Energy Monitoring Research Articles

Improving Intrusion Detection using Satin Bowerbird Optimization with Deep Learning Model for IIoT Environment

Intrusion Detection in the Industrial Internet of Things (IIoT) concentrations on the security and safety of critical structures and industrial developments. IIoT extends IoT principles to industrial environments, but linked sensors and devices can be deployed for monitoring, automation, and control of manufacturing, energy, and other critical systems. Intrusion detection systems (IDS) in IoT drive to monitor network traffic, device behavior, and system anomalies for detecting and responding to security breaches. These IDS solutions exploit a range of systems comprising signature-based detection, anomaly detection, machine learning (ML), and behavioral analysis, for identifying suspicious actions like device tampering, unauthorized access, data exfiltration, and denial-of-service (DoS) attacks. This study presents an Improving Intrusion Detection using Satin Bowerbird Optimization with Deep Learning (IID-SBODL) model for IIoT Environment. The IID-SBODL technique initially preprocesses the input data for compatibility. Next, the IID-SBODL technique applies Echo State Network (ESN) model for effectual recognition and classification of the intrusions. Finally, the SBO algorithm optimizes the configuration of the ESN, boosting its capability for precise identification of anomalies and significant security breaches within IIoT networks. By widespread simulation evaluation, the experimental results pointed out that the IID-SBODL technique reaches maximum detection rate and improves the security of the IIoT environment. Through comprehensive experimentation on both UNSW-NB15 and UCI SECOM datasets, the model exhibited exceptional performance, achieving an average accuracy of 99.55% and 98.87%, precision of 98.90% and 98.93%, recall of 98.87% and 98.80%, and F-score of 98.88% and 98.87% for the respective datasets. The IID-SBODL model contributes to the development of robust intrusion detection mechanisms for safeguarding critical industrial processes in the era of interconnected and smart IIoT environments.

Design and Performance of a Solar-Powered Single-Phase Smart Energy Monitoring System

Design and Performance of a Solar-Powered Single-Phase Smart Energy Monitoring System

MULTIMODAL ANESTHESIA AS AN IMPORTANT COMPONENT OF ERAS

Introduction. The ideology of Fast Track-Surgery (FTS) and Enhanced Recovery After Surgery (ERAS) represents modern trends in global surgical practice. Anesthesiology aims to provide ideal and universal solutions for protecting patients from surgical aggression. A multimodal approach, which includes multilevel, multifaceted antinociception, is well-founded, where maximum effectiveness is combined with minimal side effects.
 The aim. To analyze the issue of multimodal pain management as an important component of ERAS (Enhanced Recovery After Surgery) from modern sources of literature for optimizing perioperative care in the minimally invasive surgery department.
 Materials and methods. Bibliosemantic, comparative, and systemic analysis methods were employed. The proposed recommendations were developed based on an analysis of modern literature, the results of randomized trials and meta-analyses, as well as our own studies dedicated to the study of perioperative pain issues.
 The results. It has been proven that the use of opioids in anesthesia practice is decreasing. New and modern methods of continuous monitoring of vital organs in patients are being introduced as supplements to classical monitoring protocols. These methods are used to avoid excessive or inadequate dosing of anesthetics, adjust the concentration of substances used, reduce post-anesthesia complications, and improve patient comfort. The method of perioperative energy monitoring significantly complements the "International Standards for Safe Anesthetic Practice", WFSA (2010), and enhances perioperative patient safety by detecting metabolic disturbances and implementing appropriate pathogenetic correction. The importance of regional anesthesia under ultrasound control, nociception-antinociception balance management, and the impact of these methods on opioid consumption, patient satisfaction, and postoperative recovery have been proven.
 Conclusions. The most commonly used combination of drugs for multimodal analgesia often includes acetaminophen and NSAIDs (strong recommendation). It has been proven that deep and prolonged sedation in intensive care unit (ICU) patients is associated with worse outcomes, longer mechanical ventilation duration, extended ICU and hospital stays, and higher rates of complications, including infections and sometimes even death.

Real-Time Human Activity Recognition on Embedded Equipment: A Comparative Study

As living standards improve, the growing demand for energy, comfort, and health monitoring drives the increased importance of innovative solutions. Real-time recognition of human activities (HAR) in smart homes is of significant relevance, offering varied applications to improve the quality of life of fragile individuals. These applications include facilitating autonomy at home for vulnerable people, early detection of deviations or disruptions in lifestyle habits, and immediate alerting in the event of critical situations. The first objective of this work is to develop a real-time HAR algorithm in embedded equipment. The proposed approach incorporates the event dynamic windowing based on space-temporal correlation and the knowledge of activity trigger sensors to recognize activities in the case of a record of new events. The second objective is to approach the HAR task from the perspective of edge computing. In concrete terms, this involves implementing a HAR algorithm in a “home box”, a low-power, low-cost computer, while guaranteeing performance in terms of accuracy and processing time. To achieve this goal, a HAR algorithm was first developed to perform these recognition tasks in real-time. Then, the proposed algorithm is ported on three hardware architectures to be compared: (i) a NUCLEO-H753ZI microcontroller from ST-Microelectronics using two programming languages, C language and MicroPython; (ii) an ESP32 microcontroller, often used for smart-home devices; and (iii) a Raspberry-PI, optimizing it to maintain accuracy of classification of activities with a requirement of processing time, memory resources, and energy consumption. The experimental results show that the proposed algorithm can be effectively implemented on a constrained resource hardware architecture. This could allow the design of an embedded system for real-time human activity recognition.

Airborne atmospheric carbon dioxide measurement using 1.5 µm laser double-pulse IPDA lidar over a desert area.

An integrated path differential absorption (IPDA) lidar can accurately measure regional C O 2 weighted column average concentrations (X C O 2), which are crucial for understanding the carbon cycle in climate change studies. To verify the performance and data inversion methods of space-borne IPDA lidar, in July 2021, we conducted an airborne lidar validation experiment in Dunhuang, Gansu Province, China. An aircraft was equipped with a lidar system developed to measure X C O 2 and an in situ greenhouse gas analyzer (GGA). To minimize measurement errors, energy monitoring was optimized. The system bias error of the DAOD was determined by changing the laser output mode from the off/on to the on/on mode. The X C O 2 inversion results obtained through comparing the schemes of averaging signals before "log (logarithm)" and averaging after "log" indicate that the former performs better. The IPDA lidar measured X C O 2 over the validation site at 405.57ppm, and both the IPDA lidar and GGA measured sudden changes in the C O 2 concentration. The assimilation data showed a similar trend according to the altitude to the data measured by the in situ instrument. A comparison of the mean X C O 2 derived from the GGA results and assimilation data with the IPDA lidar measurements showed biases of 0.80 and 1.12ppm, respectively.

Implementasi Sistem Monitoring Alat Pengering Biji Kopi Berbasis IoT (Internet of Things)

Indonesia holds the third position in global coffee bean supply, with a 3.3% increase in demand in 2021 according to ICO data. In line with ICO Resolution 407, coffee bean quality must be high, indicated by a 12.5% moisture content through drying processes. Mechanical drying is faster than traditional methods, thus becoming the focus of this research. This study implements an IoT-based monitoring system for coffee bean drying equipment. The aim is to create and implement a monitoring system for temperature (0°C - 70°C) and electrical energy consumption (kWh) in coffee bean drying, displayed on the ThingSpeak dashboard. Test results show that the temperature monitoring system using DHT22 sensors at the inlet and outlet of the rotary dryer tube has an average error of 2.1%. The energy monitoring system using PZEM-004T has a 0% energy measurement error. These results indicate a reliable monitoring system that enables remote monitoring via the internet. Furthermore, the study tests manual (on/off) and fuzzy logic control methods to achieve 12% moisture content in coffee beans. The fuzzy logic control method demonstrates better temperature stability and 11.2% cost savings in operational expenses. This research benefits coffee farmers by facilitating efficient monitoring of the bean drying process, and recommends the use of the fuzzy logic control method for stable temperature and lower operational costs.

Energy Management of a Low-Cost Power Meter using ESP8266 and PZEM-016


 
 
 The burgeoning significance of the Internet of Things (IoT) lies in its capacity to configure interconnected environments and facilitate human-object interactions through collaborative services. This study proposes an efficient energy management approach leveraging cost-effective technologies like the ESP8266 microcontroller and the PZEM-016 Modbus RTU energy monitoring module. Tailored towards wireless connectivity, this solution is purposefully crafted for diverse sectors operating within constrained budgets, obviating the need for intricate infrastructure. A systematic deployment of the forward engineering research methodology is undertaken to discern the requisites and hurdles inherent in energy management. The amalgamation of ESP8266, PZEM-016, and the MQTT protocol, with RabbitMQ serving as a message broker, forges an efficacious framework for inter-device information exchange. The solution's instantiation entails the interconnection of power meter devices using the MQTT protocol, transmitting data in JSON format. The PZEM-016 sensor constitutes the crux, adeptly measuring voltage, current, frequency, and power with precision. Furthermore, the solution encompasses a prototype Smart Meter fortified with Wi-Fi connectivity to the internet, thus extending network coverage ubiquitously. Economic scrutiny reveals that the resultant power meter device costs less than 100 USD, competitively positioning it against analogous market offerings. This economically optimized design advocates for widespread adoption across multifarious sectors constrained by budgetary limitations, assuaging the complexities inherent in energy management through a trifecta of efficiency, reliability, and affordability.
 
 

Flexible Zn-ion Electrochromic Batteries with Multiple-color Variations.

Electrochromic batteries as emerging smart energy devices are highly sought after owing to their real-time energy monitoring through visual color conversion. However, their large-scale applicability is hindered by insufficient capacity, inadequate cycling stability, and limited color variation. Herein, a flexible Zn-ion electrochromic battery (ZIEB) was assembled with sodium vanadate (VONa+) cathode, ion-redistributing hydrogel electrolyte, and Zn anode to address these challenges. The electrolyte contains anchored -SO3 - and -NH3 +, which facilitates ionic transportation and prevents Zn dendrite formation by promoting orientated Zn2+ deposition on the Zn (002) surface. The ZIEB exhibits a continuous reversible color transition, ranging from fully charged orange to mid-charged brown and drained green. It also demonstrates a high specific capacity of 302.4 mAh ⋅ g-1 at 0.05 A ⋅ g-1 with a capacity retention of 96.3 % after 500 cycles at 3 A ⋅ g-1. Additionally, the ZIEB maintains stable energy output even under bending, rolling, knotting, and twisting. This work paves a new strategy for the design of smart energy devices in wearable electronics.

Flexible Zn‐ion Electrochromic Batteries with Multiple‐color Variations

AbstractElectrochromic batteries as emerging smart energy devices are highly sought after owing to their real‐time energy monitoring through visual color conversion. However, their large‐scale applicability is hindered by insufficient capacity, inadequate cycling stability, and limited color variation. Herein, a flexible Zn‐ion electrochromic battery (ZIEB) was assembled with sodium vanadate (VONa+) cathode, ion‐redistributing hydrogel electrolyte, and Zn anode to address these challenges. The electrolyte contains anchored −SO3− and ‐NH3+, which facilitates ionic transportation and prevents Zn dendrite formation by promoting orientated Zn2+ deposition on the Zn (002) surface. The ZIEB exhibits a continuous reversible color transition, ranging from fully charged orange to mid‐charged brown and drained green. It also demonstrates a high specific capacity of 302.4 mAh ⋅ g−1 at 0.05 A ⋅ g−1 with a capacity retention of 96.3 % after 500 cycles at 3 A ⋅ g−1. Additionally, the ZIEB maintains stable energy output even under bending, rolling, knotting, and twisting. This work paves a new strategy for the design of smart energy devices in wearable electronics.

Predicting building energy consumption in urban neighborhoods using machine learning algorithms

Assessing building energy consumption in urban neighborhoods at the early stages of urban planning assists decision-makers in developing detailed urban renewal plans and sustainable development strategies. At the city-level, the use of physical simulation-based urban building energy modeling (UBEM) is too costly, and data-driven approaches often are hampered by a lack of available building energy monitoring data. This paper combines a simulation-based approach with a data-driven approach, using UBEM to provide a dataset for machine learning and deploying the trained model for large-scale urban building energy consumption prediction. Firstly, we collected 18,789 neighborhoods containing 248,938 buildings in the Shanghai central area, of which 2,702 neighborhoods were used for UBEM. Simultaneously, building functions were defined by POI data and land use data. We used 14 impact factors related to land use and building morphology to define each neighborhood. Next, we compared the performance of six ensemble learning methods modeling impact factors with building energy consumption and used SHAP to explain the best model; we also filtered out the features that contributed the most to the model output to reduce the model complexity. Finally, the balanced regressor that had the best prediction accuracy with the minimum number of features was used to predict the remaining urban neighborhoods in the Shanghai central area. The results show that XGBoost achieves the best performance. The balanced regressor, constructed with the 9 most contributing features, predicted the building rooftop photovoltaics potential, total load, cooling load, and heating load with test set accuracies of 0.956, 0.674, 0.608, and 0.762, respectively. Our method offers an 85.5%-time advantage over traditional methods, with only a maximum of 22.75% of error.

Energy and Performance Centric Resource Allocation Framework in Virtual Machine Consolidation Using Reinforcement Learning Approach

Abstract:: Virtual machines are used to reduce cloud platform application performance, management costs, and access irregularities. Virtual machines are frequently vulnerable to delays, overburdening workloads, and other obstacles while consolidating and migrating servers. To significantly disperse loads among virtual machines, dynamic consolidation techniques are implemented to control energy dissipation, monitor overloading, and address underloading problems. Background:: The process of consolidation involves more calculations and resources in order to transfer services between virtual machines, provided that Service Level Agreements are observed. Methods:: The suggested approach promotes the use of cutting-edge architecture to combine virtual machines, and, therefore, strike a balance between performance and energy requirements. The main design considerations for the suggested Dynamic Weightage algorithm, which includes the clustering approach in relation to reinforcement learning approaches, are overall resource needs and Performance to Power Ratio (PPR). A cluster of ideal virtual machines is created, and resources are distributed according to performance and energy requirements. Virtual machine resource requests are converted into a matching relationship factor, which represents the individual hosts while taking PPR into account. The overall workload associated with virtual machine consolidation is also provided by these estimations. It is noted that there is little energy trade-off and that performance is maintained at a nominal level across the cluster. The architecture is put into practice throughout offline platforms, which are dispersed ecosystems that allow for increased system performance and scaling. Results:: The CloudSim simulator is used to validate the system using datasets that are obtained from PlanetLab. According to the data, energy saving has produced yields of up to 47% and promising quality of service attributes. Conclusion:: The validation of the system is performed using the CloudSim simulator with datasets from PlanetLab. The results indicate significant energy conservation, up to 47%, along with promising quality of service parameters. The proposed architecture is compared with other state-of-the-art algorithms for distributed architectures and heterogeneous environments, showcasing its efficiency. The conclusion emphasizes the prioritization of VM consolidation and energy efficiency in the proposed architecture, which has been tested on a Proliant G7- based data center using a variety of hosts. Notably, the CloudSim Toolkit is highlighted as outperforming OpenStack-based techniques in simulation results.

Analysis of measures to increase the energy efficiency of educational buildings of the national university of water and environmental engineering

The implementation of energy-efficient measures at the National University of Water and Environmental Engineering (NUWEE) was started since 2000. The buildings of NUWEE are located in different parts of Rivne city and Rivne region. Buildings № 1-7 were selected by the Ministry of Education and Science of Ukraine for financing their thermal modernization as part of the loan project "Higher Education of Ukraine. Energy efficiency and sustainable development" with the aim of increasing their energy efficiency. The authors analyzed the measures to increase the energy efficiency of the educational buildings of the NUWEE, namely, the installation of thermal insulation of facades, roofs, floors on the ground and first surfaces, replacement of windows and doors, installation of thermal insulation of pipelines, modernization of automated thermal energy regulation units (ATERU), heating system and lighting, implementation of the energy monitoring and dispatching system, installation of the ventilation system with exhaust air heat recovery. Implementation of the proposed measures will reduce energy consumption and related costs by 60 %, namely by 6,232 MWh/year (compared to the baseline level of energy consumption of 10,286 MWh/year). It will result increasing of the buildings’ comfort and functionality. After the implementation of the described measures, the increase of the energy efficiency class of educational buildings is predicted. The implementation of energy-efficient measures will also lead to the reduction of greenhouse gas emissions by 50 %, namely by 1,648 t/year. Measures that can pay off as soon as possible are the implementation of thermal insulation of pipelines, modernization of ATERU and lighting, implementation of energy monitoring and dispatching systems. The longest payback period will require the installation of ventilation air heat recovery, but this measure is necessary in view of the current reduction in heat energy costs for heating the external supply air in the cold period of the year.

Design and Construction of a Multi-User Prepaid Meter

The Nigerian government has used prepaid metering for nearly two decades to eliminate post-paid and estimated billing system. There is no doubt that this billing system has benefited house owners who do not have renters as well as a few persons who have the advantage of knowing the exact number of prepaid meters for their apartments. Those living in rental apartments, on the other hand, experience the identical problem with postpaid when a single prepaid meter is divided among inhabitants. Sharing a single prepayment frequently violates the aim of prepaid metering because individual use cannot be reliably tracked. To address the issue of sharing, a unique type of prepaid meter that can handle multiple users on a single prepaid is required. As a result, this study proposes a multi-user prepaid meter that completely prevent conflicts that arise from the sharing of prepaid meters. A prototype for four users was planned and built around Radio-Frequency Identification (RFID) technology for individual user identification; a quasi-current sensor to measure energy usage and an Arduino Uno microcontroller ATmega 328p to manage the activities of the system. From the process of recharging to the display unit and other aspects that permit remote transaction of the device, the designed multi-user prepaid energy monitoring system functions well. To address the demand for unmetered houses across the country, the prepaid meter could be mass produced. Considering the different obstacles people have as a result of the low distribution of prepaid meters, this multi-user prepaid meter will undoubtedly be a promising technology to suit Nigerians' demands while also eliminating potential problems with prepaid meter sharing.

The Role of Low-Cost Digital Solutions in Supporting Industrial Sustainability

Small and medium enterprise (SME) manufacturers are impeded from participating in sustainability initiatives using new technologies due to the high cost and the lack of clarity on where to start. The integration of low-cost digital solutions has enabled SME manufacturers to adopt Industry 4.0 technologies to support operations. However, using low-cost technologies to address sustainability challenges is underexplored. This article addresses three key research questions: What digital solutions do SMEs need to address industrial sustainability challenges? To what extent can existing low-cost digital solutions be used to address industrial sustainability challenges? How should new digital solutions for developing greater sustainability be prioritised? Three main tasks were conducted. Initially, a new sustainability-focused sub-catalogue was created using an existing catalogue of low-cost solution areas for manufacturing. Secondly, a workshop with 17 participants was used to identify the top ten priority solution areas, with process monitoring, energy monitoring, and quality inspection at the top. Lastly, existing low-cost digital solutions within the top ten priority areas were evaluated to identify how they could contribute to lean manufacturing. Predominantly existing solutions could contribute to waste or use reduction in lean manufacturing. This study provides a foundation for the future development of low-cost solutions for sustainability by indicating manufacturers’ key priority areas and outlining how existing solutions could be adapted to support waste reduction.

Evaluation of regression models and Bayes-Ensemble Regressor technique for non-intrusive load monitoring

Non-Intrusive Load Monitoring (NILM) is referred to as the task of decomposing the aggregated power load of a residential or commercial building into appliance-level consumption without the installation of dedicated smart meters. NILM, mostly considered as a supervised learning problem, is crucial for energy monitoring and management as this approach can detect load malfunction and prevent wastage of energy consumption. For most of regression based NILM research, not much work has been done in analyzing data against temporal parameters such as day of the week, week of the month, week of the year, and various quarters in a year. Additionally, various NILM research works focus on finding the best regression model for predicting appliance consumption but discards the fact that appliance usage varies on factors such as seasons, different working hours, and weekends. This paper aims to evaluate some regression algorithms used towards NILM research based on 8 different training and testing Methods which according to our knowledge covered major factors that affect the appliance usage. The dataset used for the evaluation of the regression models, were collected from a research lab at Grenoble INP, in Grenoble, France. The evaluation results show that instead of one algorithm, individual regression algorithms generated favorable outcomes for various appliances based on different train-test Methods. Furthermore, a novel Bayesian optimized Ensemble regressor model for predicting individual appliance consumption from aggregated load data is also proposed. Instead of just using the aggregated power information, the proposed model also uses temporal information of the dataset to estimate accurate consumption output of individual appliances. Extensive simulation results corroborate the merits of the proposed approach, which outperforms the benchmarking Methods. To ensure reproducibility of the results by the research community and a potential future improvement of the framework by other researchers, the complete source code is provided in the following repository: https://github.com/Mohammad-Kaosain-Akbar/NILM-Ensemble-Bayesian-Optimization

Real-time energy monitoring systems: Technological applications in Canada, USA, and Africa

Real-time energy monitoring systems are pivotal for reshaping the global energy landscape, optimizing consumption, and fostering sustainability. This research explores the technological, regional, and socio-economic dimensions of energy monitoring, focusing on Canada, the USA, and Africa. The technological landscape includes sensor technologies, communication protocols, and emerging innovations like AI and blockchain. Regional perspectives highlight diverse challenges and opportunities, while a cross-regional analysis emphasizes collaboration and mutual learning. Challenges such as data security and integration are viewed as catalysts for improvement. Real-time monitoring's impact on sustainability is profound, reducing carbon footprints, optimizing resource utilization, and yielding economic benefits. Improved access to energy and community engagement underscores its positive social impact. The global journey towards sustainability is enhanced through collaboration, technology transfer, and the collective pursuit of a resilient and environmentally conscious energy future.

Study on the precursor characteristics of coal energy spontaneous combustion process using infrasound wave monitoring and warning

The spontaneous combustion of coal energy has seriously threatened energy security, and there is an urgent need for monitoring and warning of coal energy. Therefore, this article innovatively proposes a method of using infrasound waves to monitor coal energy spontaneous combustion, establishes a coal spontaneous combustion(CSC) infrasound wave experimental testing system, and studies the precursor characteristics of coal energy spontaneous combustion process. The results indicate that there is a good positive correlation between the amplitude of the dominant frequency of the infrasound wave generated by CSC and temperature, with a correlation coefficient of R2 > 0.85. The energy proportion of the infrasound signal from 0 to 0.12Hz exceeds 80 %. And as the CSC stage progresses, the energy of infrasound waves in the 0.04–0.08Hz frequency band increases significantly, and the changes in infrasound signals in this frequency band have a good correlation with temperature, with a correlation coefficient above 0.8. This frequency band is the main frequency band of infrasound waves during the CSC process. The research in this article provides a theoretical basis for the application of infrasound wave monitoring and warning of coal energy spontaneous combustion, and it is of great significance to ensure the safe mining of coal energy.

An inclined pedal type piezoelectric energy harvester for pedestrian flow and vehicle safety monitoring

This paper proposed an inclined pedal-type piezoelectric energy harvester for pedestrian monitoring and vehicle safety monitoring (IPEH). The IPEH exterior adopts an inclined pedal design, the steel ball is placed inside its cylindrical channel to excite the piezoelectric patches to harvest and convert external mechanical energy. IPEH can be placed under the brake pedal of a car for the function of vehicle safety monitoring. IPEH can also be fixed on the road as an energy harvester and monitoring device, harvesting pedestrian trampling energy and monitoring the density of pedestrian traffic in realtime. The influence of the steel ball diameter and spring layout on the output performance of the prototype is studied in this paper. Under the best parameters of the prototype assembly, the maximum output voltage is 165.6 Vpp, and the maximum output power is 463.7 mW. In the application experiment, the practicability in energy harvesting applications of IPEH is verified through the experiment of lighting LEDs and charging capacity, and the monitoring ability of IPEH was verified by simulating the experiment of different human flow walking and vehicle braking. It provides a new idea for the subsequent application of piezoelectric equipment in traffic auxiliary facilities and intelligent sensing equipment.

Multichannel energy monitoring based on the sliding window method in an industrial environment

The research on nonintrusive load monitoring (NILM) typically focuses on residential and commercial users. However, high-energy industrial users also require load monitoring analysis to understand their electricity consumption patterns and load operating conditions. Currently used load monitoring methods and parameters are not applicable to industrial environments. In this paper, we propose an innovative multichannel low window sequence-to-point (MLSP) method based on deep neural networks for NILM of high-energy industrial users. First, the data from each channel of the main line terminal are normalized and then aggregated into a time series, which is several times longer than the original data to expand its data volume. Then, the multichannel low window sequence-to-point method is used to select the window data of several times the length, corresponding to the active power of the target device. Finally, the discriminative features of the data are learned using a deep neural network model. The analysis of actual industrial user data shows that the lowest mean absolute error (MAE) of the original sequence-to-point method for related branches is 20.38, and the highest correlation coefficient (CC) is 90.23%. Our proposed method reduces the MAE to 11.02 and increases the CC to 97.42%. The MAE and CC indicators of all branches decreased by 25.8% and increased by 22.4%, respectively. According to Mean Absolute Percentage Error (MAPE), the performance of this model is improved by 39.6% compared with Seq2point. Compared with the original sequence-to-point method, our proposed method achieves better load monitoring results and can more accurately decompose load fluctuations, which are closer to the actual load curve.

China's local-level monthly residential electricity power consumption monitoring

Timely implementation of electricity power consumption (EPC) analysis and evaluation helps assess energy-saving potential and develop energy management plans. Yet, timely EPC data of subnational regions are usually public unavailable, especially for developing countries. Lacking timely and local EPC data makes it difficult to satisfy the requirements for local governments to quickly monitor energy consumption and establish early warning mechanisms. As a solution, this study establishes a quick accounting method for local residential EPC utilizing nighttime light data, based on which we investigate the variations in residential EPC before and after the COVID-19 pandemic. Our method has demonstrated robust performance in estimation and proven its reliability. Compared to previous studies, the proposed methodology has four advantages. First, it monitors local-level residential EPC data at a monthly scale, which allows for observing EPC statistics at a higher frequency. Second, it separates residential EPC from urban and rural sectors, which is useful for analyzing urban-rural dichotomy energy consumption patterns. Third, it provides a less costly and time-consuming approach to estimating energy consumption over space and time. Fourth, it covers almost the whole China (except Tibet, Hongkong, Macao, and Taiwan due to data unavailability), providing useful information for achieving national energy-saving goals. Based on the methodology, we see great potential for developing “global-country-region” energy monitoring through satellite image data service globally.