Mean Average Percentage Error Research Articles

Design and validation of a power modulation system for residential demand-side management

Residential loads have great potential to provide flexibility and other services to the grid, but many legacy or non-networked loads need additional hardware to enable such functionality. Currently available devices (e.g., smart thermostats or load control switches) that equip legacy loads with energy management features, provide narrow functionality to address specific use cases.We propose the Smart Dim Fuse (SDF), a unified system with general purpose hardware, to enable legacy residential loads with versatile grid-interactive functionalities. By combining sensing, power electronics, and load modeling into a single architecture, the SDF offers comprehensive capabilities that would otherwise require a large number of disparate devices that are not inherently compatible. Based on a thoroughly tested prototype, we suggest that such a device can deliver this flexibility at a levelized cost of 0.018-0.052 $/kWh. The prototype power electronics operates at efficiencies between 96.4-98.5% at full load. The system can deliver fast load power modulation with a mean average percentage error below 1.8%.

Big Data Generation and Comparative Analysis of Machine Learning Models in Predicting the Fundamental Period of Steel Structures Considering Soil–Structure Interaction

The computing of the fundamental period of structures during seismic design is well documented in design codes but is mainly dependent on the height of the structure, which is considered to be the most influential parameter. It is, however, important to consider a phenomenon called the soil–structure interaction (SSI), as this has been found to have a detrimental effect, especially for buildings founded on soft soils. A pilot research project foresaw the use of machine learning (ML) algorithms trained on relatively limited datasets for the development of a more accurate and objective fundamental period formula. Therefore, a dataset that consists of 98,308 fundamental period data points was created through the use of a High-Performance Computer (HPC), which is the largest dataset of its kind. The HPC results were then used to train, test, and validate different ML algorithms. It was found that XGBoost-HYT-CV with hyperparameter tuning performed the best with a correlation of 99.99% and a mean average percentage error (MAPE) of 0.5%. Furthermore, the XGBoost-HYT-CV model outperformed all under-study ML models when using an additional dataset that consisted of out-of-sample building geometries and soil properties, with a resulting MAPE of 9%. Finally, irregular buildings were also used to test the performance of the proposed predictive models.

Cell Temperature Determination based on IEC61215: Solar Photovoltaic Experimental Study of Tropical Malaysia

Most commercial photovoltaic (PV) module data sheets include Nominal Operating Cell Temperature (NOCT) values, which assist PV system designers in estimating module temperatures under real outdoor conditions. However, the typical NOCT values of 45°C to 47°C do not account for tropical climates. This study seeks to develop an adjusted NOCT mathematical model and determine revised NOCT values suited for tropical conditions. The new proposed NOCT model follows the international standard IEC61215 but incorporates updated tropical Standard Reference Environment (SRE) parameters: solar irradiance (SI) of 800 W/m², ambient temperature (AT) of 31°C, and wind speed (WS) of 1 m/s. This modified NOCT model demonstrates improved accuracy over the existing model, with an average reduction of 2% in percentage error, root mean square error, and mean average percentage error. Outdoor NOCT testing conducted in Shah Alam, Malaysia, uncovered much higher NOCT values for various PV modules technology: 55°C for monocrystalline, 57°C for polycrystalline, and 59°C for thin film. These results emphasize the inadequacy of current NOCT values in commercial PV module data sheets, which do not accurately reflect conditions in tropical climates. The revised NOCT values from this study offer crucial thermal reference data for PV system designers, integrators, and researchers working in tropical regions, particularly Malaysia.

Short‐term energy forecasting using deep neural networks: Prospects and challenges

AbstractThis study presents an in‐depth overview of deep neural networks (DNN) and their hybrid applications for short‐term energy forecasting (STEF). It examines DNN‐based STEF from three perspectives: basics, challenges, and prospects. The study compares recent literature using metrics like mean absolute error (MAE), mean average percentage error (MAPE), and root mean square error (RMSE). Findings indicate that combining automated data‐driven models with enhanced DNNs effectively addresses forecasting challenges. It also highlights the role of DNNs in integrating energy prosumers, renewable energy systems, microgrids, big data, and smart grids to improve STEF.

Evaluating Seismocardiography as a Non-Exercise Method for Estimating Maximal Oxygen Uptake.

The value of maximal oxygen uptake (VO2MAX) is a key health indicator. Usually, VO2MAX is determined with cardiopulmonary exercise testing (CPET), which is cumbersome and time-consuming, making it impractical in many testing scenarios. The aim of this study is to validate a novel seismocardiography sensor (Seismofit®, VentriJect DK, Hellerup, Denmark) for non-exercise estimation of VO2MAX. A cohort of 94 healthy subjects (52% females, 48.2 (8.7) years old) were included in this study. All subjects performed an ergometer CPET. Seismofit® measurements were obtained 10 and 5 min before CPET in resting condition and 5 min after exhaustion. The CPET VO2MAX was 37.2 (8.6) mL/min/kg, which was not different from the two first Seismofit® estimates at 37.5 (8.1) mL/min/kg (p = 0.28) and 37.3 (7.8) mL/min/kg (p = 0.66). Post-exercise Seismofit® was 33.8 (7.1) mL/min/kg (p < 0.001). The correlation between the CPET and the Seismofit® was r = 0.834 and r = 0.832 for the two first estimates, and the mean average percentage error was 11.4% and 11.2%. Intraclass correlation coefficients between the first and second Seismofit® measurement was 0.993, indicating excellent test-retest reliability. The novel Seismofit® VO2MAX estimate correlates well with CPET VO2MAX, and the accuracy is acceptable for general health assessment. The repeatability of Seismofit® estimates obtained at rest was very high.

Development of soft computing-based models for forecasting water quality index of Lorestan Province, Iran.

The Water Quality Index (WQI) is widely used as a classification indicator and essential parameter for water resources management projects. WQI combines several physical and chemical parameters into a single metric to measure the status of Water Quality. This study explores the application of five soft computing techniques, including Gene Expression Programming, Gaussian Process, Reduced Error Pruning Tree (REPt), Artificial Neural Network with FireFly (ANN-FFA), and combinations of Reduced Error Pruning Tree with bagging. These models aim to predict the WQI of Khorramabad, Biranshahr, and Alashtar sub-watersheds in Lorestan province, Iran. The dataset consists of 124 observations, with input variables being sulfate (SO4), total dissolved solids (TDS), the potential of Hydrogen (pH), chloride (Cl), electrical conductivity (EC), Potassium (K), bicarbonate (HCO), magnesium (Mg), sodium (Na), and calcium (Ca), and WQI as the output variable. For model creation (train subset) and model validation (test subset), the data were split into two subsets (train and test) in a ratio of 70:30. The performance evaluation parameters values of training and testing stages of various models indicate that the ANN-FFA based data-driven model performs better than the other modeling techniques applied with the values of coefficient of correlation 0.9990 & 0.9989; coefficient of determination 0.9612 & 0.9980; root mean square error 0.3036 & 0.3340; Nash-Sutcliffe error 0.9980 & 0.9979; and Mean average percentage error 0.7259% & 0.7969% for the train and test subsets, respectively. Taylor diagram results also suggest that ANN-FFA is the best-performing model, followed by the GEP model. This study introduces a novel model for predicting WQI using advanced soft computing models that have not been previously applied in this study area, highlighting its novelty and relevance. The proposed model significantly enhances predictive accuracy and efficiency, offering real-time, cost-effective WQI predictions that outperform traditional methods in handling complex, nonlinear environmental data.

Decoding the impact of neighboring amino acids on ESI-MS intensity output through deep learning

Peptide-level quantification using mass spectrometry (MS) is no trivial task as the physicochemical properties affect both response and detectability. The specific amino acid (AA) sequence affects these properties, however the connection between sequence and intensity output remains poorly understood. In this work, we explore combinations of amino acid pairs (i.e., dimer motifs) to determine a potential relationship between the local amino acid environment and MS1 intensity. For this purpose, a deep learning (DL) model, consisting of an encoder-decoder with an attention mechanism, was built. The attention mechanism allowed to identify the most relevant motifs. Specific patterns were consistently observed where a bulky/aromatic and hydrophobic AA followed by a cationic AA as well as consecutive bulky/aromatic and hydrophobic AAs were found important for the prediction of the MS1 intensity. Correlating attention weights to mean MS1 intensities revealed that some important motifs, particularly containing Trp, His, and Cys, were linked with low responding peptides whereas motifs containing Lys and most bulky hydrophobic AAs were often associated with high responding peptides. Moreover, Asn-Gly was associated with low response. The model predicts MS1 response with a mean average percentage error of ∼11 % and a Pearson correlation coefficient of ∼0.64. While dimer representation of peptide sequences did not improve predictive capacity compared to single AA representation in earlier work, this work adds valuable insight for a better understanding of peptide response in MS analysis. SignificanceMass spectrometry is not inherently quantitative, and the response of a compound relies not only on its concentration but also on the molecular composition. For mass spectrometry-based analysis of peptides, such as in bottom-up proteomics, this directly implies that the response cannot be used directly to quantify individual peptides. Moreover, the dependency of the response on the amino acid sequence of individual peptides remains poorly understood. Using a deep learning model based on a recurrent neural network with an attention mechanism, we here investigate how the presence of dimer motifs within a peptide affects the MS1 response through the analysis of intended equimolar peptide pools comprising almost 200,000 unique peptides in total. Not only do we identify certain dimer classes and specific dimers that substantially affect the MS1 response, but the model is also able to predict peptide intensity with low error rates within the independent test subset. The findings not only improve our understanding of the link between sequence and response for peptides but also highlight the potential of utilizing deep learning for developing methods allowing for absolute, label-free peptide quantification.

The role of utilizing artificial intelligence and renewable energy in reaching sustainable development goals

Many nations want to use only renewable energy by 2050. Given the recent rapid expansion in RE use in the global energy mix and its progressive impact on the global energy sector, the evaluation and analysis of Renewable Energy's impact on achieving sustainable development goals is insufficient. Wind energy could be renewable. For smart grid supply-and-demand issues, wind power forecasting is critical. One of the biggest challenges of wind energy is its significant fluctuation and intermittent nature, which makes forecasting difficult. This study's goal is to develop data-driven models to predict wind speed and power. This paper uses Machine Learning (ML) and Deep Learning (DL) to improve a wind speed prediction and recommendation system for wind turbine power production using site climatological data. This system optimizes turbine use by selecting the right number of turbines to operate solely based on the required energy, which is related to wind power and speed, and recommends the best power station location to determine the best turbine run time. The Proposed Enhanced Recommendation System (PERS) includes the Wind Speed Prediction Module (WSPM), Wind Speed vs. Power Consumption Calculation (WSPC), and Recommendation Module (RM). Test results showed the suggested method works in run time. The XGBoost or Random Forest regressor predicted 15-day power output with 94 % accuracy and 6 % mean average percentage error.

Partial reconstruction of sparse and incomplete point clouds applied to the generation of corneal topographic maps of healthy and diseased patients

The presence of unmeasured areas or areas with missing data in corneal topographies greatly affect the quality of digital corneal models. These are more frequent in posterior than in anterior corneal surface. This work seeks to complete and improve digital corneal models generated from incomplete point clouds obtained with commercial tomographic equipment, applying three interpolation/extrapolation techniques based on population data (Polynomial, Biharmonic Splines and Cubic Radial Base Functions). 43 personalized corneal models of patients with different grades of keratoconus were used to test each interpolation method. All interpolation results were compared using the Mean Average Percentage Error (MAPE) index, observing that it is possible to interpolate/extrapolate up to the radius 5.2 mm on the anterior face and up to 4.2 mm on the posterior face in general, but none of the methods stand out above the others for all the situations considered. Consequently, extrapolation method must be chosen carefully.

SUSCEPTIBLE VACCINATED INFECTED RECOVERED SUSCEPTIBLE MODEL: EQUILIBRIA POINTS AND APPLICATION ON COVID-19 CASE DATA IN INDONESIA

Severe Respiratory Syndrome Coronavirus-2 is the infectious agent that causes COVID-19. A vaccine program is an effort to stop the spread of COVID-19 infections in Indonesia. The susceptible vaccinated infected recovered susceptible (SVIRS) model can be used to represent the spread of infectious diseases. This study aims to construct the SVIRS model, identify the equilibria points thus apply it to COVID-19 case data in Indonesia, and determine transmission patterns, model accuracy, and interpretation. Literature and applications are the research methodologies employed. First-order nonlinear differential equations form the obtained SVIRS model. The model has two equilibrium points: a disease-free equilibrium point, and the other is endemic equilibrium point. The SVIRS model on the spread of COVID-19 in Indonesia was obtained using daily secondary data from January 11 to November 30, 2022. The model is solved by the fourth-order Runge-Kutta method. The model’s accuracy is accurate enough to explain the spread of COVID-19 in Indonesia with a mean average percentage error (MAPE) value of 43%. According to the transmission pattern, the number of COVID-19 cases in Indonesia peaked on July 27, 2022, then decreased to zero, obtaining an equilibrium point when no more cases of the disease were present.

A novel modeling approach on the water–electricity–climate nexus in the context of resource sustainability

Water and energy have become essential resources and must be wisely managed for a sustainable future. This paper explores the relationship between water consumption and electricity generation in hydropower plants with dams under different climate change scenarios to contribute to the policy perspectives with a new tool and method to sustain the future. Still, as a reliable forecasting tool, the evaluation of the adaptive neuro-fuzzy inference system model has not been tested for forecasting water consumption during electricity generation. Thus, this study uses this modeling approach to generate reliable water consumption estimates based on electricity generation. The operational data of 78 hydroelectric power plants with dams and meteorological parameters were used as input variables, while water consumption was the output parameter in the model. The dataset was randomly divided into training and testing sets, and 85–15% data splitting presented the best-fitted model. The lowest mean average percent error of the hydroelectric power plants' model resulted in 9.59%, and the coefficient of determination of the model was 0.97, which showed that the developed model presented acceptable prediction performance. Various climate change scenarios are applied to analyze the effects of climate parameters on the water consumption of hydropower plants. The annual hydroelectric power plant water consumption and water intensity were estimated between 2,609 million m3 and 4,393 million m3, and 50,768 m3/GWh and 85,487 m3/GWh, respectively, based on climate change scenarios. The study concludes with significant policy suggestions to endorse this approach.Graphical abstract

Indonesian Stock Price Prediction Using Neural Basis Expansion Analysis for Interpretable Time Series Method

The stock market is an attractive investment venue for many individuals and companies. However, unexpected share price fluctuations can cause significant financial losses. In stock investment, predicting stock price movements is the most frequently discussed topic because it allows investors to make the right investment decisions to make big profits. Therefore, a model is needed to predict future stock prices, one strategy for maximising investment profits. New state-of-the-art deep learning architectures for time series forecasting are being developed yearly, making them more accurate than ever. The most commonly used network for such a solution is Long Short-Term Memory (LSTM) architecture, but it has limitations such as long training time and interpretability. This study aims to evaluate another state-of-theart solution, Neural Basis Expansion Analysis for Interpretable Time Series (N-BEATS), in comparison with LSTM by utilising historical data of PT Bank Central Asia Tbk (one of the banking companies in Indonesia) from 25 March 2013 to 21 March 2023. N-BEATS is a relatively new variable method that can produce accurate predictions using neural networks. This architecture has advantages such as interpretability, seamless applicability across diverse target domains without requiring modifications, and fast training. Based on tests carried out with prediction errors measured using the Mean Average Percentage Error (MAPE), it was found that the N-BEATS model outperformed the LSTM model with a MAPE value of 1.05 percent. In conclusion, this research shows the use of a new method of deep learning algorithms to predict stock prices, which contributes to facilitating stock buying and selling decisions by investors.

Robust design space of compression parameters for initial and reprocessed granules

The design of experiments has been widely used for product and process development based on Quality by design (QbD) approach to achieve quality product. Sources of variability are identified and controlled during manufacturing. However, uncertainty due to uncontrollable variables in the process leads to quality issues and the need for reprocessing in some cases. This study proposes a systematic approach to determine the robust design space for process parameters embraced with the variation of initial and reprocessed materials to ensure that the tablet will meet the specification. The Taguchi L36 experiment design is applied to determine suitable tableting parameters for different granules to ensure physical specifications. Four types of calcium carbonate granules were produced with different moisture contents (ZM) and manufacturing conditions (ZT). Additionally, three critical parameters of tablet compression process—filling volume (XV), compression force (XF), and turret speed (XS)—each encompassing three levels, were selected as input variables. The responses were derived from the product specification, namely weight (YW), tensile strength (YTS), and disintegration time (YDT). The experiment results were embedded into two models: the single independence response model (SRM) and the multiple dependent response model (MRM). After a confirmation experiment using predicted parameters, a comparison of their %MAPE (mean average percentage error) revealed that MRM has lower accuracy in terms of YTS but dominates SRM in terms of the region of design space. This finding relates to the effect of data transformation capturing non-linear relationships between these factors and responses. The design space derived from the models allows manufacturers to adjust critical process parameters for getting desired specification tablets and also provides a framework for continuous improvement by enhancing their original design space and providing a rigorous reprocessing plan.

Mathematical modeling and performance evaluation of Ducted Horizontal-axis Helical Wind Turbines: Insights into aerodynamics and efficiency.

With the escalating demand for energy, there is a growing focus on decentralized, small-scale energy infrastructure. The success of new turbines in this context is notable. However, many of these turbines do not follow many of the basic ideas established to evaluate their performance, leaving no precise technique or mathematical model. This research developed a Ducted Horizontal-axis Helical Wind Turbine (DHAHWT). The DHAHWT is a duct-mounted helical savonius turbine with a venturi and diffuser to improve flow. Unlike a vertical axis helical savonius turbine, DHAHWT revolves roughly parallel to the wind, making it a horizontal turbine. This complicates mathematical and theoretical analysis. This study created a DHAHWT mathematical model. COMSOL simulations utilizing Menter's Shear Stress Transport model (SST) across an incoming velocity range of 1m/s to 4m/s were used to evaluate the turbine's interaction with the wind. MATLAB was used to train an artificial neural network (ANN) utilizing COMSOL data to obtain greater velocity data. The Mean Average Percentage Error (MAPE) and Root Mean Square Error (RMSE) of ANN data were found to be 3%, indicating high accuracy. Further, using advanced statistical methods the Pearson's correlation coefficient was calculated resulting in a better understanding of the relationship of between incoming velocity and velocity at different sections of the wind turbine. This study will shed light on the aerodynamics and working of DHAHWT.

Energy Saving and Emission Reduction Optimization of Enterprise Hazardous Waste Recycling Management System based on Hybrid Genetic Algorithm

This research proposes a new path planning model for hazardous waste recycling transportation to effectively manage the hazardous waste recycling transportation, improving the transportation efficiency, while considering the actual road conditions. The new model adopts the conservation algorithm and hybrid genetic algorithm, which makes the new model better meet the complex needs of hazardous waste recycling. The new approach enables optimal transportation path planning for hazardous waste recycling while ensuring safety and compliance. The results showed that the hybrid algorithm outperformed the other two algorithms in terms of path optimization, cost reduction, accuracy improvement and error reduction. The hybrid algorithm had the best path optimization effect, which can get the optimal path with the lowest cost and highest efficiency. The hybrid algorithm had the highest accuracy of 95.62%. It also had the lowest root mean square error and average percentage error, indicating that it had less error. Finally, the hybrid algorithm had the highest loss function value, which indicated that the model had the best stability and better performance. The new hybrid genetic algorithm performed better than the single traditional algorithm, which is more efficient for hazardous waste recycling.

Optimizing energy consumption in smart homes using GA-LSTM

The need to optimize energy consumption arises from the inadequate energy supply many homes face. However, to optimize energy consumption in a home, one must be equipped with the knowledge of the energy consumption rate and energy supply rate in the home. This paper proposed the use of a Long Short-Term Memory (LSTM) model optimized by Genetic Algorithm (GA) to optimize the energy consumption in a smart home. The model was designed using 8 input variables, which were observed weather information of a given region over a span of 350 days. The data set was split into a training data set and a test data set in the ratio 4:1. Both the baseline LSTM model and our proposed GA-LSTM model was used to train and test the data. The results of the baseline LSTM model showed a Mean Average Percentage Error (MAPE) of 0.15 and a Root Mean Square Error (RMSE) of 0.0007, while our proposed GA-LSTM recorded an MAPE of 0.07 and RMSE of 0.0004. The implication of these results is a better performance of our proposed GA-LSTM model over the baseline LSTM model. This paper demonstrated how the Genetic Algorithm was able to optimize the baseline LSTM model by selecting the best weights during the LSTM training process. The findings of this paper are recommended for smart homes having the capability to monitor energy usage of installed electrical appliances and the ability to predict to weather condition of the region the home is sited.

CUBIC SPLINE INTERPOLATION TO APPROXIMATE SEA DEPTH BETWEEN TELUK SUAK AND LEMUKUTAN ISLAND

Interpolation is a technique that determines the value of a function at a point located between several known data points. Various interpolation methods include polynomial interpolation, Lagrange interpolation, Newton interpolation, and spline interpolation. Cubic spline interpolation aims to produce accurate approximations characterized by minimal oscillations in the resulting curve. This research uses the cubic spline interpolation method to estimate the sea depth in the waters between Teluk Suak and Pulau Lemukutan. The sea depth measurements are conducted to acquire information regarding the underwater topography. We collected data points using remote sensing techniques through Google Earth Pro. These points are selected based on the sea depth profile considerations, including steep areas and points of depth variation to maintain the seabed conditions within the interpolation curve, with a total of 31 data points. Subsequently, we subjected these data points to the conditions necessary for cubic spline interpolation, resulting in a system of 120 linear equations. After solving this system of linear equations, we obtained cubic spline interpolation polynomials for each subinterval and then estimated the sea depth at other points. Based on the cubic spline interpolation results, we achieved a Mean Average Percentage Error (MAPE) of 1.58%, indicating a highly accurate interpolation outcome.

Integrating machine learning and image processing for void fraction estimation in two-phase flow through corrugated channels

There is a substantial amount of information embedded in images of two-phase flow captured through high-speed video (HSV) or high-resolution photography. However, accurate image segmentation is necessary to unlock a meaningful analysis of the data. In this study, we discuss how to estimate the flow void fraction in chevron-type corrugated channels typical of compact plate heat exchangers (CPHE) from back-lit front-view HSV images, using machine learning (ML) algorithms and data processing techniques. A U-Net neural network was employed for image segmentation, demonstrating robust performance with evaluation metrics consistently exceeding 0.9. The binary masks (indicating gas or liquid phases) derived from segmentation were processed in MATLAB® to estimate void fraction through a 3D reconstruction algorithm of the gas cluster’s volume. In contrast to conventional void fraction estimates based on the area ratio of binary masks, this algorithm models the curvature of the liquid-vapor interface through the corrugated channel. When compared to other methods, our algorithm predicts very similar void fraction contour maps. However, the average discrepancy between our algorithm and the area-ratio approach can be as high as 80%, underscoring the importance of the processing method in analyzing the data and developing correlations. Finally, a drift flux model was introduced to predict the void fraction distribution using a two-part equation accommodating the dependency of the distribution coefficient C0 on the liquid flow rate for a corrugation Froude number Fr∼ larger than 1. The proposed model can predict the void fraction dataset with a mean average percentage error of 8.17%. In summary, U-Net’s pixel-level accuracy facilitates deep and precise post-processing of HSV images, enabling meaningful void fraction measurements. Thanks to its generality and minimal training effort requirements, the discussed methodology can be applied to estimate void fractions in various two-phase flow experiments and operating conditions.

Artificial Neural Network-Based Modelling for Yield Strength Prediction of Austenitic Stainless-Steel Welds

This study aimed to develop an artificial neural network (ANN) model for predicting the yield strength of a weld metal composed of austenitic stainless steel and compare its performance with that of conventional multiple regression and machine learning models. The input parameters included the chemical composition of the nine effective elements (C, Si, Mn, P, S, Ni, Cr, Mo, and Cu) and the heat input per unit length. The ANN model (comprising five nodes in one hidden layer), which was constructed and trained using 60 data points, yielded an R2 value of 0.94 and a mean average percent error (MAPE) of 2.29%. During model verification, the ANN model exhibited superior prediction performance compared with the multiple regression and machine learning models, achieving an R2 value of 0.8644 and a MAPE of 3.06%. Consequently, the ANN model effectively predicted the variation in the yield strength and microstructure resulting from the thermal history and dilution during the welding of 3.5–9% Ni steels with stainless steel-based welding consumables. Furthermore, the application of the prediction model was demonstrated in the design of welding consumables and heat input for 9% Ni steel.

Performance analysis of a blockchain enabled domestic power consumption monitoring and forecasting system

Purpose The purpose of this paper is to develop a blockchain-based data capture and transmission system that will collect real-time power consumption data from a household electrical appliance and transfer it securely to a local server for energy analytics such as forecasting. Design/methodology/approach The data capture system is composed of two current transformer (CT) sensors connected to two different electrical appliances. The CT sensors send the power readings to two Arduino microcontrollers which in turn connect to a Raspberry-Pi for aggregating the data. Blockchain is then enabled onto the Raspberry-Pi through a Java API so that the data are transmitted securely to a server. The server provides real-time visualization of the data as well as prediction using the multi-layer perceptron (MLP) and long short term memory (LSTM) algorithms. Findings The results for the blockchain analysis demonstrate that when the data readings are transmitted in smaller blocks, the security is much greater as compared with blocks of larger size. To assess the accuracy of the prediction algorithms data were collected for a 20 min interval to train the model and the algorithms were evaluated using the sliding window approach. The mean average percentage error (MAPE) was used to assess the accuracy of the algorithms and a MAPE of 1.62% and 1.99% was obtained for the LSTM and MLP algorithms, respectively. Originality/value A detailed performance analysis of the blockchain-based transmission model using time complexity, throughput and latency as well as energy forecasting has been performed.