Independent System Operator Research Articles

Virtual Prosumers’ P2P Transaction Based Distribution Network Expansion Planning

The deployment of prosumers with distributed energy resources (DERs) has facilitated the prosumer-centric transactive market, giving rise to the consequent necessity for the coordination between prosumers and the distribution networks. This paper proposes an incentive-based expansion planning method considering virtual peer-to-peer (P2P) transaction among prosumers, which is characterized as a tri-level planning-operation-transaction framework. Each prosumer optimizes its internal response of DERs and external P2P transaction jointly, formulating virtual P2P transaction. Under such a paradigm, the distribution company (DISCO) identifies the optimal expansion planning in the network assets, while the independent distribution system operator (IDSO) is responsible for the optimal operation of the expanded distribution networks. To derive appropriate incentives for each prosumer, the DISCO and IDSO allocate long-term investment network charges and short-term operation network charges on prosumers, along with the designed financial transmission rights coupling multiple time scales. Through such incentives, self-profit driven virtual transactions can relieve operation problems and postpone expansion planning, acting as a short-term alternative. Moreover, a risk-based approach is proposed for prosumer to flexibly change strategy according to different risk preference. Finally, results from the case study demonstrate the superiority and effectiveness of the proposed method in the collaborative application of virtual transaction in the expansion planning.

As Grids Reach 100% Renewable at Peak, Growing Curtailment of 8 Gigawatts Looms as a Challenge to Decarbonization

In April 2022, the California Independent System Operator (CAISO) power grid reached momentary peaks of 100% renewable energy for the first time. After a year, momentary 100% supply from renewables isn't a news any more, and CAISO reported record wind and solar renewable curtailment of 606 GWh (March 2023) and 686 GWh (April 2023). In addition, peak renewable coincided with curtailment rates of 8 GW in April 2023. Our prior studies documented monthly-peak renewable curtailment growth of 40% annually (23 GWh in March 2015 growing to 82 GWh in March 2017). Updating for 2018-2023 shows that 40% annual growth has continued through April 2023 and with it, CAISO has reached an average sunlight hours curtailment rate of 2 GW. If this 9-year trend continues unchecked for the next 5 years, monthly curtailment is projected to reach 3.3 TWh in both March and April of 2028, an average sunlight curtailment rate of nearly 11 GW. We analyze causes of increased curtailment, and discuss its likely future trajectory (growth). We also discuss the challenges its growth represents for grid decarbonization. Finally we outline the difficulties in reducing curtailment growth and highlight several new opportunities for power grids and computing systems.

Self-Unit Commitment of Combined-Cycle Units with Real Operational Constraints

This paper highlights the importance of accurately modeling the operational constraints of Combined-Cycle Gas Turbines (CCGTs) within a unit-commitment framework. In practice, in Colombia, when given an initial dispatch by the Independent System Operator, CCGT plants are operated according to the results of heuristic simulation codes. Such heuristics often omit technical operating constraints, including hot, warm, or cold startup ramps; the minimum operation hours required for a gas turbine to start a steam turbine; the relationship between the dispatched number of steam and gas turbines; the load distribution among gas turbines; and supplementary fires. Most unit-commitment models in the literature represent standard technical constraints like startup, shutdown, up/down ramps, and in some cases, supplementary fires. However, they typically overlook other real-life CCGT operating constraints, which were considered in this work. These constraints are crucial in integrated energy systems to avoid equipment damage, which can potentially put CCGT plants out of service and ultimately lead to lower operating costs.

Bi-level planning approach for incorporating the demand-side flexibility of cloud data centers under electricity-carbon markets

With the prevalence of cloud computing applications, cloud data centers (CDCs) are proliferating around the world. However, in the context of hybrid energy‑carbon markets environment, the high energy costs and environmental expenses caused by CDC operation are pressing CDC owners to restructure the future development of CDC in a more economical and low-carbon manner. The potential spatio-temporal transferability and reducibility of workloads provides CDCs with significant flexibility in their operations and thus may interact with the power grid as active demand users. Nonetheless, other than private data centers, public CDCs have no direct control over the workloads submitted by terminal cloud users. As such, this paper presents a bi-level model for CDC allocation planning, so as to incorporate cloud service-demand response (CS-DR) from the perspective of a hybrid electricity-carbon market. The upper level pertains to multi-domain resource collaborative planning model, which determines the optimum siting and sizing of CDCs as well as the incentive design for CS-DR program, with the objective of maximizing the total expected benefits of CDC. The lower level models correspond to the market clearing (electricity-carbon tariff model) of Independent system operator (ISO) and the decision-making of cloud users regarding CS-DR participation. The proposed model belongs to a bi-level mixed integer nonlinear programming problem with two non-convex lower levels, which can be intractable in mathematics. To solve such difficult problem, a hybrid solution method combining multiple linearization techniques and reformulation and decomposition (R&D) strategy based on column-and-constraint generation (C&CG) algorithm is developed. The proposed model is demonstrated on a modified IEEE 30-bus test case, and the simulation results verified the effectiveness of the proposed approach.

Congestion Relief Services by Vehicle-to-Grid Enabled Electric Vehicles Considering Battery Degradation

Battery electric vehicles (BEVs) offer substantial potential to enhance the electric grid through bi-directional charging technologies. In essence, BEVs, functioning as portable battery energy storage systems, play a pivotal role in enabling the seamless integration of renewable energy, grid optimization, and ancillary services. This article sets out to explore the value of BEVs equipped with Vehicle-to-Grid (V2G) for grid operators, particularly in the context of alleviating congestion. This valuable service, though not accompanied by direct monetary compensation for users, holds significant promise in minimizing congestion and renewable energy curtailment. This study utilizes the Day-Ahead Locational Marginal Price (LMP) data obtained from various locations within California Independent System Operator (CAISO) to ascertain the financial benefits to BEVs located on either side of congestion at different grid nodes, across various months. Similar analysis is performed on some of the largest solar energy plants in California. Mixed-integer linear programs are used to optimize the charging/discharging decisions for the BEV for maximizing revenue from LMP arbitrage and for minimizing the congestion component of LMP. Additionally, we take into account the impact of battery degradation, quantified as a cost per kilowatt-hour ($/kWh), and integrate this factor into our assessment to understand the evolving discharging behavior of BEVs. The article compares the benefits from the BEVs towards congestion minimization for the two different optimization scenarios, discusses seasonality, and addresses the importance of adequately compensating BEV users and incentivizing them to prioritize congestion relief during specific time intervals.

Residential electricity demand on CAISO Flex Alert days: a case study of voluntary emergency demand response programs

Abstract The California Independent System Operator (CAISO) utilizes a system-wide, voluntary demand response (DR) tool, called the Flex Alert program, designed to reduce energy usage during peak hours, particularly on hot summer afternoons when surges in electricity demand threaten to exceed available generation resources. However, the few analyses on the efficacy of CAISO Flex Alerts have produced inconsistent results and do not investigate how participation varies across sectors, regions, population demographics, or time. Evaluating the efficacy of DR tools is difficult as there is no ground truth in terms of what demand would have been in the absence of the DR event. Thus, we first define two metrics that to evaluate how responsive customers were to Flex Alerts, including the Flex Period Response, which estimates how much demand was shifted away from the Flex Alert period, and the Ramping Response, which estimates changes in demand during the first hour of the Flex Alert period. We then analyze the hourly load response of the residential sector, based on ∼200 000 unique homes, on 17 Flex Alert days during the period spanning 2015–2020 across the Southern California Edison (SCE) utility’s territory and compare it to total SCE load. We find that the Flex Period Response varied across Flex Alert days for both the residential (−18% to +3%) and total SCE load (−7% to +4%) and is more dependent on but less correlated with temperature for the residential load than total SCE load. We also find that responsiveness varied across subpopulations (e.g. high-income, high-demand customers are more responsive) and census tracts, implying that some households have more load flexibility during Flex Alerts than others. The variability in customer engagement suggests that customer participation in this type of program is not reliable, particularly on extreme heat days, highlighting a shortcoming in unincentivized, voluntary DR programs.

Using neural networks to forecast marginal emissions factors: A CAISO case study

Marginal Emissions Factors (MEFs) quantify the time-dependent changes in CO2 emissions resulting from changes in electricity consumption. Accurate MEFs are critical for calculating the emissions impact of demand-side management (DSM) activities and programs, but current methods of calculating MEFs are limited by their temporal resolution, accuracy (particularly in grids with high penetrations of variable renewable energy), and ability to predict MEFs ahead of time, reducing their utility for DSM. We improve upon existing techniques by introducing a novel multi-layer perceptron to linear composite model that uses publicly available grid data to calculate historical MEFs and predict day-ahead MEFs. We test our model on publicly-available data from the California Independent System Operator over the period of 2019–2021, a grid with high daytime VRE generation. Results indicate that our model produces more accurate and more granular demand-based MEF estimations than comparable regression techniques and maintains high accuracy when use to forecast future MEFs. Our MEF framework can be applied to other regional grids to evaluate and design DSM strategies that leverage CO2 emissions-reductions as motivation for altering electricity consuming behaviors.

Principal component analysis of day‐ahead electricity price forecasting in CAISO and its implications for highly integrated renewable energy markets

AbstractElectricity price forecasting is crucial for grid management, renewable energy integration, power system planning, and price volatility management. However, poor accuracy due to complex generation mix data and heteroskedasticity poses a challenge for utilities and grid operators. This paper evaluates advanced analytics methods that utilize principal component analysis (PCA) to improve forecasting accuracy amidst heteroskedastic noise. Drawing on the experience of the California Independent System Operator (CAISO), a leading producer of renewable electricity, the study analyzes hourly electricity prices and demand data from 2016 to 2021 to assess the impact of day‐ahead forecasting on California's evolving generation mix. To enhance data quality, traditional outlier analysis using the interquartile range (IQR) method is first applied, followed by a novel supervised PCA technique called robust PCA (RPCA) for more effective outlier detection and elimination. The combined approach significantly improves data symmetry and reduces skewness. Multiple linear regression models are then constructed to forecast electricity prices using both raw and transformed features obtained through PCA. Results demonstrate that the model utilizing transformed features, after outlier removal using the traditional method and SAS Sparse Matrix method, achieves the highest forecasting performance. Notably, the SAS Sparse Matrix outlier removal method, implemented via proc RPCA, greatly contributes to improved model accuracy. This study highlights that PCA methods enhance electricity price forecasting accuracy, facilitating the integration of renewables like solar and wind, thereby aiding grid management and promoting renewable growth in day‐ahead markets.This article is categorized under: Energy and Power Systems > Energy Management Energy and Power Systems > Distributed Generation Emerging Technologies > Digitalization

A tri-level programming-based frequency regulation market equilibrium under cyber attacks

Owing to their flexibility and rapid response, grid-connected distributed energy resources (DERs) are wielding growing influence in frequency regulation markets (FRMs). Nevertheless, compared with conventional large-scale generators, small-scale DERs are usually weakly shielded by cyber security measures. This offers attackers the opportunity of disrupting the clearing and settlement of FRMs by manipulating the bid information of DERs. In this paper, the frequency regulation market equilibrium is studied considering the dynamic gaming between attackers and defenders, both of which need the knowledge of FRMs for their interventions. Specifically, a tri-level programming model characterizing the attacker–defender–operator (ADO) interdiction problem in FRMs is developed and then analyzed using a column and constraint generation algorithm, thereby achieving market equilibrium representing the defender's best response to the attacker. The defense strategy in the market equilibrium can attenuate the negative influence of cyber attacks upon the FRMs to the maximum extent. Finally, based on the operating rules of the California Independent System Operator, the FRM process considering the ADO interdiction is simulated and the numerical equilibrium results are presented.

Predicting the Gap in the Day-Ahead and Real-Time Market Prices Leveraging Exogenous Weather Data

Predicting the price gap between the day-ahead Market (DAM) and the real-time Market (RTM) plays a vital role in the convergence bidding mechanism of Independent System Operators (ISOs) in wholesale electricity markets. This paper presents a model to predict the values of the price gap between the DAM and RTM using statistical machine learning algorithms and deep neural networks. In this paper, we seek to answer these questions: What will be the impact of predicting the DAM and RTM price gap directly on the prediction performance of learning methods? How can exogenous weather data affect the price gap prediction? In this paper, several exogenous features are collected, and the impacts of these features are examined to capture the best relations between the features and the target variable. An ensemble learning algorithm, namely the Random Forest (RF), is used to select the most important features. A Long Short-Term Memory (LSTM) network is used to capture long-term dependencies in predicting direct gap values between the markets stated. Moreover, the advantages of directly predicting the gap price rather than subtracting the price predictions of the DAM and RTM are shown. The presented results are based on the California Independent System Operator (CAISO)’s electricity market data for two years. The results show that direct gap prediction using exogenous weather features decreases the error of learning methods by 46%. Therefore, the presented method mitigates the prediction error of the price gap between the DAM and RTM. Thus, the convergence bidders can increase their profit, and the ISOs can tune their mechanism accordingly.

Congestion cost estimation using adaptive red fox algorithm in restructured electricity markets

Congestion of the power system is the most common challenge an Independent System Operator (ISO) faces in restructured electricity markets. It affects the efficiency of the market when transmission lines are congested causing transmission costs to rise. To prevent transmission line congestion, ISO needs to take the necessary steps. To solve these issues, this paper introduces a new method namely the Adaptive Red Fox Optimization algorithm (ARFOA) to compute the congestion cost considering the power losses in the transmission line system. Initially, all the generators in the system are selected to reschedule real power outputs. Second, by establishing a proposed optimization issue, ARFOA is employed to control transmission line congestion. The implementation of the proposed method is evaluated on the IEEE 30 bus system. The algorithm’s adaptability is tested using several case studies involving the base case and line outages, also compared with the other existing techniques such as PSO, ASO, and GSO approaches. The simulation outcomes indicate that the proposed strategy outperforms existing techniques in terms of congestion cost, power loss, generation rescheduled power, and computational time.

An Overview of Short-Term Load Forecasting for Electricity Systems Operational Planning: Machine Learning Methods and the Brazilian Experience

The advent of smart grid technologies has facilitated the integration of new and intermittent renewable forms of electricity generation in power systems. Advancements are driving transformations in the context of energy planning and operations in many countries around the world, particularly impacting short-term horizons. Therefore, one of the primary challenges in this environment is to accurately provide forecasting of the short-term load demand. This is a critical task for creating supply strategies, system reliability decisions, and price formation in electricity power markets. In this context, nonlinear models, such as Neural Networks and Support Vector Machines, have gained popularity over the years due to advancements in mathematical techniques as well as improved computational capacity. The academic literature highlights various approaches to improve the accuracy of these machine learning models, including data segmentation by similar patterns, input variable selection, forecasting from hierarchical data, and net load forecasts. In Brazil, the national independent system operator improved the operation planning in the short term through the DESSEM model, which uses short-term load forecast models for planning the day-ahead operation of the system. Consequently, this study provides a comprehensive review of various methods used for short-term load forecasting, with a particular focus on those based on machine learning strategies, and discusses the Brazilian Experience.

Profit enhancement and grid frequency control by energy level scheduling of CAES system in wind-connected electrical system

The maintenance of power balance poses significant challenges in renewable combined deregulated power systems due to the unpredictable nature of renewable energy sources. This situation leads to economic instability within the system. However, an energy storage system can help maintain energy supply and control system stability for renewable incorporated thermal power plants. Unlike in regulated markets, energy prices in deregulated markets are not fixed by any government body or particular company. Instead, the Independent System Operator (ISO) serves as the main entity in the electrical market, gathering tenders from Generation Companies (GENCOs), Distribution Companies (DISCOs), and Transmission Companies (TRANSCOs). The market controller regulates energy prices using Nodal Pricing (NP), which provides economic benefits to both GENCOs and DISCOs. However, the unpredictability of renewable sources often results in a decline in system profit due to the production of an imbalance price (CostIMC) caused by a mismatch in contracted power generation from the renewable power plant. To address these issues, this study proposes a novel combined system that utilizes a suitable scheduling technique for the optimum operation of a wind farm-compressed air energy storage (CAES) system to maximize profit and revenue while maintaining grid frequency. The CAES system’s energy level is divided into four different levels, and an optimal strategy has been developed to efficiently utilize the CAES system to maintain grid frequency. This work has been conducted in both regulated and deregulated environments using a modified IEEE 30-bus system. The proposed method has been compared with an existing approach and has yielded better results in all aspects.

Optimized hybrid ensemble learning approaches applied to very short-term load forecasting

The significance of accurate short-term load forecasting (STLF) for modern power systems’ efficient and secure operation is paramount. This task is intricate due to cyclicity, non-stationarity, seasonality, and nonlinear power consumption time series data characteristics. The rise of data accessibility in the power industry has paved the way for machine learning (ML) models, which show the potential to enhance STLF accuracy. This paper presents a novel hybrid ML model combining Gradient Boosting Regressor (GBR), Extreme Gradient Boosting (XGBoost), k-Nearest Neighbors (kNN), and Support Vector Regression (SVR), examining both standalone and integrated, coupled with signal decomposition techniques like STL, EMD, EEMD, CEEMDAN, and EWT. Through Automated Machine Learning (AutoML), these models are integrated and their hyperparameters optimized, predicting each load signal component using data from two sources: The National Operator of Electric System (ONS) and the Independent System Operators New England (ISO-NE), boosting prediction capacity. For the 2019 ONS dataset, combining EWT and XGBoost yielded the best results for very short-term load forecasting (VSTLF) with an RMSE of 1,931.8 MW, MAE of 1,564.9 MW, and MAPE of 2.54%. These findings highlight the necessity for diverse approaches to each VSTLF problem, emphasizing the adaptability and strength of ML models combined with signal decomposition techniques.

Multi-prediction of electric load and photovoltaic solar power in grid-connected photovoltaic system using state transition method

In the grid-connected photovoltaic system (GPVS), due to characteristics of fluctuation and intermittency for photovoltaic solar power, and high randomness for electric load, it is of great difficulty for integrating photovoltaic solar power into power grid. Therefore, an accurate prediction of short-term electric load and photovoltaic solar power is of great importance for balancing supply and demand. Currently, numerous isolated models about the forecasting of electric load and photovoltaic solar power have emerged, while the coupling effect between them has been hardly considered and lower stability of existing methods brings great difficulty in providing reliable predictions at practical applications. To address this gap, this paper proposes an interpretable multi-prediction model for short-term (day-ahead) electric load and photovoltaic solar power forecasting. In the framework, a non-parametric functional principal component analysis (FPCA) is constructed to extract the overall trend and identify dominant modes of variation in the daily electric load and photovoltaic solar power data. Furthermore, state transition matrix is proposed to comprehensively interpret the coupling effect, with which a novel multi-prediction strategy that takes advantage of coupling effect is further introduced, where the Maximum Likelihood Estimation (MLE) is employed to estimate unknown parameters. Moreover, data from California Independent System Operator (ISO) is utilized to investigate the performance of proposed method, and its results are compared with those from other widely-used techniques. Results show that the proposed method can increase prediction accuracy of electric load and photovoltaic solar power by 16.84% and 10.57%, respectively, with narrow fluctuations and reasonable computational cost (211.11 s), demonstrating that it can provide better predictions in terms of prediction accuracy, stability and applicability.

An Optimized Decision Model for Electric Vehicle Aggregator Participation in the Electricity Market Based on the Stackelberg Game

With the growing popularity of charging pile infrastructure and the development of smart electronic devices and 5G communication technologies, the electric vehicle aggregator (EVA) as a bidding entity can aggregate numerous electric vehicle (EV) resources to participate in the electricity market. Moreover, as the number of grid-connected EVs increases, EVA will have an impact on the nodal marginal prices of electricity market clearing. Aiming at the bidding and offering problem of EVA participation in the day-ahead and intra-day electricity markets, based on the Stackelberg game theory, this paper establishes a bilevel optimization model for EVA participation in the two-stage electricity market as a price-maker. In the proposed bilevel model, the upper-level and lower-level models are constructed as an operational problem for EVA and a market-clearing problem for independent system operator (ISO), respectively. In the day-ahead stage, EVA is optimized to maximize its own expected benefits, and ISO aims to improve the social benefits. In the intra-day stage, EVA is optimized to maximize its self-interest, and the ISO aims to make it possible to minimize the cost of expenditures to maintain the system’s supply–demand balance. Karush–Kuhn–Tucker (KKT) conditions and dual theory are used to transform the nonlinear bilevel programming model into a mixed-integer single-level linear programming model. In order to verify the validity of the proposed bilevel model as well as to comparatively analyze the impact of EVA’s participation in the electricity market on the market clearing results. Two scenarios are set up where EVA is seen as the price-taker in Scenario 1 and EVA is seen as the price-maker in Scenario 2. ISO’s revenue under Scenario 2 increased by USD 2262.66 compared to Scenario 1. In addition, the EVA acts as an energy consumer in Scenario 1 with a charging cost of USD 26,432.95, whereas in Scenario 2, the EVA can profit by participating in the electricity market with a revenue of USD 26,432.95, at which point the EVA acts like a virtual power plant. The simulation examples verify that the proposed bilevel optimization model can improve the benefits of ISO and EVA at the same time, achieving mutual benefits for both parties. In addition, the simulation analyzes the impact of abandonment penalty price on ISO and EVA intra-day revenues. Comparing the scenarios where the abandonment penalty price is 0 with USD 10/MW, the ISO’s revenue in the intra-day market decreases by USD 197.5. Correspondingly, EVA’s reserve capacity is dispatched to consume wind power in the intra-day market, and its revenue increases by USD 197.5. The proposed two-stage bilevel optimization model can provide a reference for EVA to develop scheduling strategies in the day-ahead and intra-day electricity markets.

Grid-scale demand-side flexibility services using commercial buildings lighting loads

Flexibility Services can be used to account for the high variability in electricity generation due to increasing renewable energy sources such as wind and solar energy. As buildings become smarter with the adoption of new technologies for sensing and control, more integration between buildings and the electric grid is possible. Building loads such as air conditioning and lighting in commercial buildings have the potential to provide these Flexibility Services. In commercial buildings, lighting accounts for approximately 10–15 % of the load at time. Past studies have shown that lighting can be dimmed by 15–20 % without causing visual discomfort to the occupants. Overall, this study aims to estimate the instantaneous demand reduction that can be provided due to lighting loads using prototypical building models aggregated across electric grid nodes in the Midcontinent Independent System Operator (MISO) region in the United States. Findings suggest, in a future case with 100 % LED fixtures and 30 % technology penetration for smart lighting controls, lighting loads can provide around 250 to 475 MW (0.21 to 0.39 % of MISO’s peak load) of Flexibility Services in the MISO region. The results can be used as inputs for grid levels models to predict future generation, transmission, and distribution investments for future high renewable energy scenarios.

Residential precooling on a high-solar grid: impacts on CO2 emissions, peak period demand, and electricity costs across California

Abstract As regional grids increase penetrations of variable renewable electricity (VRE) sources, demand-side management (DSM) presents an opportunity to reduce electricity-related emissions by shifting consumption patterns in a way that leverages the large diurnal fluctuations in the emissions intensity of the electricity fleet. Here we explore residential precooling, a type of DSM designed to shift the timing of air-conditioning (AC) loads from high-demand periods to periods earlier in the day, as a strategy to reduce peak period demand, CO2 emissions, and residential electricity costs in the grid operated by the California Independent System Operator (CAISO). CAISO provides an interesting case study because it generally has high solar generation during the day that is replaced by fast-ramping natural gas generators when it drops off suddenly in the early evening. Hence, CAISO moves from a fleet of generators that are primarily clean and cheap to a generation fleet that is disproportionately emissions-intensive and expensive over a short period of time, creating an attractive opportunity for precooling. We use EnergyPlus to simulate 480 distinct precooling schedules for four single-family homes across California’s 16 building climate zones. We find that precooling a house during summer months in the climate zone characterizing Downtown Los Angeles can reduce peak period electricity consumption by 1–4 kWh d−1 and cooling-related CO2 emissions by as much as 0.3 kg CO2 d−1 depending on single-family home design. We report results across climate zone and single-family home design and show that precooling can be used to achieve simultaneous reductions in emissions, residential electricity costs, and peak period electricity consumption for a variety of single-family homes and locations across California.

Multi-horizon short-term load forecasting using hybrid of LSTM and modified split convolution.

Precise short-term load forecasting (STLF) plays a crucial role in the smooth operation of power systems, future capacity planning, unit commitment, and demand response. However, due to its non-stationary and its dependency on multiple cyclic and non-cyclic calendric features and non-linear highly correlated metrological features, an accurate load forecasting with already existing techniques is challenging. To overcome this challenge, a novel hybrid technique based on long short-term memory (LSTM) and a modified split-convolution (SC) neural network (LSTM-SC) is proposed for single-step and multi-step STLF. The concatenating order of LSTM and SC in the proposed hybrid network provides an excellent capability of extraction of sequence-dependent features and other hierarchical spatial features. The model is evaluated by the Pakistan National Grid load dataset recorded by the National Transmission and Dispatch Company (NTDC). The load data is pre-processed and multiple other correlated features are incorporated into the data for performance enhancement. For generalization capability, the performance of LSTM-SC is evaluated on publicly available datasets of American Electric Power (AEP) and Independent System Operator New England (ISO-NE). The effect of temperature, a highly correlated input feature, on load forecasting is investigated either by removing the temperature or adding a Gaussian random noise into it. The performance evaluation in terms of RMSE, MAE, and MAPE of the proposed model on the NTDC dataset are 500.98, 372.62, and 3.72% for multi-step while 322.90, 244.22, and 2.38% for single-step load forecasting. The result shows that the proposed method has less forecasting error, strong generalization capability, and satisfactory performance on multi-horizon.

Market analysis for the integration of new power technologies: A case study of the deployment of hybrid fossil-based generator plus energy storage (ES-FE)

This study examines the national landscape of hybridized fossil energy (FE) power plants with energy storage (ES) technologies (“ES-FE”) and presents the compilation of an ES-FE dataset, which includes over 65 ES-FE projects and concepts in the United States, comprising approximately 500 MWh of co-located ES capacity with FE power plants. This study also estimates the economic feasibility of adding ES to existing FE power plants by characterizing the potential revenues that can be generated by the ES component through flexibility and capacity value. The analysis focuses on ES technologies with 2- to 10-h. durations located in four U.S. independent system operators (ISOs): Midcontinent ISO (MISO), Electric Reliability Council of Texas (ERCOT), PJM Interconnection (PJM), and California ISO (CAISO), which have +70,000 MW of combined FE power capacity that could add ES. Annual revenues are estimated for the ES component using a what-if-analysis approach, for capacity value, price arbitrage, or ancillary services provision. The results show that annual revenues depend on the end-use storage service, wholesale electricity and capacity market prices, and ES technology operation parameters such as discharging duration and cycling frequency. When performing a sensitivity analysis, ES accrues $7–178/kW-yr. via price arbitrage and ancillary services provision in the four ISOs, and $13–92/kW-yr. when providing capacity value only in MISO and PJM. A cash flow analysis is performed to estimate the net present value (NPV) of the ES addition using a range of ES costs. The study finds that for most ES technologies considered, these revenues alone are insufficient to achieve economic feasibility. Of the 1645 total runs analyzed, 115 had positive NPVs (7%). Therefore, other revenue streams or monetizable benefits are necessary to achieve the break-even point.