Demand Management of Distributed Energy Loads Based on Genetic Algorithm Optimization

2013 ◽  
Vol 136 (2) ◽  
Author(s):  
Jiaming Li ◽  
Glenn Platt ◽  
Geoff James
Keyword(s):  
Genetic Algorithm ◽  
Information Exchange ◽  
Energy Demand ◽  
Demand Management ◽  
Energy Resource ◽  
Electricity Consumption ◽  
Central Processor ◽  
Algorithm Optimization ◽  
Distributed Energy ◽  
Multi Agent

Management of a very large number of distributed energy resources, energy loads, and generators, is a hot research topic. Such energy demand management techniques enable appliances to control and defer their electricity consumption when price soars and can be used to cope with the unpredictability of the energy market or provide response when supply is strained by demand. We consider a multi-agent system comprising multiple energy loads, each with a dedicated controller. This paper introduces our latest research in self-organization of coordinated behavior of multiple agents. Energy resource agents (RAs) coordinate with each other to achieve a balance between the overall consumption by the multi-agent collective and the stress on the community. In order to reduce the overall communication load while permitting efficient coordinated responses, information exchange is through indirect communications between RAs and a broker agent (BA). This gives a decentralized coordination approach that does not rely on intensive computation by a central processor. The algorithm presented here can coordinate different types of loads by controlling their set-points. The coordination strategy is optimized by a genetic algorithm (GA) and a fast coordination convergence has been achieved.

Analiza potencijala za uvođenje sistema pametnih mreža u Bosni i Hercegovini

2021 ◽  
Vol 23 (3) ◽  
pp. 61-65
Author(s):  
Jasmina Imamović ◽  
Sanda Midžić Kurtagić ◽  
Esma Manić ◽  
Keyword(s):  
Renewable Energy ◽  
Smart Grid ◽  
Technological Development ◽  
Energy Resource ◽  
Electricity Consumption ◽  
Policy Framework ◽  
Distributed Energy ◽  
Smart Meters ◽  
Distributed Energy Resource ◽  
Charging Stations

The paper presents an analysis of the current situation regarding the development of an electricity distribution network and potential for a smart grid development in the selected pilot region of Bosnia and Herzegovina. Apart from the policy framework assessment, several indicator based criteria were included in the scope of analysis: share of renewable energy and renewable energy as distributed energy resource, total share of distributed energy resources, a number of installed smart meters for measuring electricity consumption, a number of charging stations for electric vehicles, energy storage capacities and technological development. The overall analysis of the assessment has been done by normalization of the calculated values of the indicators on a scale of 1-5. The indicators have showed that the smart grid sector in the Region is currently underdeveloped.

scholarly journals Multi-Label Learning for Appliance Recognition in NILM Using Fryze-Current Decomposition and Convolutional Neural Network

Energies ◽  
2020 ◽  
Vol 13 (16) ◽  
pp. 4154 ◽  
Author(s):  
Anthony Faustine ◽  
Lucas Pereira
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Energy Demand ◽  
Learning Strategy ◽  
Demand Management ◽  
Management Strategies ◽  
Electricity Consumption ◽  
Consumption Pattern ◽  
Similarity Function ◽  
Active Components

The advance in energy-sensing and smart-meter technologies have motivated the use of a Non-Intrusive Load Monitoring (NILM), a data-driven technique that recognizes active end-use appliances by analyzing the data streams coming from these devices. NILM offers an electricity consumption pattern of individual loads at consumer premises, which is crucial in the design of energy efficiency and energy demand management strategies in buildings. Appliance classification, also known as load identification is an essential sub-task for identifying the type and status of an unknown load from appliance features extracted from the aggregate power signal. Most of the existing work for appliance recognition in NILM uses a single-label learning strategy which, assumes only one appliance is active at a time. This assumption ignores the fact that multiple devices can be active simultaneously and requires a perfect event detector to recognize the appliance. In this paper proposes the Convolutional Neural Network (CNN)-based multi-label learning approach, which links multiple loads to an observed aggregate current signal. Our approach applies the Fryze power theory to decompose the current features into active and non-active components and use the Euclidean distance similarity function to transform the decomposed current into an image-like representation which, is used as input to the CNN. Experimental results suggest that the proposed approach is sufficient for recognizing multiple appliances from aggregated measurements.

scholarly journals Energy Demand Management and Social Norms

Energies ◽  
2020 ◽  
Vol 13 (15) ◽  
pp. 3779
Author(s):  
Bernadeta Gołębiowska ◽  
Anna Bartczak ◽  
Mikołaj Czajkowski
Keyword(s):  
Social Norms ◽  
Financial Incentives ◽  
Energy Demand ◽  
Consumer Preferences ◽  
Demand Management ◽  
Electricity Consumption ◽  
External Control ◽  
Revealed Preferences ◽  
Personal Norms ◽  
The Impact

The main objective of our study was investigating the impact of norms and financial motivation on the disutility of energy management for Polish households. We analyzed consumer preferences and willingness to accept demand-side management (DSM) programs. Choice experiment was applied for electricity contracts including external control of electricity consumption. Ajzen’s theory of planned behavior provided the theoretical framework of the study, which tested hypotheses about the impact of social norms on consumer choices of electricity contracts. We show that people with higher descriptive social norms about electricity consumption are less sensitive to the level of compensation and more responsive to the number of blackouts. People willing to sign a contract for financial reasons were less sensitive to the external control of electricity consumption and less inclined toward the status quo option. Injunctive social norms and personal norms had a non-significant impact on consumer decisions. We conclude that financial incentives can reduce the effect of the norms. Social and personal norms seem to be more important when we analyze the revealed preferences. European countries face significant challenges related to changes in energy policy. This study contributes to understanding the decisions of households and provides insights into the implementation of DSM.

Optimization of Hydrofoils for Horizontal Axis Marine Current Turbines Using Genetic Algorithm

2013 ◽  
Author(s):  
Krishnil R. Ram ◽  
Jai N. Goundar ◽  
Deepak Prasad ◽  
Sunil Lal ◽  
Mohammed Rafiuddin Ahmed
Keyword(s):  
Genetic Algorithm ◽  
Reynolds Number ◽  
Fossil Fuels ◽  
Energy Resource ◽  
Tidal Energy ◽  
Horizontal Axis ◽  
Geometric Constraints ◽  
Algorithm Optimization ◽  
Tidal Turbines ◽  
Marine Current

As fossil fuels near depletion and their detrimental side effects become prominent on ecosystems, the world is searching for renewable sources of energy. Tidal energy is an emerging and promising renewable energy resource. Tidal turbines can extract energy from the flowing water in a similar way as wind turbines extract energy from the wind. The upside with tidal turbines is that the density of water is approximately 800 times greater than that of air and a tidal turbine harnessing the same amount of power as a wind turbine can be considerably smaller in size. At the heart of the horizontal axis marine current turbines are carefully designed hydrofoil sections. While there is a growing need to have hydrofoils that provide good hydrodynamic and structural performances, the hydrofoils also have to avoid cavitation for safe operation. This study uses a genetic algorithm optimization code to develop hydrofoils which have the desired qualities mentioned above. The hydrofoil problem is parameterized using a composite Bezier curve with two Bezier segments and 11 control points. Appropriate curvature conditions are implemented and geometric constraints are enforced to maintain the hydrofoil thickness between 16 to 18%. XFOIL is used as the flow solver in this study. The hydrofoils are optimized at Reynolds number of 2 million and for angles between 4 to 10 degrees. The best foil from the results, named USPT4 is tested for performance with the CFD code ANSYS CFX. The CFX results are validated with experimental results in a wind tunnel at the same Reynolds number. The hydrofoil’s performance is also compared with a commonly used NACA foil.

scholarly journals An IOT based smart metering development for energy management system

2019 ◽  
Vol 9 (4) ◽  
pp. 3041 ◽  
Author(s):  
S.G Priyadharshini ◽  
C. Subramani ◽  
J. Preetha Roselyn
Keyword(s):  
Remote Monitoring ◽  
Energy Demand ◽  
Demand Management ◽  
Electricity Consumption ◽  
Smart Meter ◽  
End User ◽  
Labview Software ◽  
The Past ◽  
To Come ◽  
Smart Grid Technology

<p>The worldwide energy demand is increasing and hence necessity measures need to be taken to reduce the energy wastage with proper metering infrastructure in the buildings. A Smart meter can be used to monitor electricity consumption of customers in the smart grid technology. For allocating the available resources proper energy demand management is required. During the past years, various methods are being utilized for energy demand management to precisely calculate the requirements of energy that is yet to come. A large system presents a potential esteem to execute energy conservation as well as additional services linked to energy services, extended as a competent with end user is executed. The supervising system at the utilities determines the interface of devices with significant advantages, while the communication with the household is frequently proposing particular structures for appropriate buyer-oriented implementation of a smart meter network. Also, this paper concentrates on the estimation of vitality utilization. In this paper energy is measured in units and also product arrangement is given to create bill for energy consumption and implementing in LabVIEW software. An IOT based platform is created for remote monitoring of the metering infrastructure in the real time. The data visualization is also carried out in webpage and the data packet loss is investigated in the remote monitoring of the parameters.</p>

A Multi-Agent Machine Learning Framework for Intelligent Energy Demand Management

2011 ◽  
pp. 198-212
Author(s):  
Ying Guo ◽  
Rongxin Li
Keyword(s):  
Energy Consumption ◽  
Energy Demand ◽  
Demand Management ◽  
System Stability ◽  
Load Management ◽  
Time Interval ◽  
Learning Framework ◽  
Power Load ◽  
Negative Effect ◽  
Multi Agent

In order to cope with the unpredictability of the energy market and provide rapid response when supply is strained by demand, an emerging technology, called energy demand management, enables appliances to manage and defer their electricity consumption when price soars. Initial experiments with our multi-agent, power load management simulator, showed a marked reduction in energy consumption when price-based constraints were imposed on the system. However, these results also revealed an unforeseen, negative effect: that reducing consumption for a bounded time interval decreases system stability. The reason is that price-driven control synchronizes the energy consumption of individual agents. Hence price, alone, is an insufficient measure to define global goals in a power load management system. In this chapter the authors explore the effectiveness of a multi-objective, system-level goal which combines both price and system stability. The authors apply the commonly known reinforcement learning framework, enabling the energy distribution system to be both cost saving and stable. They test the robustness of their algorithm by applying it to two separate systems, one with indirect feedback and one with direct feedback from local load agents. Results show that their method is not only adaptive to multiple systems, but is also able to find the optimal balance between both system stability and energy cost.

A Multi-Agent Machine Learning Framework for Intelligent Energy Demand Management

2012 ◽  
pp. 318-332
Author(s):  
Ying Guo ◽  
Rongxin Li
Keyword(s):  
Energy Consumption ◽  
Energy Demand ◽  
Demand Management ◽  
System Stability ◽  
Load Management ◽  
Time Interval ◽  
Learning Framework ◽  
Power Load ◽  
Negative Effect ◽  
Multi Agent

In order to cope with the unpredictability of the energy market and provide rapid response when supply is strained by demand, an emerging technology, called energy demand management, enables appliances to manage and defer their electricity consumption when price soars. Initial experiments with our multi-agent, power load management simulator, showed a marked reduction in energy consumption when price-based constraints were imposed on the system. However, these results also revealed an unforeseen, negative effect: that reducing consumption for a bounded time interval decreases system stability. The reason is that price-driven control synchronizes the energy consumption of individual agents. Hence price, alone, is an insufficient measure to define global goals in a power load management system. In this chapter the authors explore the effectiveness of a multi-objective, system-level goal which combines both price and system stability. The authors apply the commonly known reinforcement learning framework, enabling the energy distribution system to be both cost saving and stable. They test the robustness of their algorithm by applying it to two separate systems, one with indirect feedback and one with direct feedback from local load agents. Results show that their method is not only adaptive to multiple systems, but is also able to find the optimal balance between both system stability and energy cost.

Optimal Design of a Distributed Energy Resources System That Minimizes Cost While Reducing Carbon Emissions

2017 ◽  
Author(s):  
Robert Flores ◽  
Jack Brouwer
Keyword(s):  
Carbon Emissions ◽  
Energy Demand ◽  
Energy Resource ◽  
Minimum Cost ◽  
Mixed Integer ◽  
Distributed Energy ◽  
Gas Generator ◽  
Mixed Integer Linear Program ◽  
The Cost ◽  
The University

From a practical perspective, economics drive the development of distributed energy resource (DER) systems. However, the adoption of a DER system provides an opportunity for the end user to completely control their environmental footprint. This work examines the process of designing a DER system while controlling carbon emissions. A mixed integer linear program (MILP) for sizing and dispatching a DER system is developed. The MILP includes a novel formulation of constraints that govern utility natural gas, generator operational state, and charging of thermal energy storage. The MILP is executed using real energy demand data for the University of California, Irvine to optimally design a DER system that minimizes cost while also reducing carbon emissions by a specified quantity. Two primary technology scenarios are explored (DER including storage with and without electrical export). A trajectory of DER technology adoption is determined for both technology scenarios. The different operational methods through which each system achieved lower carbon emissions at minimum cost is examined. Finally, the cost to reduce carbon emissions is calculated for both technology scenarios.

Sign in / Sign up

Export Citation Format

Share Document