Load Profile Analysis for Mitigating Load-Shedding in Central Africa: Case of Kinshasa

Load shedding is a major problem in Central Africa, with negative consequences for both society and the economy. However, load profile analysis can help to alleviate this problem by providing valuable information about consumer demand. This information can be used by power utilities to forecast and reduce power cuts effectively. In this study, the direct method was used to create load profiles for residential feeders in Kinshasa. The results showed that load shedding on weekends results in significant financial losses and changes in people’s behavior. In November 2022 alone, load shedding was responsible for $ 23,4 08,984 and $ 2 80,9 07,808 for all year in losses. The study also found that the SAIDI index for the southern direction of the Kinshasa distribution network was 122.49 hours per feeder, on average. This means that each feeder experienced an average of 5 days of load shedding in November 2022. The SAIFI index was 20 interruptions per feeder, on average, and the CAIDI index was 6 hours, on average, before power was restored. This study also proposes ten strategies for the reduction of load shedding in the Kinshasa and central Africa power distribution network and for the improvement of its reliability, namely: Improved load forecasting, Improvement of the grid infrastructure, Scheduling of load shedding, Demand management programs, Energy efficiency initiatives, Distributed Generation, Automation and Monitoring of the Grid, Education and engagement of the consumer, Policy and regulatory assistance, and Updated load profile analysis.

The Generation of Electric Load Profiles in the UK Domestic Buildings through Statistical Predictions

Various forecasting tools exist for planners of national networks that are based on historical data. These are used to make decisions at the national level to meet a countries commitment to CO2 emission targets. However, at a local community level, the guidance is not easily understood by planners. This work presents for the first time a methodology for the generation of realistic domestic electricity load profiles for different types of UK households for small communities. The work is based on a limited set of data, and has been compared with measurement. Daily load profiles from individual dwelling to community can be predicted using this method. Results have been presented, and discussed.

Comparison and Adaptation of Two Strategies for Anomaly Detection in Load Profiles Based on Methods from the Fields of Machine Learning and Statistics

The Federal Office for Economic Affairs and Export Control (BAFA) of Germany promotes digital concepts for increasing energy efficiency as part of the “Pilotprogramm Einsparzähler”. Within this program, Limón GmbH is developing software solutions in cooperation with the University of Kassel to identify efficiency potentials in load profiles by means of automated anomaly detection. Therefore, in this study two strategies for anomaly detection in load profiles are evaluated. To estimate the monthly load profile, strategy 1 uses the artificial neural network LSTM (Long Short-Term Memory), with a data period of one month (1 M) or three months (3 M), and strategy 2 uses the smoothing method PEWMA (Probalistic Exponential Weighted Moving Average). By comparing with original load profile data, residuals or summed residuals of the sequence lengths of two, four, six and eight hours are identified as an anomaly by exceeding a predefined threshold. The thresholds are defined by the Z-Score test, i.e., residuals greater than 2, 2.5 or 3 standard deviations are considered anomalous. Furthermore, the ESD (Extreme Studentized Deviate) test is used to set thresholds by means of three significance level values of 0.05, 0.10 and 0.15, with a maximum of k = 40 iterations. Five load profiles are examined, which were obtained by the cluster method k-Means as a representative sample from all available data sets of the Limón GmbH. The evaluation shows that for strategy 1 a maximum F1-value of 0.4 (1 M) and for all examined companies an average F1-value of maximum 0.24 and standard deviation of 0.09 (1 M) could be achieved for the investigation on single residuals. In variant 3 M the highest F1-value could be achieved with an average F1-value of 0.21 and standard deviation of 0.06 (3 M) for summed residuals of the partial sequence length of four hours. The PEWMA-based strategy 2 did not show a higher anomaly detection efficacy compared to strategy 1 in any of the investigated companies.

Reconstructing hourly residential electrical load profiles for Renewable Energy Communities using non-intrusive machine learning techniques

The successful implementation of Renewable Energy Communities(RECs)involves maximizing the self-consumption within a community,particularly in regulatory contexts in which shared energy is incentivized.In many countries,the absence of a metering infrastructure that provides data at an hourly or sub-hourly resolution level for low-voltage users(e.g.,residential and commercial users)makes the design of a new energy community a challenging task.This study proposes a non-intrusive machine learning methodology that can be used to generate residential electrical consumption profiles at an hourly resolution level using only monthly consumption data(i.e.,billed energy),with the aim of estimating the energy shared by RECs.The proposed methodology involves three phases:first,identifying the typical load patterns of residential users through k-Means clustering,then implementing a Random Forest algorithm,based on monthly energy bills,to identify typical load patterns and,finally,reconstructing the hourly electrical load profile through a data-driven rescaling procedure.The effectiveness of the proposed methodology has been evaluated through an REC case study composed by 37 residential users powered by a 70 kWp photovoltaic plant.The Normalized Mean Absolute Error(NMAE)and the Normalized Root Mean Squared Error(NRMSE)were evaluated over an entire year and whenever the energy was shared within the REC.The Relative Absolute Error was also measured when estimating the shared energy at both a monthly(MRAE)and at an annual basis.(RAE).A comparison between the REC load profile reconstructed using the proposed methodology and the real load profile yielded an overall NMAE of 20.04%,an NRMSE of 26.17%,and errors of 18.34%and 23.87%during shared energy timeframes,respectively.Furthermore,our model delivered relative absolute errors for the estimation of the shared energy at a monthly and annual scale of 8.31%and 0.12%,respectively.

High-resolution Load Profile Clustering Approach Based on Dynamic Largest Triangle Three Buckets and Multiscale Dynamic Warping Path Under Limited Warping Path Length

With the popularity of smart meters and the growing availability of high-resolution load data, the research on the dynamics of electricity consumption at finely resolved timescales has become increasingly popular. Many existing algorithms underperform when clustering load profiles contain a large number of feature points. In addition, it is difficult to accurately describe the similarity of profile shapes when load sequences have large fluctuations, leading to inaccurate clustering results. To this end, this paper proposes a high-resolution load profile clustering approach based on dynamic largest triangle three buckets(LTTBs) and multiscale dynamic time warping under limited warping path length(LDTW). Dynamic LTTB is a novel dimensionality reduction algorithm based on LTTB. New sequences are constructed by dynamically dividing the intervals of significant feature points. The extraction of fluctuation characteristics is optimized. New curves with more concentrated features will be applied to the subsequent clustering. The proposed multiscale LDTW is used to generate a similarity matrix for spectral clustering, providing a more comprehensive and flexible matching method to characterize the similarity of load profiles. Thus, the clustering effect of a high-resolution load profile is improved. The proposed approach has been applied to multiple datasets. Experiment results demonstrate that the proposed approach significantly improves the Davies-Bouldin indicator(DBI) and validity index(VI). Therefore, better similarity and accuracy can be achieved using high-resolution load profile clustering.

An investigation into the feasibility of a hybrid generator-photovoltaic-wind farm with variable load profile:case of headland south-west of Morocco

A hybrid system proposed by three different specifications for the equipment of a tourist lodge in the headland of south-west Morocco was sized by analysing the limits of load profile constraints,such as hour-to-hour variability(HHR),day-to-day variability(DDR)and the operating reserve rate(ROR).Based on the three-factor Doehlert matrix recommendations,the simulations employed an energy-sizing tool for hybrid renewable-energy systems.Testing was conducted with DDR at 5-30%,HHR at 10-30%and ROR at 0-20%.Under these conditions,a second-order polynomial relationship with a correlation rate of~90%was found between the net present cost(NPC)of the system,the levelized cost of electricity and the various constraint factors.The first specification,SPC(1),composed of generators and batteries,was introduced to control and validate the simulation independently of renewable energy,which showed a positive manifestation with the imposed constraints.The analysis expanded by introducing solar and wind energy resources.The SPC(2)configuration added PV modules to the SPC(1)and the SPC(3)configuration added wind turbines to SPC(2).The effect of DDR,HHR and ROR in the trials was significant by linear regression.At the same time,only DDR had a significant quadratic regression.The others,with their pairwise interactions,were insignificant.The desirability procedure made it possible to calculate the maximum limits of load profile constraint variables leading to targets of LCOE=0.41 US$/kWh and NPC=US$320080.1 of the load profile constraints:the DDR=15.47%and the HHR=26.55%at an ROR rate of 17.77%.

SmartMicro Grid Energy System Management Based on Optimum Running Cost for Rural Communities in Rwanda

The governmental electric utility and the private sector are joining hands to meet the target of electrifying all households by 2024.However,the aforementioned goal is challenged by households that are scattered in remote areas.So far,Solar Home Systems(SHS)have mostly been applied to increase electricity access in rural areas.SHSs have continuous constraints to meet electricity demands and cannot run income-generating activities.The current research presents the feasibility study of electrifying Remera village with the smart microgrid as a case study.The renewable energy resources available in Remera are the key sources of electricity in that village.The generation capacity is estimated based on the load profile.The microgrid configurations are simulated with HOMER,and the genetic algorithm is used to analyze the optimum cost.By analyzing the impact of operation and maintenance costs,the results show that the absence of subsidies increases the levelized cost of electricity(COE)five times greater than the electricity price from the public utility.The microgrid made up of PV,diesel generator,and batteries proved to be the most viable solution and ensured continuous power supply to customers.By considering the subsidies,COE reaches 0.186$/kWh,a competitive price with electricity from public utilities in Rwanda.

A Preliminary Assessment of Load Consumption and Solar Power Potential at Kota Belud,Sabah

This paper presents a detailed preliminary assessment of load consumption and solar power potential at the Eco-Tourism Centre of Liogu Ku Silou-Silou(EPLISSI),Kota Belud,Sabah.This initial investigation assessed the feasibility of an off-grid solar PV system at EPLISSI with a suitable solar panel system for project installation and commissioning purposes.Due to the absence of an electrical grid and power supply,no pre-existing electrical appliances could be found in EPLISSI.Hence,an excel-based software,the ESCoBox,was used to produce the load profiles.The input data for this software came from a list of required electrical appliances(LED lights,fans,and phone chargers)and the historical frequency of visitors to EPLISSI.Meanwhile,to assess the solar power potential at EPLISSI,an online simulator known as Global Solar Atlas version 2.3 or GSA 2.3 was used.As an input for the GSA 2.3,the initial solar panel system capacity was set for 0.5 kWp,and then an increment of 0.1 kWp was entered until specific criteria were met.The selection of the suitable size is made when the system can satisfy the daily total average load demand and a specific load fulfillment demand.As a result,it was found that the site requires a total average demand and a total peak demand of 4.60 and 11.87 kWh/day,respectively.From the GSA 2.3 generated report,an off-grid solar PV system with the capacity of 2.50 kWp solar PV can satisfy the daily total average load demand of this area,where the average PV energy output is within the range of between 7.74–9.80 kWh/day or an average of 8.72 kWh/day.In conclusion,this preliminary assessment indicates that installing an off-grid solar PV system in this area is possible.

Research on Electricity Consumption Model of Library Building Based on Data Mining

With the exponential development of Chinese population,the massive energy consumption of buildings has recently become an interest subject.Although much research has been conducted on residential buildings,heating ventilation and air conditioning(HVAC),little research has been conducted on the relationship between student’s behavior,campus buildings,and their subsystems.Using classical seasonal decomposition,hierarchical clustering,and apriori algorithm,this paper aims to provide an empirical model for consumption data in campus library.Smart meter data from a library in Beijing,China,is adopted in this paper.Building electricity consumption patterns are investigated on an hourly/daily/monthly basis.According to the monthly analysis,electricity consumption peaks each year around June and December due to teaching programs,social exams,and outdoor temperatures.Hourly data analysis revealed a relatively stable consumption pattern.It shows three different types of daily load profiles.Daily data analysis demonstrated a high relationship between HVAC consumption and building total consumption,with a lift value of 5.9.Furthermore,links between temperature and subsystems were also discovered.Through a case study of library,this study provides a unique insight into campus electricity use.The results could help to develop operational strategies for campus facilities.

Application of new techniques to renovation of 200 MW steam turbine

Presents the new techniques leading to the improvements in aerodynamics of 200MW steam turbine high pressure cylinder and mid pressure cylinder, discusses the rear loaded profile and blade bowing, and concludes from numerical simulation and experimental results that the application of rear loaded profile and blade bowing has improved the performance of 200 MW unit.

Islands of misfit buildings: Detecting uncharacteristic electricity use behavior using load shape clustering

Many energy performance analysis methodologies assign buildings a descriptive label that represents their main activity,often known as the primary space usage(PSU).This attribute comes from the intent of the design team based on assumptions of how the majority of the spaces in the building will be used.In reality,the way a building’s occupants use the spaces can be different than what was intended.With the recent growth of hourly electricity meter data from the built environment,there is the opportunity to create unsupervised methods to analyze electricity consumption behavior to understand whether the PSU assigned is accurate.Misclassification or oversimplification of the use of the building is possible using these labels when applied to simulation inputs or benchmarking processes.To work towards accurate characterization of a building’s utilization,we propose a modular methodology for identifying potentially mislabeled buildings using distance-based clustering analysis based on hourly electricity consumption data.This method seeks to segment buildings according to their daily behavior and predict which ones are misfits according to their assigned PSU label.This process finds potentially uncharacteristic behavior that could be an indication of mixed-use or a misclassified PSU.Our results on two public data sets,from the Building Data Genome(BDG)Project and Washington DC(DGS),with 507 and 322 buildings respectively,show that 26%and 33%of these buildings are potentially mislabelled based on their load shape behavior.Such information provides a more realistic insight into their true consumption characteristics,enabling more accurate simulation scenarios.Applications of this process and a discussion of limitations and reproducibility are included.

Stress testing electrical grids:Generative Adversarial Networks for load scenarion

As the energy transition is upon us,the replacement of combustion engines by electrical ones will imply a greater stress on the electrical grid of different countries.Therefore,it is of paramount importance to simulate a great number of hypothetical multi-variant scenarios to correctly plan the roll-out of new grids.In this paper,we deploy Generative Adversarial Networks(GANs)to swiftly reproduce the non-Gaussian and multimodal distribution of real energy-related samples,making GANs a valuable tool for data generation in the field.In particular,we propose an original dataset deriving from the aggregation of two European providers including hourly electric inland generation from several European countries.This dataset also comes along with the corresponding season,day of the week,hour of the day and macro-economic variables aiming at unequivocally describing the country’s energetic profile.Finally,we evaluate the performance of our model via dedicated metrics capable of grasping the non-Gaussian nature of the data and compare it with the state-of-the-art model for tabular data generation.

Load Profiling and Its Application to Demand Response: A Review

The smart grid has been revolutionizing electrical generation and consumption through a two-way flow of power and information. As an important information source from the demand side, Advanced Metering Infrastructure （AMI） has gained increasing popularity all over the world. By making full use of the data gathered by AMI, stakeholders of the electrical industry can have a better understanding of electrical consumption behavior. This is a significant strategy to improve operation efficiency and enhance power grid reliability. To implement this strategy, researchers have explored many data mining techniques for load profiling. This paper performs a state-of-the-art, comprehensive review of these data mining techniques from the perspectives of different technical approaches including direct clustering, indirect clustering, clustering evaluation criteria, and customer segmentation. On this basis, the prospects for implementing load profiling to demand response applications, price-based and incentivebased, are further summarized. Finally, challenges and opportunities of load profiling techniques in future power industry, especially in a demand response world, are discussed.

Design optimization of a grid-tied microgrid for a residential community in southern Bangladesh

Growing energy demand,diminishing fossil fuel reserves and geopolitical tensions are serious concerns for any country’s energy strategy and security.These factors have a greater impact on developing countries,as many of them rely largely on traditional energy resources.Cleaner energy generation is the viable alternative for mitigating these problems,as well as achieving energy independ-ence and tackling climate change.The article discusses planning and design optimization of a residential community microgrid based on multiple renewable resources.In particular,the design and techno-economic assessment of a grid-tied hybrid microgrid for meeting the electricity demand of an alluvial region,Urir Char,located in southern Bangladesh,was addressed.Hybrid Optimization of Multiple Energy Resources is used for the evaluation and it is supplemented by a fuzzy-logic-based load profile design strategy.In addition to the analysis,a predictive load-shifting-based demand management is also introduced.Several cases were considered for the studies and,after considering several criteria,a grid-tied system comprising a photovoltaic array,wind turbine and energy storage system was found to be the best fit for powering the loads.The suggested system reduces the life-cycle cost by 18.3%,the levelized cost of energy by 61.9%and emissions by 77.2%when compared with the grid-only option.Along with the microgrid design,cooking emissions and energy categorization were also discussed.

A Conditional Generative adversarial Network for energy use in multiple buildings using scarce data

Building consumption data is integral to numerous applications including retrofit analysis,Smart Grid integration and optimization,and load forecasting.Still,due to technical limitations,privacy concerns and the proprietary nature of the industry,usable data is often unavailable for research and development.Generative adversarial networks(GANs)-which generate synthetic instances that resemble those from an original training dataset-have been proposed to help address this issue.Previous studies use GANs to generate building sequence data,but the models are not typically designed for time series problems,they often require relatively large amounts of input data(at least 20,000 sequences)and it is unclear whether they correctly capture the temporal behaviour of the buildings.In this work we implement a conditional temporal GAN that addresses these issues,and we show that it exhibits state-of-the-art performance on small datasets.22 different experiments that vary according to their data inputs are benchmarked using Jensen-Shannon divergence(JSD)and predictive forecasting validation error.Of these,the best performing is also evaluated using a curated set of metrics that extends those of previous work to include PCA,deep-learning based forecasting and measurements of trend and seasonality.Two case studies are included:one for residential and one for commercial buildings.The model achieves a JSD of 0.012 on the former data and 0.037 on the latter,using only 396 and 156 original load sequences,respectively.