Appliance Scheduling for Energy Management with User Preferences

Shaheen, Nusrat; Javaid, Nadeem; Nisa, Najmun; Zeb, Amber Madeeha; Khan, Zahoor Ali; Qasim, Umar

doi:10.1109/imis.2016.135

Cited by 5 publications

(2 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…(1) Dispatching by establishing a fixed mathematical model of household electricity consumption: Literature [1] proposes multiple optimization objectives based on load peak and electricity cost minimization, and uses hybrid coding genetic algorithm to solve the problem to realize household electricity scheduling. Literature [2] aims at reducing the peak-to-average ratio (PAR), reducing energy costs and ensuring grid stability, and proposes a model solution method combining genetic algorithm and neural network to achieve a balance between user costs and grid stability. However, these fixed mathematical models of household electricity use are difficult to deal with the complexity of the scheduling environment and the randomness of electricity use behavior.…”

Section: Introductionmentioning

confidence: 99%

Household Electricity Scheduling Strategy Solution Based on SA-α-QLearning

Wu¹,

Wu²,

Zhang³

et al. 2023

Journal of Computers

View full text Add to dashboard Cite

<p>Traditional household power dispatching methods are difficult to deal with the complexity of dispatching environment and the randomness of power consumption behavior, and the QLearning algorithm is prone to fall into local optimal solutions and slow convergence when solving problems, this paper proposes a new method based on SA-α-QLearning’s home electricity scheduling strategy solution method. Firstly, a multi-intelligent Markov decision process model is established based on household electrical equipment; then the learning rate of a single value in the QLearning algorithm is replaced by a linear iterative learning rate; finally, a simulated annealing (SA) is used to optimize the QLearning algorithm to solve the model, by taking the Q value change difference as the new solution acceptance probability of Metropoils criterion and the dynamic adjustment temperature reduction coefficient, it alleviates the problem that the QLearing algorithm is easy to fall into the local optimal solution and the convergence speed is slow. Through a large number of comparative experiments, it is proved that the proposed method has a significant improvement in the solution of household electricity dispatching strategy.</p> <p> </p>

show abstract

Section: Introductionmentioning

confidence: 99%

Household Electricity Scheduling Strategy Solution Based on SA-α-QLearning

Wu¹,

Wu²,

Zhang³

et al. 2023

Journal of Computers

View full text Add to dashboard Cite

show abstract

“…For example, retrofitting existing meters into smart meters to do real-time monitoring and evaluation of the grid was considered in [30]. What is, therefore, noticeable in almost all the studies reviewed is that they assume that the cost of peaking is the critical constraint on the overall network as well as the preservation of consumers' comfort of use [31], [32].…”

Section: Introductionmentioning

confidence: 99%

Heuristic Optimization for Microload Shedding in Generation Constrained Power Systems

et al. 2020

View full text Add to dashboard Cite

While the causes of power system outages are often complex and multi-faceted, an apparent deficit in generation compared to a known demand for electricity could be more alarming. A sudden hike in demand at any given time may ultimately result in the total failure of an electricity network. In this paper, algorithms to efficiently allocate the available generation is investigated. Dynamic programming based algorithms are developed to achieve this constraint by uniquely controlling home appliances to reduce the overall demands for electricity by the consumers on the grid in context. To achieve this, heuristic optimization method (HOM) based on the consumers' comfort and the benefits to the electricity utility is proposed. This is then validated by simulating microload management in generation constrained power systems. Three techniques; General Shedding (GS), Priority Based Shedding (PBS) and Excess Reuse Shedding (ERS) techniques were studied for effecting efficient microload shedding. The research is aimed at reducing the burden imposed on the consumers in a generation constrained power system by the traditional load shedding approach. Additionally, the reduction of the excess curtailment is a prime objective in this paper as it helps the utility companies to reduce wastage and ultimately reduce losses resulting from over shedding. Reducing the peak-to-average ratios (PAR) on the entire network in context as a critical factor in the determination of the efficiency of an electricity network is also investigated. In the long run, the PAR affects the price charged to the final consumer. Simulation results show the associated benefits that include effectiveness, deployability, and scalability of the proposed HOM to reduce these burdens. INDEX TERMS Demand-side management (DSM), microload management, smart grid, smart metering, optimization, peak-to-average ratio (PAR).

show abstract