Назад в библиотеку

Optimization Techniques for Home Energy Management: A Review

Author: N. Qayyum, A. Amin, U. Jamil, A. Mahmood
Source: Proc. 2nd Int. Conf.Comput., Math. Eng. Technol. (iCoMET), Jan. 2019, pp. 1–7.

Abstract

Smart Gird is a technology that has brought many advantages with its evolution. Smart Grid is indispensable as it will lead us towards environmentally sustainable economic growth. Home energy management in Smart Grid is a hot research topic now a days. It aims at reducing the energy cost of users, gaining energy self–reliance and decreasing Greenhouse gas emissions. Renewable energy technologies nowadays are best suitable for off grid services without having to build extensive and complicated infrastructure. With the advent of Smart Grid (SG), the occupants have the opportunity to integrate with renewable energy sources (RESs) and to actively take part in demand side Management (DSM). This review paper is comprehensive study of various optimization techniques and their implementation with respect to electricity cost diminution, load balancing, power consumption and user's comfort maximization etc. for Home Energy Management in Smart Grid. This paper summarizes recent trends of energy usage from hybrid renewable energy integrated sources. It discusses several methodologies and techniques for hybrid renewable energy system optimization.

Keyword

Home Energy Management System, Smart Grid, Demand Side Management, Optimization

I. INTRODUCTION

The present electrical grid system is getting weaker, as the appliances are getting more delicate to the change in electrical power. Reliability will be affected, until something useful can't be done. Smart Grid is a self–sufficient system, which permits integration of any kind of generation sources to the grid which results in reliable, feasible, intact and quality electrical power to the end users [1]. In the development of Smart Grid, Demand Side Management (DSM) has been considered as a key feature to maintain the system’s security and to balance electricity demand at user's end and to maintain comfort level of both the customer and utility by using advanced power and communication technologies. DSM includes residential, commercial and industrial energy management. Implementation of DSM ensures a dynamic energy management for residential domain by permitting consumers to initiate early informed decisions concerning their energy utilization, which facilitates the utility providers to scale down the peak load demand and remodel the load curve, rather than constructing new generation and transmission units [2] Among the variety of applications of smart grid, the most significant one to be addressed is Home Energy Management System (HEMS). It is a technology platform that comprises of both hardware and software that permits the consumer to monitor energy usage and generation and to manually control and automate the usage of energy within a house. HEM system is a fundamental part of a Smart Grid which can potentially facilitate demand response applications for residential consumers [3] A big part of world’s power is consumed by residential sector. So by optimizing power at household level, we can increase benefit of both the consumer and the supplier. Optimization means the best possible optimal solution or value of some set of problems and objective functions. With the advancement in computer software and hardware technologies, optimization of power has become an important topic of research for energy efficiency. Smart grid has capability to manage load by using optimization techniques. In mathematical and computing optimization problem, function either has to be minimized or maximized. Many problems of daily life can be solved in optimization framework. Optimization of power is done by different methods and techniques [39]. These methods are implemented to minimize consumption price by using proper algorithms. Appliances scheduling, Load Forecasting (LF) and dynamic pricing are demand response approaches for getting better optimal solution in multi objectives. These multi objectives include cost minimization, PAR reduction, reduce peak load and attaining comfort for user as summarized in Fig. 1.

Various Objective Functions used for HEM

Fig.1. Various Objective Functions used for HEM

Classification of Optimization Techniques used in HEM

Fig.2. Classification of Optimization Techniques used in HEM

Variety of optimization techniques have been implemented for HEMS within the past few years. The purpose of optimization techniques is to achieve the best result relative to a set of prioritized constraints. These techniques include: Genetic Algorithm (GA), Enhanced Differential Evolution (EDE) algorithm, Knapsack Algorithm, Ant Colony Optimization (ACO), Bacteria Foraging Algorithm (BFA), Grey Wolf Optimization (GWO), Particle Swarm Optimization (PSO), Gravitational Search Algorithm (GSA), and Harmony Search Algorithm (HSA) etc. These intelligent techniques are capable of solving optimization problems and can find the optimal solution from different points. Fig. 2 shows the classification of optimization techniques used in HEMS.

In this article, various papers regarding hybrid renewable energy systems and DSM are studied thoroughly and a short review has been done regarding those papers. The entire paper discusses different aspects regarding hybrid renewable systems and their respective conclusions.

II. ROLE OF OPTIMIZATION IN HOME ENERGY MANAGEMENT

Demand Side Management (DSM) plays a vital role in the dependability and operational efficiency of Smart Grid. So, for DSM in Smart Grid, various optimization approaches are used which are helpful in solving scheduling and optimization activities. Optimization includes the integration of stored energy with renewable energy sources and generated energy, to decrease the reliability on conventional energy. The role of optimization in Smart Grid is to make power grid as favorable as possible. Several optimization algorithms have been employed in electrical power system. Many renowned optimization problems include feeder configuration, voltage control problem and unit commitment problem. Smart grid optimization is based on real–time information in view of the accessibility of Advanced Metering Infrastructure (AMI) and two–way communication. In general, optimization is implemented from generation of electricity through end usage. Optimization improves the employment of present infrastructure and defers expenses in new generation, transmission and distribution facilities. Moreover, it reduces the global cost of conveying power to end users hence making the perfect balance between dependability, availability, efficiency and cost. Moreover, to enhance the performance abilities of Smart Grid and to gain the desired objectives, it is mandatory to go through different optimization techniques and to study in detail that how they meet the desired objectives. Various optimization approaches have been proposed by numerous authors for Home Energy Management System (HEMS). This section presents the benefits and limitations of their work.

A. Knapsack

Knapsack means sack of a specific capacity filled by items with some weight and value. Knapsack is a combinatorial optimization problem in which we have to increase total value of items without increasing its weight within limited capacity of Knapsack. Many practical examples in which Knapsack problem is used i.e. shipment loading, capital budget analysis, project scheduling and home appliances scheduling. Many authors used knapsack algorithm for scheduling and optimization. A summary of their work is presented below:

A method for residential energy scheduling of appliances under dynamic pricing scheme is presented in [1] to minimize the electricity bill of customers. Knapsack Algorithm is used which permits economical and productive solution to the scheduling problems. Experimental results proved that the proposed methodology is effectual in bringing regularity in user’s energy outline. A dynamic energy allocation problem is solved in a simple way in [2] by the help of knapsack algorithm. Theoretical results determined that the presented methodology is practicable and it results in remarkable energy savings. A multiple knapsack problem is presented in [3] to model the issue of virtual machine allotment in cloud computing along with the minimization of power consumption of infrastructure. Simulation results show the efficacy of the presented approach. A knapsack approach is presented in [4] for Home Energy Management in Smart Grid. Ant Colony Optimization (ACO) is used to determine multiple knapsack problem. Results show that the presented technique is effective for Home Energy Management to minimize the cost of electricity and to enhance user’s satisfaction. A novel home energy management model is presented in [5] with multiple scheduling options and improved load categorization. Knapsack and Particle Swarm Optimization (PSO) are implemented to solve the problem of energy cost minimization. Simulation results show the efficacy of the presented model. A comparative study of various algorithms is presented in [6] with respect to time, memory and programing efforts. Experimental values show that the most favorable algorithms are Dynamic programming and Genetic algorithm. An efficient load management for Home energy management system is presented in [7]. The scheduling of home appliances is done by the help of knapsack. By comparing the results of scheduled and non–scheduled curves, a clear difference in the cost is observed. A multi criteria knapsack solution is proposed in [8] to determine the portfolio of a project in order to gain maximum benefit while considering the budget. A multi criteria study analysis tool has been employed to facilitate the application of applied technique. A mathematical optimization model, to optimally regulate the home appliances is proposed in [9] meanwhile maintaining the user’s comfort. Min–max regret knapsack approach is employed to minimize the electricity cost by optimally scheduling the appliances. A comprehensive home energy management architecture (CHMA) is presented in [10] with the inclusion of multiple load scheduling options in a smart grid. A single knapsack optimization algorithm is employed for the scheduling of appliances. An energy optimization technique for appliances scheduling in real time, is presented in [11] to optimally maintain the energy consumption of appliances to lessen the electricity consumption cost while maintaining the comfort.

B. Particle Swarm optimization:

PSO is a nature–inspired optimization technique which uses swarm intelligence concept to effectively solve large scale nonlinear optimization problems while analytical methods suffer from slow convergence and curse of dimensionality. Many authors used PSO algorithm for optimization tasks and a summary of their work is presented below:

Load balancing problem has been solved by using Particle Swarm Optimization (PSO) in [12] to find the optimal distribution of energy resources in a green smart house. Simulations proved that the presented algorithm is effective in reducing cost on initial payment. For better energy optimization and for demand side management PSO is used in [13]. Simulation results show that the presented algorithm has proved its efficacy in providing better energy consumption pattern and in reducing energy cost. A model for Home Energy Management system is presented in [14] to schedule residential load by using PSO algorithm. The basic objective of this model is to decrease the electricity cost while maximizing the comfort of users. Simulations show the efficacy of the suggested approach while reducing peak power consumption. A scheduling strategy for demand side management using PSO is presented in [15] for residential load management. Simulation results show the clear annual savings of users. A heuristically optimized controller for HEM in Smart Grid is designed in [16] to decrease the overall electricity consumption cost and for curtailment of PAR. Binary PSO proved better for cost reduction of almost 35%. A novel discrete PSO algorithm is proposed in [17] to reduce computational time and energy in the real–world computing environment. Simulation results show that DPSO proved its effectiveness in achieving the desired task. A realistic scheduling mechanism is proposed in [18] to decrease user frustration and to increase appliance utility. Binary PSO is used to optimally schedule the appliances in eachtime slot. A performance analysis of home energy management controller which is designed on the basis of different heuristic algorithms is evaluated in [19]. Simulation results show that the all the designed models proved their efficacy in increasing the reliability of Smart Grid. A home energy management system by using different heuristic algorithms is proposed in [20] for scheduling of home appliances to reduce electricity consumption cost and peak to average ratio.

C. Genetic Algorithm

GA is an optimization algorithm inspired from genetic process of living organism. The genetic chromosomes of GA represent on and off status of appliances and length of chromosomes shows number of appliances to be scheduled. GA is commonly used for combinatorial optimization. GA can search a large space and works well when search space is multi–model. It can provide good solutions and can be useful for complex problems. Many authors used Genetic Algorithm for optimization tasks and a summary of their work is presented below:

An optimized Demand Side Management (DSM) technique based on smart metering is proposed in [21] to minimize domestic power consumption during peak loads. Two optimization techniques including Genetic algorithm and Bat Algorithm are proposed and their results are compared. The presented DSM proved its potential to save more energy as compared to other DSM techniques. Hybridization of two optimization techniques is proposed in [22] for cost reduction and load management. Results showed that the presented approach successfully reduced the total cost and PAR. An Energy Management System (EMS) is proposed in [23] while considering user’s preferences for shifting the operational time of appliances. To solve the problem of energy management, Genetic Algorithm is used. A Genetic Algorithm is proposed in [24] to reduce energy cost by finding an optimal scheduling pattern for all the functions in the smart home. Simulation results proved that presented algorithm effectively lessen the user’s electricity consumption cost. A real time–based HEM system using GA is presented in [25] to decrease cost and PAR while maintaining user’s comfort. The presented algorithm effectively managed the power consumption. A performance analysis of HEM controller is presented in [26] using three different optimization techniques including GA. Simulations proved the efficacy of all the schemes with respect to appliance scheduling and deduction of electricity bill. An optimized HEM system for residential consumers is presented in [27] for scheduling of appliances to minimize electricity cost. Optimization problem is solved using different algorithms including GA. An optimal HEM system is suggested in [28] for appliances scheduling to deduce PAR and energy cost. Simulation results proved the efficacy of the suggested algorithm.

D. Bacteria Foraging Algorithm

Bacteria foraging is the multi optimal function optimization algorithm. Bacteria hunt for nutrients in a way to boost the energy gained per unit time. Separate bacterium also interacts with other bacterium through signals. A bacterium takes foraging choices after taking in consideration the two preceding factors. The key idea of bacteria foraging optimization approach is mine chemotactic shifting of virtual bacteria in the problem hunt space. Many authors considered Bacteria Foraging Algorithm for optimization tasks and a summary of their work is presented below:

A HEM system for demand side management is proposed in [29] using BFA. The basic objective function of the presented algorithm is to lessen the overall electricity consumption cost and PAR while considering user’s comfort and load management. BFA for HEM system is presented in [30] for scheduling of appliances to lessen electricity cost and PAR while maintaining consumer’s comfort. The evaluation of Home Energy Management system is done in [31] to curtail cost and peak to average ratio and to manage the power consumption. Bacteria Foraging Algorithm is used as an optimization technique. Bacteria Foraging Algorithm for HEM system is implemented in [32] to decrease the energy cost. Simulation results proved the effectiveness of the proposed algorithm. BFA is used in HEMS [32] for the scheduling of home appliances. Simulation results proved that the energy cost and Peak to average ratio are reduced effectively. A HEM system is designed based upon BFA in [34] to decrease energy cost and PAR and to increase user’s satisfaction. Simulation results proved the efficacy of proposed algorithm. The performance of HEM system is evaluated in [35] by the use of BFA to minimize cost and PAR and to maximize comfort. Simulation results showed the effectiveness of the proposed scheme. A HEM system is suggested in [36] using BFA to deduce energy cost and PAR. Simulation results proved the efficacy of proposed algorithm.

E. Ant Colony Optimization

Ant Colony Optimization (ACO) is a meta–heuristic optimization approach that is used to solve discrete combinatorial optimization problems. It has unique properties of self–healing, self–protection and self–organization. A summary of work of authors through ACO is presented below. They formulated their focused problem as a non–linear programming problem and electricity bill minimization, power optimization and comfort are achieved using ACO.

A generic architecture for DSM is introduced in [37] to decrease electricity cost and PAR while maintaining user’s comfort. Simulations showed the efficacy of the suggested algorithm in enhancing the sustainability of Smart Grid. An efficient optimization technique for home energy management is proposed in [38] to maximize user’s comfort and to save energy. Simulation results of ACO and GA are compared in the end to prove the efficacy of ACO as compared to GA.

A dynamic energy management model using ACO for cloud data centers is proposed in [39] to optimize the running time of the system and to schedule tasks for the consumption of energy. Results proved the efficacy of the presented approach. An enhanced ACO (EACO) technique to solve mixed–variable, combinatorial and continuous optimization issues is proposed in [40] Results of ACO and EACO are compared and EACO proved better in terms of efficiency enhancement. A grid connected micro grid is proposed in [41] to fulfill the load demand of residential energy users and to reduce the overall cost and PAR. Scheduling of appliances is done by ACO. Simulations proved the efficacy of the suggested algorithm. A new hybrid technique is proposed in [42] to predict the power output of a wind farm in Binaloud. The hybridization of ACO and PSO is done to optimize the proposed model. Simulation results proved that the suggested model can predict the wind energy output with respect to wind speed and ambient temperature.

F. Grey Wolf Optimization

Grey wolf optimization is a Meta heuristic approach which is based upon population that affects the leadership hierarchy and searching procedure of grey wolves. Grey wolves are recognized as apex predators which are at the top position of food chain. The social hierarchy contains four levels. In the grey wolf optimizer, we take up the fittest solution as the alpha and the second and the third fittest solutions are named as beta and delta. Many authors used GWO in their work for scheduling and optimization tasks. A summary of their work is given below:

The performance of HEMS is evaluated in [43] using Grey Wolf Optimization and Bactria foraging algorithm. The basic objective is to deduce the overall energy cost and PAR and to maintain the consumption of power. Simulation results show that GWO proved better in terms of cost reduction. Optimal scheduling of appliances is done in [44] with Grey wolf optimization and Genetic Algorithm to reduce cost and PAR. Simulation results proved the efficacy of the proposed algorithm. Grey wolf optimization is used in [45] for optimal operation of Energy Storage Unit (ESU) in smart homes. The basic objective is to decrease the overall energy consumption cost and to balance the load on grid. Results are then compared with PSO. GWO proved appropriate for cost reduction. Grey wolf Optimization algorithm for DSM of smart homes is presented in [46]. The fundamental purpose is to increase the consumer’s comfort and to balance the load. Results are then correlated with BFA. Simulation results proved the efficacy of proposed algorithm. A methodology for standalone hybrid PV/wind/battery energy generation system’s sizing optimization is suggested in [47]. The basic purpose is to reduce the overall energy cost of the system and to determine the optimal number of components i.e. batteries, wind turbines (WTs) and PV panels.

III. CONCLUSION

SG is an open and vast research area, full of potential in research side which is rising rapidly because of industrial, commercial, government, residential users and retailer requirements. To enhance the performance abilities of Smart Grid and to gain the desired objectives, it is mandatory to go through different optimization techniques and to study in detail that how they meet the desired objectives. The role of optimization in Smart Grid is to make power grid as exceptional and satisfactory as possible. Several optimization schemes have been employed in electrical power industry. This paper is a short review of various optimization techniques and their implementation in HEMS in Smart Grid.

Table I. Summary of Optimization Techniques Used in HEMS

Figure 7

REFERENCES

  1. N. Kumaraguruparan, H. Sivaramakrishnan and S. Sachin, Residential Task Scheduling Under Dynamic Pricing Using the Multiple Knapsack Method, Minneapolis, 2011.
  2. A. Mohamed K., G. Peter,. G. Floriana and Z. Michele, Smart Domestic Renewable Energy Management Using Knapsack, in 4th IEEE PES Innovative Smart Grid Technologies Europe (ISGT Europe), United Kingdom, 2013.
  3. S. R. Silvio Roberto, . C. Silvio Roberto, . R. Filipe Maciel and C. Roberto, Using the multiple knapsack problem to model the problem of virtual machine allocation in cloud computing, in IEEE 16th International Conference on Computational Science and Engineering, 2013.
  4. S. Rahim, S. Khan, N. Javaid, N. Shaheen, Z. Iqbal and G. Rehman, Towards Multiple Knapsack Problem Approach for Home Energy Management in Smart Grid, in 18th International Conference on Network–Based Information Systems, 2015.
  5. A. Mahmood, N. Javaid, N. A. Khan and S. Razzaq, 18th International Conference on Network–Based Information Systems, 2016.
  6. M. Hristakeva and D. Shrestha, Different Approaches to Solve the 0/1 Knapsack Problem.
  7. F. Baig, A. Mahmood, N. Javaid and S. Razzaq, Smart Home Energy Management System for Monitoring and Scheduling of Home Appliances using Zigbee, Journal of Basic and Applied Scientific Research , vol. 3, no. 5, pp. 880–891, 2013.
  8. O. Marinoni, A. Higgins and S. Hajkowicz, A Multi Criteria Knapsack Solution to Optimise Natural Resource Management Project Selection, in Multiple Criteria Decision Making for Sustainable Energy and Transportation Systems, 2009.
  9. B. Rasheed, N. Javaid, A. Ahmad, Z. Khan, U. Qasim and N. Alrajeh, An Efficient Power Scheduling Scheme for Residential Load Management in Smart Homes, vol. 5, no. 4, pp. 1134–1136, 2015.
  10. A. Mahmood, F. Baig, N. Alrajeh, U. Qasim, Z. Khan and N. Javaid, An Enhanced System Architecture for Optimized Demand Side Management in Smart Grid, Applied Sciences, vol. 6, no. 5, 2016.
  11. B. Rasheed, N. Javaid, A. Ahmed, M. Jamil, z. Khan, U. Qasim and N. Alrajeh, Energy Optimization in Smart Homes Using Customer Preference and Dynamic Pricing, Energies, vol. 9, no. 8, 2016.
  12. H. M. Lugo–Cordero, A. Fuentes–Rivera, . R. K. Guha and . E. I. OrtizRivera , Particle Swarm Optimization for Load Balancing in Green Smart Homes, 2011.
  13. N. Shahaeen, N. Javaid, Z. Iqbal, k. Muhammad, K. Azad and F. chaudhary, A Hybrid Algorithm for Energy Management in Smart Grid, in 18th International Conference on Network–Based Information Systems, 2015.
  14. N. Javaid, F. Ahmed, I. Ullah, S. Abid, W. Abdul, A. Alamri and A. Almorgen, Towards Cost and Comfort Based Hybrid Optimization for Residential Load Scheduling in a Smart Grid, Energies, 2017.
  15. A. K. Pathak, . D. S. Chatterji and M. S. Narkhede , Artificial Intelligence Based Optimization Algorithm for Demand Response Management of Residential Load in Smart Grid, International Journal of Engineering and Innovative Technology (IJEIT), vol. 2, no. 4, 2012.
  16. J. Nadeem, M. Naseem, B. Rasheed, D. Mahmood, S. Khan, N. Alrajeh and Z. Iqbal, A new heuristically optimized Home Energy Management controller for smart grid, Elsevier, vol. 34, pp. 2011–227, 2017.
  17. M. Christobel, T. Selvi and S. Benedict, Efficient Scheduling of Scientific Workflows with Energy Reduction Using Novel Discrete Particle Swarm Optimization and Dynamic Voltage Scaling for Computational Grids, The Scientific World Journal, p. 11, 2015.
  18. D. Mahmood, N. Javaid, N. Alrajeh, Z. Khan, U. Qasim, I. Ahmed and M. Ilahi, Realistic Scheduling Mechanism for Smart Homes, Energies, vol. 9, no. 3, 2016.
  19. S. Rahim, N. Javaid, A. Ahmad, S. Khan, Z. Khan, N. Alrajeh and U. Qasim, Exploiting heuristic algorithms to efficiently utilize energy management controllers with renewable energy sources, Energy and Buildings, vol. 129, pp. 452–470, 2016.
  20. M. Naseem, S. Abid, R. Khalid, G. Hafeez, M. Hussain and N. Javaid, Towards Heuristic Algorithms: GA, WDO, BPSO, and BFOA for Home Energy Management in Smart Grid, in International Conference on Broadband and Wireless Computing, Communication and Applications.
  21. R. R. El–Razky, A. A. Daoud and . K. El–serafi, Optimization of Residential Load Consumption during Energy Peaks using Smart Metering, Renewable Energy and power quality journal, 2017.
  22. A. Khalid, N. Javaid, A. Mateen, B. Khalid, Z. Khan and U. Qasim, Demand Side Management using Hybrid Bacterial Foraging and Genetic Algorithm Optimization Techniques, in 10th International Conference on Complex, Intelligent, and Software Intensive Systems, 2016.
  23. N. Shaheen, N. Javaid, N. Nisa, A. Zeb, Z. Khan and U. Qasim, Appliance Scheduling for Energy Management with User Preferences, in 10th International Conference on Innovative Mobile and Internet Services in Ubiquitous Computing, 2016.
  24. H. Miao, X. huang and G. Chen, A Genetic Evolutionary Task Scheduling Method for Energy Efficiency in Smart Homes, International Journal of Enterprise Network Management July 2012, vol. 7, no. 5, 2012.
  25. B. Rasheed, N. Javaid, M. Awais, Z. Khan, U. Qasim, N. Alrajeh, Z. Iqbal and Q. Javaid, Real Time Information Based Energy Management Using Customer Preferences and Dynamic Pricing in Smart Homes, vol. 9, no. 7.
  26. A. Khan, N. Javaid, A. Ahmed, S. Kazmi, M. Hussain and Z. Khan, Efficient Utilization of HEM Controller Using Heuristic Optimization Techniques, in International Conference on Emerging Internetworking, Data & Web Technologies, 2017.
  27. A. Ahmad, A. Khan, N. Javaid, M. Hussain, W. Abdul, A. Almogren, A. Alamri and I. Niaz, An Optimized Home Energy Management System with Integrated Renewable Energy and Storage Resources, vol. 10, no. 4, 2017.
  28. M. Talha, S. Saeed, G. Mohiuddin, M. Ahmad, J. Nazar and N. Javaid, Energy Optimization in Home Energy Management System Using Artificial Fish Swarm Algorithm and Genetic Algorithm, in International Conference on Intelligent Networking and Collaborative Systems, 2017.
  29. A. Ishaq, N. Ayub, A. Saba, A. Ghaffar, B. Amin and N. Javaid, An Efficient Scheduling Using Meta Heuristic Algorithms for Home Demand–side Management in Smart Grid, in International
  30. Conference on Intelligent Networking and Collaborative Systems, 2017.
  31. S. Razzaq, A. Khalid, R. Sughra, Z. Ullabidin, A. Zahra, M. Khan and N. Javaid, Demand Side Management Using Meta–Heuristic Optimization Techniques, in International Conference on Broadband and Wireless Computing, Communication and Applications, 2017.
  32. A. UlHassan, S. Khan, A. Ghaffar, S. Aimal, S. Asif and N. Javaid, Energy Optimization in Smart Grid Using Grey Wolf Optimization Algorithm and Bacterial Foraging Algorithm, in International Conference on Intelligent Networking and Collaborative Systems, 2017.
  33. A. Ghaffar, R. Khalid, M. Ali, A. UlHassan, A. Ishaq, B. Amin and N. Javaid, GreyWolf Optimization Technique for HEMS Using Day Ahead Pricing Scheme, in International Conference on Broadband and Wireless Computing, Communication and Applications, 2017.
  34. N. Mushtaq, H. Rahim, R. Khalid, S. Abid, Pamir and S. Rehman, Home Energy Management in Smart Grid Using Bacterial Foraging and Strawberry Algorithm, in International Conference on Broadband and Wireless Computing, Communication and Applications, 2017.
  35. A. Zahra, Z. UlAbideen, A. Rehman, S. Razzaq, A. Anjum and N. Javaid, Home Energy Management Using HSA, FA, BFOA Algorithms in Smart Grids, in International Conference on Network–Based Information Systems, 2017.
  36. T. Bilal, M. Awais, M. Junaid, Z. Fiaz, M. Rehman and N. Javaid, Home Energy Managment System Using Meta–heuristic Techniques, in International Conference on Network–Based Information Systems, 2017.
  37. S. Batool, A. Khalid, Z. Amjad, H. Arshad, S. Aimal, M. Farooqui and N. Javaid, Pigeon Inspired Optimization and Bacterial Foraging Optimization for Home Energy Management, in International Conference on Broadband and Wireless Computing, Communication and Applications, 2017.
  38. S. Rahim, Z. Iqbal, N. Shaheen, Z. Khan, U. Qasim, S. Khan and N. Javaid, Ant Colony Optimization based Energy Management Controller for Smart Grid, in IEEE 30th International Conference on Advanced Information Networking and Applications, 2016.
  39. A. Galbazaar, S. Ali and D. Kim, Optimization Approach for Energy Saving and Comfortable Space Using ACO in Building, International Journal of Smart Home, vol. 10, no. 4, pp. 47–56, 2016.
  40. S. Pang, W. Zang, T. Ma and Q. Gao, Ant Colony Optimization Algorithm to Dynamic Energy Management in Cloud Data Center, 2017.
  41. U. Diwekar and B. Gebreslassie, Efficient Ant Colony Optimization (EACO) Algorithm for Deterministic Optimization, International Journal of Swarm Intelligence and Evolutionary Computation, 2016.
  42. I. Fatima, A. Khalid, S. Zahoor, A. Yasmeen, S. Arif, U. Zafar and N. Javaid, Home Energy Management System Using Ant Colony Optimization Technique in Microgrid, in International Conference on Broadband and Wireless Computing, Communication and Applications, 2017.
  43. R. Rahmani, R. yousaf, M. Syedmuhiuddin and S. Mehkilif, Hybrid technique of ant colony and particle swarm optimization for short term wind energy forecasting, vol. 123, pp. 163–170, 2013.
  44. A. Ulhassan, S. Khan, A. Ghaffar, S. Aimal, S. Asif and N. Javaid, Energy Optimization in Smart Grid using Grey Wolf Optimization Algorithm and Bacterial Foraging Algorithm, 2017.
  45. F. Kazmi, A. Motameddi and S. Sharifian, A home energy management system using Gray Wolf Optimizer in smart grids, in Swarm Intelligence and Evolutionary Computation (CSIEC), 2017.
  46. F. Kazemi, A. Motamedi and S. Shriffian, Efficient energy management for smart homes with grey wolf optimizer, 2017.
  47. S. Aimal, K. Pervez, A. Saba, S. Batool, H. Arshad and N. Javaid, Energy Optimization Techniques for Demand–Side Management in Smart Homes, in International Conference on Intelligent Networking and Collaborative Systems, 2017.

Наверх