Energy efficient biomorphic pulse information coding in electronic neurons for the entrance unit of the neuroprocessor

2019 ◽  
Vol 5 (3) ◽  
pp. 186-212 ◽  
Author(s):  
Alexander D. Pisarev
Keyword(s):  
Neural Networks ◽  
Energy Efficiency ◽  
Energy Efficient ◽  
Information Transfer ◽  
Biological Systems ◽  
Technological Parameters ◽  
Input Unit ◽  
Efficient Operation ◽  
Electric Circuits ◽  
Electronic Neuron

This article studies the implementation of some well-known principles of information work of biological systems in the input unit of the neuroprocessor, including spike coding of information used in models of neural networks of the latest generation.<br> The development of modern neural network IT gives rise to a number of urgent tasks at the junction of several scientific disciplines. One of them is to create a hardware platform&nbsp;— a neuroprocessor for energy-efficient operation of neural networks. Recently, the development of nanotechnology of the main units of the neuroprocessor relies on combined memristor super-large logical and storage matrices. The matrix topology is built on the principle of maximum integration of programmable links between nodes. This article describes a method for implementing biomorphic neural functionality based on programmable links of a highly integrated 3D logic matrix.<br> This paper focuses on the problem of achieving energy efficiency of the hardware used to model neural networks. The main part analyzes the known facts of the principles of information transfer and processing in biological systems from the point of view of their implementation in the input unit of the neuroprocessor. The author deals with the scheme of an electronic neuron implemented based on elements of a 3D logical matrix. A pulsed method of encoding input information is presented, which most realistically reflects the principle of operation of a sensory biological neural system. The model of an electronic neuron for selecting ranges of technological parameters in a real 3D logic matrix scheme is analyzed. The implementation of disjunctively normal forms is shown, using the logic function in the input unit of a neuroprocessor as an example. The results of modeling fragments of electric circuits with memristors of a 3D logical matrix in programming mode are presented.<br> The author concludes that biomorphic pulse coding of standard digital signals allows achieving a high degree of energy efficiency of the logic elements of the neuroprocessor by reducing the number of valve operations. Energy efficiency makes it possible to overcome the thermal limitation of the scalable technology of three-dimensional layout of elements in memristor crossbars.

scholarly journals Feedforward Tactical Optimization for Energy-Efficient Operation of Freight Trains: The Swiss Case

2018 ◽  
Vol 2672 (10) ◽  
pp. 278-288 ◽  
Author(s):  
Valerio De Martinis ◽  
Ambra Toletti ◽  
Francesco Corman ◽  
Ulrich A. Weidmann ◽  
Andrew Nash
Keyword(s):  
Energy Efficiency ◽  
Energy Efficient ◽  
Real Data ◽  
Efficient Solutions ◽  
Future Market ◽  
Speed Profile ◽  
Efficient Operation ◽  
The North ◽  
Simulation Based ◽  
Profile Optimization

The optimization of rail operation for improving energy efficiency plays an important role for the current and future market of rail freight services and helps rail compete with other transport modes. This paper presents a feedforward simulation-based model that performs speed profile optimization together with minor rescheduling actions. The model’s purpose is to provide railway operators and infrastructure managers with energy-efficient solutions that are tailored especially for freight trains. This work starts from the assumption that freight train characteristics are completely defined only a few hours before actual departure; therefore, small specific feedforward adjustments that do not affect the surrounding operation can still be considered. The model was tested in a numerical example. The example clearly shows how the optimized solutions can be evaluated with reference to energy saved and robustness within the rail traffic. The evaluation is based on real data from the North–South corridor crossing Switzerland from Germany to Italy.

scholarly journals Energy-Efficient Coding with Discrete Stochastic Events

2002 ◽  
Vol 14 (6) ◽  
pp. 1323-1346 ◽  
Author(s):  
Susanne Schreiber ◽  
Christian K. Machens ◽  
Andreas. V. M. Herz ◽  
Simon B. Laughlin
Keyword(s):  
Energy Efficiency ◽  
Energy Efficient ◽  
Information Transfer ◽  
Energy Use ◽  
Bimodal Distribution ◽  
Fixed Cost ◽  
Signaling Cost ◽  
Trade Offs ◽  
Flow Through ◽  
Stochastic Events

We investigate the energy efficiency of signaling mechanisms that transfer information by means of discrete stochastic events, such as the opening or closing of an ion channel. Using a simple model for the generation of graded electrical signals by sodium and potassium channels, we find optimum numbers of channels that maximize energy efficiency. The optima depend on several factors: the relative magnitudes of the signaling cost (current flow through channels), the fixed cost of maintaining the system, the reliability of the input, additional sources of noise, and the relative costs of upstream and downstream mechanisms. We also analyze how the statistics of input signals influence energy efficiency. We find that energy-efficient signal ensembles favor a bimodal distribution of channel activations and contain only a very small fraction of large inputs when energy is scarce. We conclude that when energy use is a significant constraint, trade-offs between information transfer and energy can strongly influence the number of signaling molecules and synapses used by neurons and the manner in which these mechanisms represent information.

scholarly journals Energy-efficient memcapacitor devices for neuromorphic computing

2021 ◽  
Author(s):  
Kai-Uwe Demasius ◽  
Aron Kirschen ◽  
Stuart Parkin
Keyword(s):  
Neural Network ◽  
Artificial Intelligence ◽  
Neural Networks ◽  
Energy Efficiency ◽  
High Precision ◽  
Energy Efficient ◽  
Lateral Size ◽  
Data Intensive Computing ◽  
Data Intensive ◽  
Specialized Hardware

AbstractData-intensive computing operations, such as training neural networks, are essential for applications in artificial intelligence but are energy intensive. One solution is to develop specialized hardware onto which neural networks can be directly mapped, and arrays of memristive devices can, for example, be trained to enable parallel multiply–accumulate operations. Here we show that memcapacitive devices that exploit the principle of charge shielding can offer a highly energy-efficient approach for implementing parallel multiply–accumulate operations. We fabricate a crossbar array of 156 microscale memcapacitor devices and use it to train a neural network that could distinguish the letters ‘M’, ‘P’ and ‘I’. Modelling these arrays suggests that this approach could offer an energy efficiency of 29,600 tera-operations per second per watt, while ensuring high precision (6–8 bits). Simulations also show that the devices could potentially be scaled down to a lateral size of around 45 nm.

scholarly journals Autonomous Transmission Power Decision Strategy for Energy Efficient Operation of a Dense Small Cell Network

2018 ◽  
Vol 2018 ◽  
pp. 1-8
Author(s):  
Jaesung Park ◽  
Heejung Byun
Keyword(s):  
Energy Efficiency ◽  
Power Control ◽  
Programming Problem ◽  
Energy Efficient ◽  
Small Cell ◽  
Small Cells ◽  
Noncooperative Game ◽  
Efficient Operation ◽  
Cell Network ◽  
Small Cell Network

Smart interference management methods are required to enhance the throughput, coverage, and energy efficiency of a dense small cell network. In this paper, we propose a transmit power control for energy efficient operation of a dense small cell network. We cast the power control problem as a noncooperative game to satisfy the design requirement that small cells do not need any information exchange among them. We analyze the sufficient condition for the existence of a Nash equilibrium (NE) state of the proposed game. We also analyze that the NE state is unique by transforming the original nonlinear fractional programming problem into a nonlinear parametric programming problem. Through simulation studies, we verify our analysis results. In addition, we show that the proposed method achieves higher energy efficiency of a network and balances the energy efficiency among cells more evenly than the methods based on the AIMD (additive increase and multiplicative decrease) algorithm.

scholarly journals Towards Efficient Neuromorphic Hardware: Unsupervised Adaptive Neuron Pruning

Electronics ◽  
2020 ◽  
Vol 9 (7) ◽  
pp. 1059 ◽  
Author(s):  
Wenzhe Guo ◽  
Hasan Erdem Yantır ◽  
Mohammed E. Fouda ◽  
Ahmed M. Eltawil ◽  
Khaled Nabil Salama
Keyword(s):  
Neural Networks ◽  
Energy Efficiency ◽  
Real Time ◽  
Classification Accuracy ◽  
Energy Efficient ◽  
Spiking Neural Networks ◽  
Neuron Network ◽  
Neuromorphic Hardware ◽  
Neuromorphic Systems ◽  
Network Compression

To solve real-time challenges, neuromorphic systems generally require deep and complex network structures. Thus, it is crucial to search for effective solutions that can reduce network complexity, improve energy efficiency, and maintain high accuracy. To this end, we propose unsupervised pruning strategies that are focused on pruning neurons while training in spiking neural networks (SNNs) by utilizing network dynamics. The importance of neurons is determined by the fact that neurons that fire more spikes contribute more to network performance. Based on these criteria, we demonstrate that pruning with an adaptive spike count threshold provides a simple and effective approach that can reduce network size significantly and maintain high classification accuracy. The online adaptive pruning shows potential for developing energy-efficient training techniques due to less memory access and less weight-update computation. Furthermore, a parallel digital implementation scheme is proposed to implement spiking neural networks (SNNs) on field programmable gate array (FPGA). Notably, our proposed pruning strategies preserve the dense format of weight matrices, so the implementation architecture remains the same after network compression. The adaptive pruning strategy enables 2.3× reduction in memory size and 2.8× improvement on energy efficiency when 400 neurons are pruned from an 800-neuron network, while the loss of classification accuracy is 1.69%. And the best choice of pruning percentage depends on the trade-off among accuracy, memory, and energy. Therefore, this work offers a promising solution for effective network compression and energy-efficient hardware implementation of neuromorphic systems in real-time applications.

scholarly journals Energy Savings Analysis for Operation of Steam Cushion System for Sensible Thermal Energy Storages

Energies ◽  
2022 ◽  
Vol 15 (1) ◽  
pp. 286
Author(s):  
Ryszard Zwierzchowski ◽  
Olgierd Niemyjski ◽  
Marcin Wołowicz
Keyword(s):  
Energy Efficiency ◽  
Heat Flow ◽  
Thermal Energy ◽  
Energy Efficient ◽  
Energy Production ◽  
Energy Savings ◽  
Hot Water ◽  
Efficient Operation ◽  
Suction Pipe ◽  
Technical Solutions

The paper presents an analytical discussion of how to improve the energy efficiency of the steam cushion system operation for a Thermal Energy Storage (TES) tank. The EU’s green deal 2050 target policy requires an increase in the energy efficiency of energy production and use, as well as an increase in the share of renewable energy in the overall energy production balance. The use of energy-efficient TES is considered as one of the most important technologies to achieve the objectives of this EU policy. The analyses presented in the paper of energy-efficient operation of steam cushion (SC) systems were carried out by using operational data received from three District Heating Systems (DHSs) that supply heat and electricity to one of the largest cities in Poland and are equipped with the TES systems. These three analyzed TESs differ in capacities from 12,800 to 30,400 m3, tank diameters from 21 to 30 m and shell height from 37 to 48.2 m. The main purpose of using a steam cushion system in the TES tank is to protect the water stored in it against the absorption of oxygen from the surrounding atmospheric air through the surge chamber and safety valves located on the roof of the tank. The technical solutions presented here for the upper orifice for charging and discharging hot water into/from the tank and the suction pipe for circulating water allow to us achieve significant energy savings in the steam cushion systems. Both the upper orifice and the end of suction pipe are movable through the use of pontoons. Thanks to the use of this technical solution, a stable insulating water layer is created above the upper orifice in the upper part of the TES tank, where convective and turbulent transport of heat from the steam cushion space to the hot water stored in the tank is significantly limited. Ultimately, this reduces the heat flux by approximately 90% when compared to the classic technical solutions of steam cushion systems in TES tanks, i.e., for the upper orifice and circulation water pipe. The simplified analysis presented in the paper and comparison of its results with experimental data for heat flow from the steam cushion space to hot water stored in the upper part of the TES tank fully confirms the usefulness of the heat-flow models used.

scholarly journals Energy Efficient Control by the Group of Oil Pumping Stations Operation

2021 ◽  
pp. 13-22
Author(s):  
Gennadii Kaniuk ◽  
◽  
Andrii Mezeria ◽  
Victoria Kniazeva ◽  
Tetiana Fursova ◽  
...  
Keyword(s):  
Energy Efficiency ◽  
Total Energy ◽  
Energy Efficient ◽  
Economic Effect ◽  
Energy Losses ◽  
Efficient Operation ◽  
Operation Modes ◽  
Pumping Stations ◽  
Efficient Control ◽  
Pumping Units

This work is devoted to intensification of the power efficiency of computerized systems of con-trol by the pumping units group of oil pumping stations of the main lines. The criterion of the energy efficiency is a minimum total energy loss. The goal set can be reached by the develop-ment of algorithms of the energy efficient control. The most important scientific result based on the identification of the mathematical models of the objects controlled is the efficient algorithm for controlling the group of oil pumping units. It allows determining in real time the operation modes of separate pumping units, upon which the total energy losses will be minimal. The sig-nificance of the results obtained consists in the energy losses decrease across the main oil pipe-line during the combined control by the pumping units groups. Their practical significance con-sists in decreasing the cost of oil transportation at the expense of decreasing the energy con-sumed by the pumping units. The main stages of plotting the modes maps were presented of the efficient operation of the pumping units based on the definition of the necessary rotation fre-quencies and positions of the regulating valves. Experimentally was performed the analysis of the operation modes of the pumping unit using different methods for productivity regulation, and their comparative energy efficiency was shown. The experimental data extrapolation was carried out, and, on its basis, the possible economic effect was determined brought by the use of the energy-conserving systems of the controlling the group of pumping systems.

scholarly journals Development of energy efficient system of gas cooling of mobile diesel compressor stations of oil and gas industry

2020 ◽  
pp. 81-89
Author(s):  
S. I. Kryshtopa ◽  
L. I. Kryshtopa ◽  
M. М. Hnyp ◽  
I. M. Mykytiy ◽  
M. M. Tseber
Keyword(s):  
Energy Efficiency ◽  
Energy Efficient ◽  
Oil And Gas ◽  
Cooling System ◽  
Oil And Gas Industry ◽  
Gas Temperature ◽  
Gas Industry ◽  
Efficient Operation ◽  
Efficient System ◽  
Gas Cooling

The developments of domestic and foreign specialists in the field of improving the energy efficiency of mobile diesel compressor stations of the oil and gas industry is studied. The disadvantages of existing mobile diesel compressor stations in terms of their energy efficiency are identified. Theoretical studies of energy efficiency directions and designs of existing mobile diesel compressor stations have been carried out. It has been studied that for efficient operation of a compressor station it is rational to increase the load of compressors and organize the operation of equipment in energy-efficient modes. Ways to improve the energy efficiency of mobile diesel compressor stations with various options are proposed. It has been established that the optimal way to increase energy efficiency is to reduce the gas temperature to lower temperatures, in comparison with the existing gas cooling systems of compressor stations. It is found that with an increase in the degree of pressure, the savings in gas compression for a compressor with a promising scheme for intermediate gas cooling also increase. An indicator diagram of compressor stations with various cooling schemes has been built. The scheme of the existing system of multi-stage gas cooling of mobile diesel compressor stations is investigated. An improved energy-efficient cooling system for compressed gas by using the heat of compression of gases is proposed. The conclusion about the existence of a reserve to reduce the energy costs of compression due to the use of a coolant-cooler with a temperature significantly lower than the ambient temperature is presented. The description of the working processes of mobile diesel compressor stations according to the existing and perspective schemes is made.

scholarly journals INCREASING CENTRIFUGAL PUMP PERFORMANCE

2019 ◽  
Vol 46 (2) ◽  
pp. 20-27
Author(s):  
S. V. Mikhaylova ◽  
I. A. Pogrebnaya
Keyword(s):  
Energy Efficiency ◽  
Comparative Analysis ◽  
Energy Efficient ◽  
Oil Production ◽  
High Yield ◽  
Maximum Efficiency ◽  
Energy Costs ◽  
Centrifugal Pumps ◽  
Efficient Operation ◽  
Oil Companies

Objectives Investigate the prospect of improving the quality of centrifugal pumps in oil production.Method The method is based on energy-efficient installations for high-yield wells - the steps of the Borets-Weatherford installations and the Borets PC stages.Result The main hydraulic characteristics of electric centrifugal pumps with the use of energy-efficient stages with the recommended feed range have been developed. The dependence of the maximum efficiency on the applied steps of the above installations has been determined. A comparative analysis of energy-efficient and commercially available installation of electric centrifugal pumps is given. The dependence of the parameters of the installation steps on the flow, head, number of stages, nominal speed and efficiency of the pump is given.Conclusion When using submersible pumps of the 10ECNM type in oil fields, increased reliability and durability were noted, in contrast to the use of submersible ECNM-type pumps. With the help of energy efficiency programs for oil production, implemented by oil companies, by ensuring more efficient operation of pumping equipment, power consumption has been reduced. The adoption of promising solutions to improve the energy efficiency of ESP systems is a priority. The use of energy-efficient ESP systems for the operation of high-rate and low-rate wells allows to ensure maximum efficiency of the submersible equipment and reduce the specific electricity consumption. In a comparative analysis of the characteristics of pumps with a daily flow of 400 m3, the use of an energyefficient installation ESP 400–2200 with FEA provides three times lower energy costs. A comparative analysis of the energy efficiency of the presented pumps shows that the use of energy-efficient installations of electric centrifugal pumps produced by PC Borets LLC will reduce energy costs by an average of 30%. 

scholarly journals Improving Energy Efficiency of Flexible Pneumatic Systems

Energies ◽  
2021 ◽  
Vol 14 (7) ◽  
pp. 1819
Author(s):  
Slobodan Dudić ◽  
Vule Reljić ◽  
Dragan Šešlija ◽  
Nikolina Dakić ◽  
Vladislav Blagojević
Keyword(s):  
Energy Efficiency ◽  
Energy Efficient ◽  
Energy Savings ◽  
Production Systems ◽  
Pneumatic Actuator ◽  
Task Characteristics ◽  
Operating Pressure ◽  
Efficient Operation ◽  
Flexible Production Systems ◽  
Variable Weight

During pneumatic control system design, the critical value for choosing the appropriate pneumatic actuator is the weight of the workpiece. In the case of flexible production systems, which are the core part of the Industry 4.0 (I4.0) concept, the weight of the workpieces is often variable, since the crucial feature of this kind of production is its ability to deal with variable parts. Therefore, in order to deal with the variable weight of parts, a pneumatic actuator is chosen according to the heaviest part. However, according to another I4.0 principle, energy efficient operation of machines, the previous criteria for choosing a pneumatic actuator is energy efficient only when handling the heaviest part. In all other cases, operation of the pneumatic actuator is suboptimal in terms of energy efficiency. Aiming to solve this problem, this paper considers the possibility of using a new pressure regulator instead of traditional manually adjusted pressure regulators. This regulator provides operating pressure modification in real-time in accordance with the weight of the workpieces. In this way, the optimal compressed air consumption is ensured for each workpiece. Implementation of this device has yielded significant energy savings; however, the value is variable and depends on working task characteristics.

Sign in / Sign up

Export Citation Format

Share Document