Neural network forecasting of solar power for NASA Ames sustainability base

Poolla, Chaitanya; Ishihara, Abe; Rosenberg, Steven; Martin, Roscoe C.; Fong, A.; Ray, Sreejita; Basu, Chandrayee

doi:10.1109/ciasg.2014.7011545

Cited by 10 publications

(3 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…On that basis, there are several studies that offer valuable insights to public administrations on how AI can be used to address pressing societal challenges such as efficient energy (e.g. renewable energy) use and facilitate better policy making [40,41]. An example is the development of an Urban Control Centre (UCC), a control room of a smart city that allows public administrators to analyse the city dynamics and citizens to receive information on the performance of urban infrastructure and services, with a specific focus on energy efficiency and environmental sustainability [42].…”

Section: B Impacts On Political Leadership and Public Administratorsmentioning

confidence: 99%

Impacts of Artificial Intelligence on Public Administration: A Systematic Literature Review

Reis

Santo

Melão

2019

2019 14th Iberian Conference on Information Systems and Technologies (CISTI)

View full text Add to dashboard Cite

The advent of machines power-driven by Artificial Intelligence (AI) have strongly influenced the world in the 21 st century. The future of AI is promising and is offering a wide range of opportunities for scholars and academics. Although the theme has received a considerable attention over the last years, much has been speculated and little is known about its impacts on the Public Administration. Thus, the purpose of this article is to make the result of those impacts less ambiguous. To this end, we have conducted a systematic review to provide a comprehensive analysis on the latest impacts of AI on the Public Administration. Our intent is to narrow the field of study, while AI is being continuously strengthened with new empirical evidences.

show abstract

Section: B Impacts On Political Leadership and Public Administratorsmentioning

confidence: 99%

Impacts of Artificial Intelligence on Public Administration: A Systematic Literature Review

Reis

Santo

Melão

2019

2019 14th Iberian Conference on Information Systems and Technologies (CISTI)

View full text Add to dashboard Cite

show abstract

“…With the knowledge of these weather fluctuation distributions, models that map the environment states to the solar power output can be used to obtain the solar power distribution. Although neural network models can be used [22], we use a linear model similar to the one described in [23]. Let the resulting solar power probability at t k ∈ T be represented by P e (k, pv k ),…”

Section: Given the Error Populationmentioning

confidence: 99%

Designing near-optimal policies for energy management in a stochastic environment

Poolla

Ishihara

Milito³

2019

Applied Energy

Self Cite

View full text Add to dashboard Cite

With the rapid growth in renewable energy and battery storage technologies, there exists significant opportunity to improve energy efficiency and reduce costs through optimization. However, optimization algorithms must take into account the underlying dynamics and uncertainties of the various interconnected subsystems in order to fully realize this potential. To this end, we formulate and solve an energy management optimization problem as a Markov Decision Process (MDP) consisting of battery storage dynamics, a stochastic demand model, a stochastic solar generation model, and an electricity pricing scheme. The stochastic model for predicting solar generation is constructed based on weather forecast data from the National Oceanic and Atmospheric Administration. A near-optimal policy design is proposed via stochastic dynamic programming.Simulation results are presented in the context of storage and solar-integrated residential and commercial building environments. Results indicate that the near-optimal policy significantly reduces the operating costs compared to several heuristic alternatives. The proposed framework facilitates the design and evaluation of energy management policies with configurable demand-supply-storage parameters in the presence of weather-induced uncertainties.

show abstract

“…In this paper, the evaluation is carried out for the case where the power required by load/grid from the solar PV is fixed to the forecasted average power generated by the solar PV (

p^{ave_pv_op}

) on the given day. The average solar PV output

p^{ave_pv_op}

for the period of operation can be determined using the methods explained in [26] or [27]. It is to be mentioned that the effectiveness of the algorithm depends on the accuracy of

p_{j}^{pv_forcasted_op}

.…”

Section: Priority‐based Strategic Control Of Appliances For Achievimentioning

confidence: 99%

Virtual storage capacity using demand response management to overcome intermittency of solar PV generation

Kandasamy

Tseng

Soong

2017

IET Renewable Power Generation

View full text Add to dashboard Cite

The integration of solar photovoltaic (PV) systems into the distribution network creates various stability and reliability issues associated with the intermittency of solar PV power generation. Energy storage is a vital component required for overcoming the intermittency of solar PV. This study presents a priority-based demand response management (DRM) for loads with large time constants to create virtual energy storage. The virtual energy storage thus created can be used for partial levelling of intermittent output from solar PVs. The proposed DRM algorithm involves controlling loads with large time constants such as air conditioning systems and refrigerators based on the forecasted solar PV generation. The proposed method is evaluated using data-driven simulations, weather data and mathematical models. The proposed algorithm is highly suitable for megacities that have high number of multi-storey residential buildings. Utilising the virtual storage capacity available from the appliances will reduce the investment as well as the operation cost of renewable energy such as solar PV. Analyses on impact on temperature, percentage of interruptions, cost savings and impact on energy storage sizing are also presented for evaluating the performance of the proposed algorithm. Nomenclature T n ac, on(max) usual turn ON time of the nth air conditioner T n ac, off(max) usual turn OFF time of the nth air conditioner T n ref, on(max) usual turn ON time of the nth refrigerator T n ref, off(max) usual turn OFF time of the nth refrigerator x ac, on , x ac, off proportion of turn ON and turn OFF time for air conditioners x ref, on , x ref, off proportion of turn ON and turn OFF time for refrigerators T n ac, on current turn ON time of the nth air conditioner T n ac, off current turn OFF time of the nth air conditioner T n ref, on current turn ON time of the nth refrigerator T n ref, off current turn OFF time of the nth refrigerator p j vsc, c estimated virtual storage capacity (charging) during jth interval p j vsc, d estimated virtual storage capacity (discharging) during the jth interval p j bpd power required from the battery during the jth interval p ave_pv_op average solar PV output on a given day N off ref number of refrigerators that can be turned off N off ac number of air conditioners that can be turned off N on ref number of refrigerators that can be turned on N on ac number of air conditioners that can be turned on

show abstract

Neural network forecasting of solar power for NASA Ames sustainability base

Cited by 10 publications

References 30 publications

Impacts of Artificial Intelligence on Public Administration: A Systematic Literature Review

Impacts of Artificial Intelligence on Public Administration: A Systematic Literature Review

Designing near-optimal policies for energy management in a stochastic environment

Virtual storage capacity using demand response management to overcome intermittency of solar PV generation

Contact Info

Product

Resources

About