Recognition Method of Abnormal Power Consumption State of Power Users Based on Strategy Gradient Algorithm

2021 ◽  
Vol 16 (7) ◽  
pp. 1090-1097
Author(s):  
Fu Bao ◽  
Yudou Gao
Keyword(s):  
Power Consumption ◽  
Gradient Algorithm ◽  
Process Testing ◽  
Power Load ◽  
Recognition Result ◽  
Abnormal Increase ◽  
Recognition Efficiency ◽  
State Of Power ◽  
Status Recognition ◽  
And Training

Because the traditional method ignores the problem of power load data preprocessing, the accuracy of the recognition result of the power consumption status is not high, the recognition efficiency is not high, and the recognition effect is not good. For this reason, a method for identifying the abnormal power consumption status of power users based on the strategy gradient algorithm is proposed. The preprocessing of power load data mainly includes the completion of missing data and the feature extraction of power load data. Based on the results of the preprocessing, the abnormal increase in user power consumption is detected. Finally, the strategy gradient algorithm is used for initial training and training process testing to complete the identification of the abnormal state of power users. The experimental results show that the accuracy of the power status recognition result of the proposed method is higher, and the recognition time is always less than 2.0 s, indicating that the recognition effect of the method is better.

The Optimum Power Load: A Simple and Powerful Tool for Testing and Training

2021 ◽  
pp. 1-9
Author(s):  
Irineu Loturco ◽  
Antonio Dello Iacono ◽  
Fábio Y. Nakamura ◽  
Tomás T. Freitas ◽  
Daniel Boullosa ◽  
...  
Keyword(s):  
Strong Support ◽  
Current Evidence ◽  
Novel Approach ◽  
Power Load ◽  
Velocity Relationship ◽  
Potential Applications ◽  
Bar Velocity ◽  
Acute And Chronic Effects ◽  
Testing Protocols ◽  
And Training

Purpose: The optimal power load is defined as the load that maximizes power output in a given exercise. This load can be determined through the use of various instruments, under different testing protocols. Specifically, the “optimum power load” (OPL) is derived from the load–velocity relationship, using only bar force and bar velocity in the power computation. The OPL is easily assessed using a simple incremental testing protocol, based on relative percentages of body mass. To date, several studies have examined the associations between the OPL and different sport-specific measures, as well as its acute and chronic effects on athletic performance. The aim of this brief review is to present and summarize the current evidence regarding the OPL, highlighting the main lines of research on this topic and discussing the potential applications of this novel approach for testing and training. Conclusions: The validity and simplicity of OPL-based schemes provide strong support for their use as an alternative to more traditional strength–power training strategies. The OPL method can be effectively used by coaches and sport scientists in different sports and populations, with different purposes and configurations.

scholarly journals Deep Neural Network and Long Short-Term Memory for Electric Power Load Forecasting

2020 ◽  
Vol 10 (18) ◽  
pp. 6489
Author(s):  
Namrye Son ◽  
Seunghak Yang ◽  
Jeongseung Na
Keyword(s):  
Power Consumption ◽  
Short Term Memory ◽  
Load Forecasting ◽  
Power Demand ◽  
Short Term ◽  
Power Load ◽  
Short And Long Term ◽  
Long Short Term Memory ◽  
Electric Power Load

Forecasting domestic and foreign power demand is crucial for planning the operation and expansion of facilities. Power demand patterns are very complex owing to energy market deregulation. Therefore, developing an appropriate power forecasting model for an electrical grid is challenging. In particular, when consumers use power irregularly, the utility cannot accurately predict short- and long-term power consumption. Utilities that experience short- and long-term power demands cannot operate power supplies reliably; in worst-case scenarios, blackouts occur. Therefore, the utility must predict the power demands by analyzing the customers’ power consumption patterns for power supply stabilization. For this, a medium- and long-term power forecasting is proposed. The electricity demand forecast was divided into medium-term and long-term load forecast for customers with different power consumption patterns. Among various deep learning methods, deep neural networks (DNNs) and long short-term memory (LSTM) were employed for the time series prediction. The DNN and LSTM performances were compared to verify the proposed model. The two models were tested, and the results were examined with the accuracies of the six most commonly used evaluation measures in the medium- and long-term electric power load forecasting. The DNN outperformed the LSTM, regardless of the customer’s power pattern.

The Empirical Study in Smart Power Consumption Based on the Adjustment and Control System

2012 ◽  
Vol 241-244 ◽  
pp. 2010-2014 ◽  
Author(s):  
Kun Huang ◽  
Tian Yang Li ◽  
Yong Biao Yang
Keyword(s):  
Empirical Study ◽  
Power Consumption ◽  
Large Scale ◽  
Power Grid ◽  
Peak Load ◽  
Regulation System ◽  
Software Platform ◽  
Commercial Building ◽  
Smart Power ◽  
Power Load

The smart power consumption is an important orientation in peak load shifting and load shedding of power grid in particular time period. It has the significant effect to relieve the load shortage of the power grid. The large-scale electrical devices like central air-condition in commercial building have the great potential in the energy efficiency improvement and available load integration. The effectively regulation of power load in public and commercial construction can improve the stability and reliability of power grid. The power situation in china and the content of empirical study were introduced, and the system hardware design and software platform construction is demonstrated. The function modules of software platform and realization of regulation system are discussed in final.

scholarly journals The Design of Portable Battery Charging Devices Using Motorcycle Wheel Round

2019 ◽  
Vol 2 (2) ◽  
pp. 16-19
Author(s):  
Arlenny
Keyword(s):  
Power Consumption ◽  
Electric Power ◽  
Electrical Power ◽  
Electrical Energy ◽  
Threshold Value ◽  
Electric Power Consumption ◽  
Percentage Error ◽  
Average Percentage ◽  
Power Load ◽  
Average Percentage Error

This research aims to the development of reader equipment as well as control the load limitation of electric power using Atmega 8535 microcontroller. In the development of equipment of reading and controlling electrical energy consumptions, the modified KWH (Kilo Watt Hour) meter was used by placing the optocoupler sensor as the enumerator indicator the electric power consumption on the disc. Atmega 8535 microcontroller was used to control and limitation of the electric power consumption. In this research, the measuring and control system was developed to record the amount of electrical power load used, and it can be used as an alternative to the current divider for the achievement of the efficiency of practical electrical energy consumption. The results of the measurement comparison between the measured load and the output load tended to be stable with an average percentage error of 6.3%, and it was still below the optimum threshold value of the error factor, which around 10%. Therefore, results of testing developed equipment KWH digital meter using Atmega 8535 microcontroller that was produced a good performance.

scholarly journals Individualization of selection and training of female athletes in speed-power athletics from the perspective of gender identity

2020 ◽  
Vol 24 (4) ◽  
pp. 227-234
Author(s):  
Eugeny Vrublevskiy ◽  
Anatoly Skrypko ◽  
Ryszard Asienkiewicz
Keyword(s):  
Gender Identity ◽  
Short Distance ◽  
Female Athletes ◽  
Prognostic Assessment ◽  
Power Load ◽  
Effective Performance ◽  
Muscle Groups ◽  
Masculine Somatotype ◽  
And Training

Background and Study Aim. To develop and justify the criteria for morphogenetic markers of speed-power abilities of athletes and the main directions of individualization of the process of their preparation, taking into account the characteristics of the female body. Material and Methods. Using the “2D: 4D” determination methodology, finger proportions were analysed for 126 qualified athletes specializing in speed-strength types (sprinting and hurdling, jumping, shot-putting) of different ages (from 17 to 25 years old). For 13 weeks, eight qualified short-distance student runners were regularly tested using computer strain gauge equipment: 5 masculine and 3 feminine types. The tensodynamograms of the manifestation of the strength of muscle groups carrying the main load in the structure of the sprint run were recorded and processed. Results. It was found that 78% of the examined athletes observed finger proportions close to the "male" proportions. This may indicate their certain masculinization. The technique used for this can be an informative and simple marker to predict a genetic predisposition to the ability of effective performance of speed-power work. It was determined that the same amount of power load causes masculine athletes, runners for short distances, a more significant deployment of long-term adaptation restructuring of masculine athletes, runners for short distances, compared with athletes of a different gender identity. Conclusions. Criteria for the prognostic assessment of speed-power abilities of athletes based on simple biological markers for testing and identification, like finger proportions (2D: 4D), have been developed. For athletes of high qualification who have a gender identity similar to men and a masculine somatotype, it is possible to use adapted male techniques for training.

scholarly journals OPEC: Daily Load Data Analysis Based on Optimized Evolutionary Clustering

Energies ◽  
2019 ◽  
Vol 12 (14) ◽  
pp. 2668 ◽  
Author(s):  
Rongheng Lin ◽  
Zezhou Ye ◽  
Yingying Zhao
Keyword(s):  
Power Consumption ◽  
Power Grid ◽  
Electricity Consumption ◽  
Economic Benefits ◽  
Consumption Behavior ◽  
Evolutionary Clustering ◽  
Power Load ◽  
Short Period ◽  
Clustering Quality ◽  
Daily Load

Customers’ electricity consumption behavior can be studied from daily load data. Studying the daily load data for user behavior pattern analysis is an emerging research area in smart grid. Traditionally, the daily load data can be clustered into different clusters, to reveal the different categories of consumption. However, as user’s electricity consumption behavior changes over time, classical clustering algorithms are not suitable for tracing the changes, as they rebuild the clusters when clustering at any timestamp but never consider the relationship with the clusters in the previous state. To understand the changes of consumption behavior, we proposed an optimized evolutionary clustering (OPEC) algorithm, which optimized the existing evolutionary clustering algorithm by joining the Proper Restart (PR) Framework. OPEC relied on the basic fact that user’s energy consumption behavior would not abruptly change significantly, so the clusters would change progressively and remain similar in adjacent periods, except for an emergency. The newly added PR framework can deal with a situation where data changes dramatically in a short period of time, and where the former frameworks of evolutionary clustering do not work well. We evaluated the OPEC based on daily load data from Shanghai, China and the power load diagram data from UCI machine learning repository. We also carefully discussed the adjustment of the parameter in the optimized algorithm and gave an optimal value for reference. OPEC can be implemented to adapt to this situation and improve clustering quality. By understanding the changes of the users’ power consumption modes, we can detect abnormal power consumption behaviors, and also analyze the changing trend to improve the operations of the power system. This is significant for the regulation of peak load in the power grid. In addition, it can bring certain economic benefits to the operation of the power grid.

Research on Reclassification of Power Users for TOU Power Price Based on Fuzzy Clustering

2012 ◽  
Vol 229-231 ◽  
pp. 1013-1016
Author(s):  
Ling Luo ◽  
Bao Chen Jiang ◽  
Li Kai Liang
Keyword(s):  
Power Consumption ◽  
Fuzzy Clustering ◽  
Theoretical Basis ◽  
Clustering Algorithm ◽  
Simulation Analysis ◽  
Reference Value ◽  
Actual Condition ◽  
Load Curve ◽  
Fuzzy Clustering Algorithm ◽  
Power Load

Study on TOU (Time-of-Use) power price in our country almost treats power users as a unified whole, but different categories of users have the different power consumption and way in the actual condition. Therefore, they have different responses to TOU power price. According to the power load features of all kinds of users, the paper presents a solution to reclassify the users using fuzzy clustering algorithm, and provides theoretical basis for implementing categorized TOU power price. Finally comparatively perfect effect is obtained by simulation analysis, and it has great reference value to perfect TOU power price and improve load curve.

scholarly journals Individualization of selection and training of female athletes in speed-power athletics from the perspective of gender identity

2020 ◽  
Vol 24 (4) ◽  
pp. 227-234
Author(s):  
Eugeny Vrublevskiy ◽  
Anatoly Skrypko ◽  
Ryszard Asienkiewicz
Keyword(s):  
Gender Identity ◽  
Short Distance ◽  
Female Athletes ◽  
Prognostic Assessment ◽  
Power Load ◽  
Effective Performance ◽  
Muscle Groups ◽  
Masculine Somatotype ◽  
And Training

Background and Study Aim. To develop and justify the criteria for morphogenetic markers of speed-power abilities of athletes and the main directions of individualization of the process of their preparation, taking into account the characteristics of the female body. Material and Methods. Using the “2D: 4D” determination methodology, finger proportions were analysed for 126 qualified athletes specializing in speed-strength types (sprinting and hurdling, jumping, shot-putting) of different ages (from 17 to 25 years old). For 13 weeks, eight qualified short-distance student runners were regularly tested using computer strain gauge equipment: 5 masculine and 3 feminine types. The tensodynamograms of the manifestation of the strength of muscle groups carrying the main load in the structure of the sprint run were recorded and processed. Results. It was found that 78% of the examined athletes observed finger proportions close to the "male" proportions. This may indicate their certain masculinization. The technique used for this can be an informative and simple marker to predict a genetic predisposition to the ability of effective performance of speed-power work. It was determined that the same amount of power load causes masculine athletes, runners for short distances, a more significant deployment of long-term adaptation restructuring of masculine athletes, runners for short distances, compared with athletes of a different gender identity. Conclusions. Criteria for the prognostic assessment of speed-power abilities of athletes based on simple biological markers for testing and identification, like finger proportions (2D: 4D), have been developed. For athletes of high qualification who have a gender identity similar to men and a masculine somatotype, it is possible to use adapted male techniques for training.

scholarly journals Comparison of the Deep Learning Performance for Short-Term Power Load Forecasting

2021 ◽  
Vol 13 (22) ◽  
pp. 12493
Author(s):  
Namrye Son
Keyword(s):  
Deep Learning ◽  
Power Consumption ◽  
Electric Power ◽  
Electricity Consumption ◽  
Electricity Demand ◽  
Consumption Patterns ◽  
Learning Performance ◽  
Weather Data ◽  
Industrial Buildings ◽  
Power Load

Electricity demand forecasting enables the stable operation of electric power systems and reduces electric power consumption. Previous studies have predicted electricity demand through a correlation analysis between power consumption and weather data; however, this analysis does not consider the influence of various factors on power consumption, such as industrial activities, economic factors, power horizon, and resident living patterns of buildings. This study proposes an efficient power demand prediction using deep learning techniques for two industrial buildings with different power consumption patterns. The problems are presented by analyzing the correlation between the power consumption and weather data by season for industrial buildings with different power consumption patterns. Four models were analyzed using the most important factors for predicting power consumption and weather data (temperature, humidity, sunlight, solar radiation, total cloud cover, wind speed, wind direction, humidity, and vapor pressure). The prediction horizon for power consumption forecasting was kept at 24 h. The existing deep learning methods (DNN, RNN, CNN, and LSTM) cannot accurately predict power consumption when it increases or decreases rapidly. Hence, a method to reduce this prediction error is proposed. DNN, RNN, and LSTM were superior when using two-year electricity consumption rather than one-year electricity consumption and weather data.

scholarly journals Study on Electric Power Consumption Table for Fishing and Training Vessel

1989 ◽  
Vol 24 (10) ◽  
pp. 436-442
Author(s):  
Hisaharu Sakai ◽  
Hayao Akizawa ◽  
Yosuke Kitano ◽  
Katsuyuki Yamane
Keyword(s):  
Power Consumption ◽  
Electric Power ◽  
Electric Power Consumption ◽  
And Training
Sign in / Sign up

Export Citation Format

Share Document