Generation Dispatch Research Articles

Integrated planning of emission reduction based unit commitment and generation dispatch solution for sustainable power system

Integrated planning of emission reduction based unit commitment and generation dispatch solution for sustainable power system

A hybrid machine learning approach for real-time reliability evaluation of power systems

Abstract Reliable operation of modern power systems requires accurate state evaluation and efficient load management under dynamic and uncertain conditions. This study presents an AI-enhanced hybrid optimization framework that integrates DC power flow modeling, mixed-integer linear programming (MILP), and a Transformer-based architecture to dynamically optimize generator dispatch and key reliability metrics, including Loss of Load Probability (LOLP), Expected Energy Not Supplied (EENS), and Loss of Load Frequency (LOLF). The framework incorporates a self-attention mechanism to enhance stability prediction and support the integration of renewable energy sources. The proposed framework demonstrates superior performance on the IEEE RTS-96 and Saskatchewan Power Corporation (SPC) systems, achieving 93.7% prediction accuracy with the lowest RMSE and MAE among all tested models. It outperforms benchmark models such as Convolutional Neural Networks (CNN), Convolutional XGBoost (ConXGB), Convolutional Random Forest (ConRF), Physics-Informed Neural Networks (PINN), and Graph Neural Networks (GNN), while also reducing computational time by 60.5%, confirming its efficiency and suitability for real-time reliability assessment. Additionally, the proposed approach improves cost-reliability trade-offs in load curtailment decisions, offering a scalable and adaptive solution for modern power system reliability analysis.

Hybrid group method of data handling for time-series forecasting of thermal generation dispatch in electrical power systems

Hybrid group method of data handling for time-series forecasting of thermal generation dispatch in electrical power systems

Neural network-based forecasting and uncertainty analysis of new power generation capacity of electric energy

The prediction of new energy generation is challenging due to its intermittency and uncertainty. To solve this, we propose a framework combining an optimized multiscale convolutional neural network (MSCNN) and long - short - term memory network (LSTM). MSCNN improves feature extraction with dynamic scale selection and deep residual modules. LSTM captures long - term dependencies better using bidirectional processing and attention mechanisms. We also introduce a fuzzy decision support system (FDSS) to handle prediction uncertainty. Our model outperforms ARIMA, SVM, Gradient Boosting, CNN, and RNN in hourly, daily, and weekly predictions. It also excels in uncertainty quantification and generalization, offering strong support for accurate new energy generation prediction and dispatch.

Challenges of variable energy resource integration and power system security: Lessons from the 2025 Iberian system blackout

This editorial explores the challenge posed by the growing integration of variable energy resources (VERs) into power systems, referencing the April 28, 2025 blackout in the Iberian grid as a case study. Despite robust grid infrastructure and dispatchable generation capacity, a sharp solar ramp, low demand, and limited voltage control led to system collapse. The event underscores the need for improved ancillary services, real-time visibility of distributed generation, and greater demand-side flexibility to ensure reliable operation under high VER penetration.

Solution of hybrid energy based dynamic economic emission dispatch problems using chaos assisted arithmetic optimization algorithm

ABSTRACT With the substantial environmental depletion, one of the most important steps toward minimizing the carbon footprints is the integration of the renewable source of energy, for instance, wind or solar to the existing conventional generators. In this proposed work, the existing problems of conventional thermal scheduling like excessive generation cost and additional emissive components of fuel are minimized by incorporating renewable energy sources with the conventional thermal generating units. This paper proposes a thermal-solar-wind-battery (TSWB) integrated system model for 24 hourly hybrid dynamic economic emission dispatch (HDEED) generation scheduling. Here, fruitful performance of minimum cost-emission oriented TSWB system has been inspected by using chaos based arithmetic optimization algorithm (AOA) (CAOA). Chaos has been used in order to improve the exploration capability, large-scale complex problem handling and to deal with highly volatile nature of HDEED. Four test systems of different scales having six, thirty, forty and eighty thermal generators in the TSWB integrated system are used to test the proposed approach. Tested result shows that both the operating costs and pollutant emissions drop down up to 9% and 31%, respectively. Obtained results are compared with particle swarm optimization algorithm, backtracking search algorithm and Squirrel search algorithm which establishes the superiority of the CAOA.

Economic Optimality of Automatic Generation Control in a Multi-Source Power System Using an Optimization Problem Approach

Due to the incorporation of a high penetration of renewable energy resources into power generation, recent power system control strategies have combined economic dispatch (ED) and automatic generation control (AGC) to achieve economic operation. To this end, AGC parameters and control laws have been designed to optimize operation through the use of optimization approaches. Although existing studies indicate that the proposed AGC optimal control strategy offers superior performance compared to traditional AGC, the models used in these theoretical frameworks are typically dominated by a single energy source, such as a steam-turbine generator. Additionally, the models in existing studies do not consider the ramp generation constraints present in practical implementations. In this paper, we propose an algorithm to obtain the optimal AGC parameters to consider a more realistic power system with diverse sources. Numerical simulations are used to demonstrate the effectiveness of the proposed method.

Energy Cost Optimisation in a Wastewater Treatment Plant by Balancing On-Site Electricity Generation with Plant Demand

Wastewater treatment plants (WWTPs) consume a considerable amount of energy. They also generate energy in combined heat and power (CHP) units, which utilise biogas from the anaerobic digestion of sewage sludge to produce renewable electricity. Different prices apply to electricity generated on site in CHP units, to the purchase of electricity from the grid, to the sale of surplus electricity to the grid and energy tariffs, which motivates the optimisation of energy costs. This paper presents a strategy for optimising electricity costs by adapting on-site electricity generation in CHP units to the demand of the WWTP. The approach is designed for a CHP system that generates electricity in multiple internal combustion gas engines. It is implemented as a two-level control system, where the lower control level dynamically adjusts the power of the individual gas engines, and the upper control level optimises the desired total power, taking into account the current energy consumption of the WWTP, biogas reserves and electricity tariffs. The proposed concept was implemented at the Domžale-Kamnik WWTP. A six-month evaluation showed that electricity purchased from the grid could be reduced from 8.7% to 3.3% of the WWTP’s electricity consumption. This reduction affects the system economically, as electricity purchased from the grid at low and high tariffs is 35% and 76% more expensive than electricity generated on site (excluding the grid fee). This approach can be extended to balance dispatchable electricity generation at the WWTP to respond to short-term grid demand.

Frequency-Constrained Economic Dispatch of Microgrids Considering Frequency Response Performance

The increasing penetration of renewable energy sources (RESs) has reduced the inertia and reserve levels of microgrids, posing challenges to frequency security during power imbalances. To address these challenges, this paper proposes a multi-objective distributionally robust frequency-constrained economic dispatch (DRFC-ED) model. First, the model aims to jointly optimize generation dispatch, reserve deployment, and the virtual inertia and damping constants of inverter-based resources to achieve a comprehensive optimization of both economic efficiency and frequency response performance. Then, the model further considers the distinctions between inertia and damping in the frequency response for more effective parameter deployment. Furthermore, the model leverages deep neural networks (DNNs) to convexify non-convex frequency constraints and employs a distributionally robust chance-constrained approach with Wasserstein distance-based ambiguity sets to handle RES uncertainty. Additionally, a method of directly obtaining the compromise optimal solution is used to transform the multi-objective problem into a single-objective one. Finally, the model is formulated as a mixed-integer linear programming problem and validated through case studies, demonstrating (1) an 8.03% reduction in the frequency integral time absolute error (ITAE) with only a 2.1% increase in economic cost compared to single-objective approaches, while (2) maintaining maximum frequency deviation (MFD) < 0.5 Hz during disturbances.

Multi-Energy Static Modeling Approaches: A Critical Overview

In Europe and elsewhere in the world, current ambitious decarbonization targets push towards a gradual decommissioning of all fossil-fuel-based dispatchable electrical generation and, at the same time, foster a gradual increase in the penetration of Renewable Energy Sources (RES). Moreover, considerations tied to decarbonization as well as to the security of supply, following recent geo-political events, call for a gradual replacement of gas appliances with electricity-based ones. As RES generation is characterized by a variable generation pattern and as the electric carrier is characterized by scarce intrinsic flexibility, and since storage capabilities through electrochemical batteries, as well as demand-side flexibility contributions, remain rather limited, it is quite natural to think of other energy carriers as possible service providers for the electricity system. Gas and heat networks and, in the future, hydrogen networks could provide storage services for the electricity system. This could allow increasing the amount of RES penetration to be managed safely by the electric system without incurring blackouts and avoiding non-economically motivated grid reinforcements to prevent the curtailment of RES generation peaks. What is explained above calls for a new approach, both in electricity network dispatch simulations and in grid-planning studies, which extends the simulation domain to other carriers (i.e., gas, heat, hydrogen) so that a global optimal solution is found. This simulation branch, called multi-energy or multi-carrier, has been gaining momentum in recent years. The present paper aims at describing the most important approaches to static ME modeling by comparing the pros and cons of all of them with a holistic approach. The style of this paper is that of a tutorial aimed at providing some guidance and a few bibliographic references to those who are interested in approaching this theme in the next years.

Impact of demand flexibility on renewable energy integration, backup capacity, storage use and dispatchable generation: A case study for Portugal's 2030 National Energy plan

Impact of demand flexibility on renewable energy integration, backup capacity, storage use and dispatchable generation: A case study for Portugal's 2030 National Energy plan

Economic Scheduling of Microgrids With a bi‐Level Model Considering Battery Aging

ABSTRACTBattery energy storage systems (BESS) are essential for smart grids but suffer from capacity degradation due to charging and discharging cycles, leading to significant costs. To optimize BESS operation, it is crucial to include battery degradation (BD) costs in scheduling, considering equivalent cycles and depth of discharge. This paper introduces a novel degradation cost model for optimal battery scheduling. A linear model based on a semi‐empirical approach represents the calendar aging process, and a new algorithm derived from the rainflow‐counting algorithm (RCA) calculates cycle aging based on the cycle life curve and state of charge during discharge. The degradation cost model is based on battery capacity fade and economic principles. Finally, a mixed‐integer bi‐level linear model (MIBLM) examines the interaction between distributed generation dispatch and BESS charging/discharging, assessing the feasibility of integrating BD cost into energy management. Results show that the proposed MIBLM considering BD significantly influences BESS strategies, reducing microgrid (MG) operation costs by 12.69% compared to single‐level models and achieving a 3.5% reduction in expenses compared to conventional strategies that ignore BD. The analysis also highlights the importance of considering calendar aging in determining optimal BESS capacity.

Economic Load Dispatch of A Multi‐Area Power System Using Multi‐Agent Distributed Optimization Based on Genetic Algorithm

ABSTRACTThis study presents a new methodology for distributed multi‐agent optimization utilizing a genetic algorithm to address Multi‐Area Economic Dispatch Problem (MAEDP) in a power system. While numerous studies have been conducted on various optimization methods for distributed multi‐agent systems, this paper proposes a model for solving the optimal economic dispatch equations in different areas of the power system in a distributed and coordinated manner. In this model, each area is represented by an agent responsible for coordinating data exchange with other areas and solving the generation dispatch equations within its own area. The coordination model between agents and areas is described in the form of an algorithm, whereby the exchanged data values converge after several iterations, and the final solution to the problem is obtained from the perspective of each agent. The objective of each agent in each area is to minimize generation costs and meet its own area's load demand while maintaining voltage profiles. Each agent sets the power generation values of resources in each area using the genetic algorithm rules and then solves the distributed power flow equations using the proposed method. Upon achieving convergence, each agent evaluates all operational constraints within its designated region, calculates the associated generation cost, and shares the cost value to other agents, thereby facilitating the computation of the total cost for each agent. This process continues until the best possible solution is found. The results of implementing the proposed model and algorithm on several different test networks of power systems demonstrate the capability and effectiveness of the method in decomposing the optimal economic dispatch problem into smaller sub‐problems and then finding the final optimal solution through simultaneous solving with agent consensus in coordinated steps.

Electric utility vulnerability to wildfires and post-fire debris flows in California

Abstract Wildfires and post-fire debris flows (PFDFs) threaten California infrastructure and are evolving with climate change. There is significant focus on the threat of utility-caused wildfires because electric power equipment has triggered wildfires leading to major damage. California’s ambitious climate targets rely on electrification of transport and industry. As the state modernizes its electricity system to support increased demand, it must consider future climate hazards. To date, there is no rigorous characterization of the intersection of future fire threat, PFDFs, and electrical infrastructure. We estimate wildfire and PFDF threat to transmission lines, substations, and power generators in California and assess vulnerability of electric utilities by intersecting electrical infrastructure and current and future wildfire and PFDF threat, using two global climate models and two representative concentration pathways. We find clean, dispatchable power generators (e.g. hydroelectric and nuclear) and small, publicly-owned utilities are most vulnerable. Increasing threats will require additional resources and consideration of future threat distribution.

Self-adaptive differential evolution approach to solving economic load dispatch problem with renewable energy: Nigerian case study

Renewable energy penetration in power systems comes with many inherent challenges that pose a significant problem with coordination and scheduling with other conventional generation sources. These challenges if not mitigated instantly could affect the reliable operation of power systems and may even lead to a system collapse in severe cases. Therefore, the development of improved and faster economic dispatch is imperative to effectively and reliably integrate renewable energy into the power system. In this paper, four different methods namely: gradient descent, genetic algorithm, differential evolution, and self-adaptive differential evolution were utilized to coordinate the wind–thermal generation dispatch and to minimize the total production cost in the economic dispatch considering the generator ramp rate. The Nigerian grid was modeled consisting of four thermal units’ system incorporating wind power plants in each of the five different locations was utilized for the numerical simulations. Different simulation scenarios with and without losses were simulated and the results show that the self-adaptive method gives the least production cost as compared to other methods. Also, considering the case with losses, the self-adaptive differential evolution gives the least transmission losses as compared to others.

Power generation dispatching and risk analysis of the Qingjiang cascade hydropower stations under climate change

ABSTRACT Climate change alters river runoff regimes, affecting the safe operation of hydropower stations. This study proposed an optimization scheduling and risk analysis framework for cascade hydropower under climate change using the Qingjiang cascade hydropower stations as a case study. The framework has three stages. Firstly, a hydrological model coupling GCMs with SWAT under CMIP5 scenarios is established to predict future runoff. Secondly, cascade hydropower optimization scheduling under climate change is performed using the POA (Progressive Optimization Algorithm). Thirdly, a risk assessment index system is established, including risks of insufficient power generation, insufficient output, and water abandonment. The POMR (Probability Optimization Method for the Risk) is applied to calculates power scheduling risks. Results show that the simulated annual average runoff at Changyang Station increases by 6.0, 8.7, and 13.2% under the RCP2.6, RCP4.5, and RCP8.5 scenarios, respectively. Annual power generation for the Qingjiang cascade is projected to rise by 6.2–16.5%, with increases of 5.2–12.9% during flood seasons and 7.5–19.9% in non-flood seasons. Comprehensive risk rates decline to 0.1767, 0.1706, and 0.1630 across the scenarios. This research provides scientific and technical support for managing water resources and operating the Qingjiang cascade under climate change.

Mitigation strategies can alleviate power system vulnerability to climate change and extreme weather: a case study on the Italian grid

Abstract This study explores compounding impacts of climate change on power system’s load and generation, emphasising the need to integrate adaptation and mitigation strategies into investment planning. We combine existing and novel empirical evidence to model impacts on: (i) air-conditioning demand; (ii) thermal power outages; (iii) hydro-power generation shortages. Using a power dispatch and capacity expansion model, we analyse the Italian power system’s response to these climate impacts in 2030, integrating mitigation targets and optimising for cost-efficiency at an hourly resolution. We outline different meteorological scenarios to explore the impacts of both average climatic changes and the intensification of extreme weather events. We find that addressing extreme weather in power system planning will require an extra 5–8 GW of photovoltaic (PV) capacity, on top of the 50 GW of the additional solar PV capacity required by the mitigation target alone. Despite the higher initial investments, we find that the adoption of renewable technologies, especially PV, alleviates the power system’s vulnerability to climate change and extreme weather events. In fact, renewable energy sources are generally less vulnerable to the impacts of climate change, such as rising temperatures and shifting precipitation patterns, compared to thermal power and hydropower generation. Furthermore, enhancing short-term storage with lithium-ion batteries is crucial to counterbalance the reduced availability of dispatchable hydro generation.

Soaking up the Sun: Battery Investment, Renewable Energy, and Market Equilibrium

Renewable energy and battery storage are seen as complementary technologies that can together facilitate reductions in carbon emissions. We develop and estimate a framework to calculate the equilibrium effects of large‐scale battery storage. Using data from California, we find that the first storage unit breaks even by 2024 without subsidies when the renewable energy share reaches 50%. Equilibrium effects are important: the first 5000 MWh of storage capacity would reduce wholesale electricity prices by 5.6%, but an increase from 25,000 to 50,000 MWh would only reduce these prices by 2.6%. Large‐scale batteries will reduce revenues to both dispatchable generators and renewable energy sources. The equilibrium effects lead battery adoption to be virtually non‐existent until 2030, without a storage mandate or subsidy. A 30% capital cost subsidy—such as the one in the U.S. Inflation Reduction Act—achieves 5000 MWh of battery capacity by 2024, similar to the level required under California's storage mandate.

حل مسألة الإرسال الإقتصادي الحراري باستخدام الشبكات العصبية الصناعية

The problem of economic dispatch (generation) is considered as one of the optimization problems, and many different methods have been used to solve it. In this study, the problem is solved using artificial neural networks (ANNs) which are considered as a branch of the artificial intelligence. The tool used in the study is the ANNs toolbox in MATLAB, which contains advanced capabilities. Through the toolbox, many options can be tested to reach the optimal solution to the problem. ANNs need to be trained on samples of inputs-outputs (solution) of problems before they can solve them on their own. During this study computer programs have been written to solve the thermal dispatch problem using a traditional mathematical method; the -iteration method. Through it, training samples are provided to the ANN. From the results of the study it has been proved that the solutions of the problem obtained using the trained ANN almost match with the solutions obtained using the -iteration method. The goal of using ANNs is to solve the thermal of economic dispatch problem in a faster time in the case of power systems that contain a large number of generating units. Keywords: Thermal Economic Dispatch, Optimal Generation, Lambda Iteration, Multi-Layer Feed-Forward Artificial Neural Networks, Error back propagation algorithm

Robust machine-learned algorithms for efficient grid operation

Abstract Increasing penetration of variable and intermittent renewable energy resources on the energy grid poses a challenge for reliable and efficient grid operation, necessitating the development of algorithms that are robust to this uncertainty. However, standard algorithms incorporating uncertainty for generation dispatch are computationally intractable when costs are nonconvex, and machine learning-based approaches lack worst-case guarantees on their performance. In this work, we propose a learning-augmented algorithm, RobustML, that exploits the good average-case performance of a machine-learned algorithm for minimizing dispatch and ramping costs of dispatchable generation resources while providing provable worst-case guarantees on cost. We evaluate the algorithm on a realistic model of a combined cycle cogeneration plant, where it exhibits robustness to distribution shift while enabling improved efficiency as renewables penetration increases.