More households change power suppliers amid market liberalization

The Japan Times

Over 3 million households in Japan have switched their electricity suppliers to new entrants to the retail power market since the market was fully liberalized last April. Although the figure accounts for only 5 percent of overall household subscribers, the trend is expected to gather steam this year as sales of city gas are also set to be opened up next month. Before the market was liberalized, 10 major electric power companies, including Tokyo Electric Power Company Holdings Inc., had a stranglehold on the ¥8 trillion electric power business, controlling power generation, distribution and retail sales. The Ministry of Economy, Trade and Industry said that 3.11 million households had changed their power suppliers to new entrants as of the end of February. On the supply side, many companies from various industries, including telecommunications, gas and railroads, have entered the power market.


GE Cuts 12K Power Jobs as Demand, Renewables, Skew Market

U.S. News

The job cuts will mostly be outside the U.S. and will comprise approximately 18 percent of the power unit's workforce. GE would not say where workers would be effected, but the power distribution network in Europe has seen significant disruption as demand there wanes. Last month, industrial conglomerate Siemens announced plans to cut about 6,900 jobs worldwide at its power, gas and drives divisions, half of them in Germany.


Surging Stock Market Powers US Wealth to $96.2 Trillion

U.S. News

FILE - In this Tuesday, Jan. 24, 2017, file photo, specialist Anthony Rinaldi works at his post on the floor of the New York Stock Exchange.


Power Market Price Forecasting via Deep Learning

arXiv.org Machine Learning

A study on power market price forecasting by deep learning is presented. As one of the most successful deep learning frameworks, the LSTM (Long short-term memory) neural network is utilized. The hourly prices data from the New England and PJM day-ahead markets are used in this study. First, a LSTM network is formulated and trained. Then the raw input and output data are preprocessed by unit scaling, and the trained network is tested on the real price data under different input lengths, forecasting horizons and data sizes. Its performance is also compared with other existing methods. The forecasted results demonstrate that, the LSTM deep neural network can outperform the others under different application settings in this problem.


State Investigates Allegations of Market Power Abuse

U.S. News

The Office of Consumer Counsel says the investigation began after university researchers claimed Eversource and Avangrid companies intentionally created natural gas shortages so they could drive up energy rates.