The ever-growing modern smart grid with more distributed energy resources is providing efficient energy supply while facing several challenges that include harmonics induced among many. Previous and ...present literature shows that various machine and deep learning models are superior and accurate as compared to the traditional and conventional signal processing techniques. Obtaining accurate results becomes extremely important especially the fact that harmonics are essentially nonlinear, nonparametric, and adaptive in nature. This paper proposes a novel forecasting model that aggregates two deep learning models: convolutional neural network (CNN) and long short term memory (LSTM) recurrent neural network (RNN) detect and forecast harmonics in a power system. CNN-LSTM hybrid forecasting model for harmonics in the power grid system has achieved significantly superior performance in collaborative data mining on spatiotemporal measurement data. Sample features are extracted using CNN before they are passed through LSTM for prediction. To show the superiority of the hybrid CNN-LSTM deep neural prediction network model, it is compared with CNN, LSTM and NARX (Non-Linear Autoregressive with External (Exogenous) Input). CNN-LSTM forecasting performance is superior as compared to the other four models. MSE and RMSE for CNN-LSTM are 0.00038 (〖3.8 × 10〗^ (−4)) and 0.0000014917 (1.4917 × 10^(−6)) respectively.
The Integrated Energy Plan (IEP) was designed to consider South Africa's energy needs from 2015 to 2050, as a guide for energy structural savings and the development of energy policy. The main aim of ...the Department of Energy is to ensure the security of energy supply. The current energy situation in the country has its gains and challenges. With the growing population and infrastructural development, the country requires prudent measures to meet the country's energy needs for 2020-2050. The country's energy is currently dominated by coal-fired plants, which represent about 70% of the total installed capacity, crude oil contributes about 21%, with only 9% from all other energy sources, including renewables. This paper examines the scope of the IEP framework, key objectives of the IEP, the methodology applied to achieve those objectives, and the projections made for attaining the framework target. The paper further reviews the energy requirements for the key sectors of the economy and analyses the effects of CO2 emissions and the benefits of job creation for the entire period. Despite substantial renewable potential in South Africa, at present it contributes as little as 2% of the energy mix. The global renewable energy policy on CO2 emissions reduction, improvement of energy efficiency and deployment of renewable development are not met in the IEP framework.
Failure of element (s) in antenna arrays impair (s) symmetry and lead to unwanted distorted radiation pattern. The replacement of defective elements in aircraft antennas is a solution to the problem, ...but it remains a critical problem in space stations. In this paper, an antenna array diagnosis technique based on multivalued neural network (mNN) inverse modeling is proposed. Since inverse analytical input-to-output formulation is generally a challenging and important task in solving the inverse problem of array diagnosis, ANN is a compelling alternative, because it is trainable and learns from data in inverse modelling. The mNN technique proposed is an inverse modelling technique, which accommodates measurements for output model. This network takes radiation pattern samples with faults and matches it to the corresponding position or location of the faulty elements in that antenna array. In addition, we develop a new training error function, which focuses on the matching of each training sample by a value of our proposed inverse model, while the remaining values are free, and trained to match distorted radiation patterns. Thereby, mNN learns all training data by redirecting the faulty elements patterns into various values of the inverse model. Therefore, mNN is able to perform accurate array diagnosis in an automated and simpler manner.
The global energy consumption is increasing every day owing to the economic growth, urbanization, population growth, high standard of living and high income level. The conventional power plants ...cannot satisfy the world energy needs without some noticeable challenges such as greenhouse gas emissions, acid rain, health challenges, global warming, climate change and air pollution. The feasible alternative solution to meet ever increasing energy consumption in residential, commercial and industrial sectors of the economy is renewable energy sources (RESs) owing to the technical, political, societal, financial and environmental benefits. The hybrid energy system (HES) that is made up of wind turbine (WT), fuel cell (FC), photovoltaic (PV) and utility grid is proposed in the study to meet the energy needs of distinctive users in Cape Town, South Africa. The study's goal can be accomplished by making use of fmincon optimization technique to minimize the life cycle emission (LCE) of greenhouse gas (GHG), life cycle cost (LCC) and monetary value of energy purchased from the grid and maximize the job creation (JC), human development index (HDI), annual benefit (AB) and usage of PV, WT and FC. The effectiveness of the simulation technique applied in the paper can be assessed by comparing the HSE results with those from the base system. The outcomes of the HES offer a better performance with a payback period of 2.75 years, annual benefit of $329530, annual energy cost saving of $6899.3, annual electricity bill of $62747, potential energy saving of 52.37% and LCC of $419300. The annual energy purchased from the grid has reduced from 146,190 kWh to 59,593 kWh; this translates to 59.24% reduction when compared to the base system. The proposed HES with a non-renewable energy usage (NREU) of 40.78% and a renewable energy usage (REU) of 59.22% is financially feasible with a cost of energy (COE) of 0.0122 $/kWh and ecologically friendly with CO2, SO2 and NOx LCE reductions of 58.85%, 58.81% and 58.29% when compared with the base system. This indicates that PV, FC and WT can be used in the traditional power system to lower the annual electricity bill, energy purchased from the utility grid and GHG emissions. The results obtained from the assessment of the proposed HES serve as crucial decision-supporting tools that can be used by designers and operators in choosing the right parts for their power systems. The outcomes of the study can be utilized to enhance sustainability of electricity supply and minimize poverty in the developing countries.
Failure of element (s) in antenna arrays impair (s) symmetry and lead to unwanted distorted radiation pattern. The replacement of defective elements in aircraft antennas is a solution to the problem, ...but it remains a critical problem in space stations. In this paper, an antenna array diagnosis technique based on multivalued neural network (mNN) inverse modeling is proposed. Since inverse analytical input-to-output formulation is generally a challenging and important task in solving the inverse problem of array diagnosis, ANN is a compelling alternative, because it is trainable and learns from data in inverse modelling. The mNN technique proposed is an inverse modelling technique, which accommodates measurements for output model. This network takes radiation pattern samples with faults and matches it to the corresponding position or location of the faulty elements in that antenna array. In addition, we develop a new training error function, which focuses on the matching of each training sample by a value of our proposed inverse model, while the remaining values are free, and trained to match distorted radiation patterns. Thereby, mNN learns all training data by redirecting the faulty elements patterns into various values of the inverse model. Therefore, mNN is able to perform accurate array diagnosis in an automated and simpler manner.
With a view to adapting information signals to suit the frequency characteristics of digital transmission channels, it is pertinent to design channel coding schemes that can exhibit spectral shaping ...capabilities after being processed with a suitable modulation technique. This involves concentrating the frequency energy of the coded and modulated information signal towards a predetermined range of the frequency spectrum, or making it have low power content at such frequencies. One modulation scheme that is suitable for achieving this is pulse amplitude modulation (PAM). We thus present a permutation coding (PC) system with injections that can exhibit spectral nulls at rational sub-multiples of the symbol frequency. Such injections are achieved by strategically removing δ columns from the source PC. We also present a mathematical expression that allows for the prediction of zero energy positions in the codebook’s spectrum. Due to the way the injections are introduced, it gives the scheme an advantage of achieving higher symbol rate, when compared with conventional PC systems. The work is however limited to cases where δ =2 and the lengths of the codewords involved are even numbers.
The technology which utilises the power line as a medium for transferring information known as powerline communication (PLC) has been in existence for over a hundred years. It is beneficial because ...it avoids new installation since it uses the present installation for electrical power to transmit data. However, transmission of data signals through a power line channel usually experience some challenges which include impulsive noise, frequency selectivity, high channel attenuation, low line impedance, etc. The impulsive noise exhibits a power spectral density within the range of 10-15 dB higher than the background noise, which could cause a severe problem in a communication system. For better outcome of the PLC system, these noises must be detected and suppressed. This paper reviews various techniques used in detecting and mitigating the impulsive noise in PLC and suggests the application of machine learning algorithms for the detection and removal of impulsive noise in powerline communication systems.
For communication schemes employing Frequency Hopping/Multiple Frequency Shift Keying modulation, we present an algorithm for finding good non-binary synchronization sequences, which are ...permutations, to be used with permutation codes to synchronize/resynchronize data in channels with background noise and interference(frequency jamming/fading). For the synchronization sequences, new analytical expressions for the probability of false acquisition are also given. Using simulation results, we show that our synchronization sequences perform better than some conventional non-binary synchronization sequences, in the presence of background noise and interference.
Impulse Noise and Narrowband PLC Han Vinck, A J; Rouissi, F; Shongwe, T ...
arXiv (Cornell University),
09/2015
Paper, Journal Article
Odprti dostop
We discuss the influence of random- and periodic impulse noise on narrowband (< 500 kHz frequency band) Power Line Communications. We start with random impulse noise and compare the properties of the ...measured impulse noise with the common theoretical models like Middleton Class-A and Mixed Gaussian. The main difference is the fact that the measured impulse noise is noise with memory for the narrowband communication, whereas the theoretical models are memoryless. Since the FFT can be seen as a randomizing, operation, the impulse noise is assumed to appear as Gaussian noise after the FFT operation with a variance that is determined by the energy of the impulses. We investigate the problem of capacity loss due to this FFT operation. Another topic is that of periodical noise. Since periodic in the time domain means periodic in the frequency domain, this type of noise directly influences the output of the FFT for an OFDM based transmission. Randomization is necessary to avoid bursty- or dependent errors.