Provisioning for Solar-Powered Base Stations Driven by Conditional LSTM Networks

2024-10-28 · Yawen Guo, Sonia Naderi, Colleen Josephson

Solar-powered base stations are a promising approach to sustainable telecommunications infrastructure. However, the successful deployment of solar-powered base stations requires precise prediction of the energy harvested by photovoltaic (PV) panels vs. anticipated energy expenditure in order to achieve affordable yet reliable deployment and operation. This paper introduces an innovative approach to predict energy harvesting by utilizing a novel conditional Long Short-Term Memory (Cond-LSTM) neural network architecture. Compared with LSTM and Transformer models, the Cond-LSTM model reduced the normalized root mean square error (nRMSE) by 69.6% and 42.7%, respectively. We also demonstrate the generalizability of our model across different scenarios. The proposed approach would not only facilitate an accurate cost-optimal PV-battery configuration that meets the outage probability requirements, but also help with site design in regions that lack historical solar energy data.

📄 PDF Abstract BibTeX arXiv:2410.20755

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

Attention 설명 없음

Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.

Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…

Label Smoothing Label Smoothing is a regularization technique that introduces noise for the labels. This accounts for the fact that datasets may have mistakes in them, so maximizing the…

Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…

Residual Connection 설명 없음

BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…

Sigmoid Activation 설명 없음

SOLAR: AI-Powered Speed-of-Light Performance Analysis

2026-06-24 · Qijing Huang, Sana Damani, Zhifan Ye, Athinagoras Skiadopoulos 외 arxiv

How fast could a deep-learning model run on target hardware, and how far is today's implementation from that limit? These questions are central to software, hardware, and algorithm optimizations. Speed-of-Light (SOL) ana…

Short term solar energy prediction by machine learning algorithms

2020-10-25 · Farah Shahid, Aneela Zameer, Mudasser Afzal, Muhammad Hassan

Smooth power generation from solar stations demand accurate, reliable and efficient forecast of solar energy for optimal integration to cater market demand; however, the implicit instability of solar energy production ma…

BIG-bench Machine Learning

Surface solar radiation: AI satellite retrieval can outperform Heliosat and generalizes well to other climate zones

2024-09-16 · K. R. Schuurman, A. Meyer

Accurate estimates of surface solar irradiance (SSI) are essential for solar resource assessments and solar energy forecasts in grid integration and building control applications. SSI estimates for spatially extended reg…

Retrieval

A Simulation Approach to Multi-station Solar Irradiance Data Considering Temporal Correlations

2019-09-12

Solar energy is one of important renewable energy sources and simulation of solar irradiance can be used as input for simulation of photovoltaic (PV) generation. This paper proposes a simulation algorithm of multi-statio…

Short-Term Solar Irradiance Forecasting Using Calibrated Probabilistic Models

2020-10-09 · Eric Zelikman, Sharon Zhou, Jeremy Irvin, Cooper Raterink 외

Advancing probabilistic solar forecasting methods is essential to supporting the integration of solar energy into the electricity grid. In this work, we develop a variety of state-of-the-art probabilistic models for fore…

Solar Irradiance Forecasting