Machine learning-based technology to forecast solar power generation
POWER & RENEWABLE ENERGY

Machine learning-based technology to forecast solar power generation

Two new machine learning-based models for forecasting the power generated by solar projects have been developed by researchers led by Dr Kalop of Urban Environmental Engineering and Professor Heo Jong-wan of Incheon National University in South Korea.

The advanced models incorporating artificial intelligence, dubbed the adaptive neuro-fuzzy inference system (ANFIS), efficiently forecast the power generated by photovoltaic systems up to a full day ahead of time.

Renewable and Sustainable Energy Reviews published the research paper.

Integrating solar photovoltaic (PV) power into existing power grids is a difficult task because PV systems' power output is heavily influenced by environmental factors. According to the researchers, an accurate forecast of solar PV power generation is required for efficient power integration into existing power grids.

The researchers combined two models with adaptive and time-varying acceleration coefficients: ANFIS and particle swarm optimization (PSO).

According to the researchers, the two models are described as hybrid algorithms because they combine a novel hybrid approach of adaptive swarm intelligence techniques and ANFIS in forecasting solar PV project power generation over time horizons ranging from 0 to 24 hours.

The models were designed and evaluated using climatic variables and historical PV power data from a 960 kW grid-connected PV system in south Italy. To assess the accuracy of the proposed models and the impact of variables on PV power values, several statistical analyses were conducted. At time horizons of 12 hours and 24 hours, the proposed ANFIS-APSO achieved the most accurate PV power forecast with R2 = 0.657 and 0.835, RMSE = 0.081 kW and 0.088 kW, and MAE = 0.079 kW and 0.077 kW , respectively.

The newly constructed ANFIS-APSO outperformed the standard ANFIS-PSO model, as well as other hybrid models, according to the findings. According to the findings, the model could be a promising new tool for engineers to use in forecasting the power generation of solar projects over short and long time horizons.

Renewable energy project developers face a difficult task in accurately forecasting power generation. To integrate renewable generation into the grid efficiently, utilities demand accurate forecasting and scheduling. Renewable energy forecasting technologies are in high demand from utilities as well as renewable energy generators.

Image Source

Your next big infra connection is waiting at RAHSTA 2025 – Asia’s Biggest Roads & Highways Expo, Jio World Convention Centre, Mumbai. Don’t miss out!

Two new machine learning-based models for forecasting the power generated by solar projects have been developed by researchers led by Dr Kalop of Urban Environmental Engineering and Professor Heo Jong-wan of Incheon National University in South Korea. The advanced models incorporating artificial intelligence, dubbed the adaptive neuro-fuzzy inference system (ANFIS), efficiently forecast the power generated by photovoltaic systems up to a full day ahead of time. Renewable and Sustainable Energy Reviews published the research paper. Integrating solar photovoltaic (PV) power into existing power grids is a difficult task because PV systems' power output is heavily influenced by environmental factors. According to the researchers, an accurate forecast of solar PV power generation is required for efficient power integration into existing power grids. The researchers combined two models with adaptive and time-varying acceleration coefficients: ANFIS and particle swarm optimization (PSO). According to the researchers, the two models are described as hybrid algorithms because they combine a novel hybrid approach of adaptive swarm intelligence techniques and ANFIS in forecasting solar PV project power generation over time horizons ranging from 0 to 24 hours. The models were designed and evaluated using climatic variables and historical PV power data from a 960 kW grid-connected PV system in south Italy. To assess the accuracy of the proposed models and the impact of variables on PV power values, several statistical analyses were conducted. At time horizons of 12 hours and 24 hours, the proposed ANFIS-APSO achieved the most accurate PV power forecast with R2 = 0.657 and 0.835, RMSE = 0.081 kW and 0.088 kW, and MAE = 0.079 kW and 0.077 kW , respectively. The newly constructed ANFIS-APSO outperformed the standard ANFIS-PSO model, as well as other hybrid models, according to the findings. According to the findings, the model could be a promising new tool for engineers to use in forecasting the power generation of solar projects over short and long time horizons. Renewable energy project developers face a difficult task in accurately forecasting power generation. To integrate renewable generation into the grid efficiently, utilities demand accurate forecasting and scheduling. Renewable energy forecasting technologies are in high demand from utilities as well as renewable energy generators. Image Source

Next Story
Real Estate

Vitizen Hotels Signs Deal at Manyata Tech Park

Vikram Kamats Hospitality, as part of its ongoing expansion in key metropolitan markets, announced that its material subsidiary, Vitizen Hotels, has signed a long-term lease agreement for a 45-key hotel property at Manyata Tech Park, Bengaluru.Strategically located in the city’s prominent IT hub, the property is well-positioned to serve corporate travelers, business professionals, and long-stay guests. The addition aligns with the company’s asset-light growth model, leveraging long-term leases to expand its footprint in high-demand urban markets.The hotel is expected to strengthen the comp..

Next Story
Infrastructure Transport

CONCOR Signs MoU with BPIPL to Operate Container Terminal at Bhavnagar Port

Container Corporation of India (CONCOR) has signed a Memorandum of Understanding (MoU) with Bhavnagar Port Infrastructure (BPIPL) on September 4, 2025, in New Delhi to operate and maintain the upcoming container terminal at the northside of Bhavnagar Port, Gujarat.BPIPL had earlier entered into an agreement with the Gujarat Maritime Board (GMB) in September 2024 for the port’s development. Under this arrangement, 235 hectares of land has been leased to BPIPL for 30 years, with provision for expansion by an additional 250 hectares.The new terminal is expected to significantly enhance logistic..

Next Story
Infrastructure Transport

Concord Launches India’s First Indigenous Zero-Emission Rail Propulsion

Concord Control Systems (CCSL), a leader in embedded electronics and critical rail technologies, has announced the development of India’s first fully indigenous zero-emission propulsion system, marking a significant step toward the country’s railway electrification and net-zero goals for 2030.Powered by Lithium Iron Phosphate (LFP) batteries and featuring a DC chopper-based drive, the propulsion system eliminates idling losses common in diesel engines, offering higher efficiency, lower costs, and zero emissions.What sets this innovation apart is its completely indigenous design. Except for..

Advertisement

Subscribe to Our Newsletter

Get daily newsletters around different themes from Construction world.

STAY CONNECTED

Advertisement

Advertisement

Advertisement

Talk to us?