As the power system is facing a transition toward a more intelligent, flexible, and interactive system with higher penetration of renewable energy generation, load forecasting, especially short-term load forecasting for individual electric customers plays an increasingly essential role in the future grid planning and operation. Other than aggregated residential load in a large scale, forecasting an electric load of a single energy user is fairly challenging due to the high volatility and uncertainty involved. In this paper, we propose a long short-term memory (LSTM) recurrent neural network-based framework, which is the latest and one of the most popular techniques of deep learning, to tackle this tricky issue. The proposed framework is tested on a publicly available set of real residential smart meter data, of which the performance is comprehensively compared to various benchmarks including the state-of-the-arts in the field of load forecasting. As a result, the proposed LSTM approach outperforms the other listed rival algorithms in the task of short-term load forecasting for individual residential households.

Short-Term Residential Load Forecasting Based on LSTM Recurrent Neural Network

Large-scale deployment of intermittent renewable energy (namely wind energy and solar PV) may entail new challenges in power systems and more volatility in power prices in liberalized electricity markets. Energy storage can diminish this imbalance, relieving the grid congestion, and promoting distributed generation. The economic implications of grid-scale electrical energy storage technologies are however obscure for the experts, power grid operators, regulators, and power producers. A meticulous techno-economic or cost-benefit analysis of electricity storage systems requires consistent, updated cost data and a holistic cost analysis framework. To this end, this study critically examines the existing literature in the analysis of life cycle costs of utility-scale electricity storage systems, providing an updated database for the cost elements (capital costs, operational and maintenance costs, and replacement costs). Moreover, life cycle costs and levelized cost of electricity delivered by electrical energy storage is analyzed, employing Monte Carlo method to consider uncertainties. The examined energy storage technologies include pumped hydropower storage, compressed air energy storage (CAES), flywheel, electrochemical batteries (e.g. lead–acid, NaS, Li-ion, and Ni–Cd), flow batteries (e.g. vanadium-redox), superconducting magnetic energy storage, supercapacitors, and hydrogen energy storage (power to gas technologies). The results illustrate the economy of different storage systems for three main applications: bulk energy storage, T&D support services, and frequency regulation.

Electrical energy storage systems: A comparative life cycle cost analysis

Simulation and the monte carlo method

A variety of methods and ideas have been tried for electricity price forecasting (EPF) over the last 15 years, with varying degrees of success. This review article aims at explaining the complexity of available solutions, their strengths and weaknesses, and the opportunities and treats that the forecasting tools offer or that may be encountered. The paper also looks ahead and speculates on the directions EPF will or should take in the next decade or so. In particular, it postulates the need for objective comparative EPF studies involving (i) the same datasets, (ii) the same robust error evaluation procedures and (iii) statistical testing of the significance of the outperformance of one model by another.

Electricity price forecasting: A review of the state-of-the-art with a look into the future

Review of energy storage system for wind power integration support

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.

Genetic-Algorithm-Based Optimization Approach for Energy Management

This paper deals with optimal placement of the energy storage units within a deregulated power system to minimize its hourly social cost. Wind generation and load are modeled probabilistically using actual data and a curve fitting approach. Based on a model of the electricity market, we minimize the hourly social cost using probabilistic optimal power flow (POPF) then use a genetic algorithm to maximize wind power utilization over a scheduling period. A business model is developed to evaluate the economics of the storage system based on the energy time-shift opportunity from wind generation. The proposed method is used to carry out simulation studies for the IEEE 24-bus system. Transmission line constraints are addressed as a bottleneck for efficient wind power integration with higher penetration levels. Distributed storage is then proposed as a solution to effectively utilize the transmission capacity and integrate the wind power more efficiently. The potential impact of distributed storage on wind utilization is also evaluated through several case studies.

A Framework for Optimal Placement of Energy Storage Units Within a Power System With High Wind Penetration

This paper proposes a stochastic framework for optimal sizing and reliability analysis of a hybrid power system including the renewable resources and energy storage system. Uncertainties of wind power, photovoltaic (PV) power, and load are stochastically modeled using autoregressive moving average (ARMA). A pattern search-based optimization method is used in conjunction with a sequential Monte Carlo simulation (SMCS) to minimize the system cost and satisfy the reliability requirements. The SMCS simulates the chronological behavior of the system and calculates the reliability indices from a series of simulated experiments. Load shifting strategies are proposed to provide some flexibility and reduce the mismatch between the renewable generation and heating ventilation and air conditioning loads in a hybrid power system. Different percentages of load shifting and their potential impacts on the hybrid power system reliability/cost analysis are evaluated. Using a compromise-solution method, the best compromise between the reliability and cost is realized for the hybrid power system.

Stochastic Performance Assessment and Sizing for a Hybrid Power System of Solar/Wind/Energy Storage

Integration of renewable energy resources into the power system has increased the financial and technical concerns for the market-based transmission expansion planning. This paper proposes a stochastic framework for transmission grid reinforcement studies in a power system with wind generation. A multi-stage multi-objective transmission network expansion planning (TNEP) methodology is developed which considers the investment cost, absorption of private investment and reliability of the system as the objective functions. A non-dominated sorting genetic algorithm (NSGA II) optimization approach is used in combination with a probabilistic optimal power flow (POPF) to determine the Pareto optimal solutions considering the power system uncertainties. Using a compromise-solution method, the best final plan is then realized based on the decision-maker preferences. The proposed methodology is applied to the IEEE 24-bus Reliability Tests System (RTS) to evaluate the feasibility and practicality of the developed planning strategy.

A Multi-Objective Transmission Expansion Planning Framework in Deregulated Power Systems With Wind Generation

This paper proposes a novel method for fault location in distribution networks using compressive sensing. During fault and prefault voltages are measured by smart meters along the feeders. The voltage sag vector and impedance matrix produce a current vector that is sparse enough with one nonzero element. This element corresponds to the bus at which a fault occurs. Due to the limited number of smart meters installed at primary feeders, our system equation is underdetermined. Therefore, the $\ell ^{1}$ -norm minimization method is used to calculate the current vector. Primal-dual interior point (PDIP) and the log barrier algorithm (LBA) are utilized to solve the optimization problem with and without measurement noises, respectively. Our proposed method is implemented on a real 13.8-kV, 134-bus distribution network when single-phase, three-phase, double-phase, and double-phase-to-ground short circuits occur. Simulation results show the robustness of the proposed method in noisy environments and satisfactory performance for various faults with different resistances.

A. Arabali

Papers

Genetic-Algorithm-Based Optimization Approach for Energy Management

A Framework for Optimal Placement of Energy Storage Units Within a Power System With High Wind Penetration

Stochastic Performance Assessment and Sizing for a Hybrid Power System of Solar/Wind/Energy Storage

A Multi-Objective Transmission Expansion Planning Framework in Deregulated Power Systems With Wind Generation

Fault Location in Distribution Networks by Compressive Sensing