scholarly journals Bagging Ensemble of Multilayer Perceptrons for Missing Electricity Consumption Data Imputation

Sensors ◽  
2020 ◽  
Vol 20 (6) ◽  
pp. 1772 ◽  
Author(s):  
Seungwon Jung ◽  
Jihoon Moon ◽  
Sungwoo Park ◽  
Seungmin Rho ◽  
Sung Wook Baik ◽  
...  
Keyword(s):  
Energy Consumption ◽  
Energy Management ◽  
Missing Values ◽  
Electric Energy ◽  
Electricity Consumption ◽  
Multilayer Perceptrons ◽  
Imputation Methods ◽  
Electric Energy Consumption ◽  
Consumption Data ◽  
Bagging Ensemble

For efficient and effective energy management, accurate energy consumption forecasting is required in energy management systems (EMSs). Recently, several artificial intelligence-based techniques have been proposed for accurate electric load forecasting; moreover, perfect energy consumption data are critical for the prediction. However, owing to diverse reasons, such as device malfunctions and signal transmission errors, missing data are frequently observed in the actual data. Previously, many imputation methods have been proposed to compensate for missing values; however, these methods have achieved limited success in imputing electric energy consumption data because the period of data missing is long and the dependency on historical data is high. In this study, we propose a novel missing-value imputation scheme for electricity consumption data. The proposed scheme uses a bagging ensemble of multilayer perceptrons (MLPs), called softmax ensemble network, wherein the ensemble weight of each MLP is determined by a softmax function. This ensemble network learns electric energy consumption data with explanatory variables and imputes missing values in this data. To evaluate the performance of our scheme, we performed diverse experiments on real electric energy consumption data and confirmed that the proposed scheme can deliver superior performance compared to other imputation methods.

Willingness of Electricity Consumer in Malaysia to Share Electric Energy Consumption Data

2021 ◽  
pp. 689-700
Author(s):  
Salman Yussof ◽  
Nurul Nazeera Mohd Zulkefle ◽  
Yunus Yusoff ◽  
Asmidar Abu Bakar
Keyword(s):  
Energy Consumption ◽  
Electric Energy ◽  
Electric Energy Consumption ◽  
Consumption Data

Analysis and Design of Electric Energy Consumption Inspection Equipment Based on ARM9

2012 ◽  
Vol 157-158 ◽  
pp. 447-451
Author(s):  
Hu Hu ◽  
Xin Tian ◽  
Li Hong Han ◽  
Bin Chen
Keyword(s):  
Energy Consumption ◽  
Real Time ◽  
Low Cost ◽  
Electric Energy ◽  
Basic Structure ◽  
Analysis And Design ◽  
Electric Energy Consumption ◽  
Real Time Analysis ◽  
Consumption Data ◽  
Real Time Transmission

The present paper introduces a sort of analysis and design of electric energy consumption inspection equipment based on ARM9, which can inspect multiple electric energy indexes and conduct a real time inspection to electric energy consumption. Both a real time collection and a real time transmission of electric energy consumption data are realized and a real time analysis of these data that are transmitted through the network to the host computer can be carried out as well, the features of which are low power consumption, low cost, very applicable, high real time performance, etc. The paper also describes the system’s basic structure, hardware design, software design and system debugging process.

scholarly journals Parallel Evolutionary Biclustering of Short-term Electric Energy Consumption

2021 ◽  
Author(s):  
Diego P. Pinto-Roa ◽  
Hernán Medina ◽  
Federico Román ◽  
Miguel García-Torres ◽  
Federico Divina ◽  
...  
Keyword(s):  
Energy Consumption ◽  
Electric Energy ◽  
Electricity Consumption ◽  
Search Space ◽  
Consumption Pattern ◽  
Electric Energy Consumption ◽  
System A ◽  
Time Period ◽  
Computation Scheme ◽  
Significant Patterns

The discovery and description of patterns in electric energy consumption time series is fundamental for timely management of the system. A bicluster describes a subset of observation points in a time period in which a consumption pattern occurs as abrupt changes or instabilities homogeneously. Nevertheless, the pattern detection complexity increases with the number of observation points and samples of the study period. In this context, current bi-clustering techniques may not detect significant patterns given the increased search space. This study develops a parallel evolutionary computation scheme to find biclusters in electric energy. Numerical simulations show the benefits of the proposed approach, discovering significantly more electricity consumption patterns compared to a state-of-the-art non-parallel competitive algorithm.

scholarly journals Electric energy consumption of milking process on some Finnish dairy farms

2017 ◽  
Vol 26 (3) ◽  
Author(s):  
Mari Rajaniemi ◽  
Tapani Jokiniemi ◽  
Laura Alakukku ◽  
Jukka Ahokas
Keyword(s):  
Energy Consumption ◽  
Energy Savings ◽  
Electric Energy ◽  
Cooling Water ◽  
Electricity Consumption ◽  
Dairy Farms ◽  
Energy Costs ◽  
Heating Systems ◽  
Electric Energy Consumption ◽  
Energy Saving Potential

The aim of this study was to examine the electric energy consumption of milking process on dairy farms and to evaluate the methods to improve the energy efficiency. The electricity consumption of the milking process was measured on three dairy farms in Southern Finland, and it varied between 37–62 Wh kg-1 milk.  The largest energy saving potential was identified in milk cooling and the heating of cleaning water. Even simple methods, such as placing the condenser of the refrigeration system outside, may reduce the energy consumption of milk cooling by 30%. Efficient milk pre-cooling can reduce the energy consumption of the whole milking process by more than 25%. Even larger energy savings are possible with a sophisticated milk cooling – water heating systems. It was concluded that there is a significant potential to reduce the energy consumption and energy costs of the milking process, and thus to improve the profitability and sustainability of the sector at the same time.

scholarly journals Partitional Clustering-Hybridized Neuro-Fuzzy Classification Evolved through Parallel Evolutionary Computing and Applied to Energy Decomposition for Demand-Side Management in a Smart Home

Processes ◽  
2021 ◽  
Vol 9 (9) ◽  
pp. 1539
Author(s):  
Yu-Chen Hu ◽  
Yu-Hsiu Lin ◽  
Harinahalli Lokesh Gururaj
Keyword(s):  
Energy Consumption ◽  
Electric Energy ◽  
Smart Meter ◽  
Energy Decomposition ◽  
Smart Meters ◽  
Electrical Grid ◽  
Electric Energy Consumption ◽  
Partitional Clustering ◽  
Neuro Fuzzy ◽  
Consumption Data

The key advantage of smart meters over rotating-disc meters is their ability to transmit electric energy consumption data to power utilities’ remote data centers. Besides enabling the automated collection of consumers’ electric energy consumption data for billing purposes, data gathered by smart meters and analyzed through Artificial Intelligence (AI) make the realization of consumer-centric use cases possible. A smart meter installed in a domestic sector of an electrical grid and used for the realization of consumer-centric use cases is located at the entry point of a household/building’s electrical grid connection and can gather composite/circuit-level electric energy consumption data. However, it is not able to decompose its measured circuit-level electric energy consumption into appliance-level electric energy consumption. In this research, we present an AI model, a neuro-fuzzy classifier integrated with partitional clustering and metaheuristically optimized through parallel-computing-accelerated evolutionary computing, that performs energy decomposition on smart meter data in residential demand-side management, where a publicly available UK-DALE (UK Domestic Appliance-Level Electricity) dataset is used to experimentally test the presented model to classify the On/Off status of monitored electrical appliances. As shown in this research, the presented AI model is effective at providing energy decomposition for domestic consumers. Further, energy decomposition can be provided for industrial as well as commercial consumers.

MATHEMATICAL MODELS FOR MONITORING AND CONTROL OF ELECTRIC ENERGY CONSUMPTION WITH ACCOUNT OF THE SEASONAL FACTOR

2017 ◽  
Vol 11 (5) ◽  
pp. 133-140 ◽  
Author(s):  
Сергей Лавренченко ◽  
Sergey Lavrenchenko ◽  
Людмила Згонник ◽  
Lyudmila Zgonnik ◽  
Инна Гладская ◽  
...  
Keyword(s):  
Energy Consumption ◽  
Power Consumption ◽  
Electric Energy ◽  
Electricity Consumption ◽  
Daily Basis ◽  
Monitoring And Control ◽  
Theoretical Level ◽  
Electric Energy Consumption ◽  
Energy Meter ◽  
Seasonal Factor

The article proposes a method for predicting the daily energy consumption level for every day of a whole year, taking into account the season-al factor, based on only twelve actual power consumption data by the months of the year. Then a mathematical model is developed for moni-toring and controlling the level of electricity consumption on a daily basis, taking into account the seasonal factor. The model is consistent with a common model for the length of daylight (in hours). In addition, on the basis of this model, a method of monitoring and diagnostics of electricity consumption is presented, which will allow users to monitor the level of power consumption and be timely notified of any deviations from the theoretical level. Finally, this method gives rise to the operational principle for a proposed device, a smart energy meter, for detecting suspicious deviations from the theoretical level. The device will help timely detect over-consumption (or under-consumption) of electricity in order to take preventive measures. The proposed method consists of the following steps: (1) choice of a function to model the level of electricity consumption (theoretical calculated level), (2) choice of a tubular control neighborhood of the graph of the model function, (3) choice of a criterion on when the smart energy meter should notify the user of an unexpected deviation from the theoretical level in the case of exit from the tubular control neighborhood.

Agent-Based Simulation of Electric Energy Consumers

2014 ◽  
pp. 239-253 ◽  
Author(s):  
Fernanda Mota ◽  
Iverton Santos ◽  
Graçaliz Dimuro ◽  
Vagner Rosa ◽  
Silvia Botelho
Keyword(s):  
Energy Consumption ◽  
Multiagent Systems ◽  
Winter Season ◽  
Electric Energy ◽  
Synthetic Data ◽  
Agent Based ◽  
Electric Energy Consumption ◽  
Consumption Data ◽  
The Individual ◽  
Residential Consumption

The electric energy consumption is one of the main indicators of both the economic development and the quality of life of a society. However, the electric energy consumption data of individual home use is hard to obtain due to several reasons, such as privacy issues. In this sense, the social simulation based on multiagent systems comes as a promising option to deal with this difficulty through the production of synthetic electric energy consumption data. In a multiagent system the intelligent global behavior can be achieved from the behavior of the individual agents and their interactions. This chapter proposes a tool for simulation of electric energy consumers, based on multiagent systems concepts using the NetLogo tool. The tool simulates the residential consumption during working days and presented as a result the synthetic data average monthly consumption of residences, which varies according to income. So, the analysis of the produced simulation results show that economic consumers of the income 1 in the summer season had the lowest consumption among all other consumers and consumers noneconomic income 6 in the winter season had the highest.

scholarly journals Solving the Cold-Start Problem in Short-Term Load Forecasting Using Tree-Based Methods

Energies ◽  
2020 ◽  
Vol 13 (4) ◽  
pp. 886 ◽  
Author(s):  
Jihoon Moon ◽  
Junhong Kim ◽  
Pilsung Kang ◽  
Eenjun Hwang
Keyword(s):  
Random Forest ◽  
Energy Management ◽  
Load Forecasting ◽  
Electric Energy ◽  
Accurate Prediction ◽  
Electric Load ◽  
Test Set ◽  
Electric Energy Consumption ◽  
Consumption Data ◽  
Input Variables

An energy-management system requires accurate prediction of the electric load for optimal energy management. However, if the amount of electric load data is insufficient, it is challenging to perform an accurate prediction. To address this issue, we propose a novel electric load forecasting scheme using the electric load data of diverse buildings. We first divide the electric energy consumption data into training and test sets. Then, we construct multivariate random forest (MRF)-based forecasting models according to each building except the target building in the training set and a random forest (RF)-based forecasting model using the limited electric load data of the target building in the test set. In the test set, we compare the electric load of the target building with that of other buildings to select the MRF model that is the most similar to the target building. Then, we predict the electric load of the target building using its input variables via the selected MRF model. We combine the MRF and RF models by considering the different electric load patterns on weekdays and holidays. Experimental results demonstrate that combining the two models can achieve satisfactory prediction performance even if the electric data of only one day are available for the target building.

Sign in / Sign up

Export Citation Format

Share Document