized cost savings for cases 1 and 2 amount to $1,336 and $4,544, respectively, yielding substantial reductions in polluting gas emissions. Besides, the IoT-based constructed prototype model design for real-time power parameters monitoring and control shows the importance of IoT-based monitoring for remote load control, allowing users to maximize energy efficiency, resource utilization, and system visualization.

Short-Term Load Forecasting of Electric Vehicle Charging Stations Accounting for Multifactor IDBO Hybrid Models

The charging behavior of electric vehicle users is highly stochastic, which makes the short-term prediction of charging load at electric vehicle charging stations difficult. In this paper, a data-driven hybrid model optimized by the improved dung beetle optimization algorithm (IDBO) is proposed to address the problem of the low accuracy of short-term prediction. Firstly, the charging station data are preprocessed to obtain clear and organized load data, and the input feature matrix is constructed using factors such as temperature, date type, and holidays. Secondly, the optimal CNN-BiLSTM model is constructed using convolutional neural network (CNN) and Bi-directional Long Short-Term Memory (BiLSTM), which realizes the feature extraction of the input matrix and better captures the hidden patterns and regularities in it. Then, methods such as Bernoulli mapping are used to improve the DBO algorithm and its hyperparameters; for example, hidden neurons of the hybrid model are tuned to further improve the model prediction accuracy. Finally, a simulation experiment platform is established based on MATLAB R2023a to validate the example calculations on the historical data of EV charging stations in the public dataset of ANN-DATA, and comparative analyses are carried out. The results show that compared with the traditional models such as CNN, BiLSTM and PSO-CNN-BiLSTM, the coefficient of determination of the model exceeds 0.8921 and the root mean square error is maintained at about 4.413 on both the training and test sets, which proves its effectiveness and stability.

Cost-effective sizing method of Vehicle-to-Building chargers and energy storage systems during the planning stage of smart micro-grid

Demand side management (DSM) is a great challenge for new power systems based on renewable energy. Vehicle-to-Building (V2B) and Energy Storage Systems (ESS) are two important and effective tools. However, existing studies lack the sizing method of bidirectional chargers and ESSs. This study has proposed a cost-effective sizing method of V2B chargers and ESSs during the planning stage. By developing a linear model that clusters electric vehicle users based on mobility patterns and employing mixed integer linear programming for day-ahead control strategies, the method minimizes the dynamic payback period of initial investments. Tested in an office park featuring photovoltaic generation, the optimal configuration of 50% V2B chargers and 1 ESS significantly reduces cumulative peak-hour load and peak power by 51.3% and 42.4%, respectively. The price and rated power of EV chargers on the optimal sizing result are also investigated, providing guidance for the design and operation of micro-grid systems. Furthermore, the study suggests further exploration into actual data acquisition, real-time control strategy enhancement, and comprehensive user behavior for broader application.

Data Drive—Charging Behavior of Electric Vehicle Users with Variable Roles

Data Drive—Charging Behavior of Electric Vehicle Users with Variable Roles

A systematic approach to manual calibration and validation of building energy simulation

PurposeThis study aims to create an efficient approach to validate building energy simulation models amidst challenges from time-intensive data collection. Emphasizing precision in model calibration through strategic short-term data acquisition, the systematic framework targets critical adjustments using a strategically captured dataset. Leveraging metrics like Mean Bias Error (MBE) and Coefficient of Variation of Root Mean Square Error (CV(RMSE)), this methodology aims to heighten energy efficiency assessment accuracy without lengthy data collection periods.Design/methodology/approachA standalone school and a campus facility were selected as case studies. Field investigations enabled precise energy modeling, emphasizing user-dependent parameters and compliance with standards. Simulation outputs were compared to short-term actual measurements, utilizing MBE and CV(RMSE) metrics, focusing on internal temperature and CO2 levels. Energy bills and consumption data were scrutinized to verify natural gas and electricity usage against uncertain parameters.FindingsDiscrepancies between initial simulations and measurements were observed. Following adjustments, the standalone school 1’s average internal temperature increased from 19.5 °C to 21.3 °C, with MBE and CV(RMSE) aiding validation. Campus facilities exhibited complex variations, addressed by accounting for CO2 levels and occupancy patterns, with similar metrics aiding validation. Revisions in lighting and electrical equipment schedules improved electricity consumption predictions. Verification of natural gas usage and monthly error rate calculations refined the simulation model.Originality/valueThis paper tackles Building Energy Simulation validation challenges due to data scarcity and time constraints. It proposes a strategic, short-term data collection method. It uses MBE and CV(RMSE) metrics for a comprehensive evaluation to ensure reliable energy efficiency predictions without extensive data collection.

Hydro Electrometric Tracking Application

We offer a brand-new technique for real-time control over the project's water flow rate and electricity usage. Unlike current systems, which are frequently costly and solely monitor power or water, our method integrates both parameters into a single, reasonably priced platform. Our solution allows users to track their resource consumption in real-time by utilizing Arduino-based sensors and a user-friendly mobile application created with MIT App Inventor. By providing consumers with the knowledge, they need to make educated decisions about how much water and power to use, this promotes more effective and sustainable resource management. It is unique in that it provides an affordable solution that integrates water and power metering capabilities, solving major issues with current systems.

An adaptive methodology based on predictive deep learning and context aware clustering for electricity power usage mining and optimization at different granularity levels

Smart metering in electricity power grid is an optimistic trend at global level. All smart devices and appliances based on Internet of Things (IoT) are now playing very significant role in household. These days’ electric power usage mining and optimization is possible down to meter level only. However, it is very challenging and significant to go down to different granularity levels such as appliances, various sensors and activities etc. The shifting of the electric power usage to low price electricity is also significant and possible by mining and optimizing electric power usage behaviour at low level. All smart appliances and activities are needs to be customized to when you use them. This paper proposes an adaptive methodology based on predictive deep learning and context aware clustering to discover new ways for mining and optimization of electric power usage at different granularity levels and make optimal decisions for shifting electric power usage to low cost. Here we have considered households and business meters approximately 2000 with unique id of each meter. The data of three months is used for user preference of starting appliance. The predictive accuracy of proposed methodology for usage mining and optimization is improved by average 4 %. Different input data features are used to form clusters of meters with similar power consumption behaviour for household occupancy. The clustering accuracy for household occupancy is improved from 0.68 to 0.91. The impact of accurate household occupancy detection and appliance usage mining and optimization is in reduction of electric power cost. The consumer can see how electric power efficiency and time-of-use shift makes a difference using experimental setup.

Demand side management with wireless channel impact in IoT-enabled smart grid system

Demand Side Management (DSM) is a vital issue in smart grids, given the time-varying user demand for electricity and power generation cost over a day. On the other hand, wireless communications with ubiquitous connectivity and low latency have emerged as a suitable option for smart grid. The design of any DSM system using a wireless network must consider the wireless link impairments, which is missing in existing literature. In this paper, we propose a DSM system using a Real-Time Pricing (RTP) mechanism and a wireless Neighborhood Area Network (NAN) with data transfer uncertainty. A Zigbee-based Internet of Things (IoT) model is considered for the communication infrastructure of the NAN. A sample NAN employing XBee and Raspberry Pi modules is also implemented in real-world settings to evaluate its reliability in transferring smart grid data over a wireless link. The proposed DSM system determines the optimal price corresponding to the optimum system welfare based on the two-way wireless communications among users, decision-makers, and energy providers. A novel cost function is adopted to reduce the impact of changes in user numbers on electricity prices. Simulation results indicate that the proposed system benefits users and energy providers. Furthermore, experimental results demonstrate that the success rate of data transfer significantly varies over the implemented wireless NAN, which can substantially impact the performance of the proposed DSM system. Further simulations are then carried out to quantify and analyze the impact of wireless communications on the electricity price, user welfare, and provider welfare.

Simulating appliance-level household electricity data: Accounting for residential behavior and usage patterns in China

Data scarcity presents a significant challenge for improving deep learning algorithms in Non-intrusive Load Disaggregation. These algorithms heavily rely on extensive appliance electricity consumption data, which is expensive to gather through on-site measurements. Therefore, generating simulated data has emerged as a viable alternative. However, existing approaches often randomly combine appliance power, failing to capture realistic household electricity usage patterns. To address this, this study investigates the dynamics of household electricity consumption throughout a 24-h day, considering factors such as household size, age, occupation, and education. Markov chains and Variational Auto-encoder are employed as a data generation model to simulate electrical power consumption data. Appliance power consumption data are aggregated to represent the total household load by incorporating resident electricity consumption behavior. Comparing the generated data with actual data from a self-measurement dataset, the Jensen-Shannon divergence, RMSE, and MAE are utilized to assess their similarity, and the Entropy and the Coefficient of Variation are utilized to evaluate randomness and volatility. The results indicate a high level of distribution similarity between the generated and actual data. Moreover, the observed variations show the model's capability to produce diverse and rich datasets. Overall, this research demonstrates the value of simulated data created as a low-cost method for Non-intrusive Load Disaggregation.

Anomaly‐detection‐based learning for real‐time data processing in non‐intrusive load monitoring

AbstractA power system can be regarded as a cyber‐physical system with physical power networks and a cyber system based on increasing engagement with information communication technologies for smart grid functionalities for more efficient operations and control. Non‐intrusive load monitoring (NILM), an emerging smart‐grid technology, can be used to better understand the electricity usage profile and composition of smart meters using advanced data analysis algorithms. Although NILM enables various smart grid services, wider applications of NILM require addressing the challenges regarding cyber security and data privacy risks. Anomaly detection in appliance data is one of the most effective measures against potential cyber intrusions from a data perspective. This study proposes a framework of anomaly detection‐based learning algorithms to identify the anomalous periods of electricity loading data, which may be a subject for potential cyber‐attacks. Comparison studies with the hidden Markov model are performed to validate the proposed approaches. The simulation results show that these anomaly detection‐based learning algorithms work well and can precisely determine anomalous loading periods. Moreover, these trained models perform well on the testing dataset without prior knowledge of the data, providing the possibility of the real‐time assessment of power‐ loading states. The proposed framework can also be used to develop protective measures to ensure secure system operation and user data privacy.

Grounding Resistance Monitoring Device for Improved Construction Electricity Safety in Pumped Storage Power Station Construction

Abstract During the construction period of pumped storage power stations, there are prominent safety hazards in the use of electricity. Most of the underground chambers are in rocky environments, and it is difficult to meet the standard requirements for the grounding resistance of nearby distribution boxes. In addition, due to the high humidity and large amount of dust in the chambers, the grounding terminals are prone to oxidation. Furthermore, frequent blasting operations can cause poor contact of the grounding terminals, resulting in the inability to effectively guide the leakage current into the earth and causing electric shock injury. By using the TN-S wiring method, the leakage current of the equipment and distribution box is guided into the ground grid through the PE line. At the same time, a real-time monitoring system is established for the PE line, which monitors the integrity of the PE line resistance between the third-level distribution box and the transformer ground grid. When an integrity failure occurs, an alarm is quickly issued, enabling maintenance personnel to promptly detect and repair the fault, ensuring that all leakage currents have a good export channel, and further guaranteeing the safety of electricity users.

Transmission Line Power Theft

Abstract: Generation, transmission and distribution of electrical energy involve many operational losses. We can defined the losses in generation technically but distribution and transmission losses cannot be precisely quantified with the sending end information. This illustrates the involvement of nontechnical parameter in transmission and distribution of electricity. Moreover technical losses occur naturally and are caused because of power dissipation in transmission lines, transformers, and other power system components. Technical losses in Transmission & Distribution are computed with the information about total load and the total energy bill. While technology in the raising slopes, we should also note the increasing immoral activities. The system prevents the illegal usage of electricity. At this point of technological development the problem of illegal usage of electricity can be solved without any human control using IoT. With the implementation of this system will save large amount of electricity, and there by electricity will be available for more number of consumer then earlier, in highly populated country such as India, China. Power theft can be defined as the usage of the electrical power without any legal contract with the supplier. To see it, a proposed system (current measurement and comparison) is proposed in which the distribution of family power is done indirectly from the distribution box to each house. Power theft is a persistent issue in many countries, leading to significant financial losses for utility companies and affecting the reliability of power supply. In this study, we propose a novel approach for detecting power theft in transmission lines using NodeMCU ESP8266, a low-cost Wi-Fi-enabled microcontroller, and Blynk IoT platform for remote monitoring and control.The proposed system involves installing current sensors at various locations along the transmission lines to measure the current flow. The NodeMCU ESP8266 is used as a data acquisition unit that collects the current data from the sensors and sends it to the Blynk IoT platform via Wi-Fi for real-time monitoring. The Blynk platform provides a user-friendly interface for visualizing the data and setting up alarms and notifications for abnormal current patterns, which could indicate power theft. The system can also track power consumption trends, identify abnormal usage patterns, and provide insights for optimizing power distribution. The proposed system has several advantages, including low-cost implementation, real-time monitoring, remote access, and easy customization through the Blynk platform. It has the potential to significantly reduce power theft, improve revenue collection for utility companies, and enhance the overall reliability of power supply in transmission lines. Further research and development can be done to optimize the system's performance and expand its applications in different power distribution scenarios.

Monitoring the Use of Electrical Energy and Water in Homes Based on IoT

Increased awareness of energy efficiency and sustainable resource management has encouraged the development of intelligent electrical energy and water usage monitoring systems. In this context, the Internet of Things (IoT) has become a promising solution for connecting household devices to the internet, enabling users to monitor and control electricity and water consumption in real-time. This research aims to design and implement an IoT-based monitoring system for electrical energy and water usage in homes. This system uses a powerful Arduino ESP32 microcontroller and can connect to the internet via WiFi. This microcontroller acts as a control center that collects data from sensors installed in the house. Based on these problems, this research was carried out, with the aim of creating a prototype to record electrical power loads and display the amount of electricity consumption in rupiah levels to monitor the use of electrical power loads and convert them into rupiah. To conduct this research, the author used observational research methodology or field study and literature study. In this research, it is necessary to pay attention to understanding how to think and how to carry out the results of thinking according to scientific steps.

Rancang Bangun Sistem Kontrol Dan Monitoring Beban 1 dan 3 Phasa Pada Panel Distribusi Berbasis Internet of Things

The distribution panel is a place to distribute and distribute electrical energy from the power panel to the load panel (consumer) for both power installations and lighting installations. The main problem with every disturbance or improvement in electricity usage is that people need to come to the area to control and monitoring the panel manually. This research focuses on the design and manufacture of control and monitoring devices at 3 and 1 phase loads, with the method using NodeMCU esp 32/8266 with pzem004t sensor as control and reading of voltage, current and frequency on the panel, which can be viewed and controlled offline at panel or online using the blynk application. The testing of the tool is carried out using a 3-phase motor, PC monitor, fan, laptop charger, and chicken lamp. By turning on the load one by one or simultaneously. From the test results, the tool can turn on and off online through the blynk application and manually using a push button. the results obtained are quite accurate with a maximum error percentage of 8.70%. However, the microcontroller between control and monitoring is used separately.

Smart Energy Meter by Using IOT

Abstract: It is an IOT based paper electricity is one of the fundamental necessities of human beings which is commonly Used for Domestic, Agriculture, Industrial purpose. Power theft and Meter billings are biggest problems in recent days which causes a lot of loss to electricity board. If we can prevent these thefts we can save a lot of power. This is done by Smart Energy Meter by using IOT, present an efficient and cost-effective way to transfer the information of energy consumed by consumer wirelessly as well as it provides facilities to detect illegal usage of electricity. Smart Energy meter by using IOT basically consists of three major components namely controller, Wi- Fi, theft detection device. Whenever there is any fault or theft, the theft detector sensor detects the error. The controller plays a crucial role in keeping all the components in the working state. In this system the energy meter is connected to internet. The proposed system is capable of continuously monitoring and being notified about the number of units consumed to energy provider and consumer. The energy consumption is calculated automatically, and the bill is updated on the internet by using a network of internet of things. This automation can eliminate the manual work in electricity maintenance. In this paper mainly focuses on automatic billing, theft detection, power optimization and providing the relevant energy consumption information to user.

Energy Consumption Analysis in SCADA: A Case Study in the Glass Container Industry

Given the present geopolitical scenario and global energy crisis, there is a growing demand to cut energy use, particularly in industry. The glass package manufacturing business has been severely hit by the rise in energy prices in recent years, and most likely this trend will continue. There is a lack of instruments for effiectively anticipating furnace usage when it comes to managing the infrastructure's energy expenditure in the glass industry, which is the case of the BA Glass Avintes company. Because the furnaces are the key energy expenditure source in the plant, getting a thorough understanding of their energy consumption is an important step towards making educated decisions. The purpose of this study is to undertake a detailed analysis of gas and electricity usage for the three furnaces at the BA Glass Avintes facility using data obtained from PowerStudio SCADA. It was investigated which regression model produced the best accurate results when precisely adjusted to the BA Glass Avintes shop-floor setting. The findings indicate that linear regression models may not be appropriate for this application, however tree-based methods, notably the decision tree model, provide promising outcomes. Furthermore, for increased model performance, the study emphasises the necessity of a bigger training dataset and a shorter prediction interval.

Are We the Reason for Climate Change?

Abstract: Climate change is a pressing global issue, primarily driven by human activities such as burning fossil fuels, deforestation, and industrial processes, which release greenhouse gases into the atmosphere. This study explores the evidence supporting the human role in climate change, assessing individual carbon footprint patterns and their contribution to greenhouse gas emissions. It discusses various human activities leading to carbon emissions and presents a method for calculating individual carbon footprints. Additionally, it outlines strategies to reduce carbon footprints, including using public transport, minimizing electricity usage, and promoting sustainable practices like recycling and planting trees. This study highlights the urgent need for collective action to address climate change, emphasizing the critical importance of transitioning to sustainable energy sources and adopting mitigation strategies to limit temperature rise.

ANALISIS PEMASANGAN TRANSFORMATOR SISIP UNTUK MENGATASI TRAFO PSG.039 OVERLOAD PENYULANG MG.07 DI ULP MATANG GELUMPANG DUA

The MG.07 Substation in Matang Gelumpang Dua is located in the PT. PLN (Persero) Customer Service Unit Matang Gelumpang Dua Area Bireun, supplied by the Bireun Main Substation with a feeder capacity of 280 A. The MG.07 feeder supplies transformer PSG.039, loaded at 103.4% of its 250 kVA capacity. The standard load for a transformer is 80% of its capacity. The solution to address this issue is to install an insert transformer to distribute the load from PSG.039. According to data from PT. PLN (Persero) Area Bireun in 2023, the annual increase in electricity usage in Matang Gelumpang Dua Bireun is 8.3%. Therefore, using a 250 kVA insert transformer with an initial loading percentage of 26.8%, it will be able to accommodate the increase in electricity usage for the next five years, with a total loading percentage after five years of 68.3%.

Systematic Review of Models Usedto Handle Class Imbalance in Anomaly Detection for Energy Consumption

The widespread integration of Smart technologies into energy consumption systems has brought about a transformative shift in monitoring and managing electricity usage. The imbalanced nature of anomaly data often results in suboptimal performance in detecting rare anomalies. This literature review analyzes models designed to address this challenge. The methodology involves a systematic literature review based on the five-step framework proposed by Khan, encompassing framing research questions, identifying relevant literature, assessing article quality, conducting a critical review, and interpreting results. The findings show that classical machine learning models like Support Vector Machines (SVM) and Random Forests (RF) are commonly used. In conclusion, classical machine learning models like SVM and RF struggle to recognize rare anomalies, while deep learning models, notably Convolutional Neural Networks (CNNs) and Long Short-Term Memory (LSTM), show promise for automatically learning elaborate representations and improving performance while dealing with class imbalance.