## No full-text available

To read the full-text of this research,

you can request a copy directly from the authors.

Conference Paper

Smart grid is one of the most advanced technologies which plays a key role in maintaining balance between demand and supply by implementing demand response (DR). Residential users basically effect the overall performance of traditional grid due to maximum requirement of their energy demand. Home energy management (HEM) benefit the end user by monitoring, managing and controlling their energy consumption. Appliance scheduling is integral part of HEM as it manages energy demand according to supply by automatically controlling the appliances or by shifting the load from peak to off peak hours. Recently different techniques based on artificial intelligence (AI) are used to meet these objectives. In this research work, we evaluate the performance of HEM which is designed on the basis of heuristic algorithms; wind driven optimization (WDO), ganetic algorithm (GA) and binary particle swarm optimisation (BPSO). Finally, simulations are conducted in MATLAB to validate the performance of scheduling techniques in terms of cost, reduced peak to average ratio (PAR) and equally distributed energy consumption pattern. The simulation results prove that WDO algorithm based HEM proves to perform efficiently than BPSO and GA.

To read the full-text of this research,

you can request a copy directly from the authors.

... At the HEMS level, GAs are used to find the optimal switching time of each appliances. In this case, a population's individual x i is constituted by a set of binary values (x i ¼ fx i1 ;x i2 ;…;x iJ g) stating if the corresponding appliance is on or off at the considered time j [136,137], as explained below. For retailers' or aggregators' price scheme optimisation, GA usually consider individuals that consist in a set of prices p i ¼ fp i1 ;p i2 ;…;p iJ g, with p ij the price for the j th period of the day [130,134,[138][139][140]. ...

... PSO is an iterative process, where a population (swarm) of particles is randomly determined during the first step of the iteration by choosing the x 0 ijp values randomly for each particle p (or x 0 ijp can be initialised using the result of the optimisation of a simplified problem using Mixed Integer Linear Programming [161]). In parallel with the choice of the swarm's particles initial position (x 0 ijp ), the aggregator determines the utility function he wants to minimise, which is often given by the cost: c ¼ P time j P assets i p j ⋅P i ⋅x ij in the case where x ij is a binary variable, but it could also be a multi-objective function that also integrates the Peak to Average Ratio [136,[157][158][159]. ...

... In Herath et al. [165] the CLONALG-based [168] Artificial Immune System (AIS) algorithm, derived from the processes found in biological immune systems [169], is used to determine the aggregators' pricing scheme. Developed on the annealing concept, 7 the simulated annealing method is employed for DR in Spinola et al. [86], and the Wind Driven Optimisation (WDO) algorithm [136], which is based on atmospheric motion, is used to determine an optimal scheduling of appliances at the household level. ...

Recent years have seen an increasing interest in Demand Response (DR) as a means to provide flexibility, and hence improve the reliability of energy systems in a cost-effective way. Yet, the high complexity of the tasks associated with DR, combined with their use of large-scale data and the frequent need for near real-time decisions, means that Artificial Intelligence (AI) and Machine Learning (ML) — a branch of AI — have recently emerged as key technologies for enabling demand-side response. AI methods can be used to tackle various challenges, ranging from selecting the optimal set of consumers to respond, learning their attributes and preferences, dynamic pricing, scheduling and control of devices, learning how to incentivise participants in the DR schemes and how to reward them in a fair and economically efficient way. This work provides an overview of AI methods utilised for DR applications, based on a systematic review of over 160 papers, 40 companies and commercial initiatives, and 21 large-scale projects. The papers are classified with regards to both the AI/ML algorithm(s) used and the application area in energy DR. Next, commercial initiatives are presented (including both start-ups and established companies) and large-scale innovation projects, where AI methods have been used for energy DR. The paper concludes with a discussion of advantages and potential limitations of reviewed AI techniques for different DR tasks, and outlines directions for future research in this fast-growing area.

... . O sistema de energia moderno incorporadoà rede inteligente gerencia a demanda de eletricidade selecionando as prioridades do usuário por meio da comunicação nos dois sentidos. Em Smart Grid, o uso extensivo de comunicação e automação tornam inteligentes tanto a rede de distribuição de energia quanto a Demand Side Management (DSM), que consiste nos usuários da energia elétrica realizar ações afim de equilibrar a demanda, principalmente em momentos de pico (Rehman et al., 2016). ...

... Segundo (Rehman et al., 2016), no cenário de Smart Home, as técnicas de otimização convencionais, por exemplo, programação linear (Yong e Choi, 2014), programação não linear (Yong e Choi, 2014), programação convexa (Richard e Pistikopoulos, 2016), são muito lentas em relaçãoà taxa de convergência e tornam-se muito demoradas quando o número de aparelhos faz parte da resposta da demanda, do inglês Demand Response (DR), tornando-as inviáveis para o uso diário. Contudo, técnicas modernas baseadas em heurística, como PSO (Particle Swarm Optimization), ACO (Ant Colony optimization) (Raka et al., 2016) e GA (Genetic Algorithm) (et al, 2013) superaram essas desvantagens. ...

This paper proposes a solution to the Smart Home Controller (SHC) Intelligent Load Controller model using the Particle Swarm Optimization (PSO) meta-heuristic technique. SHC has been modeled so that it can contemplate the energy cost, the comfort of the users or a combination of both. Conventional optimization techniques become very slow in relation to the convergence rate and when the number of devices is part of the demand response (DR), making them unviable for daily use. However, modern techniques based on heuristics have overcome these disadvantages. In this article we compare the results of the SHC solution with Linear Programming and PSO. Resumo-O presente artigo propõe uma solução do modelo de um controlador de cargas inteligente, Smart Home Controller (SHC), utilizando a técnica de meta-heurística PSO (Particle Swarm Optimization). O SHC foi modelado de forma qué e capaz de contemplar o custo energético, o conforto dos usuários ou uma combinação dos dois. Técnicas de otimização convencionais tornam-se muito lentas em relaçãò a taxa de convergência e quando o número de aparelhos faz parte da respostà a demanda (DR), tornando-as inviáveis para o uso diário. Contudo, técnicas modernas baseadas em heurística superaram essas desvantagens. Neste artigo são comparados os resultados da solução do SHC com Programação Linear e PSO. Palavras-chave-Smart Home, Eficiência Energética, Otimização, Conforto, Respostà a Demanda Tabela 1: Lista de Símbolos Símbolo Descrição M Número de cargas planejáveis ¯ P m Vetor da potência média da m-´ esima carga ˆ P m Vetor da potência de pico da m-´ esima carga N m Duração, em número de amostras, da m-´ esima carga I Sm Amostra no horário mínimo de início da m-´ esima carga I Em Amostra no horário máximo de término da m-´ esima carga S Amostra assoc. ao início do período de planejamento E Amostra assoc. ao término do período de planejamento u mi i-´ esima variável de decisão da m-´ esima carga P k Limite de pico no k − simo instante de tempo C Vetor do custo do consumo de energia elétrica no período 1 Introdução O consumo de energiá e um dos principais indi-cadores do desenvolvimento econômico e do ní-vel de qualidade de vida de uma sociedade. Esse indicador reflete o ritmo de atividade dos seto-res industrial, comercial e de serviços, bem como a capacidade da população de adquirir bens e serviços tecnologicamente mais avançados, como automóveis, eletrodomésticos e eletroeletrônicos (ANEEL, 2008). O sistema de energia moderno incorporadò a rede inteligente gerencia a demanda de eletrici-dade selecionando as prioridades do usuário por meio da comunicação nos dois sentidos. Em Smart Grid, o uso extensivo de comunicação e automação tornam inteligentes tanto a rede de distribuição de energia quanto a Demand Side Management (DSM), que consiste nos usuários da energia elé-trica realizar ações afim de equilibrar a demanda, principalmente em momentos de pico (Rehman et al., 2016). Considerando o aumento da eficiência do uso de energia elétrica e se utilizando dos conceitos de Smart Grids, pode-se pensar em um controlador de cargas integradò a rede inteligente de energia, que possa alocar as cargas dos clientes para mo-mentos de tarifa reduzida como uma estratégia de diminuição do consumo de energia elétrica nos mo

... Scheduling and control of loads constitute the second characteristic. Here, we note that significantly more algorithms are developed at the consumer level [63][64][65] than at the aggregator level [66,67], especially with the aim of reducing energy costs and energy consumption [24]. Another characteristic of data usage comprises the design of pricing or incentive schemes, which both affect the success of the DR scheme [68][69][70][71][72]. ...

The ongoing energy transition increases the share of renewable energy sources. To combat inherent intermittency of RES, increasing system flexibility forms a major opportunity. One way to provide flexibility is demand response (DR). Research already reflects several approaches of artificial intelligence (AI) for DR. However, these approaches often lack considerations concerning their applicability, i.e., necessary input data. To help putting these algorithms into practice, the objective of this paper is to analyze, how input data requirements of AI approaches in the field of DR can be systematized from a practice-oriented information systems perspective. Therefore, we develop a taxonomy consisting of eight dimensions encompassing 30 characteristics. Our taxonomy contributes to research by illustrating how future AI approaches in the field of DR should represent their input data requirements. For practitioners, our developed taxonomy adds value as a structuring tool, e.g., to verify applicability with respect to input data requirements. 1 Introduction Due to the expansion of renewable energy sources (RES) and their inherent variability, ensuring security of supply and grid stability are becoming increasingly challenging [1]. A successful energy transition towards growing shares of RES largely depends on increasing energy system's flexibility [2-4]. To achieve this, demand needs to be adapted to generation, instead of the other way around. In order to actually provide and foster energy system flexibility, research develops and reflects several approaches of Artificial Intelligence (AI) algorithms for Demand Response (DR) to enable flexibility

... The implementation results using PSO confirm a performance enhancement with a better energy efficiency along with the flexible adjustment of mixing energy rate. The use of SI for energy management is also investigated in [201]. Here, a binary PSO algorithm is developed to implement the home energy management scheduling by following the energy consumption patterns of customers in a fashion the total power cost is minimized while satisfying user comfort. ...

In next-generation networks (NGN), a very large number of devices and applications are emerged, along with the heterogeneity of technologies, architectures, mobile data, etc., and optimizing such a network is of utmost importance. Besides convex optimization and game theory, swarm intelligence (SI) has recently appeared as a promising optimization tool for wireless networks. As a new subdivision of artificial intelligence, SI is inspired by the collective behaviors of societies of biological species. In SI, simple agents with limited capabilities can achieve intelligent strategies for high-dimensional and challenging problems, and thus SI has recently found many applications in NGN. However, SI techniques have still not fully investigated in the literature, especially in the contexts of wireless networks. In this work, our primary focus will be the integration of these two domains, i.e., NGN and SI. Firstly, we provide an overview of SI techniques from fundamental concepts to well-known optimizers. Secondly, we review the applications of SI to settle emerging issues in NGN, including spectrum management and resource allocation, wireless caching and edge computing, network security, and several other miscellaneous issues. Finally, we highlight challenges and issues in the literature, and introduce some interesting directions for future research.

... The implementation results using PSO confirm a performance enhancement with a better energy efficiency along with the flexible adjustment of mixing energy rate. The use of SI for energy management is also investigated in [201]. Here, a binary PSO algorithm is developed to implement the home energy management scheduling by following the energy consumption patterns of customers in a fashion the total power cost is minimized while satisfying user comfort. ...

Due to the proliferation of smart devices and emerging applications, many next-generation technologies have been paid for the development of wireless networks. Even though commercial 5G has just been widely deployed in some countries, there have been initial efforts from academia and industrial communities for 6G systems. In such a network, a very large number of devices and applications are emerged, along with heterogeneity of technologies, architectures, mobile data, etc., and optimizing such a network is of utmost importance. Besides convex optimization and game theory, swarm intelligence (SI) has recently appeared as a promising optimization tool for wireless networks. As a new subdivision of artificial intelligence, SI is inspired by the collective behaviors of societies of biological species. In SI, simple agents with limited capabilities would achieve intelligent strategies for high-dimensional and challenging problems, so it has recently found many applications in next-generation wireless networks (NGN). However, researchers may not be completely aware of the full potential of SI techniques. In this work, our primary focus will be the integration of these two domains: NGN and SI. Firstly, we provide an overview of SI techniques from fundamental concepts to well-known optimizers. Secondly, we review the applications of SI to settle emerging issues in NGN, including spectrum management and resource allocation, wireless caching and edge computing, network security, and several other miscellaneous issues. Finally, we highlight open challenges and issues in the literature, and introduce some interesting directions for future research.

... For example, AI systems and the IoT combined with 'smart' capabilities, such as domestic energy management to automatically control appliances (e.g. Rehman et al., 2016) and big data analysis, could enable energy systems to transition from supplying energy to matching demand, reinforcing the growing demand for electrical energy (see Cluster 3). According to some authors, these technologies could lead to progress in the development of smart grids and more efficient networks, supporting the uptake of renewables and enhancing efficiency, resulting in a continuous joint optimisation of demand and supply in all walks of life (e.g. ...

This report, building on the experience of both the EEA and Eionet, presents a synthesis of global and European megatrends with illustrations of key emerging trends, wild cards and uncertainties. It aims to inform about on‑going, emerging and potential future developments, raise awareness and contribute to the diffusion of anticipatory thinking.

... A PSO is a swarm intelligence algorithm that is frequently implemented for the optimal scheduling of the HEMS [25]. Rehman et al. developed a binary PSO (BPSO) algorithm in Rehman et al. [26]. Their proposed algorithm automatically controlled the appliance scheduling by shifting the consumers' load from a high-pricing time to a low-pricing time. ...

The transformation of a conventional power system to a smart grid has been underway over the last few decades. A smart grid provides opportunities to integrate smart homes with renewable energy resources (RERs). Moreover, it encourages the residential consumers to regulate their home energy consumption in an effective way that suits their lifestyle and it also helps to preserve the environment. Keeping in mind the techno-economic reasons for household energy management, active participation of consumers in grid operations is necessary for peak reduction, valley filling, strategic load conservation, and growth. In this context, this paper presents an efficient home energy management system (HEMS) for consumer appliance scheduling in the presence of an energy storage system and photovoltaic generation with the intention to reduce the energy consumption cost determined by the service provider. To study the benefits of a home-to-grid (H2G) energy exchange in HEMS, photovoltaic generation is stochastically modelled by considering an energy storage system. The prime consideration of this paper is to propose a hybrid optimization approach based on heuristic techniques, grey wolf optimization, and a genetic algorithm termed a hybrid grey wolf genetic algorithm to model HEMS for residential consumers with the objectives to reduce energy consumption cost and the peak-to-average ratio. The effectiveness of the proposed scheme is validated through simulations performed for a residential consumer with several domestic appliances and their scheduling preferences by considering real-time pricing and critical peak-pricing tariff signals. Results related to the reduction in the peak-to-average ratio and energy cost demonstrate that the proposed hybrid optimization technique performs well in comparison with different meta-heuristic techniques available in the literature. The findings of the proposed methodology can further be used to calculate the impact of different demand response signals on the operation and reliability of a power system.

... To solve these issues they worked on a performance of following metrics: reduced cost, PAR and energy consumption by using TOU. Different heuristic algorithms WDO, BPSO and GA are used by [10], to evaluate the results for this purpose. It is proved that GA algorithm outperforms by achieving objectives as compared to other heuristic algorithms. ...

In this paper, we present a Home Energy Management System (HEMS) using two meta-heuristic optimization techniques: Bacterial Foraging Optimization Algorithm (BFOA) and Bat Algorithm (BA). HEMS will provide different services to end user to manage and control their energy usage with time of use. The proposed model used for load scheduling between peak hour and off-peak hour. In this regard, we perform appliances scheduling to manage the frequent demand from the consumer. The aim of the proposed scheduling is to minimize peak to average ratio and the cost while having some trade-off in user comfort to achieve an optimal management of load. Simulation results show that the BA outperform than BFOA in selected performance parameters.

In this paper, we present a Home Energy Management System (HEMS) using two meta-heuristic optimization techniques: Bacterial Foraging Optimization Algorithm (BFOA) and Bat Algorithm (BA). HEMS will provide different services to end user to manage and control their energy usage with time of use. The proposed model used for load scheduling between peak hour and off-peak hour. In this regard, we perform appliances scheduling to manage the frequent demand from the consumer. The aim of the proposed scheduling is to minimize peak to average ratio and the cost while having some trade-off in user comfort to achieve an optimal management of load. Simulation results show that the BA outperform than BFOA in selected performance parameters.

This paper proposes a new strategy to meet the controllable heating, ventilation, and air conditioning (HVAC) load with a hybrid-renewable generation and energy storage system. Historical hourly wind speed, solar irradiance, and load data are used to stochastically model the wind generation, photovoltaic generation, and load. Using fuzzy C-Means (FCM) clustering, these data are grouped into 10 clusters of days with similar data points to account for seasonal variations. In order to minimize cost and increase efficiency, we use a GA-based optimization approach together with a two-point estimate method. Minimizing the cost function guarantees minimum PV and wind generation installation as well as storage capacity selection to supply the HVAC load. Different scenarios are examined to evaluate the efficiency of the system with different percentages of load shifting. The maximum capacity of the storage system and excess energy are calculated as the most important indices for energy efficiency assessment. The cumulative distribution functions of these indices are plotted and compared. A smart-grid strategy is developed for matching renewable energy generation (solar and wind) with the HVAC load.

In recent years the use of several new resources in power systems, such as distributed generation, demand response and more recently electric vehicles, has significantly increased. Power systems aim at lowering operational costs, requiring an adequate energy resources management. In this context, load consumption management plays an important role, being necessary to use optimization strategies to adjust the consumption to the supply profile. These optimization strategies can be integrated in demand response programs. The control of the energy consumption of an intelligent house has the objective of optimizing the load consumption. This paper presents a genetic algorithm approach to manage the consumption of a residential house making use of a SCADA system developed by the authors. Consumption management is done reducing or curtailing loads to keep the power consumption in, or below, a specified energy consumption limit. This limit is determined according to the consumer strategy and taking into account the renewable based micro generation, energy price, supplier solicitations, and consumers' preferences. The proposed approach is compared with a mixed integer non-linear approach.

Differential evolution (DE) is an efficient and powerful population-based stochastic search technique for solving optimization problems over continuous space, which has been widely applied in many scientific and engineering fields. However, the success of DE in solving a specific problem crucially depends on appropriately choosing trial vector generation strategies and their associated control parameter values. Employing a trial-and-error scheme to search for the most suitable strategy and its associated parameter settings requires high computational costs. Moreover, at different stages of evolution, different strategies coupled with different parameter settings may be required in order to achieve the best performance. In this paper, we propose a self-adaptive DE (SaDE) algorithm, in which both trial vector generation strategies and their associated control parameter values are gradually self-adapted by learning from their previous experiences in generating promising solutions. Consequently, a more suitable generation strategy along with its parameter settings can be determined adaptively to match different phases of the search process/evolution. The performance of the SaDE algorithm is extensively evaluated (using codes available from P. N. Suganthan) on a suite of 26 bound-constrained numerical optimization problems and compares favorably with the conventional DE and several state-of-the-art parameter adaptive DE variants.

Many areas in power systems require solving one or more nonlinear optimization problems. While analytical methods might suffer from slow convergence and the curse of dimensionality, heuristics-based swarm intelligence can be an efficient alternative. Particle swarm optimization (PSO), part of the swarm intelligence family, is known to effectively solve large-scale nonlinear optimization problems. This paper presents a detailed overview of the basic concepts of PSO and its variants. Also, it provides a comprehensive survey on the power system applications that have benefited from the powerful nature of PSO as an optimization technique. For each application, technical details that are required for applying PSO, such as its type, particle formulation (solution representation), and the most efficient fitness functions are also discussed.

In this note we present an approximate algorithm for the explicit calculation of the Pareto front for multi-objective optimization problems featuring convex quadratic cost functions and linear constraints based on multi-parametric programming and employing a set of suitable overestimators with tunable suboptimality. A numerical example as well as a small computational study highlight the features of the novel algorithm.

In this paper we propose novel and more realistic analytical models for the determination of the peak demand under four power demand control scenarios. Each scenario considers a finite number of appliances installed in a residential area, with diverse power demands and different arrival rates of power requests. We develop recursive formulas for the efficient calculation of the peak demand under each scenario, which take into account the finite population of the appliances. Moreover, we associate each scenario with a proper real-time pricing process in order to derive the social welfare. The proposed analysis is validated through simulations. Moreover, the performance evaluation of the proposed formulas reveals that the absence of the assumption of finite number of appliances could lead to serious peak-demand over-estimations.

In this paper, we utilize the GA method to optimize the start time units of all the OAAs to achieve our objectives. Since the start time unit is the only variable in our scheme and the constraint parameters are set in the beginning, we assume that the total fitness function is (14). In the selection process, we adopt a roulette selection method in which the individual with a better fitness value has a higher probability to be selected for further processing. In general, the time complexity of the GA process can be represented as O(generation number*(mutation complexity + crossover complexity + selection complexity)). Assume the maximal generation number, the size of the population, and the number of individuals are denoted by g, N, and na, respectively; therefore, the time complexity of our scheme is O(gNna). In this case, the time cost increases as the three parameters become larger, and, usually, the time cost of GA optimization does not satisfy people. However, in our approach, the power scheduling process is implemented at the beginning of the day; therefore, after time parameters are determined, there is enough time for power scheduling, and the algorithm running time problem is not so important. We think a time cost of a few seconds is acceptable. In this paper, the population size is 200; the probability of crossover and the probability of mutation are 90% and 2%, respectively. Finally, when the generation number reaches 1,000, the evolution process will finish.
Generally speaking, the relationship between electricity cost and DTRave is a tradeoff. In other words, as the value of DTRave increases, electricity cost decreases. However, the minimum electricity cost value would emerge at a position at which the DTRave value is about 50%, which is not definite, due to the random POE. From the result shown in Fig. 6, at the position that DTRave equals 0, it implies that the major consideration is minimizing the delay time; thus, in this case, ω1=0, ω2=1. However, when the minimum electricity cost is reached, ω1=1, ω2=0.

In this paper we focus on finding high quality solutions for the problem of
maximum partitioning of graphs with supply and demand (MPGSD). There is a
growing interest for the MPGSD due to its close connection to problems
appearing in the field of electrical distribution systems, especially for the
optimization of self-adequacy of interconnected microgrids. We propose an ant
colony optimization algorithm for the problem. With the goal of further
improving the algorithm we combine it with a previously developed correction
procedure. In our computational experiments we evaluate the performance of the
proposed algorithm on both trees and general graphs. The tests show that the
method manages to find optimal solutions in more than 50% of the problem
instances, and has an average relative error of less than 0.5% when compared to
known optimal solutions.

Due to the emerging of smart grid, residential consumers have the opportunity to reduce their electricity cost (EC) and peak-to-average ratio (PAR) through scheduling their power consumption. On the other hand, it is obviously impossible to integrate a large scale of renewable energy sources (RES) without extensive participation of the demand side. We are looking for a way to provide the system operators with the capability of increasing the penetration of RES besides maintaining the reliability of the power grid via load management and flexibility in the demand side. The primary aim is to provide consumers with a simple smart controller which can result in EC and PAR reduction with respect to consumer preferences and convenience level. In this paper, first we present a novel architecture of home EMS and automated DR framework for scheduling of various household appliances in a smart home, and then propose a genetic algorithm (GA) based approach to solve this optimization problem. The real-time price (RTP) model in spite of its privileges has the tendency to accumulate a lot of loads at a pretty low electricity price time. Therefore, in this paper we use the combination of RTP with the inclining block rate (IBR) model which has the capability to remarkably decrease the PAR and eliminate rebound peak during low price periods. We present three different case studies with diverse power consumption patterns to evaluate the performance of our approach. The simulation results demonstrate the terrific impact of this method for any household load shape.

We propose a method about power consumption scheduling for shaving peak load at home area using linear programming technique. Problems caused by peak load such as blackout and rolling blackout has occurred recently in the world because hourly peak load consumption is increased rapidly in the same time. So to solve these problems is using ESS. Especially, the most effective method is to utilize ESS and V2G. Electricity of the battery of parked PHEV at home area transmits through V2G to the ESS. The stored electricity in the ESS is optimized by using linear programming. This optimization reduces the hourly peak load consumption.

The Differential Evolution (DE) algorithm, introduced by Storn and Price in 1995, has become one of the most efficacious population-based optimization approaches. In this algorithm, use is made of the significant concepts of mutation, crossover, and selection. The tuning control parameters are population size, mutation scaling factor, and crossover rate. Over the last decade, several variants of DE have been presented to improve its performance aspects. In the present paper, we further enhance DE. The population size and mutation scaling factor are taken alone in the tuning process; the crossover rate is treated implicitly in the crossover stage. Five forms for crossover are suggested for the first 100 iterations of the computational algorithm. After this learning period, we pick the form which yields the best value of the objective function in the greatest number of iterations (among the 100). Our algorithm is tested on a total of 47 benchmark functions: 27 traditional functions and 20 special functions chosen from CEC2005 and CEC2013. The results are assessed in terms of the mean and standard deviation of the error, success rate, and average number of function evaluations over successful runs. Convergence characteristics are also investigated. Comparison is made with the original DE and Success-History based Adaptive DE (SHADE) as a state-of-the-art DE algorithm, and the results demonstrate the superiority of the proposed approach for the majority of the functions considered.

Demand Response (DR) and Time-of-Use (TOU) pricing refer to programs which offer incentives to customers who curtail their energy use during times of peak demand. In this paper, we propose an integrated solution to predict and re-engineer the electricity demand (e.g., peak load reduction and shift) in a locality at a given day/time. The system presented in this paper expands DR to residential loads by dynamically scheduling and controlling appliances in each dwelling unit. A decision-support system is developed to forecast electricity demand in the home and enable the user to save energy by recommending optimal run time schedules for appliances, given user constraints and TOU pricing from the utility company. The schedule is communicated to the smart appliances over a self-organizing home energy network and executed by the appliance control interfaces developed in this study. A predictor is developed to predict, based on the user's life style and other social/environmental factors, the potential schedules for appliance run times. An aggregator is used to accumulate predicted demand from residential customers.

With the development of smart grid, residents have the opportunity to schedule their power usage in the home by themselves for the purpose of reducing electricity expense and alleviating the power peak-to-average ratio (PAR). In this paper, we first introduce a general architecture of energy management system (EMS) in a home area network (HAN) based on the smart grid and then propose an efficient scheduling method for home power usage. The home gateway (HG) receives the demand response (DR) information indicating the real-time electricity price that is transferred to an energy management controller (EMC). With the DR, the EMC achieves an optimal power scheduling scheme that can be delivered to each electric appliance by the HG. Accordingly, all appliances in the home operate automatically in the most cost-effective way. When only the real-time pricing (RTP) model is adopted, there is the possibility that most appliances would operate during the time with the lowest electricity price, and this may damage the entire electricity system due to the high PAR. In our research, we combine RTP with the inclining block rate (IBR) model. By adopting this combined pricing model, our proposed power scheduling method would effectively reduce both the electricity cost and PAR, thereby, strengthening the stability of the entire electricity system. Because these kinds of optimization problems are usually nonlinear, we use a genetic algorithm to solve this problem.

Demand response (DR) is very important in the future smart grid, aiming to encourage consumers to reduce their demand during peak load hours. However, if binary decision variables are needed to specify start-up time of a particular appliance, the resulting mixed integer combinatorial problem is in general difficult to solve. In this paper, we study a versatile convex programming (CP) DR optimization framework for the automatic load management of various household appliances in a smart home. In particular, an L1 regularization technique is proposed to deal with schedule-based appliances (SAs), for which their on/off statuses are governed by binary decision variables. By relaxing these variables from integer to continuous values, the problem is reformulated as a new CP problem with an additional L1 regularization term in the objective. This allows us to transform the original mixed integer problem into a standard CP problem. Its major advantage is that the overall DR optimization problem remains to be convex and therefore the solution can be found efficiently. Moreover, a wide variety of appliances with different characteristics can be flexibly incorporated. Simulation result shows that the energy scheduling of SAs and other appliances can be determined simultaneously using the proposed CP formulation.

Demand response (DR) for residential and small commercial buildings is
estimated to account for as much as 65% of the total energy savings potential
of DR, and previous work shows that a fully automated Energy Management System
(EMS) is a necessary prerequisite to DR in these areas. In this paper, we
propose a novel EMS formulation for DR problems in these sectors. Specifically,
we formulate a fully automated EMS's rescheduling problem as a reinforcement
learning (RL) problem (referred to as the device based RL problem), and show
that this RL problem decomposes over devices under reasonable assumptions.
Compared with existing formulations, our new formulation (1) does not require
explicitly modeling the user's dissatisfaction on job rescheduling, (2) enables
the EMS to self-initiate jobs, (3) allows the user to initiate more flexible
requests and (4) has a computational complexity linear in the number of
devices. We also propose several new performance metrics for RL algorithms
applied to the device based RL problem, and demonstrate the simulation results
of applying Q-learning, one of the most popular and classical RL algorithms, to
a representative example.

Various forms of demand side management (DSM) programs are being deployed by utility companies for load flattening amongst the residential power users. These programs are tailored to offer monetary incentives to electricity customers so that they voluntarily consume electricity in an efficient way. Thus, DSM presents households with numerous opportunities to lower their electricity bills. However, systems that combine the various DSM strategies with a view to maximizing energy management benefits have not received sufficient attention. This study therefore proposes an intelligent energy management framework that can be used to implement both energy storage and appliance scheduling schemes. By adopting appliance scheduling, customers can realize cost savings by appropriately scheduling their power consumption during the low peak hours. More savings could further be achieved through smart electricity storage. Power storage allows electricity consumers to purchase power during off-peak hours when electricity prices are low and satisfy their demands when prices are high by discharging the batteries. For optimal cost savings, the customers must constantly monitor the price fluctuations in order to determine when to switch between the utility grid and the electricity storage devices. However, with a high penetration of consumer owned storage devices, the charging of the batteries must be properly coordinated and appropriately scheduled to avoid creating new peaks. This paper therefore proposes an autonomous smart charging framework that ensures both the stability of the power grid and customer savings.

This paper introduces optimized operation of household appliances in a Demand-Side Management (DSM) based simulation tool. DSM can be defined as the implementation of policies and measures to control, regulate, and reduce energy consumption. The principal purpose of the simulation tool is to illustrate customer-driven DSM operation, and evaluate an estimate for home electricity consumption while minimizing the customer's cost. An optimization algorithm i.e. Binary Particle Swarm Optimization (BPSO) is used for optimizing the DSM operation of the tool. The tool also simulates the operation of household appliances as a Hybrid Renewable Energy System (HRES). The resource management technique is implemented using an optimization algorithm, i.e. Particle Swarm Optimization (PSO), which determines the distribution of energy obtained from various sources depending on the load. The validity of the tool is illustrated through an example case study for various household situations.

Particle Swarm Optimization (PSO) is a relatively recent heuristic search method whose mechanics are inspired by the swarming or collaborative behavior of biological populations. PSO is similar to the Genetic Algorithm (GA) in the sense that these two evolutionary heuristics are population-based search methods. In other words, PSO and the GA move from a set of points (population) to another set of points in a single iteration with likely improvement using a combination of deterministic and probabilistic rules. The GA and its many versions have been popular in academia and the industry mainly because of its intuitiveness, ease of implementation, and the ability to effectively solve highly nonlinear, mixed integer optimization problems that are typical of complex engineering systems. The drawback of the GA is its expensive computational cost. This paper attempts to examine the claim that PSO has the same effectiveness (finding the true global optimal solution) as the GA but with significantly better computational efficiency (less function evaluations) by implementing statistical analysis and formal hypothesis testing. The performance comparison of the GA and PSO is implemented using a set of benchmark test problems as well as two space systems design optimization problems, namely, telescope array configuration and spacecraft reliability-based design.

In this paper, we consider a smart power infrastructure, where several subscribers share a common energy source. Each subscriber is equipped with an energy consumption controller (ECC) unit as part of its smart meter. Each smart meter is connected to not only the power grid but also a communication infrastructure such as a local area network. This allows two-way communication among smart meters. Considering the importance of energy pricing as an essential tool to develop efficient demand side management strategies, we propose a novel real-time pricing algorithm for the future smart grid. We focus on the interactions between the smart meters and the energy provider through the exchange of control messages which contain subscribers' energy consumption and the real-time price information. First, we analytically model the subscribers' preferences and their energy consumption patterns in form of carefully selected utility functions based on concepts from microeconomics. Second, we propose a distributed algorithm which automatically manages the interactions among the ECC units at the smart meters and the energy provider. The algorithm finds the optimal energy consumption levels for each subscriber to maximize the aggregate utility of all subscribers in the system in a fair and efficient fashion. Finally, we show that the energy provider can encourage some desirable consumption patterns among the subscribers by means of the proposed real-time pricing interactions. Simulation results confirm that the proposed distributed algorithm can potentially benefit both subscribers and the energy provider.

This paper introduces a novel nature-inspired global optimization technique, which we call Wind Driven Optimization. WDO is a population based iterative global optimization method, where the velocity and the position of wind controlled air parcels are updated based on the physical equations that govern atmospheric motion. The effectiveness of WDO as a tool in optimization problems is first shown with its performance on benchmark functions and then with its application to optimizing the design for a thin double-sided AMC surface at 10 GHz.

In recent years, load management (LM) programs are introduced as an impressive option in all energy policy decisions. Under deregulation, the scope of LM programs has considerably been expanded to include demand response programs (DRPs). Basically, DRPs are divided into two main categories namely, incentive-based programs (IBPs) and time-based rate (TBR) programs. In this paper, an economic model of responsive loads is derived based upon price elasticity of demand and customers' benefit function. In order to investigate the economic-driven and environmental-driven measures of demand response programs, a new linearized formulation of cost-emission based unit commitment problem associated with DRPs (UCDR) is presented. Here, UCDR is modeled as a mixed-integer programming (MIP) problem. The proposed model is applied to determine loads provided by DRPs and schedule commitment status of generating units. Moreover, the optimum value of incentive as a crucial issue for implementing DRPs is derived. Several analyses are conducted to investigate the impact of some important factors such as elasticity on the UCDR problem. The strategy success index (SSI) is employed to prioritize DRPs from the independent system operator (ISO) perspective. The conventional 10-unit test system is used to demonstrate effectiveness of the proposed methodology.

Demand side management (DSM) is one of the important functions in a smart grid that allows customers to make informed decisions regarding their energy consumption, and helps the energy providers reduce the peak load demand and reshape the load profile. This results in increased sustainability of the smart grid, as well as reduced overall operational cost and carbon emission levels. Most of the existing demand side management strategies used in traditional energy management systems employ system specific techniques and algorithms. In addition, the existing strategies handle only a limited number of controllable loads of limited types. This paper presents a demand side management strategy based on load shifting technique for demand side management of future smart grids with a large number of devices of several types. The day-ahead load shifting technique proposed in this paper is mathematically formulated as a minimization problem. A heuristic-based Evolutionary Algorithm (EA) that easily adapts heuristics in the problem was developed for solving this minimization problem. Simulations were carried out on a smart grid which contains a variety of loads in three service areas, one with residential customers, another with commercial customers, and the third one with industrial customers. The simulation results show that the proposed demand side management strategy achieves substantial savings, while reducing the peak load demand of the smart grid.

In this paper we present particle swarm optimization with Gaussian mutation combining the idea of the particle swarm with concepts from evolutionary algorithms. This method combines the traditional velocity and position update rules with the ideas of Gaussian mutation. This model is tested and compared with the standard PSO and standard GA. The comparative experiments have been conducted on unimodal functions and multimodal functions. PSO with Gaussian mutation is able to obtain a result superior to GA. We also apply the PSO with Gaussian mutation to a gene network. Consequently, it has succeeded in acquiring better results than those by GA and PSO alone.

Differential evolution (DE) has emerged as one of the fast, robust, and efficient global search heuristics of current interest. This paper describes an application of DE to the automatic clustering of large unlabeled data sets. In contrast to most of the existing clustering techniques, the proposed algorithm requires no prior knowledge of the data to be classified. Rather, it determines the optimal number of partitions of the data "on the run." Superiority of the new method is demonstrated by comparing it with two recently developed partitional clustering techniques and one popular hierarchical clustering algorithm. The partitional clustering algorithms are based on two powerful well-known optimization algorithms, namely the genetic algorithm and the particle swarm optimization. An interesting real-world application of the proposed method to automatic segmentation of images is also reported.

Genetic-algorithm-based optimization approach for energy management

- Arabali Amirsaman

Genetic algorithm methodology applied to intelligent house control

- Filipe Fernandes

Fernandes, Filipe, et al. "Genetic algorithm methodology applied
to intelligent house control." Computational Intelligence Applications In Smart Grid (CIASG), 2011 IEEE Symposium on. IEEE,
2011.

Particle swarm optimization: basic concepts, variants and applications in power systems

- Del Valle
- Yamille

Del Valle, Yamille, et al. "Particle swarm optimization: basic concepts, variants and applications in power systems." Evolutionary
Computation, IEEE Transactions on 12.2 (2008): 171-195.

Digital Information and Communication Technology and it's Applications (DICTAP)

- M Arafa
- A Elsayed
- M M Sallam
- Fahmy

Arafa, M., Elsayed A. Sallam, and M. M. Fahmy. "An enhanced
differential evolution optimization algorithm." Digital Information
and Communication Technology and it's Applications (DICTAP),
2014 Fourth International Conference on. IEEE, 2014.

Wind Driven Optimization (WDO): A novel nature-inspired optimization algorithm and its application to electromagnetics

- Zikri Bayraktar
- Muge Komurcu
- Douglas H Werner

Bayraktar, Zikri, Muge Komurcu, and Douglas H. Werner. "Wind
Driven Optimization (WDO): A novel nature-inspired optimization algorithm and its application to electromagnetics." Antennas
and Propagation Society International Symposium (APSURSI),
2010 IEEE. IEEE, 2010.

Proceedings of the 1st AIAA multidisciplinary design optimization specialist conference

- Rania Hassan

Hassan, Rania, et al. "A comparison of particle swarm optimization and the genetic algorithm." Proceedings of the 1st AIAA
multidisciplinary design optimization specialist conference. 2005.

Demand response simulation implementing heuristic optimization for home energy management

- Nikhil Gudi

Gudi, Nikhil, et al. "Demand response simulation implementing
heuristic optimization for home energy management." North
American Power Symposium (NAPS), 2010. IEEE, 2010.